JP2023516433A - Intelligent Traffic Systems Including Digital Twin Interface for Passenger Vehicles - Google Patents

Abstract

A transportation system can present a set of vehicle operating conditions to a user of the vehicle and generally includes a system for presenting a set of vehicle operating conditions to the user of the vehicle. The system includes a portion of a vehicle having a vehicle operating state, a digital twin system receiving vehicle parameter data from one or more inputs to determine the vehicle operating state, and presenting the vehicle operating state to a user of the vehicle. and an interface for the digital twin system.

Description

(Cross-reference with related application)
This application claims priority to U.S. Provisional Application No. 62/984,225, entitled "Intelligent Transportation Systems including Digital Twin Interface for a Passenger Vehicle," filed March 2, 2020, and Claims priority to U.S. Provisional Application No. 63/069,537, entitled "Information Technology Systems and Methods for Transportation Artificial Intelligence Leveraging Digital Twins," filed May 24, each of which is fully incorporated herein in its entirety incorporated by reference as if

TECHNICAL FIELD This disclosure relates to a digital twin of a passenger vehicle and, more particularly, to a configurable digital twin interface for presenting a range of vehicle states to a user of the vehicle.

A digital twin is a digital construct of information about a machine, physical device, system, process, or person. A digital twin, once created, can be used to represent the machine in a digital representation of the real-world system. A digital twin is created to look and act the same as its mechanical counterpart. Additionally, the digital twin can reflect the state of machines within a larger system. For example, sensors can be placed on machines to obtain real-time (or near-real-time) data from physical objects and relay them to a distant digital twin.

Digital twins are commonly used to simulate or imitate the behavior of machines and physical devices within a virtual world. The digital twin then represents the structural parts of the machine, shows lifecycle and design steps, and is viewable through a user interface.

Digital twins are used in various applications in the automotive industry. Such twins are used by designers and product developers when developing new vehicles. Digital twins will enable engineers to model and test new safety features in vehicles, and manufacturers to improve various components and subsystems of vehicles. However, the application of digital twins to manage and enhance the customer experience of users, including vehicle owners and drivers, has been limited. Additionally, digital twin interfaces are fairly primitive and typically do not provide options for configuring or customizing the interface based on the user's profile. Applicants have recognized a need and opportunity for a digital twin system for passenger vehicles.

In particular, provided herein are methods, systems, components, processes, modules, blocks, circuits, subsystems, articles, and other elements (such as Sometimes referred to collectively as a "platform" or "system," these terms should be understood to include any of the above unless the context otherwise dictates.

In an embodiment, a system for presenting a set of vehicle operating conditions to a user of the vehicle includes a portion of the vehicle having the vehicle operating conditions and vehicle parameter data from one or more inputs to determine the vehicle operating conditions. A receiving digital twin system and an interface to the digital twin system for presenting vehicle operating conditions to a vehicle user.

In an embodiment, the vehicle operating state is a vehicle maintenance state. In embodiments, the vehicle operating conditions are vehicle energy utilization conditions. In embodiments, the vehicle operating state is a vehicle navigation state. In embodiments, the vehicle operating conditions are vehicle component conditions. In embodiments, the vehicle operating conditions are vehicle driver conditions. In embodiments, the input of the digital twin system includes at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In embodiments, the system includes an identity management system for managing a set of identities and roles for vehicle users. In an embodiment, the identity management system includes the ability to view, modify, and configure the digital twin system and is based on identities from a set of vehicle user identities. In embodiments, the digital twin system is populated via an API from the vehicle's edge intelligence system that provides 5G connectivity to systems external to the vehicle. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system, which provides internal 5G connectivity to the vehicle's set of sensors and data sources. In embodiments, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to the in-vehicle artificial intelligence system.

In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. In an embodiment, the digital twin system is automatically configured by an artificial intelligence system based on a training set of driver-user usage activities. In an embodiment, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by rider users.

In an embodiment, the system first detects a detected well-being state of a rider user on board the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the rider user. and a second neural network that optimizes operating parameters of the vehicle in response to the rider-user's detected state of well-being to achieve the rider-user's preferred state of well-being.

In embodiments, the rider user's detected well-being state is the rider user's detected emotional state. In embodiments, the rider user's preferred state of well-being is the rider user's preferred emotional state. In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, the second neural network optimizes operating parameters based on correlations between vehicle operating conditions and the rider user's rider satisfaction. In an embodiment, the second neural network optimizes operating parameters in real-time in response to detection of the rider-user's detected well-being by the first neural network. In an embodiment, the first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a method of presenting a set of vehicle states to a user of the vehicle comprises: obtaining parameter data for one or more components of the vehicle from one or more inputs; generating one or more operating states of the vehicle; updating a digital twin of the vehicle with parameter data to provide an interface for presenting one or more operational states of the vehicle to a user of the vehicle.

In embodiments, the one or more vehicle operating states include one or more of a vehicle maintenance state, a vehicle energy utilization state, a vehicle navigation state, a vehicle component state, or a vehicle driver state. In embodiments, inputs for the digital twin system include one or more of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In an embodiment, the method includes managing a set of vehicle user identities and roles, and configuring a digital twin system based on identities from the set of vehicle user identities.

In embodiments, the method includes one or more of: 5G connectivity to systems external to the vehicle, internal 5G connectivity to the vehicle's set of sensors and data sources, or 5G connectivity to an in-vehicle artificial intelligence system. including providing inputs to the digital twin system via an API from the vehicle's edge intelligence system configured in

In an embodiment, the method includes automatically configuring a digital twin system with an artificial intelligence system based on a training set of usage activities by a set of digital twin users.

In an embodiment, the method comprises using a first neural network to analyze data collected from sensors deployed on the vehicle to collect the physiological state of the rider user before boarding the vehicle. Detecting a detected state of satisfaction of the rider user and adjusting the operating parameters of the vehicle in response to the detected state of satisfaction of the rider user to achieve a preferred state of satisfaction of the rider user using a second neural network. and optimizing for

In embodiments, the rider user's detected well-being state is the rider user's detected emotional state. In embodiments, the rider user's preferred state of well-being is the rider user's preferred emotional state.

In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, optimization of operating parameters by the second neural network is based on correlations between vehicle operating conditions and rider user satisfaction conditions of the rider user. In an embodiment, the optimization of the operating parameters by the second neural network is performed in response to detection of the rider user's detected satisfaction state by the first neural network.

In embodiments, the method includes using a first neural network to form one or more connected nodes that form a directed cycle. In embodiments, the first neural network further facilitates bi-directional flow of data between connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a computer-implemented method for generating a digital twin of a vehicle comprises receiving, via an interface, a request from a user of the vehicle to display vehicle status information; , generating a digital twin representation of the vehicle based on one or more user inputs based on the vehicle status information; using the interface to display the vehicle status information using the digital twin representation of the vehicle. . In embodiments, the vehicle status information includes one or more of vehicle maintenance status, vehicle energy utilization status, vehicle navigation status, vehicle component status, or vehicle driver status. In embodiments, the user input for the digital twin representation includes one or more of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In an embodiment, the method includes managing a set of vehicle user identities and roles, and constructing a digital twin representation based on identities from the set of vehicle user identities. In embodiments, the method comprises one or more of a 5G connection to systems external to the vehicle, an internal 5G connection to the vehicle's set of sensors and data sources, or a 5G connection to an in-vehicle artificial intelligence system. It involves inputting a digital twin representation via an API from a configured vehicle edge intelligence system. In an embodiment, the method includes automatically constructing a digital twin representation with an artificial intelligence system based on a training set of usage activities by a set of digital twin users.

In an embodiment, a system for presenting a set of vehicle operating conditions to a driver of a vehicle includes a portion of the vehicle having the vehicle operating conditions and vehicle parameter data from one or more inputs to determine the vehicle operating conditions. and an interface for the digital twin system to present vehicle operating conditions to the driver of the vehicle.

In embodiments, the interface for the digital twin system provides the driver with a 3D view showing a three-dimensional rendering of the model of the vehicle. In embodiments, the interface for the digital twin system provides the driver with navigational views for improved situational awareness through real-time information exchange with nearby vehicles, pedestrians, and infrastructure. In embodiments, the interface for the digital twin system provides the driver with an energy view to determine battery/fuel status in the vehicle, including utilization and battery health. In an embodiment, the interface for the digital twin system provides the driver with a value view to display the vehicle status and blue book value based on the vehicle status. In embodiments, an interface for the digital twin system provides a service and maintenance view to display wear and failure of vehicle components and to predict the need for service, repair, or replacement based on vehicle condition conditions. provide to the driver. In embodiments, the interface for the digital twin system provides the driver with a world view to show the vehicle immersed in a virtual reality (VR) environment. In an embodiment, the vehicle operating state is a vehicle maintenance state. In an embodiment, the vehicle operating conditions are vehicle energy utilization conditions. In an embodiment, the vehicle operating state is a vehicle navigation state. In an embodiment, the vehicle operating states are vehicle component states. In an embodiment, the vehicle operating state is a vehicle driver state. In embodiments, inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In an embodiment, the system includes an identity management system for managing a set of vehicle user identities and roles. In an embodiment, the identity management system includes the ability to view, modify, and configure the digital twin system and is based on identities from a set of vehicle user identities. In embodiments, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to systems outside the vehicle. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to a set of vehicle sensors and data sources. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to the in-vehicle artificial intelligence system.

In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by the driver. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by the driver.

In an embodiment, the system includes a first neural detecting sensed well-being state of a driver in the vehicle through analysis of data collected from sensors deployed in the vehicle to collect the physiological state of the driver. a network and a second neural network for optimizing the operating parameters of the vehicle in response to the driver's sensed state of well-being to achieve the desired driver well-being.

In embodiments, the detected well-being state of the driver is the detected emotional state of the driver. In embodiments, the driver's preferred state of well-being is the driver's preferred emotional state. In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, the second neural network optimizes operating parameters based on correlations between vehicle operating conditions and driver satisfaction conditions of the driver. In an embodiment, the second neural network optimizes operating parameters in real-time in response to detection of the driver's detected well-being by the first neural network. In an embodiment, the first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a system for presenting a set of vehicle operating conditions to a vehicle manufacturer receives vehicle parameter data from a vehicle having vehicle operating conditions and one or more inputs to determine the vehicle operating conditions. A digital twin system and an interface for the digital twin system for presenting vehicle operating conditions to the vehicle manufacturer.

In an embodiment, an interface for a digital twin system produces a design view to inform a manufacturer in determining a portion of the optimal system architecture for a new vehicle model through generative design techniques. provide to traders. In an embodiment, the interface for the digital twin system is a representation of the assembly view to allow the manufacturer to run prescriptive models to optimize the performance of the vehicle and its components and subsystems. Provide a portion to the manufacturer. In embodiments, the interface provides the manufacturer with a portion of the quality view to enable the manufacturer to run simulations to quality test the vehicle and its components in real-world conditions. In embodiments, the interface allows manufacturers to perform data analysis to calculate a wide range of metrics, build charts, graphs, and models, and determine the impact of changes in parameters of the vehicle and its components on vehicle performance. provide manufacturers with a real-time analytical view to enable visibility into In embodiments, the interface for the digital twin system provides the manufacturer with a 3D view showing a three-dimensional rendering of the model of the vehicle. In embodiments, the interface for the digital twin system provides the manufacturer with an energy view for determining battery/fuel status in the vehicle, including utilization and battery health. In an embodiment, the interface for the digital twin system provides the manufacturer with a value view to display the vehicle's condition and blue book value based on the vehicle's condition. In embodiments, an interface for the digital twin system provides a service and maintenance view to display wear and failure of vehicle components and to predict the need for service, repair, or replacement based on vehicle condition conditions. provide to the manufacturer. In an embodiment, the vehicle operating state is a vehicle maintenance state. In embodiments, the vehicle operating conditions are vehicle energy utilization conditions. In embodiments, the vehicle operating state is a vehicle navigation state. In embodiments, the vehicle operating conditions are vehicle component conditions. In embodiments, the vehicle operating conditions are vehicle driver conditions. In embodiments, the one or more inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In an embodiment, the system includes an identity management system that manages a set of vehicle user identities and roles for whom consent for communication has been granted to the manufacturer. In embodiments, the identity management system includes the ability to view, modify, and configure the digital twin system and is based on identities from a set of vehicle user identities. In embodiments, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to systems outside the vehicle. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to a set of vehicle sensors and data sources. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to the in-vehicle artificial intelligence system. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by either the driver or the manufacturer.

In an embodiment, the system includes a first neural detecting sensed well-being state of a user onboard the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the user. a network and a second neural network for optimizing operating parameters of the vehicle in response to the user's sensed state of well-being to achieve the user's preferred state of well-being.

In embodiments, the user's detected well-being state is the user's detected emotional state. In embodiments, the user's preferred satisfaction state is the user's preferred emotional state. In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, the second neural network optimizes operating parameters based on the correlation between vehicle operating conditions and user satisfaction. In an embodiment, the second neural network optimizes operating parameters in real-time in response to detection of the user's detected state of well-being by the first neural network. In an embodiment, the first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a system for presenting a set of vehicle operating conditions to a vehicle dealer includes a vehicle having vehicle operating conditions and a digital vehicle receiving vehicle parameter data from one or more inputs to determine the vehicle operating conditions. It includes a twin system and an interface for the digital twin system for presenting vehicle operating conditions to the vehicle dealer. In embodiments, the interface provides dealers with a configurator view for configuring vehicles based on potential customer preferences by choosing compatible component and subsystem combinations from a set of available components. do. In embodiments, the interface provides the dealer with a performance tuning view for changing or adjusting the characteristics of one or more components to personalize the performance of the vehicle based on driver or rider preferences. .

In embodiments, one of the components is the vehicle's engine. In embodiments, one or more of the components is the suspension of the vehicle. In embodiments, one of the components is the body of the vehicle.

In embodiments, the interface provides the dealer with a test drive view to allow potential customers of the vehicle to virtually test drive the vehicle. In embodiments, the vehicle is a used vehicle.

In embodiments, the interface provides the dealer with a proof view to enable the dealer to provide proof regarding the condition of the vehicle to potential customers. In embodiments, the vehicle is a used vehicle.

In embodiments, the interface provides the dealer with a portion of the quality view to enable the dealer to run simulations to quality test the vehicle and its components in real-world conditions. In embodiments, the interface for the digital twin system provides the dealer with a 3D view showing a three-dimensional rendering of the model of the vehicle. In an embodiment, the interface for the digital twin system provides the dealer with a value view to display the vehicle condition and blue book value based on the condition of the vehicle. In embodiments, an interface for the digital twin system provides a service and maintenance view to display wear and failure of vehicle components and to predict the need for service, repair, or replacement based on vehicle condition conditions. provide to the dealer.

In an embodiment, the vehicle operating state is a vehicle maintenance state. In embodiments, the vehicle operating conditions are vehicle energy utilization conditions. In embodiments, the vehicle operating state is a vehicle navigation state. In embodiments, the vehicle operating conditions are vehicle component conditions. In embodiments, the vehicle operating conditions are vehicle driver conditions. In embodiments, one or more of the inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In an embodiment, the system includes an identity management system for managing a set of identities and roles of vehicle users for whom consent for communication has been granted to the dealer. In an embodiment, the identity management system includes the ability to view, modify, and configure the digital twin system, which is based on identities from a set of vehicle user identities.

In embodiments, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to systems outside the vehicle. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to a set of vehicle sensors and data sources. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to the in-vehicle artificial intelligence system.

In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by either the driver or dealer.

In an embodiment, the system includes a first neural detecting sensed well-being state of a user onboard the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the user. a network and a second neural network for optimizing operating parameters of the vehicle in response to the user's sensed state of well-being to achieve the user's preferred state of well-being.

In embodiments, the user's detected well-being state is the user's detected emotional state. In embodiments, the user's preferred satisfaction state is the user's preferred emotional state. In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, the second neural network optimizes operating parameters based on the correlation between vehicle operating conditions and user satisfaction. In an embodiment, the second neural network optimizes operating parameters in real-time in response to detection of the user's detected state of well-being by the first neural network. In an embodiment, the first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a system for presenting a set of vehicle operating conditions to a vehicle owner receives vehicle parameter data from a vehicle having the vehicle operating conditions and one or more inputs to determine the vehicle operating conditions. A digital twin system and an interface for the digital twin system for presenting vehicle operating conditions to a vehicle owner.

In embodiments, the interface for the digital twin system provides owners with a fleet monitoring view to track and monitor the movement/route/status of one or more vehicles. In embodiments, the interface for the digital twin system provides the owner with a driver behavior monitoring view to enable the owner to monitor instances of unsafe or unsafe driving by the driver. In embodiments, an interface for a digital twin system provides an owner with an insurance view to assist the owner in determining an insurance policy quote for the vehicle based on the condition of the vehicle. In embodiments, the interface for the digital twin system provides the owner with a compliance view to indicate compliance status with respect to emissions/pollutants and other regulatory mandates based on vehicle conditions. In embodiments, the interface provides the owner with a performance tuning view for changing or adjusting characteristics of one or more components to personalize the performance of the vehicle based on the owner's preferences. .

In embodiments, one of the components is the vehicle's engine. In embodiments, one or more of the components is the suspension of the vehicle. In embodiments, one of the components is the body of the vehicle.

In embodiments, the interface for the digital twin system provides the owner with a 3D view showing a three-dimensional rendering of the model of the vehicle. In an embodiment, the interface for the digital twin system provides the owner with a value view to display the vehicle's condition and blue book value based on the vehicle's condition. In embodiments, an interface for the digital twin system provides a service and maintenance view to display wear and failure of vehicle components and to predict the need for service, repair, or replacement based on vehicle condition conditions. Provide to owner. In an embodiment, the vehicle operating state is a vehicle maintenance state. In embodiments, the vehicle operating conditions are vehicle energy utilization conditions. In embodiments, the vehicle operating state is a vehicle navigation state. In embodiments, the vehicle operating conditions are vehicle component conditions. In embodiments, the vehicle operating conditions are vehicle driver conditions. In embodiments, one or more of the inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. In embodiments, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to systems outside the vehicle. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to a set of vehicle sensors and data sources.

In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to the in-vehicle artificial intelligence system. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by the owner.

In an embodiment, the system includes a first neural detecting sensed well-being state of a user onboard the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the user. a network and a second neural network for optimizing operating parameters of the vehicle in response to the user's sensed state of well-being to achieve the user's preferred state of well-being.

In embodiments, the user's detected well-being state is the user's detected emotional state. In embodiments, the user's preferred satisfaction state is the user's preferred emotional state. In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, the second neural network optimizes operating parameters based on the correlation between vehicle operating conditions and user satisfaction. In an embodiment, the second neural network optimizes operating parameters in real-time in response to detection of the user's detected state of well-being by the first neural network. In an embodiment, the first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a system for presenting a set of vehicle operating conditions to a rider of the vehicle includes a vehicle having the vehicle operating conditions and a digital vehicle receiving vehicle parameter data from one or more inputs to determine the vehicle operating conditions. A twin system and an interface for the digital twin system for presenting vehicle operating conditions to a rider of the vehicle.

In embodiments, the interface presents the experience optimization view to the rider to allow the rider to select an experience mode to personalize the riding experience based on the rider's preferences. offer.

In embodiments, the experience mode includes a comfort mode. In embodiments, the experience mode includes a sports mode. In embodiments, the experience mode includes a high efficiency mode. In embodiments, the experience mode includes a working mode. In embodiments, the experience mode includes an entertainment mode. In embodiments, the experience mode includes a sleep mode. In embodiments, the experience mode includes a relaxation mode. In embodiments, the experience mode includes a long-distance travel mode.

In an embodiment, a system for presenting a set of vehicle operating conditions to a user of a vehicle receives vehicle parameter data from a vehicle having the vehicle operating conditions and one or more inputs to determine the vehicle operating conditions. A digital twin and an interface for the digital twin for presenting the vehicle operational state to a vehicle user, managing a set of vehicle user identities and roles, and viewing the digital twin based on an analysis of the identity and role set , an identity management system that determines which features to change and configure.

In an embodiment, the vehicle operating state is a vehicle maintenance state. In embodiments, the vehicle operating conditions are vehicle energy utilization conditions. In embodiments, the vehicle operating state is a vehicle navigation state. In embodiments, the vehicle operating conditions are vehicle component conditions. In embodiments, the vehicle operating conditions are vehicle driver conditions. In embodiments, inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle.

In an embodiment, the system includes an identity management system for managing a set of vehicle user identities and roles. In embodiments, the identity management system includes the ability to view, modify, and configure a digital twin system that is based on identities from a set of vehicle user identities.

In embodiments, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to systems outside the vehicle. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to a set of vehicle sensors and data sources. In an embodiment, the digital twin system is input via an API from the vehicle's edge intelligence system that provides 5G connectivity to the in-vehicle artificial intelligence system.

In embodiments, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. In an embodiment, the digital twin system is automatically configured by an artificial intelligence system based on a training set of driver-user usage activities. In an embodiment, the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by rider users.

In an embodiment, the system first detects a detected well-being state of a rider user on board the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the rider user. and a second neural network that optimizes operating parameters of the vehicle in response to the rider-user's detected state of well-being to achieve the rider-user's preferred state of well-being.

In embodiments, the rider user's detected well-being state is the rider user's detected emotional state. In embodiments, the rider user's preferred state of well-being is the rider user's preferred emotional state. In an embodiment, the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. In embodiments, at least one of the neural networks is a hybrid neural network and includes a convolutional neural network. In an embodiment, the second neural network optimizes operating parameters based on correlations between vehicle operating conditions and the rider user's rider satisfaction. In an embodiment, the second neural network optimizes operating parameters in real-time in response to detection of the rider-user's detected well-being by the first neural network. In an embodiment, the first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. In embodiments, the operating parameters that are optimized include the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

In an embodiment, a system for presenting a set of vehicle operating conditions to a user of the vehicle includes a vehicle having the vehicle operating conditions and vehicle parameter data from one or more inputs to determine the vehicle operating conditions. It includes a digital twin to receive and an interface for the digital twin to present vehicle operating conditions to a user of the vehicle. In embodiments, the digital twin is linked to the user's identity such that the digital twin is automatically provided for display and configuration via the identified user's mobile device.

In an embodiment, a system for setting a vehicle experience based on a set of vehicle operating conditions and a set of rider user experience conditions comprises: a vehicle having vehicle operating conditions; a rider having user experience conditions; a digital twin system that receives vehicle parameter data and rider user experience data from one or more inputs to determine a combined state of the vehicle and rider, and configures the vehicle experience based on the combined state; include.

In an embodiment, a system for setting a vehicle experience based on a set of vehicle operating conditions and a set of driver user experience conditions includes a vehicle with vehicle operating conditions, a driver with user experience conditions, a vehicle and a driver a digital twin system that receives vehicle parameter data and driver user experience data from one or more inputs to determine a composite state of and configures the vehicle experience based on the composite state.

In embodiments, vehicle operating conditions include vehicle physical conditions. In embodiments, vehicle operating conditions include vehicle maintenance conditions. In embodiments, vehicle operating conditions include vehicle energy utilization conditions. In embodiments, vehicle operating conditions include vehicle component conditions. In embodiments, vehicle operating conditions include vehicle environmental conditions. In embodiments, the driver user experience state includes the driver physiological state. In an embodiment, the driver user experience state includes the driver psychological state. In embodiments, the driver user experience state includes the driver physical state. In embodiments, driver user experience states include driver position states. In embodiments, the driver user experience state includes the driver emotional state. In embodiments, the vehicle is an autonomous vehicle.

Any combination of features from the methods disclosed herein and/or features from the systems disclosed herein may be used together and/or any of these aspects It is understood that any feature from or all may be combined with any of the features of the embodiments and/or examples disclosed herein to achieve the advantages as described in this disclosure. Will.

In the accompanying figures, like reference numerals indicate identical or functionally similar elements throughout the individual figures, and are incorporated in and constitute a part of this specification, along with the following detailed description, and various implementations. It serves to further explain the aspects and to explain all the various principles and advantages according to the systems and methods disclosed herein.

1 is a perspective view of an architecture for a transport system showing certain exemplary components and arrangements associated with various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating the use of a hybrid neural network for optimizing vehicle powertrain components in connection with various embodiments of the present disclosure; FIG.

FIG. 2 is an illustrative diagram showing a set of states that may be provided as input to and/or governed by an expert system/artificial intelligence (AI) system associated with various embodiments of the present disclosure;

An expert system or AI system as described throughout this disclosure, or one or more sensors, cameras that may be taken as input by such systems and/or components thereof, or in connection with various embodiments of this disclosure , or a schematic drawing showing a range of parameters that may be provided as output from an external system.

1 is a perspective view of a set of vehicle user interfaces associated with various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view showing a set of interfaces between transport system components associated with various embodiments of the present disclosure;

1 is a perspective view illustrating a data processing system capable of processing data from various sources in connection with various embodiments of the present disclosure; FIG.

FIG. 11 is a perspective view illustrating a set of algorithms that may be executed in connection with one or more of the many embodiments of transportation systems described throughout this disclosure in connection with various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view of a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view of a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout the present disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating the systems and methods described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating the systems and methods described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating the systems and methods described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

FIG. 3 is a perspective view illustrating methods described throughout the present disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

FIG. 3 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure;

1 is a perspective view illustrating methods described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating a system described throughout this disclosure in relation to various embodiments of the present disclosure; FIG.

1 is a perspective view illustrating an architecture for a transportation system including a vehicle digital twin system showing certain exemplary components and arrangements associated with various embodiments of the present disclosure; FIG.

1 is a schematic diagram of a digital twin system integrated with an identity and access management system, according to certain embodiments of the present disclosure; FIG.

1 is a schematic diagram of an interface of a digital twin system presented on a user device of a driver of a vehicle in connection with various embodiments of the present disclosure; FIG.

FIG. 4 is a schematic diagram illustrating interaction between a driver and a digital twin using one or more views and modes of an interface according to an exemplary embodiment of the present disclosure;

1 is a schematic diagram of a digital twin system interface presented on a vehicle manufacturer's user device, in accordance with various embodiments of the present disclosure; FIG.

1 depicts a scenario in which a manufacturer uses the digital twin interface quality view to run simulations and generate what-if scenarios for vehicle quality testing, according to an exemplary embodiment of the present disclosure.

1 is a schematic diagram of an interface of a digital twin system presented on a vehicle dealer's user device; FIG.

FIG. 4 illustrates interaction between a dealer and a digital twin using one or more views for the purpose of personalizing a customer's experience of purchasing a vehicle, according to an exemplary embodiment;

1 illustrates a service and maintenance view presented to vehicle users, including drivers, vehicle manufacturers and dealers, in accordance with various embodiments of the present disclosure; FIG.

4 is a method used by a digital twin to detect vehicle failures and predict any future failures, according to an exemplary embodiment;

1 is a perspective view illustrating architecture of a vehicle having a digital twin system for performing predictive maintenance on the vehicle, according to an exemplary embodiment of the present disclosure; FIG.

4 is a flowchart illustrating a method for generating a digital twin of a vehicle, according to various embodiments of the present disclosure;

FIG. 4 is a perspective view illustrating an alternative architecture for a transportation system including a vehicle and a digital twin system, according to various embodiments of the present disclosure;

1 illustrates a digital twin representing a combined set of states for both a vehicle and a driver of the vehicle, according to certain embodiments of the present disclosure; FIG.

FIG. 2 is a schematic diagram illustrating a scenario in which an integrated vehicle and driver digital twin may compose a vehicle experience, according to an exemplary embodiment;

1 is a schematic diagram illustrating an example portion of an information technology system for traffic artificial intelligence leveraging a digital twin, according to some embodiments of the present disclosure; FIG.

Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help improve understanding of the many embodiments of the systems and methods disclosed herein. There is

The present disclosure will now be described in detail by describing various exemplary, non-limiting embodiments thereof with reference to the accompanying drawings and exhibits. This disclosure may, however, be embodied in many different forms and should not be construed as limited to the exemplary embodiments set forth herein. Rather, the embodiments are provided so that this disclosure will be thorough and will fully convey the concepts of the disclosure to those skilled in the art. The claims should be consulted to ascertain the true scope of this disclosure.

Before describing in detail embodiments in accordance with the systems and methods disclosed herein, it is to be observed that embodiments reside primarily in combinations of method and/or system components. Accordingly, system components and methods are appropriately represented in the drawings by conventional symbols, showing only the specific details relevant to understanding the embodiments of the systems and methods disclosed herein.

All documents mentioned in this document are hereby incorporated by reference in their entirety. References to singular items should be understood to include plural items and vice versa unless expressly stated otherwise or clear from the context. Grammatical conjunctions are intended to express any and all conjunctive combinations of clauses, sentences, words, etc. combined, unless otherwise stated or clear from context. Thus, the term "or" should generally be understood to mean "and/or", etc., unless the context clearly dictates otherwise.

The recitation of ranges of values herein is not intended to be limiting, and instead refers individually to any and all values that fall within the range, unless otherwise indicated herein. Each individual value within such a range is incorporated herein as if it were individually recited herein. The words "about," "about," etc. when accompanied by numerical values are interpreted to indicate deviations that would be understood by those skilled in the art to perform satisfactorily for their intended purpose. Numerical ranges and/or numerical values are provided herein by way of example only and do not limit the scope of the described embodiments. The use of any and all examples, or exemplary language (“for example,” “for example,” etc.) provided herein is merely for the purpose of better illuminating the embodiments and not the embodiments or claims. It does not impose any limitation on the scope of the term. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the embodiments.

In the following description, terms such as "first", "second", "third", "upper", "lower" are terms of convenience and unless explicitly stated otherwise, they are in chronological order. or as a limitation of any corresponding element. The term "set" should be understood to encompass sets having a single member or multiple members.

Referring to FIG. 1, an architecture for transport system 111 is depicted, showing certain exemplary components and arrangements associated with certain embodiments described herein. Transportation system 111 includes various mechanical, electrical, and It may include one or more vehicles 110 including software components and systems. The vehicle may have a vehicle user interface 123, which includes a set of interfaces including a steering system, buttons, levers, touch screen interfaces, audio interfaces, etc., as described throughout this disclosure. You can A vehicle may have a set of neural networks, such as one or more neural networks (which may include the hybrid neural network 147 described herein), such as to provide input to the expert system/artificial intelligence functions described throughout this disclosure. It may have a sensor 125 (including a camera 127). Sensors 125 and/or external information inform expert systems/artificial intelligence (AI) systems 136 to determine vehicle operational states 345 (FIG. 3), user experience states 346 (FIG. 3), and other information described herein. It may also be used to indicate or track one or more such vehicle states 144, which may be taken as inputs to or as outputs from a set of expert systems/AI components. Routing information 143 includes the use of in-vehicle and external navigation functions such as GPS (Global Position System), triangulation routing (such as cell towers), peer-to-peer routing with other vehicles 121, etc. , and take input from it. The collaboration engine 129 may facilitate collaboration between vehicles and/or users of vehicles for collective experience management, fleet management, and the like. Vehicles 110 may be networked among each other in a peer-to-peer fashion, such as using cognitive radio, cellular, wireless, or other networking capabilities. The AI system 136 or other expert system inputs a wide range of vehicle parameters 130, such as from on-board diagnostic systems, telemetry systems, and other software systems, as well as from sensors 125 located on the vehicle, and from external systems. may be received as In embodiments, the system may use a set of sequences, such as to induce a particular user action, and/or to provide feedback to the AI system 136, for learning about a sequence of results for accomplishing a given task or objective. feedback/rewards 148, incentives, and the like. An expert system or AI system 136 may communicate, use, manage, or retrieve the output from a set of algorithms 149, including a wide variety as described herein. In the embodiment of the present disclosure depicted in FIG. 1, data processing system 162 is connected to hybrid neural network 147 . Data processing system 162 may process data from a variety of sources (see FIG. 7). In the embodiment of the present disclosure depicted in FIG. 1, system user interface 163 is connected to hybrid neural network 147 . For further disclosure regarding interfaces, see the disclosure below in connection with FIG. FIG. 1 illustrates that vehicle perimeter 164 may be part of transportation system 111 . The vehicle surroundings may include roads, weather conditions, lighting conditions, and the like. FIG. 1 illustrates that devices 165, such as mobile phones and computer systems, navigation systems, etc., may be connected to various elements of the transportation system 111 and thus may be part of the transportation system 111 of the present disclosure. is shown.

Referring to FIG. 2, provided herein is a transportation system having a hybrid neural network 247 for optimizing a powertrain 213 of a vehicle, wherein at least two portions of the hybrid neural network 247 are A transportation system that optimizes different parts of the train 213 . An artificial intelligence system has a model of behavior (physical, electrodynamic, hydrodynamic, chemical, etc. for energy conversion, as well as a mechanical model for the behavior of various dynamically interacting system components). Based on this, the powertrain component 215 may be controlled. For example, AI system may control powertrain component 215 by manipulating powertrain operating parameters 260 to achieve powertrain state 261 . The AI system may be trained on a dataset of results (e.g., fuel efficiency, safety, rider satisfaction, etc.) and/or a dataset of operator behavior (e.g., sensor sets, cameras, etc., or sensed by the vehicle information system). The driver may be trained to operate the powertrain component 215 by training for the driver's actions). In an embodiment, one neural network optimizes one part of the powertrain (e.g. for gearshifting) and another neural network optimizes another part (e.g. braking, clutch engagement, or energy discharging and charging). etc.) may be used. Any of the powertrain components described throughout this disclosure may be controlled by a set of control instructions comprising outputs from at least one component of hybrid neural network 247 .

FIG. 3 is provided as an input to and/or governed by expert system/AI system 336, and may be used with various systems and components in various embodiments described herein. Shows a set of states that can be used in conjunction. State 344 includes vehicle operational state 345 including vehicle configuration state, component state, diagnostic state, performance state, location state, maintenance state, and many others, as well as experience-specific states, user emotional state 366, satisfaction state. 367, location state, content/entertainment state, and user experience state 346, including many others.

FIG. 4 may be taken as input by an expert or AI system 136 (FIG. 1), or components thereof, as described throughout this disclosure, or such systems and/or one or more sensors 125 ( 1), camera 127 (FIG. 1), or a range of parameters 430 that may be provided as output from an external system. Parameters 430 may include one or more goals 431 or objectives (such as iteration and/or machine learning, expert system/ such as to be optimized by an AI system). Parameters 430 may include market feedback parameters 435, such as relating to price, availability, location, etc. of goods, services, fuel, electricity, advertising, content, and the like. Parameters 430 may include rider condition parameters 437, such as parameters relating to comfort 439, emotional state, satisfaction, goals, trip type, fatigue, and the like. Parameters 430 can include various traffic-related parameters such as traffic profile 440 (location, direction, density, patterns over time, and many others), road profile 441 (elevation, curvature, direction, road surface conditions, and many others), user profile, and more. May contain profile parameters. Parameters 430 define routing parameters 442 such as current vehicle location, destination, waypoints, points of interest, trip type, trip goals, desired arrival time, desired user experience, and many others. may contain. Parameters 430 may include satisfaction parameters 443 for riders (including drivers), fleet managers, advertisers, merchants, owners, operators, insurance companies, regulators, and others. Parameters 430 may include operating parameters 444, including a variety of those described throughout this disclosure.

FIG. 5 illustrates a set of vehicle user interfaces 523 . The vehicle user interface 523 may include an electromechanical interface 568 such as a steering interface, brake interface, seat, window, moonroof, glovebox, etc. interfaces. Interface 523 may include various software interfaces (touch panels, dials, knobs, buttons, icons or other functions) such as game interface 569, navigation interface 570, entertainment interface 571, vehicle settings interface 572, search interface 573, e-commerce interface 574, and the like. may have). The vehicle interface may be used to provide input to, and be governed by, one or more AI/expert systems as described in embodiments throughout this disclosure.

FIG. 6 illustrates transport system components, including interfaces within the host system (such as managing a vehicle or fleet of vehicles) and host interfaces 650 between the host system and one or more third parties and/or external systems. Fig. 2 shows a series of interfaces between; The interfaces include third party interfaces 655 and end user interfaces 651 for users of the host system, including in-vehicle interfaces that can be used by riders as noted in connection with FIG. 5, as well as fleet managers, insurance companies, regulators, Also included are user interfaces for others such as police, advertisers, merchants, content providers, and many others. Interfaces may include a merchant interface 652, such that merchants may provide advertisements, content related to offerings, and one or more rewards for inducing routing or other actions on the part of the user. . Interfaces may include machine interfaces 653 such as application programming interfaces (APIs) 654, networking interfaces, peer-to-peer interfaces, connectors, brokers, extraction transform loading (ETL) systems, bridges, gateways, ports, and the like. The interface allows one or more of the many embodiments described herein, such as setting neural network components, setting weights for models, setting one or more goals or objectives, setting reward parameters 656, etc. It may include one or more host interfaces that the host may manage and/or configure. The interface includes selection of one or more models 658, selection and configuration of datasets 659 (such as sensor data, external data, and other inputs described herein), AI selection 660 and AI configuration 661 (neural network category selection, parameter weighting, etc.), expert system/AI system feedback selection 662 such as for learning, and supervisory configuration 663, and an expert system/AI system configuration interface 657 for many others.

FIG. 7 processes data from various sources including social media data sources 769, weather data sources 770, road profile sources 771, traffic data sources 772, media data sources 773, sensor sets 774, and many others. A possible data processing system 758 is shown. The data processing system extracts the data, transforms the data into an appropriate format (such as for use by interface systems, AI systems/expert systems, or other systems), loads it into the appropriate location, and renders the data. It can be configured to normalize, cleanse data, deduplicate data, store data (such as to enable querying), and perform a wide range of processing tasks described throughout this disclosure.

FIG. 8 illustrates a set of algorithms 849 that may be executed in conjunction with one or more of the many embodiments of transportation systems described throughout this disclosure. Algorithm 849 may take input from, provide output from, and be managed by a set of AI/expert systems, such as many types described herein. Algorithm 849 determines preferred states, parameters, or combinations of states/parameters in relation to optimizing one or more of the algorithms, systems described herein, for providing or managing user satisfaction 874. may include one or more genetic algorithms 875 such as for Algorithms 849 include vehicle routing algorithms 876 that are sensitive to various vehicle operating parameters, user experience parameters, or other conditions, parameters, profiles, etc. described herein, and various goals or objectives. It's okay. Algorithms 849 may include object detection algorithms 876 . Algorithms 849 may include energy calculation algorithms 877, such as to calculate energy parameters, to optimize fuel usage, electricity usage, etc., to optimize refueling or recharging times, locations, amounts, etc. good. Algorithms may include prediction algorithms, such as traffic prediction algorithm 879, traffic prediction algorithm 880, and algorithms for predicting other conditions or parameters of the transportation system as described throughout this disclosure.

In various embodiments, the transportation system 111 described herein may include vehicles (including fleets and other sets of vehicles), as well as various infrastructure systems. Infrastructure systems include Internet of Things systems (e.g., traffic lights, poles, toll booths, signs and other roadside devices and systems placed on or in roads, cameras and other sensors on or in buildings, etc.). use), refueling and charging systems (service stations, charging stations, etc., and wireless charging systems using wireless power transfer, etc.), and many others.

The electrical, mechanical and/or powertrain components of the vehicles described herein include transmissions, gear systems, clutch systems, braking systems, fuel systems, lubrication systems, steering systems, suspension systems, lighting systems (interior and emergency lighting as well as outdoor lighting), electrical systems, and their various subsystems and components.

Vehicle operating conditions and parameters include route, trip purpose, geolocation, direction, vehicle range, powertrain parameters, current gear, speed/acceleration, suspension profile (including various parameters such as each wheel), electrical and It can include state of charge for hybrid vehicles, fuel state for fueled vehicles, as well as many others described throughout this disclosure.

The rider and/or user experience states and parameters described throughout this disclosure may include emotional states, comfort states, psychological states (e.g., anxiety, tension, relaxation, etc.), wakefulness/sleep states, and/or satisfaction, wakefulness, health , wellness, one or more goals or objectives, and many others. The user experience parameters described herein include driving, braking, curve approach, seat position, window conditions, ventilation system, climate control, temperature, humidity, sound level, entertainment content type (e.g. news, music, sports , comedy, etc.), route selection (POIs, landscapes, new sites, etc.), and many others.

In embodiments, paths may be given various parameters of value, such as parameters of value that may be optimized to improve user experience or other factors under the control of an AI system/expert system. . Path value parameters include speed, duration, on-time arrival, length (e.g., in miles), goals (e.g., viewing POIs (Points of Interest), tasks (e.g., shopping list completion, delivery schedule completion, completion of a meeting, etc.), refueling or charging parameters, game-based goals, etc. As one of many examples, the route may be configured in the model and/or to optimize the route. Values can be attributed for task completion as input or feedback to an AI system or expert system designed by the user, for example, by interacting with a user interface or menu that can set objectives. A route can indicate a goal to meet at least one of a set of friends in a route, which can be a predicted friend location (which can be a neural network or other AI system/ and by providing an in-vehicle message (or a message to the mobile device) that indicates the likelihood of an appointment, so as to increase the likelihood of an appointment (other (including by interaction with a system that includes vehicle location information and/or inputs that provide awareness of the friend's location, such as social data feeds).

Market feedback factors include various elements of the transportation system as described throughout this disclosure, such as current and projected prices and/or costs (e.g., fuel, electricity, etc.) and along the route and/or vehicle (goods, services, content, etc. available in the capacity or availability of autonomous vehicles), supply and/or demand, and many others.

The in-vehicle or on-vehicle interface may include a negotiation system, such as a bidding system, a price negotiation system, a compensation negotiation system, and the like. For example, a user may bargain for a higher reward in exchange for agreeing to reroute to a merchant's location, and the user mentions the price the user would like to pay for fuel. (may be offered to a nearby refueling station that may offer to meet that price), or the like. Outputs from negotiations (agreed prices, trips, etc.) may automatically result in reconfiguration of routes, such as those governed by AI/expert systems.

Rewards as described herein, particularly as provided by merchants or hosts, include one or more coupons, such as redeemable at a location, high priority (such as in mass routing of multiple vehicles), Provision of rights, permission to use "fast lanes", prioritization of charging or refueling capabilities, and many others may be included. Activities that lead to rewards in vehicles include playing games, downloading apps, driving to a place, taking pictures of places or objects, visiting websites, watching or listening to advertisements, watching videos, and Many others may be included.

In embodiments, the AI system/expert system may use or optimize one or more parameters for charging plans, such as for charging batteries of electric or hybrid vehicles. Charging plan parameters include route (such as route to charging location), amount of charge or fuel provided, time for charging, battery state, battery charging profile, time required to charge, value of charge, value of charge Indices, market prices, bids for charging, available capacity (e.g. within a geofence or range of a collection of vehicles), demand (based on detected charging/refueling status, requested demand) etc.), supply, and others. Neural networks or other systems (optionally hybrid systems described herein) that employ models or algorithms (such as genetic algorithms) may be used (by being trained over a series of trials on the outcome, and/or using a training set of human-created or human-supervised inputs), can provide preferred and/or optimal charging plans for a vehicle or set of vehicles based on the parameters. Other inputs may include a priority for a particular vehicle (eg, for emergency responders or those given priority in connection with various embodiments described herein).

In embodiments, processors as described herein may include neural processing chips, such as those employing fabrics such as the lambda fabric. Such chips may have multiple cores, such as 256, each configured in a neuron-like arrangement with other cores on the same chip. Each core may constitute a microscale digital signal processor, and the fabric may allow the core to be easily connected to other cores on the chip. In embodiments, the fabric may connect a large number of cores (eg, over 500,000 cores) and/or chips, thereby, for example, providing large-scale neural networks, massively parallel computing, and It can facilitate use in computing environments that require complex conditional logic. In embodiments, low latency fabrics are used, such as those with device-to-device, rack-to-rack, etc. latencies of 400 ns, 300 ns, 200 ns, 100 ns, or less. The chip may be a low power chip such that it can be powered by energy harvesting from the environment, energy harvesting from test signals, energy harvesting from an on-board antenna, or the like. In embodiments, the core may be configured to enable application of a set of sparse matrix heterogeneous machine learning algorithms. The chip may run object-oriented programming languages such as C++, Java, and the like. In embodiments, the chip may be programmed to run each core with a different algorithm, thereby enabling one or more of the hybrid neural network embodiments described throughout this disclosure. heterogeneity can be achieved. The chip thereby takes multiple inputs from multiple data sources (e.g., one per core), performs massively parallel processing using a large set of different algorithms, and produces multiple outputs (either per core or per core). such as one per set) can be provided.

In embodiments, the chip implements security fabrics, such as fabrics for performing content inspection, packet inspection (against blacklists, whitelists, etc.), etc., in addition to taking on processing tasks such as neural networks, hybrid AI solutions, etc. include or enable.

In embodiments, the platforms described herein may include, integrate with, or connect with systems for robotic process automation (RPA), whereby artificial intelligence/machine learning systems are may be trained on a training set of data consisting of tracking and recording a set of human interactions as they interact with a series of interfaces, e.g. graphical user interfaces (e.g. mouse, trackpad, keyboard, through interaction with touch screens, joysticks, remote control devices), audio system interfaces (microphones, smart speakers, voice response interfaces, intelligent agent interfaces (e.g., Siri and Alexa), etc.). ), human-machine interfaces (robot systems, prosthetics, cybernetic systems, exoskeleton systems, wearables (clothes, headgear, headphones, watches, wristbands, eyeglasses, armbands, torso bands, belts, rings, necklaces and other accessories) ), physical or mechanical interfaces (e.g. buttons, dials, toggles, knobs, touch screens, levers, handles, steering systems, wheels, etc.), optical interfaces (trigger eye tracking, facial recognition, gesture recognition, emotion recognition, etc.) sensor-enabled interfaces (cameras, EEG or other electrical signal sensing (such as for brain-computer interfaces), magnetic sensing, accelerometers, galvanic skin response sensors, optical sensors, IR sensors, LIDAR , and other sensor sets that can recognize thoughts, gestures (faces, hands, postures, etc.), speech, etc.) In addition to tracking and recording human interactions, RPA systems can Sequences of states, actions, events and outcomes that occur by, in, from, or about the systems and processes involved can also be tracked and recorded.For example, RPA systems allow humans to human review of the video, such as highlighting points of interest in the video, tagging objects in the video, retrieving parameters (size, dimensions, etc.), or performing other operations on the video within a graphical user interface You may record mouse clicks on frames of video that appear within the process you are using. The RPA system can also record the state and events of the system or process, such as which elements were interacted with, what the state of the system was before, during and after the interaction, and what actions were taken by the system. It can be recorded whether output was provided or what results were achieved. Through a large training set of observing human interactions and system states, events, and outcomes, RPA systems can learn to interact with systems in a way that mimics that of humans. Learning is the ability of an RPA system to perform actions that a human would have performed (e.g., tag the correct object, label the item correctly, select the correct button to activate the next step in the process, etc.). May be augmented by training and monitoring, such as the human correcting as he or she attempts to perform a series of trials, during a series of trials the RPA system becomes increasingly effective at replicating behaviors that a human would have performed. can be made to be Learning is deep learning, such as by reinforcing learning based on outcomes such as successful process completion, financial yield, and many other outcome measures discussed throughout this disclosure. may include In embodiments, the RPA system may be seeded with a set of expert human interactions during the learning phase so that the RPA system begins to be able to replicate the expert's interactions with the system. For example, an expert driver's interactions with a robotic system, such as a remote-controlled vehicle or UAV, may be recorded along with information about the vehicle's state (e.g., surroundings, navigation parameters, and objectives) so that the RPA system can make the same selections as the expert driver. to learn to drive the vehicle in a way that reflects After being taught to replicate the human skills or expertise of an expert, the RPA system may transition to a deep learning mode, where the system is configured to try some level of variation in approach. further improved based on a set of results (e.g., if the RPA system is randomized, rule-based, etc., such as using variations/experiments (genetic programming techniques, random walk techniques, random forest techniques, etc.) and by selection track outcomes (using feedback) so that they can learn beyond the expertise of human experts. , acquire expertise in interacting with a system or process, and facilitate process automation (e.g., by taking over some of the more repetitive tasks, including those that require consistent execution of acquired skills). ), can give artificial intelligence a very effective seed, such as providing a seed model or system that can be improved by machine learning with feedback on the results of the system or process.

RPA systems are useful in situations where human expertise or knowledge is acquired through training and experience, and where the human brain and sensory system have been specifically adapted and evolved to solve computationally difficult or highly complex problems. , may be of particular value. Thus, in embodiments, the RPA system may be used to learn to undertake, among other things, visual pattern recognition tasks for the various systems, processes, workflows and environments described herein. (e.g. recognizing the meaning of dynamic interactions of objects or entities in a video stream (e.g. understanding what happens when humans and objects interact in a video), recognizing the significance of visual patterns (e.g. , recognizing objects, structures, defects and conditions in photographs or X-ray images); display of metrics within a visual pattern (such as the dimensions of an object indicated by clicking on a dimension such as an X-ray image); labeling activities within a visual pattern by category (e.g. which Recognition of patterns displayed as signals (e.g., waves or similar patterns in the frequency domain, time domain, or other signal processing representation), future states based on current states prediction of (e.g., predicting future states based on current states (e.g., predicting motion of flying or rolling objects, predicting human next actions in a process, predicting machine next steps, predicting human reactions to events, and many more), recognizing and predicting emotional states and reactions (e.g., based on facial expressions, posture, body language, etc.), achieving preferred states without deterministic calculations applying heuristics for (e.g. choosing a favorable strategy in sports or games, choosing a business strategy, choosing a negotiation strategy, setting the price of a product, developing a message to promote a product or idea, creative content , recognition of preferred style or fashion, and many others), any of many others.In embodiments, the RPA system performs visual inspection of people, systems, and objects (including internal workflows involving the execution of software tasks such as sequential interaction with a series of screens in a software interface; workflows involving remote manipulation of robots and other systems and devices; workflows involving content creation (e.g., selection , editing, and sequencing), workflows involving content creation can be automated. Content creation (content selection, editing, ordering, etc.), financial decision-making and negotiation (setting prices and terms for financial transactions, etc.), decision-making (selection of optimal configuration of systems or subsystems, workflows, processes, workflows with dynamic decision-making (e.g. choosing the optimal path or sequence of actions in other activities with dynamic decision-making).

In embodiments, the RPA system may use an array of IoT devices and systems (such as cameras and sensors) to track and record human actions and interactions with respect to various interfaces and systems in the environment. RPA systems may also use data from on-board sensors, telemetry, and event recording systems (such as telemetry systems on vehicles and event logs on computers). Thus, RPA systems include various entities (human and non-human), systems, processes, applications (e.g., software applications used to enable workflows), states, events, and outcomes. or a set of dedicated RPA systems) to automate various processes and workflows to achieve them in a way that reflects and mimics accumulated human expertise, and ultimately further machine learning. can be used to improve the results of that human expertise by

Referring to FIG. 9, in embodiments provided herein, at least one genetic algorithm is used to search a set of possible vehicle operating conditions 945 to determine at least one optimized operating condition. A transport system 911 with an artificial intelligence system 936 using algorithms 975 . In an embodiment, genetic algorithm 975 takes inputs related to at least one vehicle performance parameter 982 and at least one rider state 937 .

Aspects provided herein are a transportation system 911 that includes a vehicle 910 having a vehicle operating state 945 and generating variations from the initial vehicle operating state to determine at least one optimized vehicle operating state. and an artificial intelligence system 936 that executes a genetic algorithm 975 . In an embodiment, vehicle operating state 945 includes a set of vehicle parameter values 984 . In an embodiment, the genetic algorithm 975 varies the set of vehicle parameter values 984 for a corresponding set of time periods such that the vehicle 910 operates according to the set of vehicle parameter values 984 during the corresponding time periods, and performs the evaluation. Evaluating the vehicle operating conditions 945 for each of the corresponding time periods according to the set of actions 983 to generate, and selecting an optimized set of vehicle parameter values for future operation of the vehicle 910 based on the evaluation.

In an embodiment, vehicle operating states 945 include rider states 937 of riders of the vehicle. In an embodiment, the at least one optimized vehicle operating condition includes an optimized rider condition. In an embodiment, the genetic algorithm 975 is to optimize the lidar state. In an embodiment, evaluating according to the set of actions 983 is to determine rider conditions corresponding to vehicle parameter values 984 .

In an embodiment, the vehicle operating state 945 includes the state of the rider of the vehicle. In an embodiment, vehicle parameter value sets 984 include vehicle performance control value sets. In embodiments, the at least one optimized vehicle operating condition includes an optimized condition of vehicle performance. In an embodiment, the genetic algorithm 975 is to optimize rider conditions and vehicle performance conditions. In an embodiment, evaluating according to the set of actions 983 is to determine a rider state and a vehicle performance state corresponding to vehicle performance control values.

In an embodiment, vehicle parameter value sets 984 include vehicle performance control value sets. In embodiments, the at least one optimized vehicle operating condition includes an optimized condition of vehicle performance. In an embodiment, the genetic algorithm 975 is to optimize the state of vehicle performance. In an embodiment, evaluating according to the set of actions 983 is to determine a state of vehicle performance corresponding to a vehicle performance control value.

In an embodiment, the set of vehicle parameter values 984 includes rider occupancy parameter values. In an embodiment, the rider occupancy parameter value affirms the presence of a rider on vehicle 910 . In an embodiment, vehicle operating states 945 include rider states 937 for riders of the vehicle. In embodiments, the at least one optimized vehicle operating condition includes an optimized rider condition. In an embodiment, the genetic algorithm 975 is to optimize the lidar state. In an embodiment, evaluating according to the set of actions 983 is to determine rider conditions corresponding to vehicle parameter values 984 . In an embodiment, the rider status includes a rider satisfaction parameter. In an embodiment, the rider's state includes input representative of the rider. In embodiments, the rider-representative input is selected from the group consisting of a rider state parameter, a rider comfort parameter, a rider emotional state parameter, a rider satisfaction parameter, a rider goal parameter, a trip classification, and combinations thereof.

In an embodiment, vehicle parameter value sets 984 include vehicle performance control value sets. In embodiments, the at least one optimized vehicle operating condition includes an optimized condition of vehicle performance. In an embodiment, the genetic algorithm 975 is to optimize rider conditions and vehicle performance conditions. In an embodiment, the evaluation according to the set of actions 983 is to determine rider status and vehicle performance status corresponding to vehicle performance control values. In an embodiment, the set of vehicle parameter values 984 includes a set of vehicle performance control values. In embodiments, the at least one optimized vehicle operating condition includes an optimized condition of vehicle performance. In an embodiment, the genetic algorithm 975 is to optimize the state of vehicle performance. In an embodiment, evaluating according to the set of actions 983 is to determine a state of vehicle performance corresponding to a vehicle performance control value.

In an embodiment, the set of vehicle performance control values includes fuel efficiency, duration of trip, vehicle wear, vehicle make, vehicle model, vehicle energy consumption profile, fuel capacity, real-time fuel level, charging capacity, charging capacity, regenerative braking status, and selected from the group consisting of combinations thereof; In embodiments, at least a portion of the set of vehicle performance control values are provided from at least one of an on-board diagnostic system, a telemetry system, a software system, sensors located on the vehicle, and systems external to the vehicle 910. be done. In an embodiment, the set of actions 983 are associated with a set of vehicle operating criteria. In an embodiment, the set of measures 983 relates to a set of rider satisfaction criteria. In an embodiment, the set of actions 983 relate to a combination of vehicle performance criteria and rider satisfaction criteria. In embodiments, each evaluation uses feedback that indicates an impact on at least one of vehicle performance state and rider state.

Aspects provided herein are systems for transportation 911 in which a genetic algorithm 975 is used to optimize a set of vehicle parameters affecting vehicle state or rider state 937 . It features an artificial intelligence system 936 that processes inputs representative of the state of the vehicle during and the input representative of the rider state 937 of the rider occupying the vehicle. In an embodiment, the genetic algorithm 975 is to perform a series of evaluations using variations of the input. In embodiments, each evaluation in the series of evaluations uses feedback that indicates an effect on at least one of vehicle operating state 945 and rider state 937 . In an embodiment, an input representing rider status 937 indicates that the rider is absent from vehicle 910 . In an embodiment, the vehicle state includes vehicle operating state 945 . In an embodiment, the vehicle parameters in the set of vehicle parameters include vehicle performance parameters 982 . In an embodiment, the genetic algorithm 975 is to optimize a set of vehicle parameters for rider conditions.

In an embodiment, optimizing the set of vehicle parameters is responsive by genetic algorithm 975 to identifying at least one vehicle parameter that provides favorable rider conditions. In an embodiment, genetic algorithm 975 is to optimize a set of vehicle parameters for vehicle performance. In an embodiment, the genetic algorithm 975 is to optimize a set of vehicle parameters for rider condition and to optimize the set of vehicle parameters for vehicle performance. In an embodiment, optimizing the set of vehicle parameters is responsive to genetic algorithm 975 identifying at least one of a preferred vehicle operating state and a preferred vehicle performance that maintains rider state 937. is. In an embodiment, artificial intelligence system 936 further includes a neural network selected from a plurality of different neural networks. In an embodiment, neural network selection includes a genetic algorithm 975 . In embodiments, neural network selection is based on structured competition between multiple different neural networks. In an embodiment, genetic algorithm 975 facilitates training a neural network to process interactions between multiple vehicle operating systems and riders to produce an optimized set of vehicle parameters. do.

In embodiments, the set of inputs related to the at least one vehicle parameter is provided by at least one of an on-board diagnostic system, a telemetry system, sensors located on the vehicle, and systems external to the vehicle. In embodiments, the input representative of rider state 937 consists of at least one of comfort, emotional state, satisfaction, goals, trip classification, or fatigue. In embodiments, inputs representative of rider status 937 reflect satisfaction parameters of at least one of drivers, fleet managers, advertisers, merchants, owners, operators, insurers, and regulators. In an embodiment, the input representative of rider state 937 consists of input about the user that, when processed by the cognitive system, results in rider state 937 .

Referring to FIG. 10, embodiments provided herein provide a transportation system 1011 having a hybrid neural network 1047 for optimizing the operating conditions of the continuously variable powertrain 1013 of the vehicle 1010 . In an embodiment, at least a portion of hybrid neural network 1047 operates to classify the state of vehicle 1010 and another portion of hybrid neural network 1047 operates to optimize at least one operating parameter 1060 of transmission 1019. Operate. In embodiments, vehicle 1010 may be a self-driving vehicle. In one example, the first portion 1085 of the hybrid neural network may detect the vehicle 1010 in high traffic conditions (e.g., using LIDAR, RADAR, etc. to indicate the presence of other vehicles, or obtaining input from traffic monitoring systems, or mobile traffic). devices may be classified to operate by detection of high density presence, etc.), adverse weather conditions (e.g., wet roads (e.g., using vision-based systems), precipitation (e.g., determined by radar), by taking inputs that indicate the presence of ice (temperature sensing, vision-based sensing, etc.), hail (impact detection, sound sensing, etc.), lightning (vision-based systems, sound-based systems, etc.), etc.), etc. Once classified, another neural network 1086 (optionally of another type) may optimize vehicle operating parameters based on the classified conditions, such as by placing vehicle 1010 in a safe driving mode ( Auto-braking more aggressively than in good weather, e.g. by providing forward-sensing warnings at a greater distance and/or slower than in good weather, thereby providing auto-braking earlier and more aggressively than in good weather provide automatic braking more aggressively than in good weather).

Aspects provided herein are a system 1011 for transportation comprising a hybrid neural network 1047 for optimizing operating conditions of a continuously variable powertrain 1013 of a vehicle 1010 . In an embodiment, part 1085 of hybrid neural network 1047 is operable to classify state 1044 of vehicle 1010, thereby producing a classified state of the vehicle; A portion 1086 is operable to optimize at least one operating parameter 1060 of the transmission 1019 portion of the continuously variable powertrain 1013 .

In an embodiment, transportation system 1011 includes artificial intelligence system 1036 operating on at least one processor 1088 and artificial intelligence system 1036 operating portion 1085 of hybrid neural network 1047 operating to classify vehicle conditions. an artificial intelligence system 1036 that operates another portion 1086 of the hybrid neural network 1047 to optimize at least one operating parameter 1087 of the transmission 1019 portion of the continuously variable powertrain 1013 based on the classified vehicle conditions; is further provided. In an embodiment, vehicle 1010 constitutes a system for automating at least one control parameter of the vehicle. In embodiments, vehicle 1010 is at least a semi-autonomous vehicle. In an embodiment, vehicles 1010 are automatically routed. In an embodiment, vehicle 1010 is a self-driving vehicle. In an embodiment, the categorized status of the vehicle includes vehicle maintenance status, vehicle health status, vehicle operating status, vehicle energy utilization status, vehicle charging status, vehicle satisfaction status, vehicle component status, vehicle subsystem status, vehicle powertrain system status. state, vehicle brake system state, vehicle clutch system state, vehicle lubrication system state, vehicle traffic infrastructure system state, or vehicle occupant state. In embodiments, at least a portion of hybrid neural network 1047 is a convolutional neural network.

FIG. 11 is a diagram illustrating a method 1100 for optimizing operation of a continuously variable vehicle powertrain of a vehicle, according to embodiments of the systems and methods disclosed herein. At 1102, the method includes executing a first of the hybrid neural networks on at least one processor, the first network classifying a plurality of operating conditions of the vehicle. In embodiments, at least some of the operating conditions are based on the conditions of the vehicle's continuously variable powertrain. At 1104, the method includes executing a second network of hybrid neural networks on the at least one processor, the second network analyzing the vehicle for at least one of the plurality of classified driving conditions of the vehicle. and processing inputs describing at least one detected condition associated with the vehicle occupants. In an embodiment, processing the input by the second network causes optimization of at least one operating parameter of the continuously variable powertrain of the vehicle for multiple operating conditions of the vehicle.

10 and 11 together, in an embodiment the vehicle comprises an artificial intelligence system 1036 and the method further includes automating at least one control parameter of the vehicle with the artificial intelligence system 1036. In embodiments, vehicle 1010 is at least a semi-autonomous vehicle. In an embodiment, vehicles 1010 are automatically routed. In an embodiment, vehicle 1010 is a self-driving vehicle. In an embodiment, the method optimizes at least one of the continuously variable powertrains 1013 by adjusting at least one other operating parameter 1087 of the transmission 1019 portion of the continuously variable powertrain 1013 by the artificial intelligence system 1036 . Further comprising optimizing the operating conditions of the vehicle's continuously variable powertrain 1013 based on the operating parameters 1060 .

In an embodiment, the method further comprises optimizing operating conditions of continuously variable powertrain 1013 by processing social data from multiple social data sources by artificial intelligence system 1036 . In an embodiment, the method further includes optimizing the operating conditions of the continuously variable powertrain 1013 by processing data provided by the artificial intelligence system 1036 from a stream of data from unstructured data sources. Prepare. In an embodiment, the method further comprises optimizing the operating conditions of continuously variable powertrain 1013 by processing data supplied from the wearable device by artificial intelligence system 1036 . In an embodiment, the method further comprises optimizing the operating conditions of the continuously variable powertrain 1013 by processing data supplied from onboard sensors by the artificial intelligence system 1036 . In an embodiment, the method further comprises optimizing the operating conditions of the continuously variable powertrain 1013 by processing data supplied from the rider's helmet by the artificial intelligence system 1036 .

In an embodiment, the method further comprises optimizing the operating conditions of the continuously variable powertrain 1013 by processing data supplied from the rider headgear by the artificial intelligence system 1036 . In an embodiment, the method further comprises optimizing the operating conditions of the continuously variable powertrain 1013 by processing data supplied from the lidar audio system by the artificial intelligence system 1036 . In an embodiment, the method operates a third network of hybrid neural networks 1047 by artificial intelligence system 1036 to determine at least one of a plurality of classified operating states of the vehicle and at least one operation of transmission 1019. and predicting the vehicle state based at least in part on the parameters. In an embodiment, the first network of hybrid neural networks 1047 constitutes a structure adaptive network for adapting the structure of the first network in response to the results of operating the first network of hybrid neural networks 1047. are doing. In an embodiment, a first network of hybrid neural network 1047 is to process social data from social data sources to classify operational states of the vehicle.

In embodiments, at least a portion of hybrid neural network 1047 is a convolutional neural network. In embodiments, at least one of the categorized plurality of operational states of the vehicle is a vehicle maintenance state or a vehicle health state. In embodiments, at least one of the categorized states of the vehicle is vehicle operating state, vehicle energy utilization state, vehicle charging state, vehicle satisfaction state, vehicle component state, vehicle subsystem state, vehicle powertrain system state, vehicle braking. system status, vehicle clutch system status, vehicle lubrication system status, or vehicle traffic infrastructure system status. In embodiments, at least one of the categorized states of the vehicle is a vehicle driver state. In embodiments, at least one of the categorized states of the vehicle is a vehicle rider state.

Referring to FIG. 12, provided herein, in embodiments, at least within a set of vehicles 1294 based on route parameters determined by facilitating negotiation between a specified set of vehicles. A transport system 1211 with a cognitive system for routing one vehicle 1210 . In embodiments, the negotiation accepts input regarding the value that at least one rider attributes to at least one parameter 1230 of route 1295 . User 1290 is attributed by behavior (e.g., arriving on time, following predetermined route 1295, etc.) through a user interface that evaluates one or more parameters (e.g., any of the parameters noted throughout). (e.g., by offering or providing value (e.g., by offering currency, tokens, points, cryptocurrencies, rewards, etc.)). For example, a user 1290 may negotiate a preferred route by providing the system with a token that is awarded if the user 1290 arrives at a specified time, while others take alternative routes ( may offer to accept tokens in exchange for reducing congestion). Thus, the artificial intelligence system may optimize the combination of offers to provide rewards or undertake actions in response to rewards such that the reward system optimizes the set of outcomes. Negotiation includes explicit negotiation, for example, where the driver offers to reward the driver ahead of him on the road in exchange for temporarily leaving the route as the driver passes. It's okay.

Aspects provided herein are a system 1211 for transportation in which at least one vehicle within a set of vehicles 1294 is routed based on routing parameters determined by facilitating negotiation between a specified set of vehicles. A cognitive system for routing two vehicles 1210 wherein negotiation includes receiving input regarding values attributed to at least one parameter of a route 1295 by at least one user 1290 .

FIG. 13 is a diagram illustrating a method 1300 of negotiation-based vehicle routing in accordance with embodiments of the systems and methods disclosed herein. At 1302, the method includes facilitating negotiation of route adjustments for a plurality of parameters used by a vehicle routing system to route at least one vehicle in the set of vehicles. At 1304, the method includes determining parameters in the plurality of parameters for optimizing at least one result based on the negotiation.

12 and 13, in an embodiment user 1290 is a manager for a set of roads used by at least one vehicle 1210 in set of vehicles 1294 . In embodiments, user 1290 is an administrator for a fleet of vehicles that includes set 1294 of vehicles. In an embodiment, the method further includes providing the user 1290 with a set of provided user-indicated values for the plurality of parameters 1230 for the set of vehicles 1294 . In an embodiment, the route adjustment values 1224 are based at least in part on the set of user-indicated values 1297 provided. In embodiments, route adjustments 1224 are further made based on at least one user response to the offer. In an embodiment, the route adjustment values 1224 are based at least in part on a set of provided user instruction values 1297 and at least one response thereto by at least one user of the set of vehicles 1294 . In embodiments, the determined parameters facilitate adjusting the route 1295 of at least one of the vehicles 1210 within the set of vehicles 1294 . In embodiments, adjusting the route includes prioritizing the determined parameters for use by the vehicle routing system.

In embodiments, facilitating negotiation includes facilitating negotiation of a price for the service. In embodiments, facilitating negotiations includes facilitating price negotiations for fuel. In embodiments, facilitating negotiation includes facilitating negotiation of a price for charging. In embodiments, facilitating negotiation includes facilitating negotiation of rewards for taking routing actions.

Aspects provided herein include a transportation system 1211 for negotiation-based vehicle routing. A route in which users 1290 of a set of users 1291 negotiate route adjustments 1224 for at least one of a plurality of parameters 1230 used by a vehicle routing system 1292 to route at least one vehicle 1210 in a set of vehicles 1294. an adjustment negotiation system 1289 and a user route optimization circuit 1293 that optimizes a portion of a route 1295 for at least one user 1290 of a set of vehicles 1294 based on route adjustment values 1224 for at least one of a plurality of parameters 1230; Prepare. In an embodiment, route adjustment values 1224 are based at least in part on user indicated values 1297 and at least one negotiation response thereto by at least one user of vehicle set 1294 . In an embodiment, transportation system 1211 further comprises a vehicle-based route negotiation interface into which user indications 1297 for parameters 1230 used by the vehicle routing system are captured. In embodiments, user 1290 is a rider of at least one vehicle 1210 . In embodiments, user 1290 is the manager of a set of roads 1294 used by at least one vehicle 1210 .

In embodiments, user 1290 is an administrator for a fleet of vehicles that includes vehicle set 1294 . In embodiments, at least one of plurality of parameters 1230 facilitate adjusting route 1295 of at least one vehicle 1210 . In an embodiment, adjusting the route 1295 includes prioritizing parameters determined for use by the vehicle routing system. In embodiments, at least one of the user-indicated values 1297 is reduced to at least one of the plurality of parameters 1230 via an interface to facilitate expression of the evaluation of one or more route parameters. In embodiments, a vehicle-based route negotiation interface facilitates the expression of ratings for one or more route parameters. In an embodiment, user indicated values 1297 are derived from user 1290 actions. In embodiments, a vehicle-based route negotiation interface facilitates translating user behavior into user directives 1297 . In embodiments, the user behavior reflects the value assigned to at least one parameter used by the vehicle routing system to influence the route 1295 of at least one vehicle 1210 in vehicle set 1294 . In embodiments, the user-indicated value indicated by at least one user 1290 correlates to the item of value provided by the user 1290 . In embodiments, the item of value is offered by the user 1290 through offering of the item of value in exchange for routing results based on at least one parameter. In an embodiment, negotiating route adjustments 1224 includes providing items of value to users of vehicle set 1294 .

Referring to FIG. 14, in the embodiments provided herein, at least one vehicle 1410 is selected within a vehicle set 1494 based on routing parameters determined by facilitating coordination between designated vehicle sets 1498 . A transport system 1411 is provided that has a cognitive system for routing. In embodiments, coordination is accomplished by taking at least one input from at least one game-based interface 1499 for the rider of the vehicle. The game-based interface 1499 may include rewards for undertaking game-like behaviors (ie, game activity 14101) that provide ancillary benefits. For example, the rider of vehicle 1410 may be rewarded for routing vehicle 1410 to off-highway points of interest (collecting coins, capturing items, etc.), and the rider's departure is , to make room for other vehicles trying to achieve other objectives, such as arriving on time. For example, a game such as Pokemon Go™ may be configured to indicate the presence of rare Pokemon™ creatures to draw traffic away from crowded areas. Others may provide rewards (eg, currency, cryptocurrency, etc.) that can be pooled to attract users 1490 off the busy roads.

Aspects provided herein are a system 1411 for transportation in which routing within a vehicle set 1494 is based on a set of routing parameters 1430 determined by facilitating coordination between a designated vehicle set 1498 . Coordination is achieved by taking at least one input from at least one game-based interface 1499 to the user 1490 of the vehicle 1410 in the vehicle set 1498. It is characterized by comprising a recognition system.

In an embodiment, a system for transportation includes a vehicle routing system 1492 that routes at least one vehicle 1410 based on a set of routing parameters 1430 and a user 1490 performing a game activity 14101 provided in a game-based interface 1499. Further comprising a game-based interface 1499 for prompting routing preferences 14100 for at least one vehicle 1410 in the set of vehicles 1494 to undertake, the game-based interface 1499 prompting the user 1490 to provide routing parameters based on the set of routing parameters 1430 . to induce it to accept its preferred set of routing alternatives. As used herein, “route” means to select path 1495 .

In an embodiment, vehicle routing system 1492 considers routing preferences 14100 of user 1490 when routing at least one vehicle 1410 within vehicle set 1494 . In an embodiment, the game-based interface 1499 is arranged for in-vehicle use, as shown in FIG. 14 by the line extending from the game-based interface into the box for vehicle 1 . In embodiments, user 1490 is a rider of at least one vehicle 1410 . In an embodiment, user 1490 is the manager of a road set used by at least one vehicle 1410 in vehicle set 1494 . In embodiments, user 1490 is an administrator for a fleet of vehicles that includes set 1494 of vehicles. In an embodiment, the set of routing parameters 1430 includes traffic congestion, desired arrival time, preferred route, fuel efficiency, pollution reduction, accident avoidance, bad weather avoidance, bad road conditions avoidance, fuel consumption reduction, carbon footprint. reduction of local noise, avoidance of high crime areas, collective satisfaction, maximum speed limits, avoidance of toll roads, avoidance of city roads, avoidance of undivided highways, avoidance of left turns, avoidance of driver-operated vehicles contains at least one In embodiments, game activity 14101 provided in game-based interface 1499 includes contests. In embodiments, game activities 14101 provided in game-based interface 1499 include entertainment games.

In embodiments, game activity 14101 provided in game-based interface 1499 includes competitive games. In embodiments, game activity 14101 provided in game-based interface 1499 includes a strategy game. In embodiments, game activity 14101 provided in game-based interface 1499 includes a scavenger hunt. In an embodiment, the set of advantageous route selections are configured such that vehicle routing system 1492 achieves fuel efficiency goals. In an embodiment, the set of advantageous route choices is configured such that vehicle routing system 1492 achieves traffic reduction objectives. In an embodiment, the set of advantageous routings is configured such that the vehicle routing system 1492 achieves the reduced pollution objective. In an embodiment, the advantageous routing set is configured such that vehicle routing system 1492 achieves a reduced carbon footprint objective.

In an embodiment, the set of advantageous route selections is configured such that the vehicle route control system 1492 achieves the neighborhood noise reduction objective. In an embodiment, the advantageous routing set is configured such that vehicle routing system 1492 achieves the goal of collective satisfaction. In an embodiment, the set of advantageous route selections is configured such that the vehicle route control system 1492 achieves the goal of avoiding the accident scene. In an embodiment, the set of advantageous route selections is configured so that the vehicle routing system 1492 achieves the goal of avoiding high crime areas. In an embodiment, the set of advantageous route choices is configured such that vehicle routing system 1492 achieves the goal of reducing traffic congestion. In an embodiment, the advantageous routing set is configured so that vehicle routing system 1492 achieves severe weather avoidance objectives.

In an embodiment, the set of advantageous route choices is configured such that the vehicle route control system 1492 achieves the maximum travel time goal. In an embodiment, the advantageous routing set is configured such that vehicle routing system 1492 achieves maximum speed limit objectives. In an embodiment, the set of advantageous route choices is configured such that the vehicle routing system 1492 achieves toll road avoidance objectives. In an embodiment, the advantageous routing set is configured such that vehicle routing system 1492 achieves city road avoidance objectives. In an embodiment, the advantageous routing set is configured such that vehicle routing system 1492 achieves undivided highway avoidance. In an embodiment, the advantageous routing set is configured so that the vehicle routing system 1492 achieves the left turn avoidance objective. In an embodiment, the advantageous routing set is configured such that the vehicle routing system 1492 achieves driver-operated vehicle avoidance objectives.

FIG. 15 is a diagram illustrating a method 1500 of game-based collaborative vehicle routing according to embodiments of the systems and methods disclosed herein. At 1502, the method includes presenting, in a game-based interface, a game activity that affects vehicle route preferences. At 1504, the method includes receiving a user response to the presented game activity via the game-based interface. At 1506, the method includes adjusting the user's route preferences in response to the received response. At 1508, the method includes determining at least one vehicle routing parameter used to route the vehicle to reflect the adjusted routing preferences for routing the vehicle. In, the method includes, in a vehicle routing system, routing vehicles in the set of vehicles in response to at least one determined vehicle routing parameter adjusted to reflect the adjusted routing preferences. , routing the vehicle includes adjusting the determined routing parameters for at least a plurality of vehicles in the set of vehicles.

14 and 15, in an embodiment, the method further comprises indicating, via game-based interface 1499, reward value 14102 for accepting game activity 14101. FIG. In an embodiment, game-based interface 1499 further comprises routing preference negotiation system 1436 for negotiating reward values 14102 for riders to accept game activity 14101 . In an embodiment, reward value 14102 is the result of pooling value contributions from riders in a set of vehicles. In an embodiment, at least one routing parameter 1430 used by vehicle routing system 1492 to route vehicles 1410 in vehicle set 1494 is associated with game activity 14101 and user acceptance of game activity 14101 is a routing preference. Adjust at least one routing parameter 1430 (eg, with routing adjustment value 1424) to reflect the . In embodiments, user responses to presented game activity 14101 are derived from user interaction with game-based interface 1499 . In embodiments, the at least one routing parameter used by vehicle routing system 1492 to route vehicle 1410 in vehicle set 1494 includes at least one of the following. Traffic Congestion, Desired Arrival Time, Preferred Route, Fuel Efficiency, Pollution Reduction, Accident Avoidance, Bad Weather Avoidance, Bad Road Conditions Avoidance, Lower Fuel Consumption, Lower Carbon Emissions, Lower Local Noise, High Crime At least one of the following: neighborhood avoidance, collective satisfaction, maximum speed limit, toll road avoidance, city road avoidance, undivided highway avoidance, left turn avoidance, and maneuver vehicle avoidance.

In embodiments, game activity 14101 presented in game-based interface 1499 includes a contest. In embodiments, game activity 14101 presented in game-based interface 1499 includes entertainment games. In embodiments, game activity 14101 presented in game-based interface 1496 includes competitive games. In embodiments, game activity 14101 presented in game-based interface 1499 includes a strategy game. In an embodiment, game activity 14101 presented in game-based interface 1499 includes a scavenger hunt. In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves fuel efficiency goals. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the reduced traffic objective.

In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves reduced pollution goals. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves a reduced carbon footprint objective. In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves neighborhood noise reduction objectives. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the goal of collective satisfaction. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the goal of avoiding the accident scene. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the goal of avoiding high crime areas. In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves traffic congestion reduction objectives.

In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the goal of severe weather avoidance. In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves a maximum travel time goal. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the maximum speed limit objective. In embodiments, routing in response to at least one determined vehicle routing parameter 14103 achieves the goal of toll road avoidance. In an embodiment, routing in response to the at least one determined vehicle routing parameter 14103 achieves city road avoidance objectives. In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves undivided highway objective avoidance. In an embodiment, routing in response to at least one determined vehicle routing parameter 14103 achieves left turn objective avoidance. In an embodiment, routing in response to the at least one determined vehicle routing parameter 14103 achieves an avoidance objective for the driver-operated vehicle.

In embodiments, provided herein is a transport system 1611 having a cognitive system for routing at least one vehicle, the routing being a rider taking on an action while in the vehicle. determined at least in part by processing at least one input from a rider interface that can obtain a reward 16102 by. In an embodiment, the rider interface rewards the rider for controlling the routing of the vehicle's navigation system (or of a rideshare system that is at least partially controlled by the user 1690) or the autonomous vehicle's routing system 1692. A set of rewards to pursue, such as enabling behaviors, available for performing various actions (eg, by interacting with a touch panel or audio interface) may be displayed. For example, selection of a reward for joining a site can result in signaling the navigation or routing system 1692 to set an intermediate destination to the site. As another example, indicating intent to view a portion of the content may cause routing system 1692 to select a route that allows sufficient time to view and listen to the content.

Aspects provided herein are cognitive systems 1611 for routing at least one vehicle 1610, the routing being based, at least in part, by processing at least one input from a rider interface. and wherein rewards 16102 are made available to riders in response to the riders undertaking predetermined actions while aboard at least one vehicle 1610 .

Aspects provided herein include a transportation system 1611 for reward-based collaborative vehicle routing, comprising: A reward-based interface 16104 for providing a reward 16102 and through which a user 1690 associated with a set of vehicles 1694 receives a reward 16102 by responding to the reward 16102 provided at the reward-based interface 16104. A reward-based interface 16104 for indicating 1690 routing preferences. a reward-providing-response processing circuit 16105 that determines at least one user action resulting from the user's response to the reward 16102 and determines a corresponding effect 16106 on at least one routing parameter 1630, and routing preferences 16100 and at least one routing parameter of the user 1690; A vehicle routing system 1692 that governs the routing of a set of vehicles 1694 using corresponding effects on the vehicle routing system 1692 .

In an embodiment, user 1690 is a rider of at least one vehicle 1610 in set of vehicles 1694 . In embodiments, user 1690 is an administrator for a set of roads used by at least one vehicle 1610 in set of vehicles 1694 . In embodiments, user 1690 is an administrator for a fleet of vehicles that includes a set of vehicles 1694 . In an embodiment, reward-based interface 16104 is arranged for vehicle use. In an embodiment, the at least one routing parameter 1630 is congestion, desired arrival time, preferred route, fuel efficiency, pollution reduction, accident avoidance, bad weather avoidance, bad road condition avoidance, fuel consumption reduction, carbon footprint. reduction of local noise, avoidance of high-crime areas, collective satisfaction, maximum speed limits, avoidance of toll roads, avoidance of city roads, avoidance of undivided highways, avoidance of left turns, avoidance of driver-operated vehicles including at least one of In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of fleets of vehicles to achieve fuel efficiency goals. be. In an embodiment, vehicle routing system 1692 uses routing preferences of user 1690 and corresponding effects on at least one routing parameter to route a fleet of vehicles to achieve traffic reduction objectives. is to do In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of the vehicle set in order to achieve the reduced pollution objective. That is. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing selection and the corresponding effect on at least one routing parameter to route the fleet of vehicles to achieve carbon footprint reduction objectives. That is.

In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of fleets of vehicles to achieve neighborhood noise reduction objectives. is. In an embodiment, the vehicle routing system 1692 uses the routing preferences of the user 1690 and the corresponding effects on at least one routing parameter to govern routing of the vehicle set to achieve collective satisfaction objectives. , is to use In an embodiment, the vehicle routing system 1692 uses the routing preferences of the user 1690 and the corresponding effects on at least one routing parameter to route the fleet of vehicles to achieve the accident scene avoidance objective. control. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of vehicle sets to achieve the goal of avoiding high crime areas. It is to be. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of fleets of vehicles to achieve traffic congestion reduction objectives. is.

In an embodiment, vehicle routing system 1692 uses routing preferences of user 1690 and corresponding effects on at least one routing parameter to route a set of vehicles to achieve severe weather avoidance objectives. , is to use In an embodiment, the vehicle routing system 1692 uses the routing preferences of the user 1690 and corresponding values for at least one routing parameter to govern routing of a set of vehicles to achieve a maximum travel time objective. The effect is to use In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of the set of vehicles to achieve the maximum speed limit objective. be. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of a set of vehicles to achieve toll road avoidance objectives. It is to be. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of a set of vehicles to achieve city road avoidance objectives. It is to be.

In an embodiment, the vehicle routing system 1692 controls the routing preferences of the user 1690 and at least one routing parameter to govern routing of the set of vehicles to achieve undivided highway avoidance objectives. with corresponding effects. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to manage the routing of a set of vehicles to achieve left turn avoidance objectives. That is. In an embodiment, the vehicle routing system 1692 uses the user's 1690 routing preferences and corresponding effects on at least one routing parameter to govern the routing of the vehicle set to achieve driver-operated vehicle avoidance objectives. That is.

FIG. 17 illustrates a method 1700 of reward-based coordinated vehicle routing according to embodiments of the systems and methods disclosed herein. At 1702, the method includes receiving, through the reward-based interface, a user response associated with the fleet of vehicles to rewards provided in the reward-based interface. At 1704, the method includes determining routing preferences based on the user's responses. At 1706, the method includes determining at least one user action resulting from the user's response to the reward. At 1708, the method includes determining a corresponding effect of at least one user action on at least one routing parameter. In, the method includes governing routing of a set of vehicles in response to routing preferences and corresponding effects on at least one routing parameter.

In an embodiment, user 1690 is a rider of at least one vehicle 1610 in set of vehicles 1694 . In embodiments, user 1690 is an administrator for a set of roads used by at least one vehicle 1610 in set of vehicles 1694 . In embodiments, user 1690 is an administrator for a fleet of vehicles that includes a set of vehicles 1694 .

In an embodiment, reward-based interface 16104 is arranged for vehicle use. In an embodiment, the at least one routing parameter 1630 is congestion, desired arrival time, preferred route, fuel efficiency, pollution reduction, accident avoidance, bad weather avoidance, bad road condition avoidance, fuel consumption reduction, carbon footprint. reduction of local noise, avoidance of high crime areas, collective satisfaction, maximum speed limits, avoidance of toll roads, avoidance of city roads, avoidance of undivided highways, avoidance of left turns, avoidance of maneuvering vehicles. At least one. In embodiments, the user 1690 may accept the reward 16102 provided at the reward-based interface 16104, decline the reward 16102 provided at the reward-based interface 16104, or accept the reward 16102 provided at the reward-based interface 16104. Respond to reward 16102 by ignoring 16102 . In embodiments, user 1690 indicates routing preferences by either accepting or rejecting rewards 16102 provided in reward-based interface 16104 . In an embodiment, user 1690 indicates routing priority by taking action on at least one vehicle 1610 in vehicle set 1694 that facilitates forwarding reward 16102 to user 1690 .

In an embodiment, the method signals vehicle routing system 1692, via rewarding response processing circuit 16105, to select a vehicle route that allows sufficient time for user 1690 to perform at least one user action. Further comprising transmitting. In an embodiment, the method sends a signal to vehicle routing system 1692 via rewarding response processing circuitry 16105, the signal indicating a vehicle destination associated with at least one user action; Further comprising adjusting, by the routing system 1692, the route of the vehicle 1695 associated with the at least one user action to include the destination. In embodiments, the reward 16102 is related to achieving vehicle routing fuel efficiency goals.

In embodiments, the reward 16102 is associated with achieving vehicle routing reduced traffic objectives. In embodiments, the reward 16102 is associated with achieving vehicle routing reduced pollution objectives. In embodiments, the reward 16102 is associated with achieving vehicle routing reduced carbon footprint objectives. In an embodiment, the reward 16102 is associated with achieving vehicle routing reduced neighborhood noise objectives. In embodiments, the reward 16102 is associated with achieving a vehicle routing population satisfaction objective. In embodiments, the reward 16102 is associated with achieving vehicle routing accident scene avoidance objectives.

In embodiments, the reward 16102 is associated with achieving vehicle routing objectives around high crime areas. In embodiments, the reward 16102 is related to achieving vehicle routing traffic congestion reduction objectives. In embodiments, the reward 16102 is associated with achieving vehicle routing severe weather avoidance objectives. In embodiments, the reward 16102 is associated with achieving a vehicle routing maximum travel time objective. In embodiments, the reward 16102 is associated with achieving a vehicle routing maximum speed limit objective. In embodiments, the reward 16102 is associated with achieving vehicle routing toll road avoidance objectives. In an embodiment, the reward 16102 is associated with achieving a city road vehicle routing avoidance objective. In an embodiment, reward 16102 is associated with achieving vehicle routing avoidance for undivided highway objectives. In embodiments, the reward 16102 is associated with achieving a left turn vehicle routing avoidance objective. In an embodiment, the reward 16102 is associated with achieving a vehicle routing avoidance objective for the maneuvered vehicle.

Referring to FIG. 18, the embodiments provided herein take data 18114 from multiple social data sources 1869 and use a neural network 18108 to predict emerging transportation needs 18112 for groups of individuals. A transportation system 1811 having a data processing system 1862 for Of the various social data sources 18107 mentioned above, a large amount of data on social groups such as friend groups, families, work colleagues, club members, people with common interests or affiliations, political groups, etc. is available. It is possible. The expert system described above is trained to predict the transportation needs of the group, for example using a training dataset of human predictions and/or a model with feedback of results, as described throughout. Is possible. For example, it may become apparent that a group meeting or trip will take place based at least in part on a social group discussion thread shown on a social network feed, and the system will (each member's location information and travel destination using set metrics, etc.) to predict when and where each participating member will need to travel to participate. Based on such predictions, the system can automatically identify and display travel options, such as available public transportation options, flight options, rideshare options, and the like. Such options may include those that allow the group to share transportation, such as showing a route that will pick up a set of members of the group to travel together. Social media information can include posts, tweets, comments, chats, photos, etc., and can be processed as described above.

Aspects provided herein are a system 1811 for transportation that takes data 18114 from multiple social data sources 1869 and uses a neural network 18108 to identify new transportation needs 18112 for groups of individuals 18110. a data processing system 1862 for predicting the .

FIG. 19 is a diagram illustrating a method 1900 of predicting a group's common transportation needs according to embodiments of the systems and methods disclosed herein. At 1902, the method includes collecting social media source data about multiple individuals, where the data is sourced from multiple social media sources. At 1904, the method includes processing data to identify a subset of a plurality of individuals forming a social group based on group membership references in the data. At 1906, the method includes detecting keywords in the data indicative of transportation needs. At 1908, the method includes identifying common transportation needs for a plurality of subsets of individuals using a neural network trained to predict transportation needs based on the detected keywords.

18 and 19, in an embodiment, neural network 18108 is convolutional neural network 18113. FIG. In an embodiment, neural network 18108 is trained based on a model that facilitates matching social media phrases to traffic activity. In embodiments, the neural network 18108 predicts at least one of the destination and arrival time for a subset of a plurality of individuals 18110 who share common transportation needs. In an embodiment, neural network 18108 predicts common transportation needs based on analysis of transportation need suggestive keywords detected in discussion threads among a subset of individuals within a social group. In embodiments, the method further includes identifying at least one shared transportation service 18111 that facilitates meeting the predicted common transportation needs 18112 of a portion of the social group. In embodiments, the at least one shared transportation service comprises generating a vehicle route that facilitates picking up part of a social group.

FIG. 20 illustrates a method 2000 of predicting a group's transportation needs in accordance with embodiments of the systems and methods disclosed herein. At 2002, the method includes collecting social media source data about a plurality of individuals, the data being provided from the plurality of social media sources. In 2004, the method includes processing data to identify a subset of a plurality of individuals who share group transportation needs. In 2006, the method includes detecting keywords in data that indicate group transportation needs for a subset of a plurality of individuals. In 2008, the method includes predicting group transportation needs using a neural network trained to predict transportation needs based on detected keywords. In 2009, the method includes directing a vehicle routing system to meet group transportation needs.

18 and 20, in an embodiment, neural network 18108 is convolutional neural network 18113. FIG. In an embodiment, directing a vehicle routing system to meet group transportation needs includes routing multiple vehicles to destinations derived from social media source data 18114 . In embodiments, neural network 18108 is trained based on models that facilitate matching phrases in social media sourced data 18114 to transportation activities. In an embodiment, the method further includes predicting, by a neural network 18108, at least one of a destination and arrival time for a subset 18110 of a plurality of individuals 18109 sharing group transportation needs. In embodiments, the method further comprises predicting group transportation needs based on analysis of transportation need suggestive keywords detected in discussion threads in social media source data 18114 by neural network 18108 . In embodiments, the method further comprises identifying at least one shared transportation service 18111 that facilitates meeting predicted group transportation needs for at least a portion of the subset of the plurality of individuals 18110 . In an embodiment, at least one shared transportation service 18111 comprises generating a vehicle route that facilitates picking up at least a portion of a subset of the plurality of individuals 18110.

FIG. 21 illustrates a method 2100 of predicting group transportation needs in accordance with embodiments of the systems and methods disclosed herein. At 2102, the method includes collecting social media source data from multiple social media sources. At 2104, the method includes processing the data to identify the event. At 2106, the method includes detecting keywords in the data indicative of the event to determine transportation needs associated with the event. In, the method includes directing a vehicle routing system to meet transportation needs using a neural network trained to predict transportation needs based at least in part on social media source data.

18 and 21, in an embodiment, neural network 18108 is convolutional neural network 18113. FIG. In embodiments, a vehicle routing system is directed to meet transportation needs by routing multiple vehicles to locations associated with an event. In embodiments, the vehicle routing system is directed to meet transportation needs by routing multiple vehicles to avoid areas proximate to the location associated with the event. In embodiments, the vehicle routing system routes vehicles associated with users whose social media source data 18114 do not indicate a need for transportation by routing vehicles associated with the user to avoid areas proximate to locations associated with the event, directed to meet transportation needs. In embodiments, the method further includes offering at least one transportation service to satisfy the transportation need. In embodiments, neural network 18108 is trained based on models that facilitate matching phrases in social media sourced data 18114 to traffic activity.

In embodiments, neural network 18108 predicts at least one of a destination and arrival time for individuals participating in an event. In an embodiment, neural network 18108 predicts transportation needs based on analysis of transportation need suggestive keywords detected in discussion threads within social media source data 18114 . In embodiments, the method further comprises identifying at least one shared transportation service that facilitates meeting predicted transportation needs for at least a subset of the individuals identified in the social media-sourced data 18114. In an embodiment, the at least one shared transportation service includes generating vehicle routes that facilitate picking up a portion of the subset of individuals identified in the social media sourced data 18114.

Referring to FIG. 22, embodiments provided herein include a transportation system 22111 having a data processing system 2211 for ingesting social media data 22114 from a plurality of social data sources 22107 2269 and a hybrid neural network 2247. and a system 2247 for using and processing the social data sources 22107 to optimize the operating conditions of the transportation system 22111 . Hybrid neural network 2247 may be, for example, a neural network component that performs classification or prediction based on processing social media data 22114 (e.g., processing images on many social media feeds that indicate interest in an event for many people). predictions of high attendance at events, predictions of traffic, etc. (classification of individual interest in topics, and many others), and in-vehicle states, routing states (for individual vehicles 2210 or collections of vehicles 2294), user experience states. , or other conditions described throughout this disclosure (e.g. individual , playing music content in vehicles 2210 for bands attending music festivals, etc.).

Aspects provided herein include a system for transportation, a data processing system 2211 for taking social media data 22114 from a plurality of social data sources 2269, and data 22114 from a plurality of social data sources 2269. and using the hybrid neural network 2247 to optimize the operating conditions of the transportation system based on processing with the hybrid neural network 2247 .

Aspects provided herein include a hybrid neural network system 22115 for transportation system optimization, wherein the hybrid neural network system 22115 social media data 22114 fed from a plurality of 2269 social media data sources 22107. A hybrid network comprising a first neural network 2222 that predicts local effects 22116 on the transportation system through analysis of 2247.

In embodiments, at least one of first neural network 2222 and second neural network 2220 is a convolutional neural network. In an embodiment, the second neural network 2220 is to optimize the in-vehicle rider experience conditions. In an embodiment, first neural network 2222 identifies a set of vehicles 2294 that contribute to local effect 22116 based on correlations between vehicle positions and areas of local effect 22116 . In an embodiment, the second neural network 2220 is to optimize the routing state of the transportation system for vehicles proximate to the local effect 22116 location. In an embodiment, hybrid neural network 2247 is trained for at least one of prediction and optimization based on keywords within social media data that indicate results of transportation system optimization actions. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on social media posts.

In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on social media feeds. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on ratings derived from social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on the likes and dislikes activity detected in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on relationship indicators in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on user behavior detected in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on discussion threads in social media data 22114 .

In an embodiment, hybrid neural network 2247 is trained for at least one of chat-based prediction and optimization on social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on photos in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on traffic impact information in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on the appearance of particular individuals at locations in social media data 22114 . In embodiments, the particular individual is a celebrity. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on the presence of rare or transient phenomena at locations in social media data 22114 .

In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on commerce-related events at locations within social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing entertainment events at locations in social media data 22114 . In embodiments, the social media data analyzed to predict local impacts on transportation systems includes traffic conditions. In embodiments, the social media data analyzed to predict local impacts on transportation systems includes weather conditions. In embodiments, social media data analyzed to predict local impacts on transportation systems includes entertainment options.

In embodiments, social media data analyzed to predict local impacts on transportation systems includes risk-related terms. In embodiments, risk-related conditions include crowds gathering for potentially dangerous reasons. In embodiments, the social media data analyzed to predict local impacts on transportation systems includes commerce-related terms. In embodiments, the social media data analyzed to predict local impacts on the transportation system includes conditions related to goals.

In embodiments, the social media data analyzed to predict local impacts on transportation systems includes estimates of event attendees. In embodiments, the social media data analyzed to predict local impacts on the transportation system includes predictions of event attendance. In embodiments, the social media data analyzed to predict local impacts on the transportation system includes modes of transportation. In embodiments, aspects of traffic include motor vehicle traffic. In embodiments, the modes of transportation include public transportation options.

In embodiments, social media data analyzed to predict local impacts on transportation systems includes hashtags. In embodiments, the social media data analyzed to predict local impacts on transportation systems includes topic trending. In embodiments, the outcome of a transportation system optimization action is a reduction in fuel consumption. In embodiments, the outcome of a traffic system optimization action is to reduce traffic congestion. In embodiments, the outcome of transportation system optimization actions is reduced pollution. In embodiments, the outcome of a transportation system optimization action is avoidance of severe weather. In an embodiment, the operating conditions of the traffic system to be optimized include in-vehicle conditions. In embodiments, the operational state of the transport system to be optimized includes routing state.

In an embodiment, routing states are for individual vehicles 2210 . In embodiments, the routing state is for a set of vehicles 2294 . In embodiments, the transport system operating conditions that are optimized include user experience conditions.

FIG. 23 illustrates a method 2300 of optimizing operating conditions of a transportation system according to embodiments of the systems and methods disclosed herein. At 2302, the method includes collecting social media source data about a plurality of individuals, the data being sourced from a plurality of social media sources. In, the method includes using a hybrid neural network to optimize operating conditions of a transportation system. At 2306, the method includes predicting impacts on the transportation system through analysis of social media-supplied data by a first neural network of the hybrid neural network. At 2308, the method includes optimizing at least one operational state of the transportation system in response to the predicted impact thereon by a second neural network of the hybrid neural network.

22 and 23, in embodiments at least one of the first neural network 2222 and the second neural network 2220 is a convolutional neural network. In an embodiment, the second neural network 2220 optimizes the in-vehicle rider experience. In an embodiment, the first neural network 2222 identifies the set of vehicles that contribute to the effect based on correlations between vehicle positions and areas of effect. In an embodiment, the second neural network 2220 optimizes the routing state of the traffic system for vehicles proximate to the location of influence.

In an embodiment, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on keywords within social media data that indicate results of transportation system optimization actions. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on social media posts. In an embodiment, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on social media feeds. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on ratings derived from social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on the likes and dislikes activity detected in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on relationship indicators in social media data 22114 .

In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on user behavior detected in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on discussion threads in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of chat-based prediction and optimization in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on photos in social media data 22114 . In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing based on information affecting traffic in social media data 22114 .

In embodiments, the hybrid neural network 2247 is trained for prediction and/or optimization based on the appearance of particular individuals at locations within the social media data. In embodiments, the particular individual is a celebrity. In embodiments, the hybrid neural network 2247 is trained for at least one of predicting and optimizing based on the presence of rare or transient phenomena at locations within the social media data. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing commerce-related events at locations within social media data. In embodiments, hybrid neural network 2247 is trained for at least one of predicting and optimizing entertainment events at locations within social media data. In embodiments, the social media data analyzed to predict impacts on transportation systems includes traffic conditions.

In embodiments, social media data analyzed to predict impacts on transportation systems includes weather conditions. In embodiments, the social media data analyzed to predict impact on transportation systems includes entertainment options. In embodiments, social media data analyzed to predict impacts on transportation systems includes conditions associated with risk. In embodiments, risk-related conditions include crowds gathering for potentially dangerous reasons. In embodiments, the social media data analyzed to predict impacts on transportation systems includes commercial-related terms. In embodiments, social media data analyzed to predict impacts on transportation systems includes conditions related to goals.

In embodiments, the social media data analyzed to predict impacts on transportation systems includes estimates of event attendees. In embodiments, the social media data analyzed to predict impacts on the transportation system includes predictions of event attendees. In embodiments, social media data analyzed to predict impacts on transportation systems includes modes of transportation. In embodiments, the mode of transportation includes motor vehicle traffic. In embodiments, the modes of transportation include public transportation options. In embodiments, the social media data analyzed to predict impacts on transportation systems includes hashtags. In embodiments, the social media data analyzed to predict impacts on transportation systems includes topic trending.

In embodiments, the outcome of a transportation system optimization action is to reduce fuel consumption. In embodiments, the outcome of a traffic system optimization action is a reduction in traffic congestion. In embodiments, the outcome of transportation system optimization actions is a reduction in pollution. In embodiments, the outcome of a transportation system optimization action is avoidance of severe weather. In an embodiment, the operating conditions of the traffic system to be optimized include in-vehicle conditions. In embodiments, the operational state of the transportation system being optimized includes routing states. In embodiments, routing states are for individual vehicles. In an embodiment, the routing state is for a set of vehicles. In embodiments, the transport system operating conditions that are optimized include user experience conditions.

FIG. 24 is a diagram illustrating a method 2400 of optimizing operating conditions of a transportation system according to embodiments of the systems and methods disclosed herein. At 2402, the method includes using a first neural network of the hybrid neural network to classify social media data sourced from multiple social media sources as affecting the transportation system. At 2404, the method includes predicting at least one operational goal of the transportation system based on the classified social media data using a second of the hybrid neural networks. At 2406, the method includes using a third of the hybrid neural networks to optimize operational conditions of the transportation system to achieve at least one operational objective of the transportation system.

22 and 24, in embodiments at least one of the neural networks of hybrid neural network 2247 is a convolutional neural network.

Referring to FIG. 25, embodiments provided herein use a transportation system 2511 having a data processing system 2562 for taking social media data 25114 from multiple social data sources 25107, and a hybrid neural network 2547. A hybrid neural network 2547 can be used to optimize the operating state 2545 of the vehicle 2510 based on processing social data sources with In an embodiment, hybrid neural network 2547 uses one neural network category for prediction, another for classification, and one or more desired outcomes (e.g., efficient locomotion, satisfying rider experience, , providing a comfortable ride, on-time arrival, etc.). Social data sources 2569 may be used for predicting travel times, for classifying content such as for profiling user interests, for transportation planning purposes (such as providing overall satisfaction for an individual or group). may be used by different neural network categories (such as any of the types described herein), such as to predict Social data sources 2569 can also inform optimization, such as by providing indicators of successful results (e.g., social data sources 25107, such as Facebook feeds, indicate whether a trip is "great" or "bad"). Yelp reviews may indicate that the restaurant is terrible, etc.). Thus, social data sources 2569 can help determine timing, destination, purpose of travel, what individuals to invite, what entertainment options to choose, and many other things by contributing to outcome tracking. Related, etc., can be used to train the system to optimize transportation planning.

Aspects provided herein are a transportation system 2511, a data processing system 2562 for capturing social media data 25114 from a plurality of social data sources 25107, and processing data 25114 from the plurality of social data sources 25107 into and a hybrid neural network 2546 for optimizing the operating conditions 2545 of the vehicle 2510 based on processing by the hybrid neural network 2547 .

FIG. 26 illustrates a method 2600 of optimizing vehicle operating conditions in accordance with embodiments of the systems and methods disclosed herein. At 2602, the method uses a first neural network 2522 (FIG. 25) of a hybrid neural network to apply social media data 25119 (FIG. 25) sourced from multiple social media sources to the transportation system. including classifying as At 2604, the method predicts one or more effects 25118 (FIG. 25) of the classified social media data on the transportation system using the second neural network 2520 (FIG. 25) of the hybrid neural network. including. At 2606, the method includes optimizing the state of at least one vehicle of the transportation system using a third neural network 25117 (FIG. 25) of the hybrid neural network, the optimization comprising: including addressing the impact of one or more predicted effects on

25 and 26, in an embodiment at least one of the neural networks of hybrid neural network 2547 is a convolutional neural network. In embodiments, social media data 25114 includes social media posts. In embodiments, social media data 25114 includes social media feeds. In embodiments, social media data 25114 includes detected likes and dislikes activity in social media. In embodiments, social media data 25114 includes relationship indicators. In embodiments, social media data 25114 includes user actions. In embodiments, social media data 25114 includes discussion threads. In embodiments, social media data 25114 includes chats. In embodiments, social media data 25114 includes photographs.

In embodiments, social media data 25114 includes traffic affection information. In embodiments, social media data 25114 includes representations of specific individuals at a location. In embodiments, social media data 25114 includes representations of celebrities at a location. In embodiments, social media data 25114 includes the presence of rare or transient phenomena at a location. In embodiments, social media data 25114 includes commerce-related events. In embodiments, social media data 25114 includes entertainment events at the location. In embodiments, social media data 25114 includes traffic conditions. In embodiments, social media data 25114 includes weather conditions. In embodiments, social media data 25114 includes entertainment options.

In embodiments, social media data 25114 includes risk-related terms. In embodiments, social media data 25114 includes predictions of attendance at events. In embodiments, social media data 25114 includes estimates of attendance at events. In embodiments, social media data 25114 includes transportation used with the event. In an embodiment, the effect 25118 on transportation includes reducing fuel consumption. In an embodiment, the effect 25118 on the traffic system includes reducing traffic congestion. In an embodiment, the effect 25118 on the transportation system includes reducing carbon footprint. In an embodiment, the effect 25118 on the transportation system includes reduced pollution.

In an embodiment, the at least one optimized state 2544 of the vehicle 2510 is the operating state 2545 of the vehicle. In embodiments, the at least one optimized state of the vehicle includes an on-board state. In embodiments, the at least one optimized state of the vehicle includes a rider state. In embodiments, the optimized state of the at least one vehicle includes a routing state. In embodiments, the at least one optimized state of the vehicle includes a user experience state. In embodiments, characterization of optimization results in social media data 25114 is used as feedback to improve optimization. In embodiments, the feedback includes likes and dislikes of the results. In embodiments, the feedback includes social media activity referencing results.

In embodiments, the feedback includes trending social media activity with reference to results. In embodiments, the feedback includes hashtags associated with the results. In embodiments, the feedback includes evaluation of performance. In embodiments, the feedback includes demands for performance.

FIG. 26A illustrates a method 26A00 of optimizing vehicle operating conditions according to embodiments of the systems and methods disclosed herein. At 26A02, the method includes using a first neural network of a hybrid neural network to classify social media data sourced from a plurality of social media sources as affecting a transportation system. At 26A04, the method includes predicting at least one vehicle motion objective of the transportation system based on the classified social media data using a second neural network of the hybrid neural network. In 26A06, the method includes using a third neural network of the hybrid neural networks to optimize vehicle conditions in the transportation system to achieve at least one vehicle operating objective of the transportation system. .

25 and 26A, in an embodiment at least one of the neural networks of hybrid neural network 2547 is a convolutional neural network. In an embodiment, the vehicle motion objective consists of achieving a rider status for at least one rider in the vehicle. In embodiments, social media data 25114 includes social media posts.

In embodiments, social media data 25114 includes social media feeds. In embodiments, social media data 25114 includes detected likes and dislikes activity in social media. In embodiments, social media data 25114 includes relationship indicators. In embodiments, social media data 25114 includes user actions. In embodiments, social media data 25114 includes discussion threads. In embodiments, social media data 25114 includes chats. In embodiments, social media data 25114 includes photographs. In embodiments, social media data 25114 includes traffic affection information.

In embodiments, social media data 25114 includes representations of specific individuals at a location. In embodiments, social media data 25114 includes representations of celebrities at locations. In embodiments, social media data 25114 includes the presence of rare or transient phenomena at a location. In embodiments, social media data 25114 includes commerce-related events. In embodiments, social media data 25114 includes entertainment events at the location. In embodiments, social media data 25114 includes traffic conditions. In embodiments, social media data 25114 includes weather conditions. In embodiments, social media data 25114 includes entertainment options.

In embodiments, social media data 25114 includes risk-related terms. In embodiments, social media data 25114 includes predictions of attendance at events. In embodiments, social media data 25114 includes estimates of attendance at events. In embodiments, social media data 25114 includes the mode of transportation used with the event. In embodiments, the effect on transportation includes reducing fuel consumption. In embodiments, the effect on the transportation system includes reducing traffic congestion. In embodiments, the effect on the transportation system includes a reduction in carbon footprint. In embodiments, the effect on the transportation system includes reduced contamination. In embodiments, the optimized state of the vehicle is the operating state of the vehicle.

In embodiments, the optimized state of the vehicle includes an on-board state. In embodiments, the optimized state of the vehicle includes a rider state. In embodiments, the optimized state of the vehicle includes routing states. In embodiments, the optimized state of the vehicle includes the user experience state. In embodiments, characterization of optimization results in social media data is used as feedback to improve optimization. In embodiments, the feedback includes likes and dislikes of the results. In embodiments, feedback includes social media activity that references results. In embodiments, the feedback includes trending social media activity with reference to results.

In embodiments, the feedback includes hashtags associated with the results. In embodiments, feedback includes evaluation of results. In embodiments, the feedback includes requests for results.

Referring to FIG. 27, in embodiments provided herein, a transport system 2711 having a data processing system 2762 for taking social data 27114 from a plurality of social data sources 2769 and a hybrid neural network 2747 to Using hybrid neural network 2746 to optimize satisfaction 27121 of at least one rider 27120 in vehicle 2710 based on processing data sources. Social data sources 2769 may be used, for example, by one neural network category to predict what entertainment options will be most effective for riders 27120, another neural network category is route planning. It may be used for optimization (eg, based on social data indicating likely traffic, points of interest, etc.). Social data 27114 can also be used for outcome tracking and feedback to optimize the system, both regarding entertainment options, transportation planning, routing, and the like.

Aspects provided herein are a transportation system 2711, a data processing system 2762 for capturing social data 27114 from a plurality of social data sources 2769, and processing the social data 27114 from the plurality of social data sources 2769. and a system comprising a hybrid neural network 2746 for optimizing the satisfaction 27121 of at least one rider 27120 in the vehicle 2710 based on processing by the hybrid neural network 2747.

FIG. 28 is a diagram illustrating a method 2800 of optimizing rider satisfaction according to embodiments of the systems and methods disclosed herein. At 2802, the method uses a first neural network 2722 (FIG. 27) of a hybrid neural network to generate social media data 27119 (FIG. 27) sourced from a plurality of social media sources to show impact on the transportation system. including classifying as At 2804, the method uses the second neural network 2720 (FIG. 27) of the hybrid neural network to determine the traffic system impact obtained from the social media data classified as indicative of the traffic system impact. predicting at least one aspect 27122 (FIG. 27) of rider satisfaction affected by . At 2806, the method optimizes at least one aspect of rider satisfaction for at least one rider occupying a vehicle in the transportation system using a third neural network 27117 (FIG. 27) of the hybrid neural network. including converting.

27 and 28, in embodiments at least one of the neural networks of hybrid neural network 2547 is a convolutional neural network. In embodiments, at least one aspect of rider satisfaction 27121 is optimized by predicting entertainment options to present to the rider. In an embodiment, at least one aspect of rider satisfaction 27121 is optimized by optimizing route planning for vehicles occupied by riders. In an embodiment, at least one aspect of rider satisfaction 27121 is rider state, and optimizing the rider satisfaction aspect includes optimizing rider state. In embodiments, rider-specific social media data is analyzed to determine at least one optimization action likely to optimize at least one aspect 27121 of rider satisfaction. In embodiments, optimization actions include adjusting route planning to pass through points of interest to the user, avoiding traffic jams predicted from social media data, and presenting entertainment options. selected from a group of actions consisting of

In embodiments, social media data includes social media posts. In embodiments, social media data includes social media feeds. In embodiments, the social media data includes detected likes and dislikes activity on social media. In embodiments, the social media data includes relationship indicators. In embodiments, the social media data includes user actions. In embodiments, the social media data includes discussion threads. In embodiments, social media data includes chats. In embodiments, social media data includes photographs.

In embodiments, the social media data includes information affecting traffic. In embodiments, social media data includes representations of specific individuals at a location. In embodiments, the social media data includes celebrity appearances at a location. In embodiments, social media data includes the presence of rare or transient phenomena in a location. In embodiments, social media data includes commerce-related events. In embodiments, the social media data includes entertainment events at the location. In embodiments, the social media data includes traffic conditions. In embodiments, the social media data includes weather conditions. In embodiments, the social media data includes entertainment options. In embodiments, the social media data includes risk-related conditions. In embodiments, the social media data includes predictions of attendance at events. In embodiments, the social media data includes estimates of attendance at events. In embodiments, the social media data includes the mode of transportation used with the event. In embodiments, the effect on transportation includes reducing fuel consumption. In embodiments, the effect on the transportation system includes reducing traffic congestion. In embodiments, the effect on the transportation system includes a reduction in carbon footprint. In embodiments, the effect on the transportation system includes reduced pollution. In embodiments, at least one aspect of rider satisfaction that is optimized is vehicle operating conditions. In embodiments, the optimized at least one aspect of rider satisfaction includes interior conditions. In embodiments, the optimized at least one aspect of rider satisfaction includes rider status. In embodiments, at least one aspect of rider satisfaction that is optimized includes routing status. In embodiments, at least one aspect of rider satisfaction that is optimized includes user experience state.

In embodiments, characterization of optimization results in social media data is used as feedback to improve optimization. In embodiments, the feedback includes likes and dislikes of the results. In embodiments, feedback includes social media activity that references results. In embodiments, the feedback includes trending social media activity with reference to results. In embodiments, the feedback includes hashtags associated with the results. In embodiments, feedback includes evaluation of results. In embodiments, the feedback includes demands for performance.

Aspects provided herein include a rider satisfaction system 27123 for optimizing rider satisfaction 27121, the system comprising: A first neural network 2722 of a hybrid neural network 2747 that classifies social media data 27114 sourced from a plurality of social media sources 27107 as indicative of impact on the transportation system 2711 and as indicative of impact on the transportation system. a second neural network 2720 of the hybrid neural network 2747 that predicts at least one aspect 27122 of rider satisfaction 27121 affected by the impact on the transportation system derived from the social media data obtained from the received social media data; is for optimizing at least one aspect 27121 of rider satisfaction for at least one rider 2744 occupying a vehicle 2710 in transportation system 2711 . In an embodiment, at least one of the neural networks of hybrid neural network 2747 is a convolutional neural network.

In embodiments, at least one aspect of rider satisfaction 27121 is optimized by predicting entertainment options to present to rider 2744 . In an embodiment, at least one aspect of rider satisfaction 27121 is optimized by optimizing the route plan for vehicle 2710 occupied by rider 2744 . In an embodiment, at least one aspect of rider satisfaction 27121 is rider state 2737 and optimizing at least one aspect of rider satisfaction 27121 comprises optimizing rider state 2737 . In an embodiment, social media data specific to rider 2744 is analyzed to determine at least one optimization action likely to optimize at least one aspect 27121 of rider satisfaction. In embodiments, the at least one optimization action is adjusting the route plan to include waypoints of interest to the user, avoiding traffic jams predicted from social media data, and obtaining economic benefits. , obtaining altruistic benefits, and presenting entertainment options.

In embodiments, the economic benefit is fuel saved. In embodiments, the altruistic benefit is a reduction in environmental impact. In embodiments, social media data includes social media posts. In embodiments, social media data includes social media feeds. In embodiments, the social media data includes detected likes and dislikes activity on social media. In embodiments, the social media data includes relationship indicators. In embodiments, the social media data includes user actions. In embodiments, the social media data includes discussion threads. In embodiments, social media data includes chats. In embodiments, social media data includes photographs. In embodiments, the social media data includes information affecting traffic. In embodiments, the social media data includes a particular individual's display at a location.

In embodiments, the social media data includes representations of celebrities at the location. In embodiments, the social media data includes the presence of rare or transient phenomena at a location. In embodiments, the social media data includes commerce-related events. In embodiments, the social media data includes entertainment events at the location. In embodiments, the social media data includes traffic conditions. In embodiments, the social media data includes weather conditions. In embodiments, the social media data includes entertainment options. In embodiments, the social media data includes risk-related conditions. In embodiments, the social media data includes predictions of attendance at events. In embodiments, the social media data includes estimates of attendance at events. In embodiments, the social media data includes transportation used with the event.

In embodiments, the effect on the transportation system includes reducing fuel consumption. In embodiments, the effect on the transportation system includes reducing traffic congestion. In embodiments, the benefits for transportation systems include a reduction in carbon footprint. In embodiments, the effect on the transportation system includes reduced pollution. In embodiments, at least one aspect of rider satisfaction that is optimized is vehicle operating conditions. In embodiments, the optimized at least one aspect of rider satisfaction includes interior conditions. In embodiments, the optimized at least one aspect of rider satisfaction includes rider status. In embodiments, at least one aspect of rider satisfaction that is optimized includes routing status. In embodiments, at least one aspect of rider satisfaction that is optimized includes user experience state. In embodiments, characterization of optimization results in social media data is used as feedback to improve optimization. In embodiments, the feedback includes likes and dislikes of the results. In embodiments, feedback includes social media activity that references results. In embodiments, the feedback includes trending social media activity with reference to results. In embodiments, the feedback includes hashtags associated with the results. In embodiments, feedback includes evaluation of results. In embodiments, the feedback includes demands for performance.

Referring to FIG. 29, in the embodiments provided herein, one neural net 2922 processes sensor input 29125 regarding rider 2944 of vehicle 2910 to determine emotional state 29126, and another neural net processes the rider's emotional state 29126. A transportation system 2911 having a hybrid neural network 2947 that optimizes at least one operating parameter 29124 of a vehicle to improve an emotional state 2966. For example, a neural net 2922 including one or more perceptrons 29127 that mimic human senses may be used to mimic or assist in determining the likely emotional state of rider 29126 based on the degree to which various senses are stimulated. Another neural network 2920 is used, an expert system (entertainment settings, seat settings, suspension settings, route types, etc.) that performs random and/or systematic variation of various combinations of operating parameters. root types, etc.), optionally with genetic programming that promotes favorable combinations and eliminates unfavorable combinations, based on input from the output of a perceptron-containing neural network 2922 that predicts emotional states. be. These and many other such combinations are encompassed by this disclosure. In FIG. 29, perceptron 29127 is drawn as an option.

Aspects provided herein are a transportation system 2911 in which one neural network 2922 processes sensor inputs 29125 corresponding to a rider 2944 of a vehicle 2910 to determine an emotional state 2966 of the rider 2944; Another neural network 2920 is characterized by comprising a hybrid neural network 2947 that optimizes at least one operating parameter 29124 of the vehicle to improve the emotional state 2966 of the rider 2944.

An aspect provided herein is a hybrid neural network 2947 for rider satisfaction that analyzes sensor inputs 29125 collected from sensors 2925 deployed on the vehicle 2910 to collect the physiological state of the rider. a first neural network 2922 for detecting the detected emotional state 29126 of a rider 2944 occupying a vehicle 2910 through a second neural network 2922 for optimizing the vehicle's operational parameters 29124 in response to the rider's preferred emotional state 29126; a rider's emotional state detector 2917 comprising a neural network 2920;

In an embodiment, first neural network 2922 is a recurrent neural network and second neural network 2920 is a radial basis function neural network. In an embodiment, at least one of the neural networks of hybrid neural network 2947 is a convolutional neural network. In an embodiment, the second neural network 2920 is to optimize the operating parameters 29124 based on the correlation between the vehicle operating state 2945 and the rider's emotional state 2966. In an embodiment, second neural network 2920 is to optimize operational parameters 29124 in real time in response to detection of detected emotional state 29126 of rider 2944 by first neural network 2922 . In an embodiment, the first neural network 2922 consists of a plurality of connected nodes forming a directed cycle, and the first neural network 2922 further facilitates bi-directional flow of data between connected nodes. In embodiments, the operational parameters 29124 that are optimized include the vehicle's route, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. affect at least one of the proximity to

Aspects provided herein are an artificial intelligence system 2936 for optimizing rider satisfaction, comprising a hybrid neural network 2947, a recurrent neural network (e.g. may also be included). 29, the neural network 2922 may be a recurrent neural network) and at least one sensor 2925 deployed to capture data indicative of the rider's emotional state while on board the vehicle 2910. A radial basis function neural network (e.g., in FIG. 29, the second neural network 2920 uses a radial basis A functional neural network, which may be a functional neural network, is used to optimize vehicle operating parameters 29124 in response to indications of changes in the rider's emotional state in order to achieve the rider's preferred emotional state. In an embodiment, the vehicle operating parameters 29124 to be optimized are determined and adjusted to induce a favorable emotional state of the rider.

Aspects provided herein are an artificial intelligence system 2936 for optimizing rider satisfaction, comprising a hybrid neural network 2947, at least one image sensor (depicted by reference numeral 2922 in FIG. 29) The neural network 1, which may optionally be a convolutional neural network, is used to indicate changes in the rider's emotional state while on board the vehicle through recognition of patterns in the rider's visual data captured by the convolutional neural network. A convolutional neural network (Network 2, depicted by reference numeral 2922 in FIG. 29, is optionally not a neural network). 29, the sensor 2925 is a second sensor for indicating changes in the emotional state of a rider on board the vehicle through recognition of patterns in the rider's visual data captured by the sensor 2925, which may optionally be an image sensor. 2 neural network 2920 and a second neural network 2920 for optimizing vehicle operating parameters 29124 in response to indications of changes in the rider's emotional state to achieve the rider's preferred emotional state. Prepare.

In an embodiment, the vehicle operating parameters 19124 to be optimized are determined and adjusted to induce a preferred emotional state of the rider.

Referring to FIG. 30, embodiments provided herein process a feature vector of a facial image of a rider in a vehicle to determine an emotional state, and at least adjust the vehicle to improve the rider's emotional state. A transportation system 3011 is provided having an artificial intelligence system 3036 for optimizing one operating parameter. Faces can be classified based on images from on-board cameras, available cell phone or other mobile device cameras, or other sources. An expert system, optionally trained on a training set of human-provided data or trained by deep learning, uses vehicle parameters (as described herein) to provide improved emotional state. , etc.). For example, if the rider's face indicates stress, the vehicle may select a less stressful route, play relaxing music, play humorous content, and so on.

Aspects provided herein are a transportation system 3011, an artificial intelligence system for processing feature vectors of an image 30129 of a face 30128 of a rider 3044 in a vehicle 3010 to determine the rider's emotional state 3066. 3036 and an artificial intelligence system for optimizing vehicle operating parameters 30124 to improve the emotional state 3066 of the rider 3044 .

In embodiments, artificial intelligence system 3036 includes: A first neural network 3022 for detecting the rider's emotional state 30126 through recognition of patterns in the feature vector 30130 of the image 30129 of the face 30128 of the rider 3044 in the vehicle 3010, wherein the feature vector 30130 is the rider's preferred emotional state and the rider's a first neural network 3022 indicative of at least one of the unfavorable emotional states; and a second neural network 3020 that transforms the

In an embodiment, the first neural network 3022 is a recurrent neural network and the second neural network 3020 is a radial basis function neural network. In an embodiment, the second neural network 3020 is to optimize the operating parameters 30124 based on the correlation between the vehicle operating state 3045 and the rider's emotional state 3066. In an embodiment, the second neural network 3020 determines optimal values for the vehicle's operating parameters, and the transportation system 3011 adjusts the vehicle's operating parameters 30124 to the optimal values to induce the rider's preferred emotional state. is. In an embodiment, the first neural network 3022, by processing the training data set 30131, further learns to classify patterns in feature vectors and associate patterns with a range of emotional states and their changes. In embodiments, the training data set 30131 is sourced from at least one of data streams from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider speech recognition systems. be done.

In an embodiment, the second neural network 3020 is to optimize the operational parameters 30124 in real time in response to the detection of the rider's emotional state by the first neural network 3022 . In an embodiment, the first neural network 3022 is to detect patterns of feature vectors. In embodiments, the pattern is associated with a change in the rider's emotional state from a first emotional state to a second emotional state. In an embodiment, the second neural network 3020 optimizes operating parameters of the vehicle in response to detecting patterns associated with changes in emotional state. In an embodiment, the first neural network 3022 comprises a plurality of interconnected nodes forming a directed cycle, the first neural network 3022 directing bi-directional flow of data between the interconnected nodes. Promote further. In an embodiment, transportation system 3011 is a feature vector generation system that processes a set of images of the rider's face, captured over time intervals from multiple image capture devices 3027 while rider 3044 is in vehicle 3010. The set of further comprises processing the set of images to generate a feature vector 30130 of the image of the rider's face. In an embodiment, the transportation system includes an image capture device 3027 arranged to capture a set of facial images of the rider in the vehicle from multiple viewpoints, and the images captured from at least one of the multiple viewpoints. and an image processing system that generates a feature vector from the set of .

In an embodiment, the transportation system 3011 further comprises an interface 30133 between the first neural network and the image processing system 30132 for communicating a time sequence of feature vectors, the feature vectors indicative of the rider's emotional state. It is. In an embodiment, the feature vector is a change in the rider's emotional state, a stable emotional state of the rider, a rate of change in the rider's emotional state, a direction of change in the rider's emotional state, a polarity of change in the rider's emotional state, a At least one of the emotional state changing to an unfavorable emotional state and the rider's emotional state changing to a favorable emotional state is indicated.

In embodiments, the operational parameters that are optimized are the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and to other vehicles along the route. , which affects at least one of the proximity of In an embodiment, the second neural network is to interact with the vehicle control system to adjust operating parameters. In embodiments, the artificial intelligence system includes one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. It also has a neural network. In an embodiment, the artificial intelligence system includes a recurrent neural network that directs changes in the rider's emotional state through recognition of patterns in feature vectors of facial images of the rider in the vehicle, and responds to the changes in the rider's emotional state. and a radial basis function neural network that optimizes vehicle operating parameters to achieve the rider's preferred emotional state.

In an embodiment, the radial basis function neural network is to optimize the operating parameters based on the correlation between the vehicle's operating state and the rider's emotional state. In embodiments, the optimized vehicle operating parameters are determined and adjusted to induce a favorable rider emotional state. In embodiments, the recurrent neural network was fed from at least one of streams of data from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. It is further learned to classify feature vector patterns from the training data set to associate feature vector patterns with emotional states and their changes. In an embodiment, the radial basis function neural network is to optimize the operating parameters in real time in response to the detection of changes in the rider's emotional state by the recurrent neural network. In an embodiment, the recurrent neural network detects patterns of feature vectors that indicate that the rider's emotional state is changing from a first emotional state to a second emotional state. In an embodiment, the radial basis function neural network is to optimize the operating parameters of the vehicle in response to changes in the indicated emotional state.

In embodiments, the recurrent neural network comprises a plurality of connected nodes forming a directed cycle, and the recurrent neural network further facilitates bi-directional flow of data between connected nodes. In an embodiment, the feature vectors are: the rider's emotional state is changing, the rider's emotional state is stable, the rate of change of the rider's emotional state, the direction of change of the rider's emotional state, and the rider's emotional state The rider's emotional state is changing to an unfavorable emotional state, and the rider's emotional state is changing to a favorable emotional state, indicating at least one of the polarities of the state change. In embodiments, the operational parameters that are optimized are the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and to other vehicles along the route. affects at least one of the proximity of

In an embodiment, the radial basis function neural network is interacting with vehicle control system 30134 to adjust operating parameters 30124 . In an embodiment, the artificial intelligence system 3036 uses one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. It is further provided with a neural network including. In an embodiment, the artificial intelligence system 3036 is to maintain the rider's preferred emotional state via a modular neural network, which processes feature vectors of the rider's facial image in the vehicle to identify patterns. a detecting rider emotional state determination neural network. In an embodiment, the pattern of feature vectors is indicative of at least one of a favorable emotional state and an unfavorable emotional state. A vehicle operating state optimization neural network that responds to adjust vehicle operating parameters.

In an embodiment, the vehicle operating state optimization neural network is to adjust the vehicle operating parameters 30124 to achieve the rider's preferred emotional state. In an embodiment, the vehicle motion state optimization neural network is to optimize motion parameters based on the correlation between vehicle motion state 3045 and rider emotion state 3066 . In embodiments, the optimized vehicle operating parameters are determined and adjusted to induce a favorable rider emotional state. In embodiments, the rider emotional state determination neural network is derived from at least one of data streams from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. From the supplied training data set, we further learn to classify the feature vector patterns and associate the feature vector patterns with emotional states and their changes.

In an embodiment, the vehicle driving state optimization neural network is to optimize the driving parameters 30124 in real time in response to detection of changes in the rider's emotional state 30126 by the rider emotional state determination neural network. In an embodiment, the rider emotional state determination neural network is to detect patterns in the feature vector 30130 that indicate that the rider's emotional state is changing from a first emotional state to a second emotional state. In an embodiment, the vehicle driving state optimization neural network is to optimize driving parameters of the vehicle in response to changes in the indicated emotional state. In an embodiment, the artificial intelligence system 3036 comprises a plurality of connected nodes forming a directed cycle, and the artificial intelligence system further facilitates bi-directional flow of data between connected nodes.

In an embodiment, the feature vector 30130 includes information about whether the rider's emotional state is changing, whether the rider's emotional state is stable, the rate of change of the rider's emotional state, the direction of change of the rider's emotional state, and the rider's The rider's emotional state is changing to an unfavorable emotional state, and the rider's emotional state is changing to a favorable emotional state, indicating at least one of the polarities of the change in the emotional state. In embodiments, the driving parameters that are optimized are the vehicle's route, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and to other vehicles along the route. affects at least one of the proximity of In an embodiment, the vehicle driving state optimization neural network interacts with the vehicle control system to adjust driving parameters.

In an embodiment, the artificial intelligence system 3036 uses one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. Further including a neural net comprising: It will be appreciated that the terms "neural net" and "neural network" are used interchangeably in this disclosure. In embodiments, the rider emotional state determination neural network facilitates determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated, one or more of which mimic human senses. of perceptrons. In an embodiment, the artificial intelligence system 3036 includes a recurrent neural network that indicates changes in the emotional state of the rider in the vehicle through recognition of patterns in feature vectors of facial images of the rider in the vehicle, and the transportation system comprises a plurality of vehicles. It further comprises a vehicle control system 30134 that controls operation of the vehicle by adjusting operating parameters 30124 and a feedback loop that communicates indicated changes in the rider's emotional state between the vehicle control system 30134 and the artificial intelligence system 3036. . In an embodiment, the vehicle control system is to adjust at least one of a plurality of vehicle operating parameters 30124 in response to indicated changes in the rider's emotional state. In embodiments, the vehicle control system adjusts at least one of a plurality of vehicle operational parameters based on correlations between vehicle operational states and rider emotional states.

In an embodiment, the vehicle control system adjusts at least one of a plurality of vehicle operating parameters 30124 indicative of a preferred rider emotional state. In an embodiment, the vehicle control system 30134 selects adjustments to at least one of the plurality of vehicle operating parameters 30124 indicative of producing a favorable rider emotional state. In embodiments, the recurrent neural network was fed from at least one of streams of data from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. It further learns to classify patterns of feature vectors from the training data set 30131 to associate emotional states with their changes. In an embodiment, the vehicle control system 30134 adjusts at least one of the plurality of vehicle operating parameters 30124 in real time. In an embodiment, the recurrent neural network detects patterns of feature vectors that indicate that the rider's emotional state is changing from a first emotional state to a second emotional state. In embodiments, the vehicle driving control system adjusts the driving parameters of the vehicle in response to the indicated emotional state change. In embodiments, the recurrent neural network comprises a plurality of connected nodes forming a directed cycle, and the recurrent neural network further facilitates bi-directional flow of data between connected nodes.

In an embodiment, the feature vectors are: the rider's emotional state is changing, the rider's emotional state is stable, the rider's emotional state change rate, the rider's emotional state change direction, and the rider's emotional state The rider's emotional state is changing to an unfavorable state and the rider's emotional state is changing to a favorable state, indicating at least one of the polarities of the state change. In embodiments, at least one of the plurality of vehicle driving parameters that are responsively adjusted are vehicle route, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, distance to objects along the route. Proximity, affecting proximity to other vehicles along the route. In embodiments, at least one of the plurality of vehicle operating parameters that are responsively adjusted affects operation of the vehicle's powertrain and the vehicle's suspension system. In an embodiment, the radial basis function neural network interacts with a recurrent neural network through an intermediary component of the artificial intelligence system 3036 that produces vehicle control data indicative of the rider's emotional state response to the vehicle's current operating state. In embodiments, the recognition of the pattern of feature vectors is performed prior to adjusting at least one of the plurality of vehicle operating parameters, during adjusting at least one of the plurality of vehicle operating parameters, and at least one of the plurality of vehicle operating parameters. processing the feature vectors of the lidar facial images captured between at least two after adjusting .

In an embodiment, adjusting 30124 at least one of the plurality of vehicle operating parameters improves the emotional state of the rider within the vehicle. In embodiments, adjusting at least one of the plurality of vehicle operating parameters changes the rider's emotional state from an unfavorable emotional state to a favorable emotional state. In embodiments, the changes are represented by a recurrent neural network. In an embodiment, the recurrent neural network uses a first set of feature vectors of captured rider facial images prior to adjusting at least one of the plurality of driving parameters and at least one of the plurality of driving parameters. The emotional state of the rider in response to changes in the operating parameters of the vehicle by determining the difference between a second set of feature vectors of the rider's facial image captured during or after adjusting one. to change the

In an embodiment, the recurrent neural network detects patterns of feature vectors that indicate that the rider's emotional state is changing from a first emotional state to a second emotional state. In embodiments, the vehicle driving control system adjusts the driving parameters of the vehicle in response to the indicated emotional state change.

Referring to FIG. 31 , provided herein, in embodiments, is processing audio of a rider in a vehicle to determine an emotional state, and controlling at least one of the vehicles to improve the emotional state of the rider. A transport system with an artificial intelligence system for optimizing operating parameters. A speech analysis module takes speech input and uses a training set of labeled data indicative of emotional states while an individual speaks and/or is analyzed by others to indicate emotional states perceived while an individual speaks. Whether or not the data is tagged can be used by a machine learning system (such as any of the types described herein) to classify an individual's emotional state based on speech (supervised learning, deep learning etc.). Machine learning may improve classification by using feedback from a large set of trials, where the feedback at each instance indicates whether the system correctly assessed the individual's emotional state for the speaking instance. ing. Once trained to classify emotional states, the expert system (optionally using another machine learning system or other artificial intelligence system), based on the resulting feedback of a set of individual emotional states: It can be trained to optimize various vehicle parameters noted throughout this disclosure in order to maintain or induce more favorable conditions. For example, if an individual's voice indicates well-being, among many other indicators, the expert system can select or recommend upbeat music to maintain that state. If the voice indicates stress, the system provides a recommendation or control signal to change the planned route to something less stressful (e.g., less stop-and-go traffic, or a higher probability of on-time arrival). You may In an embodiment, the system uses a series of questions, such as by using the intelligent agent module of the system, to determine if the rider is experiencing stress and what the stress is (e.g., traffic conditions, engage in dialogue (e.g., on-screen dialogue or voice dialogue) designed to help obtain feedback from the user regarding their emotional state, such as asking the rider questions about the likelihood of being late, probability of arriving on time, etc.) It may be configured as Sources of stress (such as traffic conditions, possible late arrivals, behavior of other drivers, or other causes unrelated to the nature of the ride), potential stress relievers (routing options, communication (e.g., offer to send a note that may be delayed), entertainment options, ride configuration options, etc.), etc.). The driver's reaction is not only input to the expert system as an indicator of emotional state, but also is used to determine the behavior of one or more vehicles, such as by excluding configuration options unrelated to the driver's stress source from the set of available configurations. It may also be provided to limit efforts to optimize parameters.

Aspects provided herein are a transportation system 3111, an artificial intelligence system 3136 for processing audio 31135 of a rider 3144 in a vehicle 3110 to determine an emotional state 3166 of the rider 3144; optimizing at least one operating parameter 31124 of the vehicle 3110 to improve the emotional state 3166 of the vehicle.

Aspects provided herein are an artificial intelligence system 3136 for speech processing to improve rider satisfaction in a transportation system 3111, comprising: A rider audio capture system 30136 arranged to capture the audio output 31128 of a rider 3144 aboard a vehicle 3110 and trained using machine learning to classify the rider's emotional state 31138 for the captured audio output of the rider. an expert system 31139 using machine learning to optimize at least one operating parameter 31124 of the vehicle to transform the rider's emotional state into an emotional state classified as an improved emotional state; Prepare.

In an embodiment, the rider voice capture system 31136 consists of an intelligent agent 31140 that interacts with the rider to obtain rider feedback for use by the speech analysis circuit 31132 for rider emotional state classification. In an embodiment, speech analysis circuit 31132 uses a first machine learning system and expert system 31139 uses a second machine learning system. In an embodiment, the expert system 31139 is trained to optimize the at least one operating parameter 31124 based on the resulting feedback of the emotional state in adjusting the at least one operating parameter 31124 for the set of individuals. be done. In an embodiment, the rider's emotional state 3166 is determined by a combination of the rider's captured audio output 31128 and at least one other parameter. In embodiments, the at least one other parameter is the rider's camera-based emotional state determination. In embodiments, the at least one other parameter is traffic information. In embodiments, the at least one other parameter is weather information. In embodiments, the at least one other parameter is vehicle condition. In embodiments, the at least one other parameter is at least one pattern of the rider's physiological data. In embodiments, the at least one other parameter is the vehicle's route. In embodiments, the at least one other parameter is in-vehicle audio content. In embodiments, the at least one other parameter is vehicle speed. In embodiments, the at least one other parameter is vehicle acceleration. In embodiments, the at least one other parameter is vehicle deceleration. In embodiments, at least one other parameter is proximity to objects along the path. In embodiments, the at least one other parameter is proximity to other vehicles along the route.

Aspects provided herein are an artificial intelligence system 3136 for audio processing to improve rider satisfaction, including: A first neural network 3122, trained to classify emotional states based on analysis of human voice, uses the rider's voice output 31128, captured while the rider is on board the vehicle 3110, at least for the rider. A second neural network 3120 detects the rider's emotional state through the perception of aspects correlated to one emotional state 3166, and the second neural network 3120 processes the vehicle in response to the detected rider's emotional state 31126 to achieve a preferred rider emotional state. optimizing 3142 the operating parameters 31124 of the . In embodiments, at least one of the neural networks is a convolutional neural network. In an embodiment, the first neural network 3122 is trained through the use of a training data set that associates emotional state classes with human speech patterns. In an embodiment, the first neural network 3122 is trained through the use of a training data set of voice recordings tagged with emotional state identification data. In embodiments, the rider's emotional state is determined by a combination of the rider's captured audio output and at least one other parameter. In embodiments, the at least one other parameter is the rider's camera-based emotional state determination. In embodiments, the at least one other parameter is traffic information. In embodiments, the at least one other parameter is weather information. In embodiments, the at least one other parameter is vehicle condition.

In embodiments, the at least one other parameter is at least one pattern of the rider's physiological data. In embodiments, the at least one other parameter is the vehicle's route. In embodiments, the at least one other parameter is in-vehicle audio content. In embodiments, the at least one other parameter is vehicle speed. In embodiments, the at least one other parameter is vehicle acceleration. In embodiments, the at least one other parameter is vehicle deceleration. In embodiments, at least one other parameter is proximity to objects along the path. In embodiments, the at least one other parameter is proximity to other vehicles along the route.

Referring now to FIG. 32, embodiments provided herein process data from the interaction of the rider with the vehicle's e-commerce system to determine and improve the rider's condition. transportation system 3211 having an artificial intelligence system 3236 for optimizing at least one operating parameter of the vehicle for Another common activity for users of device interfaces is electronic commerce, such as shopping, bidding in auctions, and selling items. E-commerce systems use search capabilities, undertake advertising, and engage users in a variety of workflows that can ultimately result in orders, purchases, bids, and the like. As described herein for searches, a set of vehicle-related search results may be provided for electronic commerce as well as vehicle-related advertising. Additionally, in-vehicle related interfaces and workflows may be configured based on in-vehicle lidar detection, which may be quite different from the workflows provided for e-commerce interfaces configured for smartphones or desktop systems. be. Among other factors, the in-vehicle system provides route information (including directions, scheduled stops, scheduled times, etc.), rider mood and behavior information (such as detected from past routes and from in-vehicle sensor sets), Information not available to conventional e-commerce systems may be accessed, including vehicle configuration and condition information (such as make and model), as well as any of the other vehicle-related parameters discussed throughout this disclosure. An example is being bored (detected by an in-vehicle sensor set, such as using an expert system trained to detect boredom) and taking a long trip (as indicated by the route being taken by the car). Riders may be much more patient and involved in deeper, richer content and longer workflows than typical mobile users. As another example, in-vehicle users may be much more likely to engage in free trials, surveys, or other behaviors that drive engagement with the brand. Also, in-vehicle users may be able to use other time to accomplish specific goals, such as buying necessities. Presenting in-vehicle users with the same interface, content, and workflow can miss out on an excellent opportunity for deeper engagement that would be rare in other environments where many compete for the user's attention. . In embodiments, an e-commerce system interface may be provided for in-vehicle users, including interface display, content, search results, advertisements, and one or more related workflows (shopping, bidding, searching, purchasing, providing feedback, product display, rating or review input, etc.) is configured based on detecting use of the vehicle interface. Display and interaction can vary depending on display type (e.g., enabling rich or larger images for large HD displays), network capabilities (e.g., faster loading and audio system capabilities (e.g., use audio for dialogue management and intelligent assistant interactions), and detection of the same for vehicles (optionally based on a set of rules or machine learning). ) may be further set. Display elements, content, and workflows may be configured through machine learning, such as using A/B testing and/or genetic programming techniques, such as configuring alternative interaction types and tracking results. Outcomes used to train the automated configuration of the in-vehicle e-commerce interface workflow may include degree of engagement, yield, purchases, rider satisfaction, ratings, and others. In-vehicle users may be profiled and clustered by behavioral profiling, demographic profiling, psychostatistical profiling, location-based profiling, collaborative filtering, similarity-based clustering, etc., similar to traditional e-commerce, but profiles are information, vehicle information, vehicle configuration information, vehicle state information, rider information, and the like. A set of in-vehicle user profiles, groups, and clusters may be maintained separately from traditional user profiles, and differences in in-vehicle shopping areas are taken into account when targeting search results, advertisements, product offers, discounts, etc. learning about what to present and how to present it.

Aspects provided herein are a transportation system 3211, an artificial intelligence system 3236 for processing data from the interaction of a rider 3244 and a vehicle e-commerce system to determine rider status; optimizing at least one operating parameter of the vehicle to improve rider conditions.

Aspects provided herein include a rider satisfaction system 32123 for optimizing rider satisfaction 32121, the rider satisfaction system comprising: e-commerce interface 32141 deployed for access by riders in vehicle 3210; rider interaction circuitry that captures rider interactions with deployed interfaces 32141; and an artificial intelligence system 3236 trained to optimize at least one parameter 32124 affecting operation of the vehicle to improve the rider state 3237 in response to the rider state 3237. , provided. In an embodiment, vehicle 3210 includes a system for automating at least one control parameter of the vehicle. In embodiments, the vehicle is at least a semi-autonomous vehicle. In embodiments, the vehicle is automatically routed. In embodiments, the vehicle is a self-driving vehicle. In embodiments, the e-commerce interface is self-adaptive and responsive to at least one of rider identity, vehicle route, rider mood, rider behavior, vehicle configuration, and vehicle state.

In embodiments, the e-commerce interface 32141 provides in-vehicle related content 32146 based on at least one of rider identity, vehicle route, rider mood, rider behavior, vehicle configuration, and vehicle state. In embodiments, the e-commerce interface implements a user interaction workflow 32147 adapted for use by the rider 3244 of the vehicle 3210. In embodiments, the e-commerce interface provides one or more results of the search query 32148 adapted for presentation in the vehicle. In embodiments, search query results adapted for vehicular presentation are presented in an e-commerce interface along with advertisements adapted for vehicular presentation. In embodiments, rider interaction circuitry 32142 captures rider interactions 32144 with the interface in response to content 32146 presented on the interface.

FIG. 33 is a diagram illustrating a method 3300 for optimizing vehicle parameters according to embodiments of the systems and methods disclosed herein. At 3302, the method includes capturing lidar interactions with an in-vehicle e-commerce system. At 3304, the method includes determining a rider state based on the captured rider interaction and at least one operating parameter of the vehicle. At 3306, the method includes processing rider conditions with a rider satisfaction model that is adapted to suggest at least one operating parameter of the vehicle that affects rider conditions. In, the method includes optimizing the proposed at least one operating parameter for at least one of maintaining and improving lidar conditions.

See FIGS. 32 and 33. FIG. 33. Aspects provided herein are artificial intelligence systems 3236 for improving rider satisfaction, including: Lidar with in-vehicle e-commerce system to detect lidar state 32149 through recognition of aspects of lidar interaction 32144 captured while the rider is on board the vehicle that correlate to at least one state 3237 of the rider. A first neural network 3222 trained to classify rider conditions based on an analysis of interactions 32144 and, in response to detected rider conditions, adjusting vehicle operating parameters to achieve preferred rider conditions. It has a second neural network 3220 that optimizes.

Referring to FIG. 34, in the embodiments provided herein, for processing data from at least one Internet of Things (IoT) device 34150 within the environment 34151 of the vehicle 3410 to determine the state 34152 of the vehicle. and optimizing at least one operating parameter 34124 of the vehicle to improve the rider's condition 3437 based on the determined condition 34152 of the vehicle.

Aspects provided herein are a transportation system 3411 that processes data from at least one IoT device 34150 in an environment 34151 of a vehicle 3410 to determine a determination state 34152 of the vehicle; An artificial intelligence system 3436 that optimizes at least one operating parameter 34124 of the vehicle to improve the rider's condition 3437 based on the condition 34152.

FIG. 35 is a diagram illustrating a method 3500 for improving rider conditions through optimizing vehicle operation, according to embodiments of the systems and methods disclosed herein. At 3502, the method includes capturing vehicle operation related data with at least one IoT device. At 3504, the method includes analyzing the captured data with a first neural network that determines a state of the vehicle based at least in part on captured vehicle motion-related data. At 3506, the method includes receiving data describing conditions of a rider occupying the vehicle in motion. At 3508th, the method includes using a neural network to determine at least one vehicle operating parameter that affects the condition of a rider on board the operating vehicle. In, the method includes optimizing at least one vehicle operating parameter using an artificial intelligence-based system such that the result of the optimization consists of improving rider conditions.

Referring to FIGS. 34 and 35, in an embodiment vehicle 3410 comprises a system for automating at least one control parameter 34153 of vehicle 3410 . In embodiments, vehicle 3410 is at least a semi-autonomous vehicle. In an embodiment, vehicle 3410 is automatically routed. In an embodiment, vehicle 3410 is a self-driving vehicle. In an embodiment, at least one IoT device 34150 is placed in the operating environment 34154 of the vehicle. In an embodiment, at least one IoT device 34150 that captures data about vehicle 3410 is located external to vehicle 3410 . In embodiments, at least one IoT device is a dashboard camera. In embodiments, at least one IoT device is a mirror camera. In embodiments, at least one IoT device is a motion sensor. In embodiments, at least one IoT device is a seat-based sensor system. In embodiments, at least one IoT device is an IoT enabled lighting system. In embodiments, the lighting system is an interior lighting system. In embodiments, the lighting system is a headlight lighting system. In embodiments, at least one IoT device is a traffic light camera or sensor. In embodiments, at least one IoT device is a roadway camera. In embodiments, the road surface cameras are located on telephones and/or utility poles. In embodiments, at least one IoT device is an in-road sensor. In embodiments, at least one IoT device is an automotive thermostat. In embodiments, at least one IoT device is a toll booth. In embodiments, at least one IoT device is a road sign. In embodiments, at least one IoT device is a traffic light. In embodiments, at least one IoT device is a vehicle-mounted sensor. In embodiments, at least one IoT device is a refueling system. In embodiments, at least one IoT device is a recharging system. In embodiments, at least one IoT device is a wireless charging station.

Aspects provided herein include a rider condition modification system 34155 for improving the condition 3437 of a rider 3444 within a vehicle 3410, the system comprising: A first neural network 3422 operable to classify the state of the vehicle through analysis of information about the vehicle captured by the Internet of Things device 34150 during operation of the vehicle 3410 and the classified state of the vehicle 34152, boarding the vehicle. a second neural network 3420 operable to optimize at least one operating parameter 34124 of the vehicle based on information relating to the rider's condition and information correlating vehicle operation and effects on the rider's condition; Prepare.

In embodiments, the vehicle constitutes a system for automating at least one control parameter 34153 of the vehicle 3410 . In embodiments, vehicle 3410 is at least a semi-autonomous vehicle. In an embodiment, vehicles 3410 are automatically routed. In an embodiment, vehicle 3410 is a self-driving vehicle. In embodiments, at least one Internet of Things device 34150 is located within the operating environment of the vehicle 3410 . In an embodiment, at least one IoT device 34150 that captures data about vehicle 3410 is located external to vehicle 3410 . In embodiments, at least one IoT device is a dashboard camera. In embodiments, at least one IoT device is a mirror camera. In embodiments, at least one IoT device is a motion sensor. In embodiments, at least one IoT device is a seat-based sensor system. In embodiments, at least one IoT device is an IoT enabled lighting system.

In embodiments, the lighting system is an interior lighting system. In embodiments, the lighting system is a headlight lighting system. In embodiments, at least one IoT device is a traffic light camera or sensor. In embodiments, at least one IoT device is a roadway camera. In embodiments, the road surface cameras are located on telephones and/or utility poles. In embodiments, at least one IoT device is an in-road sensor. In embodiments, at least one IoT device is an automotive thermostat. In embodiments, at least one IoT device is a toll booth. In embodiments, at least one IoT device is a road sign. In embodiments, at least one IoT device is a traffic light. In embodiments, at least one IoT device is a vehicle-mounted sensor. In embodiments, at least one IoT device is a refueling system. In embodiments, at least one IoT device is a recharging system. In embodiments, at least one IoT device is a wireless charging station.

Aspects provided herein include an artificial intelligence system 3436 comprising: A first neural network 3422 trained to determine an operating state 34152 of the vehicle 3410 from data about the vehicle captured in the operating environment 34154 of the vehicle, the first neural network 3422 having at least one object while the vehicle is operating. A first neural network 3422 that operates to identify the operating state 34152 of the vehicle by processing information about the vehicle 3410 captured by the internet appliance 34150 . A data structure 34156 that facilitates determining operating parameters that affect vehicle operating conditions, information about the conditions of riders 3444 on board the vehicle 3410, and information that correlates vehicle operation with effects on rider conditions. and a second neural network 3420 operable to process to optimize at least one of the determined operating parameters 34124 of the vehicle based on the identified operating conditions 34152 .

In embodiments, improvements in rider conditions are reflected in updated data describing rider conditions captured in response to vehicle operation based on the optimized at least one vehicle operating parameter. In embodiments, improvements in rider conditions are reflected in data captured by at least one IoT device 34150 arranged to capture information about riders 3444 while occupying vehicle 3410 in response to optimization. be. In an embodiment, vehicle 3410 constitutes a system for automating at least one control parameter 34153 of the vehicle. In embodiments, vehicle 3410 is at least a semi-autonomous vehicle. In an embodiment, vehicle 3410 is automatically routed. In an embodiment, vehicle 3410 is a self-driving vehicle. In an embodiment, at least one IoT device 34150 is placed in the operating environment 34154 of the vehicle. In embodiments, at least one IoT device 34150 that captures data about the vehicle is located outside the vehicle. In an embodiment, at least one IoT device 34150 is a dashboard camera. In embodiments, at least one IoT device 34150 is a mirror camera. In embodiments, at least one IoT device 34150 is a motion sensor. In an embodiment, at least one IoT device 34150 is a seat-based sensor system. In an embodiment, at least one IoT device 34150 is an IoT-enabled lighting system.

In embodiments, the lighting system is an interior lighting system. In embodiments, the lighting system is a headlight lighting system. In embodiments, at least one IoT device 34150 is a traffic light camera or sensor. In an embodiment, at least one IoT device 34150 is a roadway camera. In embodiments, the road surface cameras are located on telephones and/or utility poles. In an embodiment, at least one IoT device 34150 is an in-road sensor. In an embodiment, at least one IoT device 34150 is an automotive thermostat. In embodiments, at least one IoT device 34150 is a toll booth. In embodiments, at least one IoT device 34150 is a road sign. In embodiments, at least one IoT device 34150 is a traffic light. In embodiments, at least one IoT device 34150 is a vehicle-mounted sensor. In embodiments, at least one IoT device 34150 is a refueling system. In embodiments, at least one IoT device 34150 is a recharging system. In embodiments, at least one IoT device 34150 is a wireless charging station.

Referring to FIG. 36, in embodiments provided herein, sensory input from a wearable device 36157 in a vehicle 3610 is processed to determine an emotional state 36126 and the vehicle is used to improve the rider's emotional state 3637. 3610 is a transportation system 3611 having an artificial intelligence system 3636 for optimizing at least one operating parameter 36124 of 3610; A wearable device 36150, such as any described throughout this disclosure, detects any of the emotional states described herein (whether favorable or unfavorable) and improves the unfavorable condition or maintains the favorable condition. As an input to a real-time control system (such as any type of model-based, rule-based or artificial intelligence system described herein) to indicate purpose, and to promote or maintain a preferred state of operating parameters 36124 It can be used both as a feedback mechanism to train the artificial intelligence system 3636 to construct the set.

Aspects provided herein are a transportation system 3611 that processes sensory input from a wearable device 36157 within a vehicle 3610 to determine an emotional state 36126 of a rider 3644 within the vehicle 3610. Optimizing driving parameters 36124 of the vehicle to improve the emotional state 3637 of the rider 3644. In embodiments, the vehicle is a self-driving vehicle. In an embodiment, the artificial intelligence system 3636 is to detect the emotional state 36126 of the rider on the autonomous vehicle by recognizing patterns of emotional state-indicative data from the set of wearable sensors 36157 worn by the rider 3644 . In embodiments, the pattern is indicative of at least one of a preferred emotional state of the rider and an unfavorable emotional state of the rider. In embodiments, the artificial intelligence system 3636 is configured to achieve at least one of maintaining a detected favorable emotional state of the rider and achieving a favorable emotional state of the rider following detection of an unfavorable emotional state. Second, optimizing the vehicle's operating parameters 36124 in response to the rider's sensed emotional state. In an embodiment, the artificial intelligence system 3636 comprises an expert system that detects a rider's emotional state by processing rider emotional state-indicative data received from a set of wearable sensors 36157 worn by the rider. In embodiments, the expert system processes rider emotional state indicator data using at least one of a training set of emotional state indicators for a set of riders and a trainer-generated rider emotional state indicator. In an embodiment, the artificial intelligence system includes a recurrent neural network 3622 that detects the rider's emotional state.

In embodiments, the recurrent neural network consists of a plurality of connected nodes forming a directed cycle, and the recurrent neural network further facilitates bi-directional flow of data between connected nodes. In an embodiment, artificial intelligence system 3636 comprises a radial basis function neural network that optimizes operating parameters 36124 . In an embodiment, optimizing operating parameters 36124 is based on the correlation between vehicle operating state 3645 and rider emotional state 3637 . In embodiments, the correlation is determined using at least one of a training set of emotional state indicators of the set of riders and a human trainer-generated rider emotional state indicator. In embodiments, the vehicle operating parameters to be optimized are determined and adjusted to induce a favorable rider emotional state.

In embodiments, the artificial intelligence system 3636 is fed from at least one of data streams from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. It further learns to classify patterns of emotional state indicator data from the training data set 36131 and associate patterns with emotional states and their changes. In an embodiment, the artificial intelligence system 3636 detects patterns in the rider emotional state indication data indicating that the rider's emotional state is changing from a first emotional state to a second emotional state, and determines the operating parameters of the vehicle. Optimization is responsive to changes in the indicated emotional state. In an embodiment, the pattern of rider emotional state indication data includes: rider emotional state changing; rider emotional state stable; rate of change in rider emotional state; rate of change in rider emotional state; The direction and at least one of the polarity of the change in the rider's emotional state, the rider's emotional state changing to an unfavorable state, and the rider's emotional state changing to a favorable state.

In embodiments, the operational parameters 36124 that are optimized include the vehicle's route, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and other vehicles along the route. Affects at least one of proximity to In embodiments, the artificial intelligence system 3636 interacts with the vehicle control system to optimize operating parameters. In an embodiment, the artificial intelligence system 3636 uses one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. Further includes a neural net 3622 that includes: In embodiments, the set of wearable sensors 36157 include watches, rings, wristbands, armbands, ankle bands, body bands, skin patches, head worn devices, eyeglasses, footwear, gloves, in-ear devices, clothing, headphones, At least two of a belt, a finger ring, a thumb ring, and a necklace. In an embodiment, the artificial intelligence system 3636 uses deep learning to determine patterns in the wearable sensor-generated emotional state-indicative data that indicate the rider's emotional state as at least one of a favorable emotional state and a negative emotional state. do. In embodiments, the artificial intelligence system 3636 responds to the rider's indicated emotional state by optimizing operational parameters to at least one of achieving and maintaining the rider's indicated emotional state.

In an embodiment, the artificial intelligence system 3636 characterizes the rider's preferred emotional state based on context gathered from multiple sources, including data indicating the rider's purpose for riding the autonomous vehicle, time of day, traffic conditions, and weather. Optimizing operating parameters 36124 for at least one of adapting the attachment and achieving and maintaining the adapted preferred emotional state. In an embodiment, the artificial intelligence system 3636 optimizes operational parameters in real-time in response to sensing the rider's emotional state. In embodiments, the vehicle is a self-driving vehicle. In embodiments, an artificial intelligence system comprises: A first neural network 3622 for detecting the emotional state of a rider through expert system-based processing of rider emotional state indicator wearable sensor data from a plurality of wearable physiological state sensors worn by the rider on the vehicle, the emotional state indicator wearable sensor data. a first neural network 3622, indicative of at least one of the rider's favorable emotional state and the rider's unfavorable emotional state; and the rider's detected emotion and a second neural network 3620 that optimizes vehicle operating parameters 36124 in response to conditions. In an embodiment, first neural network 3622 is a recurrent neural network and second neural network 3620 is a radial basis function neural network.

In an embodiment, second neural network 3620 optimizes operating parameters 36124 based on correlations between vehicle operating state 3645 and rider emotional state 3637 . In embodiments, the vehicle operating parameters to be optimized are determined and adjusted to induce a favorable rider emotional state. In an embodiment, the first neural network 3622 extracts data from at least one of streams of data from unstructured data sources, social media sources, wearable devices, in-vehicle sensors, rider helmets, rider headgear, and rider voice systems. From the supplied training data set, it further learns to classify patterns in rider emotional state-indicative wearable sensor data and associate patterns with emotional states and their changes. In an embodiment, the second neural network 3620 optimizes operational parameters in real-time in response to detection of the rider's emotional state by the first neural network 3622 . In an embodiment, the first neural network 3622 detects patterns in the wearable sensor data indicative of the rider's emotional state indicating that the rider's emotional state is changing from a first emotional state to a second emotional state. do. In an embodiment, the second neural network 3620 optimizes the operating parameters of the vehicle in response to changes in the indicated emotional state.

In an embodiment, the first neural network 3622 consists of a plurality of connected nodes forming a directed cycle, the first neural network 3622 further facilitating bi-directional flow of data between the connected nodes. In an embodiment, the first neural network 3622 includes one or more perceptrons that mimic human senses that facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. including. In an embodiment, the wearable sensor data indicating the rider's emotional state includes information such as whether the rider's emotional state is changing, whether the rider's emotional state is stable, the rider's emotional state change rate, and the rider's emotional state. indicating at least one of the direction of change and the polarity of the change in the rider's emotional state that the rider's emotional state is changing to an unfavorable state and that the rider's emotional state is changing to a favorable state; is. In embodiments, the driving parameters that are optimized are the vehicle's path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and to other vehicles along the route. affects at least one of the proximity of In an embodiment, the second neural network 3620 interacts with the vehicle control system to adjust operating parameters. In an embodiment, the first neural network 3622 includes one or more perceptrons that mimic human senses that facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. including.

In embodiments, the vehicle is a self-driving vehicle. In an embodiment, the artificial intelligence system 3636 detects changes in the emotional state of a rider in an autonomous vehicle, at least in part by recognizing patterns in emotional state-indicative data from a set of wearable sensors worn by the rider. That is. In embodiments, the pattern is indicative of at least one of the decline of the rider's favorable emotional state and the development of the rider's unfavorable emotional state. In an embodiment, the artificial intelligence system 3636 determines at least one operational parameter 36124 of the autonomous vehicle indicative of a change in emotional state based on correlations between patterns of data indicative of the emotional state and a set of operational parameters of the vehicle. It is to be. In an embodiment, the artificial intelligence system 3636 determines the at least one operating parameter 36124 to achieve at least one of restoring a rider's favorable emotional state and achieving a reduction in the development of a rider's unfavorable emotional state. is to determine regulation.

In embodiments, the correlation of patterns of rider emotional state indicator wearable sensor data is performed using at least one of a training set of emotional state wearable sensor indicators of a set of riders and a human trainer generated rider emotional state wearable sensor indicator. It is determined. In embodiments, the artificial intelligence system 3636 is fed from at least one of data streams from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. From the training data set, we further learn to classify patterns in the emotional state indicator wearable sensor data and associate patterns with changes in the rider's emotional state. In an embodiment, the patterns of the wearable sensor data indicative of the rider's emotional state include: the rider's emotional state is changing; the rider's emotional state is stable; the rider's emotional state is changing; Indicating at least one of the direction of change and the polarity of the change in the rider's emotional state, the rider's emotional state is changing to an unfavorable state, and the rider's emotional state is changing to a favorable state.

In embodiments, the operational parameters determined from processing the wearable sensor data indicative of the rider's emotional state may include vehicle path, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, objects along the route. and/or to other vehicles along the route. In embodiments, the artificial intelligence system 3636 further interacts with the vehicle control system to adjust operating parameters. In an embodiment, the artificial intelligence system 3636 includes one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. Further includes a neural net.

In embodiments, the set of wearable sensors includes watches, rings, wristbands, armbands, ankle bands, torso bands, skin patches, head worn devices, eye glasses, footwear, gloves, ear devices, clothing, headphones, At least two of a belt, a finger ring, a thumb ring, and a necklace. In an embodiment, the artificial intelligence system 3636 uses deep learning to determine patterns in wearable sensor-generated emotional state-indicative data indicative of changes in the rider's emotional state. In embodiments, the artificial intelligence system 3636 may also detect changes in the rider's emotional state based on context gathered from multiple sources, including data indicating the rider's purpose for riding the autonomous vehicle, time of day, traffic conditions, and weather. Determining and optimizing operating parameters 36124 to at least one of achieving and maintaining the matched preferred emotional state. In embodiments, the artificial intelligence system 3636 adjusts operational parameters in real-time in response to detecting changes in rider emotional state.

In embodiments, the vehicle is a self-driving vehicle. In an embodiment, the artificial intelligence system 3636 uses recurrent neural networks to indicate changes in the emotional state of a rider in an autonomous vehicle by recognizing patterns in wearable sensor data indicative of the emotional state from a set of wearable sensors worn by the rider. Including network. In embodiments, the pattern is indicative of at least one of a first degree of the rider's favorable emotional state and a second degree of the rider's unfavorable emotional state, and is responsive to an indication of a change in the rider's emotional state. has a radial basis function neural network that optimizes the vehicle operating parameters 36124 to achieve the target emotional state of the rider.

In an embodiment, a radial basis function neural network optimizes operating parameters based on correlations between vehicle operating states and rider emotional states. In an embodiment, the target emotional state is a preferred rider emotional state and the optimized vehicle operating parameters are determined and adjusted to induce the preferred rider emotional state. In embodiments, the recurrent neural network was fed from at least one of streams of data from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. From the training data set, it further learns to classify patterns in wearable sensor data indicative of emotional states and to associate emotional states with changes in them. In an embodiment, the radial basis function neural network optimizes operational parameters in real-time in response to detection of changes in the rider's emotional state by the recurrent neural network. In an embodiment, the recurrent neural network detects patterns in the emotional state indicator wearable sensor data indicating that the rider's emotional state is changing from a first emotional state to a second emotional state. In an embodiment, a radial basis function neural network optimizes vehicle operating parameters in response to changes in the indicated emotional state. In embodiments, the recurrent neural network comprises a plurality of connected nodes forming a directed cycle, and the recurrent neural network further facilitates bi-directional flow of data between connected nodes.

In an embodiment, the pattern of the wearable sensor data indicative of the emotional state includes: the rider's emotional state is changing; the rider's emotional state is stable; the rate of change in the rider's emotional state; indicating at least one of the direction of change and the polarity of the change in the rider's emotional state that the rider's emotional state is changing to an unfavorable state and that the rider's emotional state is changing to a favorable state; is. In embodiments, the operational parameters that are optimized are the vehicle's route, in-vehicle audio content, vehicle speed, vehicle acceleration, vehicle deceleration, proximity to objects along the route, and to other vehicles along the route. at least one parameter of the proximity of . In an embodiment, a radial basis function neural network interacts with the vehicle control system to adjust operating parameters. In embodiments, the recurrent neural net includes one or more perceptrons that mimic human senses that facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated.

In an embodiment, the artificial intelligence system 3636 is to maintain the rider's preferred emotional state through the use of a modular neural network that processes wearable sensor data indicative of the rider's emotional state within the vehicle. a lidar emotional state determination neural network for detecting patterns in the rider. In embodiments, the pattern found in the emotional state indicator wearable sensor data is indicative of at least one of the rider's favorable emotional state and the rider's unfavorable emotional state. A mediator circuit for transforming and a vehicle operating condition optimization neural network for adjusting vehicle operating parameters 36124 in response to vehicle operating condition data.

In an embodiment, the vehicle driving state optimization neural network adjusts the driving parameters of the vehicle to achieve the rider's preferred emotional state. In an embodiment, the vehicle driving state optimization neural network optimizes driving parameters based on the correlation between vehicle driving state and rider emotional state. In embodiments, the optimized vehicle operating parameters are determined and adjusted to induce a favorable rider emotional state. In embodiments, the rider emotional state determination neural network is derived from at least one of data streams from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. From the supplied training data set, it further learns to classify patterns in wearable sensor data indicative of emotional states and associate them with emotional states and their changes.

In an embodiment, the vehicle driving state optimization neural network optimizes driving parameters in real time in response to detection of changes in the rider's emotional state by the rider emotional state determination neural network. In an embodiment, the rider emotional state determination neural network detects patterns in the emotional state-indicative wearable sensor data that indicate that the rider's emotional state is changing from a first emotional state to a second emotional state. In an embodiment, the vehicle operating state optimization neural network optimizes the operating parameters of the vehicle in response to changes in the indicated emotional state. In embodiments, the artificial intelligence system 3636 comprises a plurality of connected nodes forming a directed cycle, and the artificial intelligence system 3636 further facilitates bi-directional flow of data between connected nodes. In an embodiment, the patterns of the wearable sensor data indicating the emotional state are: the rider's emotional state is changing, the rider's emotional state is stable, the rate of change of the rider's emotional state, the change direction of the rider's emotional state. , and the polarity of the change in the rider's emotional state, the rider's emotional state is changing to an unfavorable state, and the rider's emotional state is changing to a favorable state.

In embodiments, the operational parameters that are optimized are the vehicle's route, the in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the route, and other vehicles along the route. affects at least one of the proximity of In an embodiment, the vehicle driving state optimization neural network interacts with the vehicle control system to adjust driving parameters. In an embodiment, the artificial intelligence system 3636 uses one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. Further including a neural net comprising: In an embodiment, the rider emotional state determination neural network includes one or more perceptrons that mimic human senses that facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. Prepare.

In an embodiment, the artificial intelligence system 3636 is to indicate changes in the emotional state of the rider in the vehicle through recognition of patterns in wearable sensor data indicative of the emotional state of the rider in the vehicle, and the transportation system is to It also includes a vehicle control system that controls the operation of the vehicle by adjusting operating parameters and a feedback loop through which indications of changes in the rider's emotional state are communicated between the vehicle control system and the artificial intelligence system 3636 . In embodiments, the vehicle control system adjusts at least one of a plurality of vehicle operating parameters in response to the change indication. In embodiments, the vehicle control system adjusts at least one of the plurality of vehicle operating parameters based on the correlation between the vehicle operating state and the rider emotional state.

In embodiments, the vehicle control system adjusts at least one of a plurality of vehicle operating parameters indicative of a favorable rider emotional state. In an embodiment, the vehicle control system selects an adjustment of at least one of the plurality of vehicle operating parameters indicative of producing a favorable rider emotional state. In embodiments, the artificial intelligence system 3636 is fed from at least one of data streams from unstructured data sources, social media sources, wearable devices, vehicle sensors, rider helmets, rider headgear, and rider voice systems. From the training data set, it further learns to classify patterns in wearable sensor data indicative of emotional states and associate emotional states with changes in them. In embodiments, a vehicle control system adjusts at least one of a plurality of vehicle operating parameters in real time.

In an embodiment, the artificial intelligence system 3636 further detects patterns in the emotional state-indicative wearable sensor data indicating that the rider's emotional state is changing from a first emotional state to a second emotional state. In embodiments, the vehicle driving control system adjusts the driving parameters of the vehicle in response to the indicated emotional state change. In embodiments, the artificial intelligence system 3636 comprises a plurality of connected nodes forming a directed cycle, and the artificial intelligence system 3636 further facilitates bi-directional flow of data between connected nodes. In embodiments, at least one of the plurality of vehicle operating parameters that are responsively adjusted affects operation of the vehicle's powertrain and the vehicle's suspension system.

In an embodiment, the radial-based function neural network interacts with the recurrent neural network through an intermediate component of the artificial intelligence system 3636 that produces vehicle control data indicative of the rider's emotional state response to the vehicle's current operating state. In an embodiment, the artificial intelligence system 3636 further comprises a modular neural network including a rider emotional state recurrent neural network for indicating changes in the rider's emotional state, a vehicle motion state radial-based function neural network, and an intermediary system. In an embodiment, the mediation system uses the rider emotional state characterization data from the recurrent neural network as vehicle control data that the radial based function neural network uses to interact with the vehicle control system to adjust at least one operating parameter. to process.

In an embodiment, the artificial intelligence system 3636 includes one or more perceptrons that mimic human senses to facilitate determining the rider's emotional state based on the degree to which at least one of the rider's senses is stimulated. Equipped with a neural net. In embodiments, recognizing patterns in wearable sensor data indicative of an emotional state is performed prior to adjusting at least one of a plurality of vehicle operating parameters, during adjusting at least one of a plurality of vehicle operating parameters, and after adjusting at least one of a plurality of vehicle operating parameters. Processing wearable sensor data indicative of an emotional state captured during at least two after adjusting at least one of the parameters.

In an embodiment, the artificial intelligence system 3636 includes a first set of wearable sensor data indicative of the rider's emotional state captured prior to adjusting at least one of the plurality of operating parameters and at least one of the plurality of operating parameters. changes in the rider's emotional state in response to changes in the vehicle's operating parameters 36124 by determining differences between a second set of wearable sensor data indicative of the rider's emotional state captured during or after adjusting the indicates

Referring to FIG. 37, in embodiments provided herein, a transportation system 3711 is provided having a cognitive system 37158 for managing an advertising marketplace of in-seat advertising for riders 3744 of autonomous vehicles. In an embodiment, the perception system 37158 uses the vehicle and/or rider 3744 to determine at least one of the price, type, and location of advertisements to be delivered within the interface 3713 to the rider 3744 in the vehicle seat 3728 . At least one parameter 37124 related input is taken. As noted above in relation to search, in-vehicle lidars, particularly those in self-driving vehicles, may be contextually placed to advertisements quite differently when in a vehicle than at other times. Bored riders may be more active in viewing advertising content, clicking on offers or promotions, engaging in surveys, and the like. In embodiments, the ad marketplace platform may segment and process ad placement for in-vehicle ads (including processing bids and requests for ad placement, etc.) separately. Such ad marketplace platforms use vehicle-specific information, such as vehicle type, display type, audio system capabilities, screen size, rider demographic information, route information, and location information, in characterizing ad placement opportunities. , bids for in-vehicle advertising placements may reflect such vehicles, riders, and other traffic-related parameters. For example, an advertiser may bid for placement of an ad on the on-board display system of a self-driving vehicle that is worth more than $50,000 and is routed north on Highway 101 during the morning commute. The ad marketplace platform configures many such vehicle-related placement opportunities, processes bids for such opportunities, places ads (e.g., by load-balancing servers that cache the ads), and resolves the results. may be used to Yield metrics may be tracked and used to optimize marketplace configuration.

An aspect provided herein is a system for transportation, a cognitive system 37158 for managing an advertising marketplace of in-seat advertising for riders of autonomous vehicles, the cognitive system 37158 comprising: Takes input corresponding to at least one parameter 37159 of the vehicle or rider 3744 to determine characteristics 37160 of the advertisement to be delivered to the rider 3744 of the vehicle seat 3728 in the interface 3713, wherein the characteristics 37160 of the advertisement are price, category , location and combinations thereof.

FIG. 38 illustrates a method 3800 of vehicle in-seat advertising according to embodiments of the systems and methods disclosed herein. At 3802, the method includes taking input related to at least one parameter of the vehicle. At 3804, the method includes taking input related to at least one parameter of a rider occupying the vehicle. , the method determines the price, classification, content, and location of advertisements to be delivered within a vehicle interface to a rider in a vehicle seat based on vehicle-related inputs and rider-related inputs. Determining at least one.

Referring to Figures 37 and 38, in an embodiment the vehicle 3710 is automatically routed. In an embodiment, vehicle 3710 is a self-driving vehicle. In embodiments, the perception system 37158 also determines at least one of the price, classification, content, and location of the ad placement. In embodiments, the advertisement is delivered from the winning advertiser. In embodiments, delivering the advertisement is based on the winning bid. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes vehicle classification. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes display classification. In an embodiment, the inputs 37162 related to at least one parameter of the vehicle include audio system capabilities. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes screen size.

In an embodiment, the input 37162 related to at least one parameter of the vehicle includes route information. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes location information. In embodiments, the input 37163 related to at least one parameter of the rider includes rider demographic information. In an embodiment, the input 37163 related to at least one parameter of the rider includes the emotional state of the rider. In an embodiment, the input 37163 related to the rider's at least one parameter includes the rider's response to a prior in-seat advertisement. In embodiments, the input 37163 related to the rider's at least one parameter includes the rider's social media activity.

FIG. 39 is a diagram illustrating a method 3900 of in-vehicle advertising interaction tracking according to embodiments of the systems and methods disclosed herein. At 3902, the method includes taking input related to at least one parameter of the vehicle and input related to at least one parameter of a rider occupying the vehicle. At 3904, the method includes aggregating inputs across multiple vehicles. At 3906, the method includes using the cognitive system to determine in-vehicle advertising placement opportunities based on the aggregated inputs. At 3907, the method includes providing a placement opportunity at an advertising network that facilitates bidding on the placement opportunity. At 3908, the method includes delivering an advertisement for placement within the user interface of the vehicle based on the results of the bids. At 3909, the method includes monitoring interaction of the vehicle rider with the advertisement presented on the vehicle user interface.

37 and 39, in an embodiment vehicle 3710 comprises a system for automating at least one control parameter of the vehicle. In embodiments, vehicle 3710 is at least a semi-autonomous vehicle. In an embodiment, vehicles 3710 are automatically routed. In an embodiment, vehicle 3710 is a self-driving vehicle. In embodiments, the advertisement is delivered from the winning advertiser. In embodiments, delivery of advertisements is based on winning bids. In embodiments, the monitored vehicle rider interaction information includes information for resolving click-based payments. In embodiments, the monitored vehicle rider interaction information includes monitoring analysis results. In embodiments, the analytical result is a measure of interest in the advertisement. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes vehicle classification.

In an embodiment, the input 37162 related to at least one parameter of the vehicle includes display classification. In an embodiment, the inputs 37162 related to at least one parameter of the vehicle include audio system capabilities. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes screen size. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes route information. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes location information. In embodiments, the input 37163 related to at least one parameter of the rider includes rider demographic information. In an embodiment, the input 37163 related to at least one parameter of the rider includes the emotional state of the rider. In an embodiment, the input 37163 relating to the rider's at least one parameter includes the rider's reaction to prior in-seat advertisements. In embodiments, the input 37163 related to the rider's at least one parameter includes the rider's social media activity.

FIG. 40 illustrates a method 4000 of in-car advertising according to embodiments of the systems and methods disclosed herein. At 4002, the method includes taking input related to at least one parameter of the vehicle and input related to at least one parameter of a rider occupying the vehicle. At 4004, the method includes aggregating inputs across multiple vehicles. At 4006, the method includes using the cognitive system to determine in-vehicle advertising placement opportunities based on the aggregated inputs. At 4008, the method includes providing a placement opportunity at an advertising network that facilitates bidding for the placement opportunity. At 4009, the method includes delivering an advertisement for placement within the vehicle's interface based on the results of the bid.

37 and 40, in an embodiment vehicle 3710 comprises a system for automating at least one control parameter of the vehicle. In embodiments, vehicle 3710 is at least a semi-autonomous vehicle. In an embodiment, vehicles 3710 are automatically routed. In an embodiment, vehicle 3710 is a self-driving vehicle. In embodiments, the perception system 37158 also determines at least one of the price, classification, content, and location of the ad placement. In embodiments, the advertisement is delivered from the winning advertiser. In embodiments, delivering the advertisement is based on the winning bid. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes vehicle classification.

In an embodiment, the input 37162 related to at least one parameter of the vehicle includes display classification. In an embodiment, the inputs 37162 related to at least one parameter of the vehicle include audio system capabilities. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes screen size. In embodiments, the input 37162 related to at least one parameter of the vehicle includes route information. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes location information. In embodiments, the input 37163 related to at least one parameter of the rider includes rider demographic information. In an embodiment, the input 37163 related to at least one parameter of the rider includes the emotional state of the rider. In an embodiment, the input 37163 related to the rider's at least one parameter includes the rider's response to a prior in-seat advertisement. In embodiments, the input 37163 related to the rider's at least one parameter includes the rider's social media activity.

Aspects provided herein include an advertising system for vehicle in-seat advertising, the advertising system comprising: a. A perception system 37158 that takes input 37162 relating to at least one parameter 37124 of the vehicle 3710 and takes input relating to at least one parameter 37161 of a rider on board the vehicle; a system 3714 that determines at least one of the price, classification, content and location of advertisements to be delivered within the interface 37133 of the vehicle 3710 to the riders 3744 of the 3728;

In an embodiment, vehicle 4110 includes a system for automating at least one control parameter of the vehicle. In embodiments, vehicle 4110 is at least a semi-autonomous vehicle. In an embodiment, vehicle 4110 is automatically routed. In an embodiment, vehicle 4110 is a self-driving vehicle. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes vehicle classification. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes display classification. In an embodiment, the inputs 37162 related to at least one parameter of the vehicle include audio system capabilities. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes screen size. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes route information. In an embodiment, the input 37162 related to at least one parameter of the vehicle includes location information. In embodiments, the input 37163 related to at least one parameter of the rider includes rider demographic information. In an embodiment, the input 37163 related to at least one parameter of the rider includes the emotional state of the rider. In an embodiment, the input 37163 relating to the rider's at least one parameter includes the rider's reaction to prior in-seat advertisements. In embodiments, the input 37163 related to the rider's at least one parameter includes the rider's social media activity.

In embodiments, the advertising system is further characterized by determining vehicle operating conditions from inputs 37162 related to at least one parameter of the vehicle. In embodiments, the advertisements to be delivered are determined based at least in part on the determined vehicle operating conditions. In embodiments, the advertising system further comprises determining rider status 37149 from inputs 37163 related to at least one parameter of the rider. In embodiments, the advertisement to be delivered is determined based at least in part on the determined rider state 37149 .

Referring to FIG. 41, in the embodiments provided herein, a transportation system 4111 having a hybrid cognitive system 41164 for managing an advertising marketplace for in-seat advertising to riders of vehicles 4110 . In embodiments, at least a portion of the hybrid perception system 41164 processes input 41162 relating to at least one parameter 41124 of the vehicle to determine vehicle operating conditions, and at least another portion of the perception system processes input relating to the rider. to determine the rider state. In embodiments, the perception system determines at least one of the price, type, and location of advertisements to be delivered within the interface to riders in seats of the vehicle.

Aspects provided herein feature a transportation system 4111 comprising a hybrid cognitive system 41164 for managing an advertising marketplace for in-seat advertising to a rider 4144 of a vehicle 4110. . In an embodiment, at least one portion 41165 of the hybrid cognitive system processes input 41162 corresponding to at least one parameter of the vehicle to determine vehicle operating conditions 41168 and at least one other portion 41166 of the cognitive system 41164. processes rider related inputs 41163 to determine rider state 41149. In an embodiment, perception system 41164 determines characteristics 41160 of advertisements to be delivered within interface 41133 to rider 4144 in seat 4128 of vehicle 4110 . In embodiments, the advertisement characteristics 41160 are selected from the group consisting of price, category, location, and combinations thereof.

Aspects provided herein include an artificial intelligence system 4136 for vehicle in-seat advertising and are as follows. A first portion 41165 of an artificial intelligence system 4136 that determines an operating state 41168 of the vehicle by processing inputs 41162 related to at least one parameter of the vehicle and processing inputs 41163 related to at least one parameter of the rider. and a second portion 41166 of the artificial intelligence system 4136 that determines the state 41149 of the rider of the vehicle by means of the second portion 41166 of the artificial intelligence system 4136 . and at least one of the price, classification, content and location of advertisements to be delivered within the vehicle's interface 41133 to the rider 4144 in the seat of the vehicle 4110 based on the vehicle (operational) state 41168 and the rider state 41149. a third portion 41167 of the artificial intelligence system 4136 that determines

In an embodiment, vehicle 4110 includes a system for automating at least one control parameter of the vehicle. In embodiments, the vehicle is at least a semi-autonomous vehicle. In embodiments, the vehicle is automatically routed. In embodiments, the vehicle is a self-driving vehicle. In embodiments, the perception system 41164 also determines at least one of the price, classification, content, and location of the ad placement. In embodiments, the advertisement is delivered from the winning advertiser. In embodiments, delivering the advertisement is based on the winning bid. In embodiments, the input related to at least one parameter of the vehicle includes vehicle classification.

In embodiments, the input related to at least one parameter of the vehicle includes display classification. In embodiments, the input related to at least one parameter of the vehicle includes audio system capabilities. In embodiments, the input related to at least one parameter of the vehicle includes screen size. In embodiments, the input relating to at least one parameter of the vehicle includes route information. In embodiments, the input related to at least one parameter of the vehicle includes location information. In embodiments, the input related to the at least one parameter of the rider includes rider demographic information. In embodiments, the input related to the rider's at least one parameter includes the rider's emotional state. In an embodiment, the input related to the rider's at least one parameter includes the rider's reaction to the prior in-seat advertisement. In embodiments, the input related to the rider's at least one parameter includes the rider's social media activity.

FIG. 42 is a diagram illustrating a method 4200 of in-vehicle advertising interaction tracking according to embodiments of the systems and methods disclosed herein. At 4202, the method includes taking input related to at least one parameter of the vehicle and input related to at least one parameter of a rider occupying the vehicle. At 4204, the method includes aggregating inputs across multiple vehicles. At 4206, the method includes using the hybrid cognitive system to determine in-vehicle advertising placement opportunities based on the aggregated inputs. At 4207, the method includes providing placement opportunities at an advertising network that facilitates bidding for placement opportunities. At 4208, the method includes delivering an advertisement for placement within the user interface of the vehicle based on the results of the bids. At 4209, the method includes monitoring interaction of the vehicle rider with the advertisement presented within the vehicle's user interface.

Referring to Figures 41 and 42, in an embodiment a vehicle 4110 comprises a system for automating at least one control parameter of the vehicle. In embodiments, vehicle 4110 is at least a semi-autonomous vehicle. In an embodiment, vehicles 4110 are auto-routed. In an embodiment, vehicle 4110 is a self-driving vehicle. In an embodiment, the first portion 41165 of the hybrid perception system 41164 determines the operational state of the vehicle by processing inputs related to at least one parameter of the vehicle. In an embodiment, the second portion 41166 of the hybrid perception system 41164 determines the rider's state 41149 of the vehicle by processing input related to at least one parameter of the rider. In an embodiment, the third portion 41167 of the hybrid perception system 41164 determines the price, classification, content and location of advertisements to be delivered within the vehicle's interface to the rider in the vehicle's seat based on vehicle state and rider state. determine at least one of In embodiments, the advertisement is delivered from the winning advertiser. In embodiments, delivery of advertisements is based on winning bids. In embodiments, the monitored vehicle rider interaction information includes information for resolving click-based payments. In embodiments, the monitored vehicle rider interaction information includes monitoring analysis results. In embodiments, the analytical result is a measure of interest in the advertisement. In embodiments, the input 41162 related to at least one parameter of the vehicle includes vehicle classification. In an embodiment, the input 41162 related to at least one parameter of the vehicle includes display classification. In an embodiment, the input 41162 related to at least one parameter of the vehicle includes audio system capabilities. In embodiments, the input 41162 related to at least one parameter of the vehicle includes screen size. In embodiments, the input 41162 related to at least one parameter of the vehicle includes route information. In embodiments, the input 41162 related to at least one parameter of the vehicle includes location information. In embodiments, the input 41163 related to at least one parameter of the rider includes rider demographic information. In embodiments, the input 41163 related to at least one parameter of the rider includes the emotional state of the rider. In an embodiment, the input 41163 relating to the rider's at least one parameter includes the rider's reaction to the prior in-seat advertisement. In embodiments, the input 41163 related to the rider's at least one parameter includes the rider's social media activity.

FIG. 43 illustrates a method 4300 of in-car advertising according to embodiments of the systems and methods disclosed herein. At 4302, the method includes taking input related to at least one parameter of the vehicle and input related to at least one parameter of a rider occupying the vehicle. At 4304, the method includes aggregating inputs across multiple vehicles. At 4306, the method includes using the hybrid cognitive system to determine in-vehicle advertising placement opportunities based on the aggregated inputs. At 4308, the method includes providing the placement opportunity at an advertising network that facilitates bidding on the placement opportunity. At 4309, the method includes delivering an advertisement for placement within the vehicle's interface based on the results of the bids.

Referring to Figures 41 and 43, in an embodiment a vehicle 4110 comprises a system for automating at least one control parameter of the vehicle. In embodiments, vehicle 4110 is at least a semi-autonomous vehicle. In an embodiment, vehicles 4110 are auto-routed. In an embodiment, vehicle 4110 is a self-driving vehicle. In an embodiment, the first portion 41165 of the hybrid perception system 41164 determines the operational state 41168 of the vehicle by processing inputs 41162 related to at least one parameter of the vehicle. In an embodiment, the second portion 41166 of the hybrid perception system 41164 determines the rider's state 41149 of the vehicle by processing inputs 41163 related to at least one parameter of the rider. In an embodiment, the third portion 41167 of the hybrid perception system 41164 selects advertisements to be delivered within the interface 41133 of the vehicle 4110 to the rider 4144 of the seat 4128 of the vehicle 4110 based on the vehicle (motion) state 41168 and the rider state 41149. determine at least one of the price, classification, content and location of In embodiments, the advertisement is delivered from the winning advertiser. In embodiments, delivering the advertisement is based on the winning bid. In embodiments, the input 41162 related to at least one parameter of the vehicle includes vehicle classification. In an embodiment, the input 41162 related to at least one parameter of the vehicle includes display classification. In an embodiment, the input 41162 related to at least one parameter of the vehicle includes audio system capabilities. In embodiments, the input 41162 related to at least one parameter of the vehicle includes screen size. In embodiments, the input 41162 related to at least one parameter of the vehicle includes route information. In embodiments, the input 41162 related to at least one parameter of the vehicle includes location information. In embodiments, the input 41163 related to at least one parameter of the rider includes rider demographic information. In embodiments, the input 41163 related to at least one parameter of the rider includes the emotional state of the rider. In an embodiment, the input 41163 relating to the rider's at least one parameter includes the rider's reaction to the prior in-seat advertisement. In embodiments, the input 41163 related to the rider's at least one parameter includes the rider's social media activity.

Referring to FIG. 44, in embodiments provided herein, a transport having a motorcycle helmet 44170 configured to provide an augmented reality experience based on registration of the position and orientation of the wearer 44172 in the environment 44171 System 4411.

Aspects provided herein include a transportation system 4411, a motorcycle helmet 44170 for providing an augmented reality experience based on registration of the position and orientation of the wearer 44172 of the helmet 44170 in the environment 44171. Including being prepared.

Aspects provided herein include a motorcycle helmet 44170 comprising: A data processor 4488 configured to facilitate communication between a rider 44172 wearing a helmet 44170 and a motorcycle 44169, wherein the motorcycle 44169 and the helmet 44170 communicate position and orientation 44173 of the motorcycle 44169 , and an augmented reality system 44174 comprising a display 44175 positioned to facilitate presenting augmented content in a helmet-wearing rider's environment 44171, the augmented position and orientation of a motorcycle 44169 being communicated. Extended system 44274 responsive to 44128 registrations. In embodiments, at least one parameter of augmentation is determined by machine learning regarding at least one input associated with at least one of rider 44172 and motorcycle 44180 .

In an embodiment, the motorcycle 44169 includes a system for automating at least one control parameter of the motorcycle. In embodiments, motorcycle 44169 is at least a semi-autonomous motorcycle. In an embodiment, the motorcycle 44169 is automatically routed. In embodiments, motorcycle 44169 is a self-driving motorcycle. In embodiments, the content in the environment is content that is visible in a portion of the helmet-wearing rider's field of view. In an embodiment, machine learning of the rider's input determines the rider's emotional state, and values for the at least one parameter are adapted in response to the rider's emotional state. In an embodiment, machine learning of the motorcycle's inputs determines the operating conditions of the motorcycle, and the values for the at least one parameter are adapted in response to the operating conditions of the motorcycle. In an embodiment, the helmet 44170 further comprises a motorcycle configuration expert system 44139 for recommending adjustments to the value of the at least one parameter 44156 to the augmented reality system in response to at least one input.

Aspects provided herein include a motorcycle helmet augmented reality system. a display 44175 arranged to facilitate presenting enhanced content in the environment of the rider wearing the helmet; circuitry 4488 for registering at least one of the position and orientation of the motorcycle the rider is riding; machine learning circuitry 44179 for determining at least one expansion parameter 44156 by processing at least one input associated with 44163 and/or motorcycle 44180; a reality augmentation circuit 4488 producing 44155 and a reality augmentation circuit 4488 producing augmentation elements 44177 for presentation on a display 44175 in response to at least one of the position and orientation of the registered motorcycle, wherein the producing is , a reality augmentation circuit 4488 based at least in part on the determined at least one augmentation parameter 44156 .

In an embodiment, the motorcycle 44169 includes a system for automating at least one control parameter of the motorcycle. In embodiments, motorcycle 44169 is at least a semi-autonomous motorcycle. In an embodiment, the motorcycle 44169 is automatically routed. In embodiments, motorcycle 44169 is a self-driving motorcycle. In an embodiment, content 44176 in the environment is content that is visible in a portion of the field of view of rider 44172 wearing a helmet. In an embodiment, machine learning of the rider's input determines the rider's emotional state, and values for the at least one parameter are adapted in response to the rider's emotional state. In an embodiment, machine learning of the motorcycle's inputs determines the operating conditions of the motorcycle, and the values for the at least one parameter are adapted in response to the operating conditions of the motorcycle.

In an embodiment, the helmet further comprises a motorcycle configuration expert system 44139 for recommending adjustment of the value of at least one parameter 44156 to the augmented reality system 4488 in response to at least one input.

In embodiments, leveraging network technology for transportation systems may support cognitive collective charging or refueling plans for vehicles within the transportation system. Such a transportation system for taking inputs related to multiple vehicles, such as autonomous vehicles, and determining at least one parameter of a recharging or refueling plan for at least one of the multiple vehicles based on the inputs. It may also include an artificial intelligence system.

In embodiments, the transportation system may be a vehicle transportation system. Such a vehicle transportation system may provide a network (e.g., Internet, etc.) interface through which inputs such as operating status and energy consumption information from at least one of a plurality of network-enabled vehicles 4510 may be collected. An intake port 4532 may also be included. In embodiments, such input may be collected in real-time as multiple network-enabled vehicles 4510 connect and deliver vehicle operating status, energy consumption, and other relevant information. In embodiments, the input may relate to vehicle energy consumption and may be determined from battery state of charge of a portion of a plurality of vehicles. Inputs may include vehicle route plans, vehicle charging value indicators, and the like. The input may include predicted traffic conditions for multiple vehicles. The transportation system can also include vehicle charging or refueling infrastructure, which can include one or more vehicle charging infrastructure control system(s) 4534 . These control system(s) 4534 may receive operating status and energy consumption information for a plurality of networked vehicles 4510 via an intake port 4532 or directly through a common or series of connected networks such as the Internet. . Such a transportation system determines at least one charging plan parameter 4514 on which a charging plan 4512 for at least a portion of the plurality of network-enabled vehicles 4510 depends, for example, in response to receiving operating conditions and energy consumption information. may further include an artificial intelligence system 4536 that may be operatively connected with the vehicle charging infrastructure control system(s) 4534 that may provide, coordinate or create. This dependency can result in changes in the application of the charging plan 4512 by the control system(s) 4534, such as when the processor of the control system(s) 4534 executes a program derived from or based on the charging plan 4512. be. The charging infrastructure control system(s) 4534 may include cloud-based computing systems remote from the charging infrastructure system (e.g., remote from electric vehicle charging kiosks, etc.); also fuel stations, charging kiosks, etc. may include a local charging infrastructure system 4538 that may be co-located with and/or integrated with the infrastructure elements of. In embodiments, artificial intelligence system 4536 may interface with and coordinate with cloud-based system 4534, local charging infrastructure system 4538, or both. In embodiments, coordinating the cloud-based system may take the form of a different interface than coordinating with the local charging infrastructure system 4538, such as providing parameters that affect multiple charging kiosks, etc. Information may be provided that may be used to adapt charging system control commands, etc. that may be provided from cloud-based control system 4534 . In one example, a cloud-based control system (which may control only a portion, such as a localized set of available charging/refueling infrastructure devices) sets charging rates that facilitate highly parallel vehicle charging. The charging plan parameters 4514 of the artificial intelligence system 4536 may be responded to by doing. However, local charging infrastructure system 4538 may, for example, allow local charging within a period of time to allow different charging rates (eg, faster charging rates) based, for example, on control plan parameters provided by artificial intelligence system 4536 . This control strategy may be adapted for short periods of time to accommodate the accumulation of vehicles queued or estimated to use the kiosk. Thus, the adjustment to at least one parameter 4514 made to the charging infrastructure operations plan 4512 is that at least one of the plurality of vehicles 4510 has access to energy updates in the target energy update geographic region 4516. is guaranteed.

In embodiments, a charging or refueling plan may have multiple parameters that may affect a wide range of transportation aspects, from vehicle-specific to vehicle group-specific, vehicle location-specific and infrastructure impacting aspects. Therefore, planning parameters should be based on vehicle routing to the charging infrastructure, amount of charge allowed to be provided, time or rate for charging, battery condition or state, battery charging profile, consumption needs of the vehicle. the time required to charge to the minimum value, the market value of the charge, an index of market value, the market price, the infrastructure provider profit, the bidding or provision of fuel or electricity to one or more charging or refueling infrastructure kiosks; It can affect or relate to any of the offerings, available supply capacity, charging demand (local, regional, system-wide), and so on.

In embodiments, the transportation system interacts with an artificial intelligence system 4536 to apply adjustments 4524 to at least one of a plurality of charging plan parameters 4514 to facilitate cognitive charging or refueling plans. May include update facilities. The adjustment value 4524 may be further adjusted based on feedback of applying the adjustment value. In embodiments, the feedback may be used by the artificial intelligence system 4534 to further adjust the adjustment values. As an example, feedback can affect adjustments applied to charging or refueling infrastructure in a localized manner, such as a target charging geographic region 4516 or geographic range for one or more vehicles. In embodiments, providing parameter adjustments may facilitate optimizing consumption of remaining battery state of charge of at least one of the plurality of vehicles.

By processing energy-related consumption, demand, availability, and access information, etc., the artificial intelligence system 4536 may optimize aspects of the transportation system, such as vehicle electricity usage, as shown in the box at 4526. . Artificial intelligence system 4536 may also optimize at least one of charging time, location, and quantity. In one example, the charging plan parameters that may be configured and updated based on the feedback may be routing parameters for at least one of the plurality of vehicles, as boxed at 4526 .

The artificial intelligence system 4536 may, for example, generate transportation system charging or refueling control planning parameters 4514 to accommodate short-term charging needs for a plurality of rechargeable vehicles 4510 based on at least one optimized parameter. may be further optimized. The artificial intelligence system 4536 calculates energy parameters (including vehicular and non-vehicle energies) to optimize at least vehicle and/or charging or refueling infrastructure power usage, and at least one charging or refueling infrastructure specific charging time. An optimization algorithm may be run that may optimize , location, and quantity.

In embodiments, artificial intelligence system 4534 may predict geolocation 4518 of one or more vehicles within geographic region 4516 . A geographic region 4516 may include vehicles currently located or expected to be in that region, which may optionally require or prefer recharging or refueling. As an example of predicting geolocation and its impact on charging plans, charging plan parameters may include allocation of current or projected vehicles to charging or refueling infrastructure within a geographic region 4516 . In an embodiment, the geolocation prediction is the state-of-charge or It may include receiving input related to the predicted vehicle.

There are many aspects of charging plans that can be affected. Some aspects may be financially relevant, such as automatic negotiation of duration, quantity, and/or price for charging or refueling a vehicle.

The transportation system cognitive charging planning system may include an artificial intelligence system configured with a hybrid neural network. A first neural network 4522 of the hybrid neural network may be used to process input regarding the charge or fuel status of multiple vehicles (received directly from the vehicle or via the vehicle information port 4532), and the hybrid neural network A second neural network 4520 of neural networks is used to process inputs such as those relating to charging or refueling infrastructure. In an embodiment, the first neural network 4522 processes input consisting of vehicle route and stored energy state information for a plurality of vehicles to predict a target energy update region for at least one of the plurality of vehicles. good too. A second neural network 4520 processes usage and demand information for vehicle energy update infrastructure within the target energy update area to provide access to updated energy in the target energy update area 4516 by at least one of the plurality of vehicles. At least one parameter 4514 of the charging infrastructure operations plan 4512 that facilitates may be determined. In embodiments, the first and/or second neural networks may be configured as any of the neural networks described herein, including but not limited to convolutional networks.

In an embodiment, the transportation system may be distributed, taking inputs related to multiple vehicles 4510 and developing at least one of the recharging and refueling plans 4512 for at least one of the multiple vehicles based on the inputs. An artificial intelligence system 4536 may be included for determining parameters 4514 . In embodiments, such inputs may be collected in real-time as multiple vehicles 4510 connect and deliver vehicle operating status, energy consumption, and other relevant information. In embodiments, the input may relate to vehicle energy consumption and may be determined from battery state of charge of a portion of a plurality of vehicles. Inputs may include vehicle route plans, vehicle charging value indicators, and the like. The input may include predicted traffic conditions for multiple vehicles. A distributed transportation system may also include cloud-based and vehicle-based systems that exchange information about vehicles, such as energy consumption and operational information, as well as information about the transportation system, such as charging or refueling infrastructure. An artificial intelligence system responds to transportation system and vehicle information shared by cloud and vehicle-based systems with control parameters that facilitate execution of a cognitive charging plan for at least a portion of the transportation system's charging or refueling infrastructure. You may Artificial intelligence system 4536 may determine, provide, adjust, or create at least one charging plan parameter 4514 upon which charging plan 4512 for at least a portion of plurality of vehicles 4510 depends. This dependency can result in changes in execution of the charging plan 4512 by cloud-based and/or vehicle-based systems, such as when a processor executes a program derived from or based on the charging plan 4512. .

In an embodiment, the artificial intelligence system of the transportation system applies a vehicle charging facility utilization optimization algorithm to a plurality of rechargeable vehicle specific inputs, e.g. Execution of a cognitive charging plan may be facilitated by applying it to the vehicle's current operating state data. The artificial intelligence system may also evaluate the impact of multiple charging plan parameters on the charging infrastructure of the transportation system within the target charging range. The artificial intelligence system selects, for example, at least one of a plurality of charging plan parameters facilitating optimization of energy use by a plurality of rechargeable vehicles, and adjusts values for at least one of the plurality of charging plan parameters. may be generated. The artificial intelligence system identifies an impending need for charging for a portion of the plurality of rechargeable vehicles within the region of interest based on operating conditions of the plurality of rechargeable vehicles, which may be determined from, for example, rechargeable vehicle specific inputs. You can predict more. Based on this prediction and near-term charging infrastructure availability and capacity information, the artificial intelligence system may optimize at least one parameter of the charging plan. In embodiments, the artificial intelligence system may operate hybrid neural networks for prediction and parameter selection or tuning. In an embodiment, a first portion of the hybrid neural network may process inputs related to one or more rechargeable vehicle route plans. In an embodiment, a second part of the hybrid neural network, different from the first part, may process inputs related to charging infrastructure within at least one charging range of the rechargeable vehicle. In this example, a second, different part of the hybrid neural net predicts the geolocation of multiple vehicles within the target region. To facilitate execution of the charging plan, the parameters can affect allocation of vehicles to at least a portion of the charging infrastructure within the predicted geographic region.

In embodiments, the vehicles described herein may include a system for automating at least one control parameter of the vehicle. The vehicle may also operate at least as a semi-autonomous vehicle. Vehicles may be routed automatically. Also, the vehicle, charging, etc. may be a self-propelled vehicle.

In embodiments, leveraging network technology for transportation systems may support cognitive collective charging or refueling plans for vehicles within the transportation system. Such transportation systems take inputs related to battery status of multiple vehicles, such as autonomous vehicles, and recharge and/or refuel to optimize battery operation of at least one of the multiple vehicles based on the inputs. An artificial intelligence system may be included for determining at least one parameter of the plan.

In embodiments, such a vehicular transportation system is a network (e.g., the Internet, etc.) in which inputs such as operating status and energy consumption information and battery status from at least one of a plurality of network-enabled vehicles 4610 may be collected. May include a network-enabled vehicle information intake port 4632 that may provide an interface. In embodiments, such inputs may be collected in real-time as multiple vehicles 4610 connect to the network and distribute vehicle operating status, energy consumption, battery status, and other relevant information. In embodiments, the input may relate to vehicle energy consumption and may include battery state of charge of a portion of a plurality of vehicles. Inputs may include vehicle route plans, vehicle charging value indicators, and the like. The input may include predicted traffic conditions for multiple vehicles. Transportation systems can also include vehicle charging or refueling infrastructure, which can include one or more vehicle charging infrastructure control systems 4634 . These control systems receive battery status information, etc., of multiple network-enabled vehicles 4610 directly via an intake port 4632 and/or through a common or series of connected networks, such as Internet infrastructure, including wireless networks, etc. You may Such a transportation system determines at least one charging plan parameter 4614 on which a charging plan 4612 for at least a portion of the plurality of network-enabled vehicles 4610 depends on at least battery status information from a portion of the plurality of vehicles. It may further include an artificial intelligence system 4636 that may be functionally connected with the vehicle charging infrastructure control system that may determine, provide, coordinate or create. This parameter dependency can lead to changes in the application of the charging plan 4612 by the control system(s) 4634, such as when the processor of the control system(s) 4634 executes a program derived from or based on the charging plan 4612. There is These changes may be applied to optimize the expected battery usage of one or more vehicles. Optimization may be vehicle-specific, aggregated across a set of vehicles, or the like. The charging infrastructure control system(s) 4634 may include cloud-based computing systems remote from the charging infrastructure system (e.g., remote from electric vehicle charging kiosks, etc.); also fuel stations, charging kiosks, etc. may include a local charging infrastructure system 4638 that may be co-located with and/or integrated with infrastructure elements of. In embodiments, artificial intelligence system 4636 may interface with cloud-based system 4634, local charging infrastructure system 4638, or both. In embodiments, the artificial intelligence system may interface with individual vehicles to facilitate optimization of expected battery usage. In embodiments, the interface with the cloud-based system may affect the overall infrastructure impact of the charging plan, such as providing parameters that affect multiple charging kiosks. Interfacing with the local charging infrastructure system 4638 provides information that the local system can use to adapt charging system control commands, etc., which can be provided from regional or broader control systems, such as the cloud-based control system 4634, for example. may include providing a In one example, a cloud-based control system (which may control only a localized set of available charging or refueling infrastructure devices, a target or geographic area such as a town, county, city, ward, county, etc.) controls a vehicle battery Artificial intelligence system 4636 may respond to charging plan parameters 4614 by setting charging rates that promote highly parallel vehicle charging to optimize usage. However, the local charging infrastructure system 4638, based on control plan parameters provided by the artificial intelligence system 4636, may vary, such as for a short period of time, to accommodate an accumulation of vehicles whose expected battery usage has not yet been optimized. This control scheme may be adapted to allow charging rates (eg, faster charging rates). In this manner, adjustments to at least one parameter 4614 made to the charging infrastructure operations plan 4612 ensure that at least one of the plurality of vehicles 4610 has access to energy updates in the target energy update region 4616. . In embodiments, the target energy update area may be defined by a geofence that may be configured by the administrator of the area. In an example, an administrator may have control or responsibility for a jurisdiction (eg, town, village, etc.). In an example, an administrator may configure geofences for regions that substantially match a jurisdiction.

In embodiments, a charging or refueling plan may have multiple parameters that may affect a wide range of transportation aspects, from vehicle-specific to vehicle group-specific to vehicle location-specific and infrastructure impacting aspects. Therefore, the parameters of the plan should be based on the vehicle's route to the charging infrastructure, the amount of charge allowed to be provided, the time or rate for charging, the state or condition of the battery, the battery charging profile, and the consumption needs of the vehicle. can affect or relate to any of the time required to charge to a minimum value. market value of charging, indicators of market value, market price, interests of infrastructure providers, bids or offers to provide fuel or electricity to one or more charging or refueling infrastructure kiosks, available supply capacity, charging demand ( local, regional, system-wide), maximum energy utilization, time between battery charges, and so on.

In embodiments, the transportation system interacts with an artificial intelligence system 4636 to apply adjustments 4624 to at least one of a plurality of charging plan parameters 4614 to facilitate cognitive charging or refueling plans. May include update facilities. Adjustment value 4624 may be further adjusted based on feedback of applying the adjustment value. In embodiments, the feedback may be used by the artificial intelligence system 4634 to further adjust the adjustment values. In one example, the feedback is for vehicles affected or predicted to be affected by traffic jams, e.g., to have sufficient battery power during periods of traffic jams, so that battery operation is optimized. Adjustments applied locally to charging or refueling infrastructure may be affected, such as affecting aggregates only. In embodiments, providing parameter adjustments may facilitate optimizing consumption of remaining battery state of charge of at least one of the plurality of vehicles.

By processing energy-related consumption, demand, availability, and access information, etc., the artificial intelligence system 4636 can optimize aspects of the transportation system, such as the vehicle's electricity use as shown in the box at 4626. can. Artificial intelligence system 4636 may further optimize at least one of recharge time, location, and amount, as shown in box at 4626 . In one example, charging plan parameters that may be configured and updated based on feedback may be routing parameters for at least one of the plurality of vehicles.

The artificial intelligence system 4636 may determine transportation system charging or refueling control planning parameters 4614 based on the optimized at least one parameter, for example, to accommodate short-term charging needs for a plurality of rechargeable vehicles 4610 . may be further optimized. The artificial intelligence system 4636 calculates energy parameters (including vehicular and non-vehicle energy) that can affect expected battery usage to optimize power usage for at least the vehicle and/or charging or refueling infrastructure; A vehicle recharge optimization algorithm may be implemented that may optimize charging time, location and quantity specific to at least one charging or refueling infrastructure.

In embodiments, artificial intelligence system 4634 may predict geolocation 4618 of one or more vehicles within geographic region 4616 . A geographic region 4616 may include vehicles currently located or expected to be in that region and optionally may require or prefer recharging or refueling. As an example of predicting geolocation and its impact on charging plans, charging plan parameters may include allocation of current or projected vehicles to charging or refueling infrastructure within a geographic area 4616 . In embodiments, the geolocation prediction is performed on the batteries of multiple vehicles within a geolocation range such that the artificial intelligence system can optimize at least one charging plan parameter 4614 based on the prediction of the geolocation of the multiple vehicles. It may include receiving input related to state of charge and recharging needs.

There are many aspects of charging plans that can be affected. Some aspects may be financially relevant, such as automatic negotiation of duration, quantity and/or price for charging or refueling the vehicle.

The transportation system cognitive charging planning system may include an artificial intelligence system configured with a hybrid neural network. A first neural network 4622 of the hybrid neural network may be used to process inputs regarding battery charge or fuel status of multiple vehicles (received directly from the vehicle or via vehicle information port 4632). Often, the second neural network 4620 of the hybrid neural network is used to process inputs regarding charging or refueling infrastructure and the like. In an embodiment, the first neural network 4622 processes input including information about charging systems and vehicle routes of a plurality of vehicles and stored energy state information to generate a target energy update for at least one of the plurality of vehicles. Regions may be predicted. A second neural network 4620 may also predict the geolocation of a portion of a plurality of vehicles relative to another vehicle or collection of vehicles. A second neural network 4620 processes vehicle energy update infrastructure usage and demand information within the target energy update region to provide updated energy within the target energy update region 4616 by at least one of the plurality of vehicles. At least one parameter 4614 of the charging infrastructure operations plan 4612 that facilitates access may be determined. In embodiments, the first and/or second neural networks may be configured as any of the neural networks described herein, including but not limited to convolutional networks.

In an embodiment, the transportation system may be distributed, taking inputs related to multiple vehicles 4610 and developing at least one of the recharging and refueling plans 4612 for at least one of the multiple vehicles based on the inputs. An artificial intelligence system 4636 for determining parameters 4614 may be included. In embodiments, such inputs may be collected in real-time as multiple vehicles 4610 connect to the network to deliver vehicle operating status, energy consumption, and other relevant information. In embodiments, the input may relate to vehicle energy consumption and may be determined from battery state of charge of a portion of a plurality of vehicles. Inputs may include vehicle route plans, vehicle charging value indicators, and the like. The input may include predicted traffic conditions for multiple vehicles. A distributed transportation system may also include cloud-based and vehicle-based systems that exchange information about vehicles, such as energy consumption and operational information, as well as information about the transportation system, such as charging or refueling infrastructure. The artificial intelligence system integrates traffic system and vehicle information shared by cloud-based and vehicle-based systems with control parameters that facilitate executing cognitive charging plans for at least a portion of the transportation system's charging or refueling infrastructure. You may respond. Artificial intelligence system 4636 may determine, provide, adjust, or create at least one charging plan parameter 4614 upon which charging plan 4612 for at least a portion of plurality of vehicles 4610 depends. This dependency can result in changes in the execution of the charging plan 4612 by cloud-based and/or vehicle-based systems, such as when a processor executes a program derived from or based on the charging plan 4612. .

In an embodiment, the artificial intelligence system of the transportation system incorporates a plurality of rechargeable vehicle-specific inputs, e.g., current operating state data of rechargeable vehicles present in a target charging range of one of the plurality of rechargeable vehicles, into vehicle battery Execution of a cognitive charging plan may be facilitated by applying vehicle recharging facility utilization of motion optimization algorithms. The artificial intelligence system may also evaluate the impact of multiple charging plan parameters on the charging infrastructure of the transportation system within the target charging range. The artificial intelligence system selects, for example, at least one of a plurality of charging plan parameters facilitating optimization of energy use by a plurality of rechargeable vehicles, and adjusts values for at least one of the plurality of charging plan parameters. may be generated. The artificial intelligence system identifies the impending need for charging for a portion of the plurality of rechargeable vehicles within the region of interest based on operating conditions of the plurality of rechargeable vehicles, which may be determined from, for example, rechargeable vehicle-specific inputs. You can predict more. Based on this prediction and near-term charging infrastructure availability and capacity information, the artificial intelligence system may optimize at least one parameter of the charging plan. In embodiments, the artificial intelligence system may operate hybrid neural networks for prediction and parameter selection or tuning. In an embodiment, a first portion of the hybrid neural network may process inputs related to one or more rechargeable vehicle route plans. In an embodiment, a second part of the hybrid neural network, different from the first part, may process inputs related to charging infrastructure within at least one charging range of the rechargeable vehicle. In this example, a second, different part of the hybrid neural net predicts the geolocation of multiple vehicles within the target region. To facilitate execution of the charging plan, the parameters can affect allocation of vehicles to at least a portion of the charging infrastructure within the predicted geographic region.

In embodiments, the vehicles described herein may include a system for automating at least one control parameter of the vehicle. The vehicle may also operate at least as a semi-autonomous vehicle. Vehicles may be routed automatically. Also, the vehicle, charging, etc. may be a self-propelled vehicle.

In embodiments, leveraging network technology for transportation systems may support cognitive collective charging or refueling plans for vehicles within the transportation system. Such transportation systems take inputs related to multiple vehicles, such as self-driving vehicles, and determine at least one parameter of a recharging and/or refueling plan for at least one of the multiple vehicles based on the inputs. may include a cloud-based artificial intelligence system for

In embodiments, such a vehicle transportation system collects inputs such as operational status and energy consumption information from at least one of a plurality of network-enabled vehicles 4710 and implements the cloud-based control and control described herein. It may include a cloud-enabled vehicle information ingestion port 4732 that may provide a network (eg, Internet, etc.) interface that may be provided to cloud resources such as artificial intelligence systems. In embodiments, such inputs are collected in real-time as multiple vehicles 4710 connect to the cloud and deliver vehicle operating status, energy consumption, and other relevant information through at least port 4732. good too. In embodiments, the input may relate to vehicle energy consumption and may be determined from battery state of charge of a portion of a plurality of vehicles. Inputs may include vehicle route plans, vehicle charging value indicators, and the like. The input may include predicted traffic conditions for multiple vehicles. The transportation system may also include vehicle charging or refueling infrastructure, which may include one or more vehicle charging infrastructure cloud-based control system(s) 4734. These cloud-based control system(s) 4734 communicate the operational status and energy consumption information of multiple network-enabled vehicles 4710 via cloud-enabled ingest ports 4732 and/or through a common or series of connected networks, such as the Internet. You can receive it directly. Such a transportation system may, for example, be a vehicle charging infrastructure cloud-based control system (such as a may further include a cloud-based artificial intelligence system 4736 that may be operatively connected with 4734. This dependency changes in the application of the charging plan 4712 by the cloud-based control system(s) 4734, such as when the processor of the cloud-based control system(s) 4734 runs a program derived from or based on the charging plan 4712. can result in The charging infrastructure cloud-based control system(s) 4734 may include cloud-based computing systems remote from the charging infrastructure system (e.g., remote from electric vehicle charging kiosks, etc.); It may also include a local charging infrastructure system 4738 that may be co-located with and/or integrated with infrastructure elements. In embodiments, the cloud-based artificial intelligence system 4736 can interface with and coordinate with the cloud-based charging infrastructure control system 4734, the local charging infrastructure system 4738, or both. In embodiments, coordinating the cloud-based system may take the form of an interface, such as providing parameters that affect multiple charging kiosks, etc., which may differ from coordinating with the local charging infrastructure system 4738; The system may provide information that may be used to adapt cloud-based charging system control commands, which may be provided by the cloud-based control system 4734, for example. In one example, a cloud-based control system (which may control only a portion, such as a localized set of available charging or refueling infrastructure devices) can set charging rates that facilitate highly parallel vehicle charging. may respond to charging plan parameters 4714 of cloud-based artificial intelligence system 4736 by. However, the local charging infrastructure system 4738 uses a different charging rate (eg, faster charging rate) based on control plan parameters provided by the cloud-based artificial intelligence system 4736, e.g., the local charging kiosk within a period of time. This control strategy may be adapted, such as allowing charging rates for short periods of time to accommodate the build-up of vehicles queued or estimated to be charged. In this manner, adjustments to at least one parameter 4714 made to the charging infrastructure operations plan 4712 ensure that at least one of the plurality of vehicles 4710 has access to energy updates in the target energy update region 4716. It is a thing.

In embodiments, a charging or refueling plan may have multiple parameters that may affect a wide range of transportation aspects, from vehicle-specific to vehicle group-specific to vehicle location-specific and infrastructure impacting aspects. Therefore, planning parameters should be based on vehicle routing to the charging infrastructure, amount of charge allowed to be provided, time or rate for charging, battery condition or state, battery charging profile, consumption needs of the vehicle. time required to charge to the minimum value, market value of charging, market value index, market price, infrastructure provider profits, bidding or providing fuel or electricity to one or more charging or refueling infrastructure kiosks; It can affect or relate to any of the offerings, available supply capacity, charging demand (local, regional, system-wide), and so on.

In embodiments, the transportation system interacts with a cloud-based artificial intelligence system 4736 to apply adjustments 4724 to at least one of a plurality of charging plan parameters 4714 to facilitate cognitive charging or refueling plans. It may also include a charging plan update facility that The adjustment value 4724 may be further adjusted based on feedback of applying the adjustment value. In embodiments, the feedback may be used by the cloud-based artificial intelligence system 4734 to further adjust the adjustment values. As an example, feedback may affect adjustments applied to charging or refueling infrastructure in a localized manner, such as a target charging area 4716 or geographic extent for one or more vehicles. In embodiments, providing parameter adjustments may facilitate optimizing consumption of remaining battery state of charge of at least one of the plurality of vehicles.

By processing energy-related consumption, demand, availability, access information, and the like, the cloud-based artificial intelligence system 4736 may optimize aspects of the transportation system, such as vehicle electricity usage. Cloud-based artificial intelligence system 4736 may also optimize at least one of charging time, location, and quantity. In one example, charging plan parameters that may be configured and updated based on feedback may be routing parameters for at least one of the plurality of vehicles.

The cloud-based artificial intelligence system 4736 may, based on the optimized at least one parameter, plan charging or refueling control planning parameters of the transportation system, for example, to meet the short-term charging needs of multiple rechargeable vehicles 4710. 4714 may be further optimized. A cloud-based artificial intelligence system 4736 calculates energy parameters (including vehicular and non-vehicle energy) to optimize power usage for at least vehicles and/or charging or refueling infrastructure, and at least one charging or refueling infrastructure specific An optimization algorithm may be run that can optimize the charging time, location and amount of .

In embodiments, cloud-based artificial intelligence system 4734 may predict geolocation 4718 of one or more vehicles within geographic region 4716 . A geographic region 4716 may include vehicles currently located or expected to be in that region, optionally requiring or preferring recharging or refueling. As an example of predicting geolocation and its impact on charging plans, charging plan parameters may include allocation of current or projected vehicles to charging or refueling infrastructure within a geographic region 4716 . In embodiments, the geolocation prediction is performed on multiple vehicles within a geolocation range such that the cloud-based artificial intelligence system can optimize at least one charging plan parameter 4714 based on the prediction of the geolocation of multiple vehicles. receiving an input related to the state of charge of the vehicle or a predicted vehicle.

There are many aspects of charging plans that can be affected. Some aspects may be financially relevant, such as automatic negotiation of duration, quantity and/or price for charging or refueling the vehicle.

A transportation system aware charging planning system may include a cloud-based artificial intelligence system configured with a hybrid neural network. A first neural network 4722 of the hybrid neural network may be used to process input regarding the charge or fuel status of multiple vehicles (received directly from the vehicle or via the vehicle information port 4732), and the hybrid neural network A second neural network 4720 of neural networks is used to process inputs regarding charging or refueling infrastructure and the like. In an embodiment, the first neural network 4722 processes input consisting of vehicle route and stored energy state information for a plurality of vehicles to predict a target energy update region for at least one of the plurality of vehicles. good too. A second neural network 4720 processes vehicle energy update infrastructure usage and demand information within the target energy update area to provide updated energy within the target energy update area 4716 by at least one of the plurality of vehicles. At least one parameter 4714 of the charging infrastructure operations plan 4712 that facilitates access may be determined. In embodiments, the first and/or second neural networks may be configured as any of the neural networks described herein, including but not limited to convolutional networks.

In an embodiment, the transportation system may be distributed, taking inputs related to multiple vehicles 4710 and developing at least one of the recharging and refueling plans 4712 for at least one of the multiple vehicles based on the inputs. A cloud-based artificial intelligence system 4736 for determining parameters 4714 may also be included. In embodiments, such input may be collected in real-time as multiple vehicles 4710 connect and deliver vehicle operating status, energy consumption, and other relevant information. In embodiments, the input may relate to vehicle energy consumption and may be determined from battery state of charge of a portion of a plurality of vehicles. Inputs may include vehicle route plans, vehicle charging value indicators, and the like. The input may include predicted traffic conditions for multiple vehicles. A distributed transportation system may also include cloud-based and vehicle-based systems that exchange information about vehicles, such as energy consumption and operational information, as well as information about the transportation system, such as charging or refueling infrastructure. A cloud-based artificial intelligence system uses control parameters to facilitate the execution of a cognitive charging plan for at least a portion of the transportation system's charging or refueling infrastructure, with the transportation system shared by the cloud-based system and the vehicle-based system. It may respond with information and vehicle information. Cloud-based artificial intelligence system 4736 may determine, provide, adjust, or create at least one charging plan parameter 4714 upon which charging plan 4712 for at least a portion of plurality of vehicles 4710 relies. This dependency can result in changes in execution of the charging plan 4712 by cloud-based and/or vehicle-based systems, such as when a processor executes a program derived from or based on the charging plan 4712. .

In an embodiment, the transportation system's cloud-based artificial intelligence system applies a vehicle charging facility utilization optimization algorithm to a plurality of rechargeable vehicle-specific inputs, e.g., a target charging range of one of the plurality of rechargeable vehicles. Execution of a cognitive charging plan may be facilitated by applying it to the current operational state data of the rechargeable vehicle. The cloud-based artificial intelligence system may also evaluate the impact of multiple charging plan parameters on the transportation system's charging infrastructure within the target charging range. A cloud-based artificial intelligence system selects, for example, at least one of a plurality of charging plan parameters facilitating optimization of energy use by a plurality of rechargeable vehicles, and selects at least one of the plurality of charging plan parameters. may generate an adjustment value for A cloud-based artificial intelligence system can determine near-term charging schedules for a portion of a plurality of rechargeable vehicles within a region of interest based on, for example, the operational status of the plurality of rechargeable vehicles, which can be determined from rechargeable vehicle-specific inputs. Further needs may be foreseen. Based on this prediction and near-term charging infrastructure availability and capacity information, the cloud-based artificial intelligence system may optimize at least one parameter of the charging plan. In embodiments, the cloud-based artificial intelligence system may operate hybrid neural networks for prediction and parameter selection or tuning. In an embodiment, a first portion of the hybrid neural network may process inputs related to one or more rechargeable vehicle route plans. In an embodiment, a second part of the hybrid neural network, different from the first part, may process inputs related to charging infrastructure within at least one charging range of the rechargeable vehicle. In this example, a second, different part of the hybrid neural net predicts the geolocation of multiple vehicles within the target region. To facilitate execution of the charging plan, the parameters can affect allocation of vehicles to at least a portion of the charging infrastructure within the predicted geographic area.

In embodiments, the vehicles described herein may include a system for automating at least one control parameter of the vehicle. The vehicle may also operate at least as a semi-autonomous vehicle. Vehicles may be routed automatically. Also, the vehicle, charging, etc. may be a self-propelled vehicle.

Referring to FIG. 48, provided herein is a transportation system 4811 having a robotic process automation system 48181 (RPA system). In an embodiment, data is captured for each of a set of individuals/users 4891 as the individuals/users 4890 interact with the user interface 4823 of the vehicle 4811, and an artificial intelligence system 4836 is trained using the data to Interact with vehicle 4810 to automatically undertake actions with vehicle 4810 on behalf of user 4890 . Data 48114 collected for RPA system 48181 may include sequences of images, sensor data, telemetry data, etc., among many other types of data described throughout this disclosure. Individual/user 4890 interaction with vehicle 4810 may include interaction with various vehicle interfaces as described throughout this disclosure. For example, the Robotic Process Automation (RPA) system 4810 can measure braking patterns, typical following distances behind other vehicles, approach to curves (e.g., entry angle, entry velocity, exit angle, exit velocity, etc.), acceleration Driver patterns such as patterns, lane preferences, overtaking preferences, etc. may be observed. Such patterns are transmitted through the vision system 48186 (e.g., which observes the driver, steering wheel, brakes, surroundings 48171, etc.) through the vehicle data system 48185 (e.g., steering, braking, etc.) data streams indicating states and changes in state. , and front and rear cameras and sensors), connected systems 48187 (e.g., GPS, cellular systems, and other networked systems, as well as peer-to-peer, vehicle-to-vehicle, mesh and cognitive networks, etc.), and other sources to provide training datasets use. Using the training data set, the RPA system 48181 may learn to drive in the same style as the driver, such as through any type of neural network 48108 described herein. In embodiments, the RPA system 48181 may learn style variations, such as varying levels of aggression in different situations based on time of day, length of trip, type of trip, and the like. In this way, an autonomous vehicle may learn to drive like its typical driver. Similarly, RPA system 48181 may be used for navigation systems, audio entertainment systems, video entertainment systems, climate control systems, seat heating and/or cooling systems, steering systems, braking systems, mirror systems, window systems, door systems, trunk systems, refueling systems. It may be used to observe the interaction of drivers, passengers or other individuals with systems, moon roof systems, ventilation systems, lumbar support systems, seat positioning systems, GPS systems, WIFI systems, glove box systems, etc.

Aspects provided herein are systems for transportation 4811 comprising robotic process automation systems 48181 . In an embodiment, a set of data is captured for each user 4890 in the set of users 4891 as each user 4890 interacts with user interface 4823 of vehicle 4810 . In an embodiment, the artificial intelligence system 4836 is trained using a set of data 48114 interacting with the vehicle 4810 to automatically undertake actions with the vehicle 4810 on behalf of the user 4890 .

FIG. 49 is a diagram illustrating a method 4900 of robotic process automation that facilitates mimicking human operator manipulation of a vehicle, in accordance with embodiments of the systems and methods disclosed herein. At 4902, the method includes tracking human interaction with the vehicle control facilitator interface. , the method includes recording tracked human interactions in a robotic process automation system training data structure. At 4906, the method includes tracking vehicle operating state information. In an embodiment, the vehicle is controlled via a vehicle control-facilitation interface. At 4908, the method includes recording vehicle operating state information in a robotic process automation system training data structure. At 4909, the method operates a vehicle in a manner consistent with human interaction based on human interaction and vehicle operating state information in a robotic process automation system training data structure through the use of at least one neural network. including training an artificial intelligence system to do so.

In embodiments, the method further comprises controlling at least one aspect of the vehicle with a trained artificial intelligence system. In embodiments, the method applies deep learning to the control of at least one side of the vehicle through structured variation in control of the at least one side of the vehicle to mimic human interaction; Further comprising processing feedback from controls of at least one aspect of the vehicle. In embodiments, controlling at least one aspect of the vehicle is performed via a vehicle control facilitating interface.

In embodiments, controlling at least one aspect of the vehicle is performed by an artificial intelligence system that emulates a human-operated control-facilitating interface. In embodiments, the vehicle control-facilitation interface comprises at least one of a voice capture system that captures audible human representations, a human-machine interface, a machine interface, an optical interface, and a sensor-based interface. In embodiments, the tracked vehicle operating state information includes tracking at least one of a set of vehicle systems and a set of vehicle operating processes affected by human interaction. In an embodiment, the tracked vehicle operating state information includes tracking at least one vehicle system element. In embodiments, at least one vehicle system element is controlled via a vehicle control facilitation interface. In embodiments, at least one vehicle system element is affected by human interaction. In embodiments, tracking vehicle operating state information includes tracking vehicle operating state information before, during, and after human interaction.

In embodiments, the tracked vehicle operating state information is adapted to track at least one of a plurality of vehicle control system outputs resulting from human interaction and vehicle operating results achieved in response to human interaction. include. In embodiments, the vehicle is controlled to achieve results consistent with those achieved through human interaction. In embodiments, the method further includes tracking and recording conditions proximate to the vehicle with a plurality of vehicle-mounted sensors. In embodiments, the training of the artificial intelligence system is further responsive to proximity conditions of the tracked vehicle contemporaneously with human interaction. In embodiments, the training is further responsive to multiple data feeds from remote sensors, the multiple data feeds including data collected by the removal sensor contemporaneously with the human interaction. In embodiments, the artificial intelligence system employs a workflow with decision making and the robotic process automation system facilitates automation of decision making. In embodiments, the artificial intelligence system employs a workflow involving remote control of the vehicle, and the robotic process automation system facilitates automation of the remote control of the vehicle.

Aspects provided herein include a transportation system 4811 for mimicking human manipulation of a vehicle 4810, a robotic process automation system 48181 comprising: an operator data collection module 48182 that captures human operator interactions with the vehicle control system interface 48191; a vehicle data collection module 48183 that captures vehicle responses and operating conditions associated at least contemporaneously with the human operator interactions; A robotic process automation system 48181 mimics an environmental data collection module 48184 that captures instances of environmental information that are relevant at least contemporaneously with interactions and an artificial intelligence system 4836 that learns to imitate a human operator (e.g., user 4890). , an artificial intelligence system 4836 that controls the vehicle 4810 in response to detecting data 48114 indicative of at least one of a plurality of instances of environmental information related to vehicle responses and operating conditions captured contemporaneously. And prepare.

In an embodiment, the operator data collection module 48182 is to capture patterns of data including braking patterns, following distance, curve approach acceleration patterns, lane preferences, and overtaking preferences. In an embodiment, the vehicle data collection module 48183 captures data from multiple vehicle data systems 48185 that provide data streams indicating the state and changes in steering, braking, acceleration, forward looking images, and rear looking images. In an embodiment, the artificial intelligence system 4836 includes a neural network 48108 for training the artificial intelligence system 4836.

FIG. 50 illustrates a robotic process automation method 5000 that mimics human manipulation of a vehicle, according to embodiments of the systems and methods disclosed herein. At 5002, the method includes capturing human operator interaction with the vehicle control system interface. At 5004, the method includes capturing vehicle responses and operating conditions associated with human operator interaction at least contemporaneously. At 5006, the method includes capturing instances of environmental information associated at least concurrently with human operator interaction. At 5008, the method is responsive to the environmental data collection module detecting data indicative of at least one of a plurality of instances of environmental information associated with contemporaneously captured vehicle responses and operating conditions. , involves training an artificial intelligence system to control a vehicle by imitating a human operator.

In embodiments, the method affects control of at least one side of the vehicle by structured variation in control of at least one side of the vehicle to mimic human interaction, and machine learning to influence control of at least one side of the vehicle. Further comprising applying deep learning in the artificial intelligence system to optimize the margin of vehicle driving safety by processing feedback from the control of at least one aspect. In embodiments, the robotic process automation system facilitates automation of decision-making workflows employed by artificial intelligence systems. In embodiments, the robotic process automation system facilitates automation of remote control workflows employed by artificial intelligence systems to remotely control vehicles.

Referring to FIG. 51, a transport system 5111 is provided having an artificial intelligence system 5136 that automatically randomizes parameters of the in-vehicle experience to improve user conditions that benefit from variation. In embodiments, the system used to control the driver or passenger experience (as in self-driving, assisted, or conventional vehicles) may be one or more of health, well-being, mood, safety, financial Automatic, based on objectives or feedback functions, such as an artificial intelligence system 5136 trained with results from a training data set to provide output to one or more vehicle systems to improve metrics, efficiency, etc. It may be configured to actively undertake actions.

Such a system can measure a wide range of in-vehicle experience parameters (including any of the experience parameters described herein), such as driving experience (assisted and autonomous driving, as well as controlled suspension performance, approach to curves, seat position (lumbar support, legroom, seat back angle, seat height and angle, etc.), climate control (including ventilation, window or moonroof conditions (e.g., Sound (e.g. volume, bass, treble, individual speaker control, sound focus range, etc.), content (music, news, advertisements, audio, video, other types), route selection (e.g. speed, road conditions ( For example: selecting smooth or rough, flat or hilly, speed, road conditions (e.g. flat or hilly, straight or curved), POIs (Points of Interest), scenery (e.g. scenic routes), new (eg, to see different places) and/or for defined purposes (eg, shopping opportunities, fuel savings, refueling opportunities, charging opportunities, etc.).

In many situations, variations in one or more of the vehicle experience parameters may cause the vehicle 5110 (or set of vehicles), It may provide or result in favorable conditions for the user (such as vehicle rider 51120), or both. For example, a user may have a preferred seating position, but sitting in the same position every day, or for long periods of time on the same day, puts too much pressure on certain joints, encourages atrophy of certain muscles, It can have adverse effects, such as reducing soft tissue flexibility. In such a situation, the automated control system (including those configured to use artificial intelligence of any of the types described herein) will use one of the user experience parameters described herein. may be configured to induce variations in one or more, optionally random variations or variations prescribed according to regimens such as those developed to provide physical therapy, chiropractic, or other medical or health benefits. You can have what can be. As an example, seat positioning can be changed over time to promote joint, muscle, ligament, cartilage, etc. health. As another example, based on evidence that human health improves when individuals experience significant changes in temperature, humidity, and other climatic factors, we may use temperature variability to improve a user's health, mood, or alertness. , humidity, fresh air (including by opening windows or ventilation), etc., the climate control system may be changed (randomly or according to a set regimen).

The artificial intelligence-based control system 5136 uses a series of results (described herein as of various types). As another example, audio systems may be used to maintain hearing (e.g., based on tracking cumulative sound pressure level, cumulative dose, etc.), to promote arousal (e.g., by varying types of content), and/or may be changed (such as to provide a mix of stimulating and relaxing content) to improve health. In embodiments, such an artificial intelligence system 5136 may be a wearable device 51157 (including a sensor set) or a system and/or set of sensors capable of providing physiological monitoring within the vehicle 5110 (e.g., observing a user). Sensor data 51444 can be provided, such as from a physiological sensing system 51190 including a vision-based system 51186 that can measure physiological parameters, sensors 5125 embedded in seats, steering wheels, etc.). For example, a vehicle interface 51188 (such as a steering wheel or any other interface described herein) can be used to monitor physiological parameters (eg, a driver's or other user's stress level, galvanic skin response, etc. to indicate cortisol levels, etc.). ), which can be used to indicate the current state for control purposes, or which can benefit from control, such as controlling variations in the user experience to achieve desired results. can be used as part of the training dataset for optimizing the parameters of In one such example, the artificial intelligence system 5136 considers changes in the user's hormonal system (such as cortisol and other adrenal system hormones), driving experience, music, etc. to induce healthy changes in condition. (While varying cortisol levels during the day are typical for healthy individuals, excessively high or low levels at certain times may be unhealthy or unsafe.) consistent with the evidence). Such systems could, for example, "upgrade" the experience with more aggressive settings (e.g., acceleration into curves, tighter suspension, and/or louder music) in the morning, when cortisol levels are healthy. ' and the experience could be 'mellowed out' (such as soft suspension, relaxing music and/or gentle driving behavior) in the afternoon when cortisol levels should drop to low levels to promote good health. Experiences can consider both the user's health and safety. For example, the level may vary over time, but should be high enough to ensure alertness (and thus safety) in situations where high alertness is required. Cortisol (a key hormone) is provided as an example, but the user experience may vary with respect to the insulin-related system, the cardiovascular system (e.g., related to pulse and blood pressure), the gastrointestinal system, and many other hormonal or biological systems. Parameters may be controlled (optionally with random or set variations).

Aspects provided herein feature a transportation system 5111 comprising an artificial intelligence system 5136 that automatically randomizes parameters of the in-vehicle experience to improve user conditions. In embodiments, user states benefit from parameter variations.

Aspects provided herein are a system for transportation 5111, a vehicle interface 51188 for collecting physiological sensory data of a rider 51120 in a vehicle 5110 and a set of achievements related to the rider's in-vehicle experience. an artificial intelligence-based circuit 51189 that, in response to sensed lidar physiological data, induces variations in one or more user experience parameters to achieve at least one desired outcome in the set of outcomes, and artificial intelligence-based circuitry 51189, in which the induction of variation includes control of timing and extent of variation.

In embodiments, the induced variation comprises random variation. In embodiments, induced variations include variations that follow a predetermined pattern. In embodiments, the predetermined pattern is prescribed according to a regimen. In embodiments, regimens are developed to provide at least one of physical therapy, chiropractic, and other medical health benefits. In embodiments, the one or more user experience parameters affect at least one of seat position, temperature, humidity, cabin air source, or audio output. In an embodiment, vehicle interface 51188 comprises at least one wearable sensor 51157 arranged to be worn by rider 51120 . In an embodiment, vehicle interface 51188 comprises a vision system 51186 arranged to capture and analyze images from multiple viewpoints of lidar 51120 . In embodiments, variations in one or more of the user experience parameters constitute variations in vehicle 5110 control.

In embodiments, variations in controlling vehicle 5110 include configuring vehicle 5110 for aggressive driving performance. In embodiments, variations in control of vehicle 5110 include configuring vehicle 5110 for non-aggressive driving performance. In embodiments, variations respond to physiological sensory data, including an indication of the rider's 51120 hormonal levels, and the artificial intelligence-based circuit 51189 generates one or more user experiences to promote hormonal conditions that promote rider safety. Vary parameters.

Referring now to FIG. 52, a transportation system having a system 52192 for taking an indication of a user's 5290 hormonal system level and automatically altering the user's experience in the vehicle 5210 to promote a hormonal state that promotes safety. 5211 is also provided herein.

Aspects provided herein are systems for transportation 5211 that detect indicators of hormonal levels of a user 5290 and automatically adjust the user's experience in a vehicle 5210 to promote hormonal conditions that promote safety. Equipped with system 52192 for changing.

Aspects provided herein include a system 5211 for transportation: a lidar (e.g., artificial intelligence-based circuit 52189) trained on a set of outcomes related to the rider's in-vehicle experience, sensed rider to induce variation in one or more of the user experience parameters to achieve at least one desired result in the set of results, the set of results promoting rider safety at least Including one result and inducing variation includes controlling the timing and extent of variation.

In embodiments, variation of one or more user experience parameters is controlled by artificial intelligence system 5236 to promote a desired hormonal state of the rider (eg, user 5290). In embodiments, the rider's desired hormonal status promotes safety. In embodiments, at least one desired outcome in the set of outcomes is at least one outcome that promotes rider safety. In embodiments, varying one or more user experience parameters includes varying at least one of food and beverage provided to a rider (eg, user 5290). In embodiments, the one or more user experience parameters affect at least one of seat position, temperature, humidity, cabin air source, or audio output. In an embodiment, vehicle interface 52188 comprises at least one wearable sensor 52157 arranged to be worn by a rider (eg, user 5290).

In an embodiment, the vehicle interface 52188 consists of a vision system 52186 arranged to capture and analyze images from multiple viewpoints of a rider (eg, user 5290). In embodiments, variation in one or more of the user experience parameters includes variation in control of vehicle 5210 . In an embodiment, variation in control of vehicle 5210 includes configuring vehicle 5210 for aggressive driving performance. In embodiments, variations in control of vehicle 5210 include configuring vehicle 5210 for non-aggressive driving performance.

Referring to FIG. 53, provided herein is a transportation system 5311 having a system for optimizing at least one of vehicle parameters 53159 and user experience parameters 53205 to provide a safety margin 53204. . In embodiments, the margin of safety 53204 is selected based on the user's profile, actively selected by the user, such as by interacting with a user interface, or based on behavior in the vehicle 5310 and on social media, e-commerce, May be user-selected safety margin or user-based safety margin, such as selected based on a profile developed by tracking user behavior including behavior in other contexts such as content consumption, movement from place to place, etc. . In many situations, there is a trade-off between optimizing dynamic system performance (e.g., achieving some objective function such as fuel efficiency) and one or more risks present in the system. . This is especially true when there is an asymmetry between the benefits of optimizing one or more parameters and the risks present in dynamic systems involving those parameters. For example, trying to minimize travel time (such as your daily commute) increases the likelihood of arriving late. This is because various effects in dynamic systems involving vehicular traffic tend to cascade, resulting in large (and often unfavorable) cyclical travel times. Variations in many systems are not symmetrical. For example, an unusually uncongested road might improve a 30-mile commute by a few minutes, but an accident or high traffic could add an hour or more to the same commute. A wide margin of safety may therefore be required to avoid high risk of adverse effects. In embodiments, an expert system (which as described herein may be model-based, rule-based, deep learning, hybrid, or other intelligent system) is used to analyze transportation-related dynamic A system is provided herein for providing a desired margin of safety with respect to adverse events present in the system. Safety margins 53204 may be provided via expert system 5336 outputs, such as instructions, control parameters for the vehicle 5310 or in-vehicle user experience. The artificial intelligence system 5336 provides traffic data, weather data, accident data, vehicle maintenance data, refueling and charging system data (including in-vehicle data and data from charging stations, refueling stations, and infrastructure systems such as energy production, transportation, and storage systems). data), user behavior data, user health data, user satisfaction data, financial information (e.g., user financial information, pricing information (e.g., fuel, food, on-route accommodations, etc.), vehicle safety data, failure modes data, vehicle information system data, etc.), and many other types of data described herein and in the documents incorporated herein by reference.

Aspects provided herein comprise a transportation system 5311 comprising a system for optimizing at least one of vehicle parameters 53159 and user experience parameters 53205 to provide a margin of safety 53204. include.

Aspects provided herein include a transportation system 5311 for optimizing safety margins when mimicking human operation of a vehicle 5310, the transportation system 5311 comprising a set of robotic process automation systems 53181; Prepare. an operator data collection module 53182 that captures interactions 53201 of the human operator 5390 with the vehicle control system interface 53191; and a vehicle data collection module 53183 that captures vehicle responses and operating conditions associated at least contemporaneously with the human operator interactions 53201. , an environmental data collection module 53184 that captures instances of relevant environmental information 53203 at least contemporaneously with human operator interactions 53201 and learning to control the vehicle 5310 with an optimized margin of safety while mimicking a human operator. An artificial intelligence system 5336 for In embodiments, the artificial intelligence system 5336 is responsive to the robotic process automation system 53181. In an embodiment, the artificial intelligence system 5336 is to detect data indicative of at least one of multiple instances of environmental information associated with vehicle responses and operating conditions captured contemporaneously. In an embodiment, the optimized safety margin for controlling the vehicle 5310 is based on a set of human operator interaction data collected from a set of expert human vehicle operators interacting with the vehicle control system interface 53191. is achieved by training the artificial intelligence system 5336 to

In an embodiment, the operator data collection module 53182 captures patterns of data including braking patterns, following distance, curve approach acceleration patterns, lane preferences, or passing preferences. In an embodiment, vehicle data collection module 53183 captures data from multiple vehicle data systems that provide data streams indicative of conditions and changes in conditions in steering, braking, acceleration, forward looking images, or rearward looking images. In embodiments, the artificial intelligence system includes a neural network 53108 for training the artificial intelligence system 53114.

FIG. 54 illustrates a robotic process automation method 5400 for achieving optimized margins of vehicle operational safety, according to embodiments of the systems and methods disclosed herein. At 5402, the method includes tracking expert vehicle control human interactions with the vehicle control facilitation interface. At 5404, the method includes recording the tracked expert vehicle control human interactions in a robotic process automation system training data structure. At 5406, the method includes tracking vehicle operating state information for the vehicle. At 5407, the method includes recording vehicle operating state information in a robotic process automation system training data structure. at 5408, a method of matching an expert vehicle-control human interaction based on the expert vehicle-control human interaction and vehicle operating state information in the robotic process automation system training data structure via at least one neural network. training the vehicle to operate with an optimized margin of vehicle operational safety in At 5409, the method includes controlling at least one aspect of the vehicle with a trained artificial intelligence system.

53 and 54, in an embodiment, the method controls at least one side of the vehicle through structured variation in control of at least one side of the vehicle to mimic expert vehicle control human interaction 53201. Optimizing a margin of vehicle operational safety by controlling the at least one aspect of the vehicle, further comprising applying deep learning to process feedback from the control with machine learning. In an embodiment, controlling at least one aspect of the vehicle is performed through the vehicle control facilitating interface 53191. In an embodiment, control of at least one aspect of the vehicle is performed by an artificial intelligence system emulating a control-facilitation interface operated by an expert vehicle control human 53202. In embodiments, the vehicle control facilitation interface 53191 comprises at least one of a voice capture system that captures an audible representation of an expert vehicle control human, a human-machine interface, a machine interface, an optical interface, and a sensor-based interface. In embodiments, the tracked vehicle operating state information includes tracking at least one of vehicle systems and vehicle operating processes affected by expert vehicle control human interaction. In an embodiment, the tracked vehicle operating state information comprises tracking at least one vehicle system element. In embodiments, at least one vehicle system element is controlled via a vehicle control facilitating interface. In embodiments, at least one vehicle system element is affected by human interaction of the expert vehicle control.

In an embodiment, tracking vehicle operating state information comprises tracking vehicle operating state information before, during, and after expert vehicle control human interaction. In embodiments, the tracked vehicle operating state information tracks at least one of a plurality of vehicle control system outputs resulting from the expert vehicle control human interaction and vehicle operating results achieved in response to the expert vehicle control human interaction. consists of doing In an embodiment, the vehicle is controlled to achieve results consistent with those achieved through expert vehicle control human interaction.

In embodiments, the method further includes tracking and recording conditions proximate to the vehicle with a plurality of vehicle-mounted sensors. In embodiments, the training of the artificial intelligence system is more responsive to conditions in proximity to the tracked vehicle contemporaneously with the human interaction of the expert vehicle control. In embodiments, the training is further responsive to multiple data feeds from remote sensors, the multiple data feeds including data collected by the remote sensors contemporaneously with the expert vehicle control human interaction.

FIG. 55 illustrates a method 5500 for mimicking human manipulation of a vehicle through robotic process automation according to embodiments of the systems and methods disclosed herein. At 5502, the method includes capturing human operator interaction with a vehicle control system interface operatively connected to the vehicle. At 5504, the method includes capturing vehicle responses and operating conditions associated at least contemporaneously with human operator interaction. At 5506, the method includes capturing environmental information associated at least concurrently with the human operator interaction. In, the method includes training an artificial intelligence system to control a vehicle with an optimized margin of safety while imitating a human operator, the artificial intelligence system learning simultaneously collected vehicle responses and operating conditions. Takes input from the environmental data collection module regarding instances of environmental information associated with the . In an embodiment, the optimized safety margin is based on a set of human operator interaction data collected from expert human vehicle operator interactions and result data from a set of vehicle safety events. This is achieved by training an artificial intelligence system to control the

Referring to FIGS. 53 and 55 in an embodiment, a method controls at least one side of a vehicle through structured variation in control of at least one side of the vehicle to mimic expert vehicle control human interaction 53201. Applying deep learning artificial intelligence systems 53114 to optimize margins for vehicle operational safety 53204 by influencing controls and using machine learning to process feedback from controls of at least one aspect of the vehicle further comprising: In embodiments, the artificial intelligence system employs workflows with decision making and the robotic process automation system 53181 facilitates automation of decision making. In embodiments, the artificial intelligence system employs a workflow involving remote control of the vehicle, and the robotic process automation system facilitates automation of remotely controlling the vehicle 5310 .

Referring now to Figure 56, a set of expert systems 5657 provide respective outputs 56193 for managing at least one of a set of vehicle parameters, a set of fleet parameters, and a set of user experience parameters. A transport system 5611 is depicted including an interface 56133 that can be configured to.

Such interfaces 56133 may include graphical user interfaces (such as having a series of visual elements, menu items, forms, etc. that may be manipulated to enable selection and/or configuration of the expert system 5657), application programming interfaces, computing platforms It may also include interfaces to (eg, configuring parameters of one or more services, programs, modules, or the like), and so on. For example, the interface 56133 may display models (e.g., selected models for representing vehicle, fleet, or user behavior, or transportation-related models such as weather models, traffic models, fuel consumption models, energy distribution models, pricing models, etc.). models that represent aspects of the environment), artificial intelligence systems (e.g. select types such as neural networks of any kind described in this document, deep learning systems, etc.), or any combination or hybrid of these. may be used to For example, in interface 56133, the user may select a recurrent neural network for predicting the user's shopping behavior (e.g., indicating the user's likely preferences along a traffic route), as well as a weather forecast that can affect the traffic environment. You may choose to use the European Intermediate Range Weather Forecasting Center (ECMWF) for forecasting events.

Interface 56133 thus provides hosts, managers, operators, service providers, vendors, or other entities interacting with or within transportation system 5611 with the ability to view a range of models, expert systems 5657, neural network categories, etc. may be configured to Interface 56133 may optionally be provided with one or more indicators of suitability for a given purpose, such as one or more ratings, statistical measures of effectiveness, and the like. Interface 56133 may also be configured to select sets (eg, models, expert systems, neural networks, etc.) that are well suited for a given transportation system, environment, and purpose. In embodiments, such an interface 56133 allows the user 5690 to input one or more parameters of the expert system 5657, e.g., one or more input data sources to which the model is to be applied and/or one or more parameters to the neural network. one or more types of outputs, goals, periods or objectives, one or more weights in a model or artificial intelligence system, a model, a graph structure, one or more node sets and/or interconnections in a neural network It may be possible to set the one or more periods of input, output, or behavior, one or more frequencies of behavior, calculations, etc., one or more rules (applied to any of the parameters configured as described herein) or rules that act on any of the inputs or outputs described herein), one or more infrastructure parameters (such as storage parameters, network utilization parameters, processing parameters, processing platform parameters, etc.), etc. be done. As one example, among many other possible examples, user 5690 takes input from weather models, traffic models, and real-time traffic reporting systems to provide real-time output 56193 to the routing system for vehicle 5610. A neural network of choice may be configured to have 10 million nodes and be configured to undertake processing on a cloud platform of choice.

In embodiments, the interface 56133 selects and selects objectives, goals, or desired results for the system and/or subsystems, such as those that provide input, feedback, or oversight to the model, to the machine learning system. and/or may include elements for configuration. For example, the user 5690 may select at the interface 56133 a mode corresponding to a desired outcome, which may include an emotional outcome, a monetary outcome, a performance outcome, a travel duration outcome, an energy use outcome, an environmental impact outcome, a traffic avoidance outcome, etc. (e.g., comfort mode, sport mode, high efficiency mode, work mode, entertainment mode, sleep mode, relax mode, long travel mode, etc.). Outcomes can be declared with varying levels of specificity. Outcomes may be achieved by or for a given user 5690 (such as based on user profile or behavior), or by a group of users (e.g., a desired configuration consistent with acceptable conditions for each of a set of riders). selection) by one or more functions that coordinate outcomes according to multiple user profiles. As an example, one rider may exhibit a favorable outcome of positive entertainment, while another rider may exhibit a favorable outcome of maximum safety. In such cases, the interface 56133 can provide reward parameters to the model or expert system 5657 for risk-reducing and entertainment-enhancing behaviors, resulting in outcomes consistent with both rider objectives. . Rewards may be weighted to optimize the set of outcomes. Competition between potentially conflicting outcomes can be determined by models, by rules (e.g. vehicle owner objectives may be weighted higher for parents than for children than for other riders), or by machine learning. e.g. by using genetic programming techniques (e.g. randomly or systematically varying combinations of weights and/or outcomes to determine the overall satisfaction of a rider or set of riders). can.

Aspects provided herein are a system 5611 for transportation, a set of parameters selected from the group consisting of a set of vehicle parameters, a set of fleet parameters, a set of user experience parameters, and combinations thereof. and an interface 56133 for configuring the set of expert systems 5657 to provide respective outputs 56193 for managing the .

Aspects provided herein include a system for configuration management of components of a transport system 5611, comprising an interface 56133 comprising: A first part 56194 of the interface 56133 for configuring a first expert computing system of an expert computing system 5657 for managing a set of vehicle parameters, an expert computing system for managing a set of vehicle fleet parameters A second portion 56195 of the interface 56133 for configuring a second expert computing system of 5657 and a second portion 56195 of the interface 56133 for configuring a third expert computing system for managing a set of user experience parameters. It has 3 parts 56196. In embodiments, the interface 56133 is configured such that when a set of visual elements 56197 presented in a graphical user interface are manipulated in the interface 56133, one of the first, second, and third expert systems 5657 or A graphical user interface through which at least one of a plurality of selections and configurations is induced. In embodiments, interface 56133 is an application programming interface. In embodiments, interface 56133 is an interface to a cloud-based computing platform upon which one or more transportation-centric services, programs, and modules are configured.

Aspects provided herein include a transportation system 5611: the transportation system 5611 comprises an interface 56133 for configuring a set of expert systems 5657 to provide outputs 56193 that manage transportation-related parameters. In embodiments, the parameters facilitate manipulation of at least one of a set of vehicles, a fleet of vehicles, and a transport system user experience; and an expert system 5657 configurable by an interface 56133 and a plurality of transport systems 5611 a plurality of visual elements 56197 representing attributes and parameters of a set of . In embodiments, interface 56133 is configured to facilitate manipulating visual elements 56197 , thereby causing configuration of a set of expert systems 5657 . In an embodiment, multiple transport systems are made up of a set of vehicles 5610 .

In embodiments, the multiple transport system consists of a set of infrastructure elements 56198 that support a set of vehicles 5610 . In an embodiment, the set of infrastructure elements 56198 consist of vehicle refueling elements. In an embodiment, the set of infrastructure elements 56198 consist of vehicle charging elements. In an embodiment, the set of infrastructure elements 56198 consist of traffic control lights. In an embodiment, the set of infrastructure elements 56198 consists of toll booths. In an embodiment, the set of infrastructure elements 56198 consists of a railway system. In an embodiment, the set of infrastructure elements 56198 consist of automated parking facilities. In an embodiment, the set of infrastructure elements 56198 consist of vehicle monitoring sensors.

In an embodiment, visual element 56197 displays multiple models that can be selected for use with set of expert systems 5657 . In an embodiment, visual element 56197 displays multiple neural network categories that may be selected for use in set of expert systems 5657 . In embodiments, at least one of the plurality of neural network categories includes convolutional neural networks. In embodiments, the visual element 56197 includes one or more indicators of the suitability of the item represented by the plurality of visual elements 56197 for a given purpose. In an embodiment, configuring the plurality of expert systems 5657 includes facilitating select sources of input for use by at least some of the plurality of expert systems 5657 . In embodiments, interface 56133 facilitates selection of one or more output types, targets, durations, and objectives for at least a portion of plurality of expert systems 5657 .

In embodiments, interface 56133 facilitates, for at least a portion of plurality of expert systems 5657, selection of one or more weights within a model or artificial intelligence system. In embodiments, the interface 56133 facilitates selection of one or more sets of nodes or interconnections within the model to at least a portion of the plurality of expert systems 5657 . In embodiments, interface 56133 facilitates selection of graph structures for at least a portion of plurality of expert systems 5657 . In embodiments, interface 56133 facilitates selection of neural networks for at least a portion of plurality of expert systems 5657 . In embodiments, the interface facilitates selection of one or more time periods of input, output, or operation for at least some of the plurality of expert systems.

In embodiments, interface 56133 facilitates selection of one or more operating frequencies for at least a portion of plurality of expert systems 5657 . In embodiments, interface 56133 facilitates selection of frequency of calculations for at least a portion of plurality of expert systems 5657 . In embodiments, interface 56133 facilitates selection of one or more rules to apply to parameters for at least a portion of expert systems 5657 . In embodiments, the interface 56133 selects one or more rules to operate on at least a portion of the plurality of expert systems 5657, on any of the inputs, or on the outputs provided. make it easier. In embodiments, the plurality of parameters comprises one or more infrastructure parameters selected from the group consisting of storage parameters, network utilization parameters, processing parameters, and processing platform parameters.

In embodiments, the interface 56133 includes a class of artificial intelligence computing system, a source of input to the selected artificial intelligence computing system, the computing power of the selected artificial intelligence computing system, the artificial intelligence computing system running facilitating the selection of a processor for and the resulting purpose of running an artificial intelligence computing system. In embodiments, the interface 56133 facilitates selecting one or more modes of operation of at least one of the vehicles 5610 within the transportation system 5611 . In embodiments, interface 56133 facilitates selecting a degree of specificity for output 56193 generated by at least one of plurality of expert systems 5657 .

57, an example transportation system 5711 is depicted having an expert system 5757 for constructing recommendations for vehicle 5710 configurations. In embodiments, the recommendation includes at least one parameter of configuration for expert system 5757 that controls at least one of vehicle parameters 57159 and user experience parameters 57205 . Such recommendation systems include user profiles, user behavior tracking (in-vehicle and out-of-vehicle), content recommendation systems (such as collaborative filtering systems used to recommend music, movies, videos and other content), content retrieval systems. (e.g., used to provide relevant search results to a query), e-commerce tracking systems (e.g., indicating user preferences, interests and intentions), as well as other user satisfaction data sets , may recommend settings to the user based on a wide variety of information. The recommender system 57199 may use the foregoing to profile the rider and determine the configuration of the vehicle 5710 for the rider, or the experience within the vehicle 5710, based on metrics of satisfaction by other riders. can.

The construction may use similarity (eg, similarity matrix approaches, attribute-based clustering approaches (eg, k-means clustering), or other techniques to group riders with other similar riders. Configuration asks riders about particular content, experiences, etc., and takes input as to whether they liked or disliked them (optionally, a preference system such as a rating system (e.g., 5 stars for great items of content)). The recommender system 57199 constructs combinations of vehicle parameters and/or user experience parameters (with random and/or systematic variation) to determine whether the rider or Genetic programming may be used, such as taking input from a set of riders (e.g., a large research group) to determine a set of preferred configurations, which may occur with machine learning over a large set of results. , where the results may include various reward functions of the types described herein, including measures of overall satisfaction and/or measures of specific objectives, thus machine learning systems or other 's expert system 5757 may learn to configure the overall ride for a rider or set of riders, and to recommend such configurations to riders. group, time of day (or week, month, year), type of trip, purpose of trip, type or route, duration of trip, route, etc.

Aspects provided herein are a system 5711 for transportation comprising an expert system 5757 for making vehicle configuration recommendations. In embodiments, the recommendation includes at least one parameter of configuration for expert system 5757 controlling parameters selected from the group consisting of vehicle parameters 57159, user experience parameters 57205, and combinations thereof.

Aspects provided herein include a recommendation system 57199 for recommending a configuration of a vehicle 5710, the recommendation system 57199 controlling at least one of a vehicle parameter 57159 and a vehicle rider experience parameter 57205 a vehicle control system 57134. and an expert system 5757 that generates parameter recommendations for configuring the .

In an embodiment, vehicle 5710 includes a system for automating at least one control parameter of vehicle 5710 . In embodiments, the vehicle is at least a semi-autonomous vehicle. In embodiments, the vehicle is automatically routed. In embodiments, the vehicle is a self-driving vehicle.

In an embodiment, expert system 5757 is a neural network system. In an embodiment, expert system 5757 is a deep learning system. In embodiments, expert system 5757 is a machine learning system. In embodiments, expert system 5757 is a model-based system. In embodiments, expert system 5757 is a rule-based system. In an embodiment, expert system 5757 is a random walk-based system. In an embodiment, expert system 5757 is a genetic algorithm system. In an embodiment, expert system 5757 is a convolutional neural network system. In embodiments, expert system 5757 is a self-organizing system. In an embodiment, expert system 5757 is a pattern recognition system. In embodiments, expert system 5757 is a hybrid artificial intelligence-based system. In an embodiment, expert system 5757 is an acrylic graph-based system.

In an embodiment, expert system 5757 generates recommendations based on the satisfaction of multiple riders of vehicles 5710 in transportation system 5711 . In embodiments, the expert system 5757 generates recommendations based on rider entertainment satisfaction. In embodiments, the expert system 5757 makes recommendations based on rider safety satisfaction. In an embodiment, the expert system 5757 generates recommendations based on rider comfort satisfaction. In an embodiment, the expert system 5757 makes recommendations based on the rider's in-car search satisfaction.

In embodiments, at least one rider (or user) experience parameter 57205 is a traffic jam parameter. In an embodiment, at least one rider experience parameter 57205 is a desired arrival time parameter. In an embodiment, at least one rider experience parameter 57205 is a preferred route parameter. In an embodiment, at least one rider experience parameter 57205 is a fuel economy parameter. In an embodiment, at least one rider experience parameter 57205 is a parameter of pollution reduction. In an embodiment, at least one rider experience parameter 57205 is an accident avoidance parameter. In an embodiment, at least one rider experience parameter 57205 is a parameter for avoiding severe weather. In an embodiment, at least one rider experience parameter 57205 is a parameter for avoiding bad road conditions. In an embodiment, at least one rider experience parameter 57205 is a fuel consumption reduction parameter. In an embodiment, at least one rider experience parameter 57205 is a reduced carbon footprint parameter. In an embodiment, at least one rider experience parameter 57205 is a parameter by which noise is reduced in an area. In embodiments, at least one rider experience parameter 57205 is a high crime area avoidance parameter.

In embodiments, at least one rider experience parameter 57205 is a group satisfaction parameter. In an embodiment, at least one rider experience parameter 57205 is a maximum speed limit parameter. In an embodiment, at least one rider experience parameter 57205 is a toll road avoidance parameter. In an embodiment, at least one rider experience parameter 57205 is an urban road avoidance parameter. In an embodiment, at least one rider experience parameter 57205 is a parameter that avoids undivided highways. In an embodiment, at least one rider experience parameter 57205 is a left turn avoidance parameter. In an embodiment, at least one rider experience parameter 57205 is a maneuvered vehicle avoidance parameter.

In an embodiment, at least one vehicle parameter 57159 is a fuel consumption parameter. In an embodiment, at least one vehicle parameter 57159 is a carbon footprint parameter. In an embodiment, at least one vehicle parameter 57159 is a parameter of vehicle speed. In an embodiment, at least one vehicle parameter 57159 is a parameter of vehicle acceleration. In an embodiment, at least one vehicle parameter 57159 is a travel time parameter.

In embodiments, the expert system 5757 generates recommendations based on at least one of the user behavior of the rider (eg, the user 5790) and the rider's interaction with the content access interface 57206 of the vehicle 5710. In embodiments, the expert system 5757 generates recommendations based on similarities between a rider's (eg, user 5790) profile and other riders' profiles. In an embodiment, the expert system 5757 interrogates a rider (e.g., user 5790) by taking input that facilitates classifying the rider's response thereto on a scale of response classes ranging from favorable to unfavorable. A recommendation is generated based on the determined collaborative filtering results. In an embodiment, the expert system 5757 includes at least one selected from the group consisting of trip classification, time period, road classification, trip duration, configured route, and number of riders (e.g., user 5790) to generate recommendations based on relevant content.

Referring now to FIG. 58, an exemplary transportation system 5811 is depicted having a search system 58207 configured to provide network search results to in-vehicle searchers.

In self-driving cars, the opportunities to interact with in-vehicle interfaces such as touch screens, virtual assistants, entertainment system interfaces, communication interfaces, and navigation interfaces have increased significantly. Although systems exist to display the rider's mobile device interface on the in-vehicle interface, the content displayed on the mobile device's screen is not necessarily tailored to the unique situation of the rider in the vehicle. In fact, riders in vehicles tend to show many different things to users sitting at home, sitting at desks, or walking around, so it's not just the other people involved in the interface. individuals may collectively have significantly different immediate needs. Searching across devices such as desktops, mobiles, and wearables is one activity that nearly every device user participates in. Searches typically involve keyword input, natural language text input, and spoken queries. Queries are processed to provide search results in one or more lists or menu elements, often with a distinction between sponsored and non-sponsored results. Ranking algorithms generally consider a wide range of inputs, in particular the degree of usefulness of a given search result to other users (as indicated by engagement, clicks, attention, navigation, purchases, viewing, listening, etc.); Make more useful items rank higher in the list.

But the usefulness of search results for riders in self-driving cars and more general searchers can be very different. For example, a rider being driven on a defined route (because the route is the required input for an autonomous vehicle) would be more likely to be on the route than the same individual sitting at his personal desk at work or at his computer at home. You may be much more likely to evaluate search results that are related to locations beyond the rider. Therefore, traditional search engines may fail to deliver the most relevant results given the situation of riders in self-driving vehicles, or may mix up and deliver more relevant results. .

In the system 5811 embodiment of FIG. 58, the search result ranking system (search system 58207) may be configured to provide in-vehicle related search results. In embodiments, such a configuration may be used to include ranking parameters observed only in relation to a set of in-vehicle searches, such that in-vehicle results are ranked based on results related to in-vehicle searches by other users. It may be achieved by partitioning the result ranking algorithm. In an embodiment, such a configuration detects in-vehicle system indicators when an in-vehicle search is detected (e.g., communication protocol type, IP address, presence of cookies stored in the vehicle, mobility detection, etc.). by), by adjusting the weighting parameters applied to one or more weights in the conventional search algorithm. For example, ranking algorithms can give more weight to local search results.

In embodiments, route information from vehicles 5810 may be used as input to ranking algorithms, such as to allow favorable weighting of results associated with local points of interest ahead on the route.

In embodiments, content types may be weighed more heavily in search results based on detection of in-vehicle queries such as weather information, traffic information, event information, and the like. In embodiments, tracked performance includes rerouting as a ranking factor (e.g., if search results appear temporally related to rerouting to locations that were the subject of the search results); Improve in-vehicle search rankings, such as by including rider feedback on results (e.g., ride satisfaction metrics) and detecting in-vehicle behavior that appears to come from search results (e.g., playing music that appears in search results) can be adjusted.

In an embodiment, the set of automotive related search results is displayed in a search results interface (e.g., lidar interface 58208 ) may be provided in another part of the In embodiments, both general search results and sponsored search results may be any of the techniques described herein or understood by those skilled in the art to provide automotive related search results. It may also be constructed using other techniques.

In embodiments where automotive-related search results and traditional search results are presented in the same interface (e.g., lidar interface 58208), selection and engagement of automotive-related search results can be used to successfully train or reinforce one or more search algorithms 58211. can be used as a metric. In embodiments, the in-vehicle search algorithm 58211 may optionally be provided with initial parameters adjusted based on one or more models of user behavior that may account for differences between in-vehicle behavior and other behaviors. It may be trained using machine learning seeded by one or more conventional search models. Machine learning may include the use of neural networks, deep learning systems, model-based systems, and the like. Feedback to machine learning may include traditional engagement metrics used for search, as well as rider satisfaction metrics, emotional states, yield metrics (e.g., sponsored search results, banner ads, and the like), etc. .

Aspects provided herein feature a transport system 5811 comprising a search system 58207 that provides network search results to an in-vehicle searcher.

Aspects provided herein include an in-vehicle network search system 58207 of a vehicle 5810, the search system comprising: a. A lidar interface 58208 that allows a rider 58120 of a vehicle 5810 to engage with a search system 58207 and search results that prioritize search results based on a set of in-vehicle search criteria derived from multiple previously conducted in-vehicle searches. A generator circuit 58209 and a search result display ranking circuit 58210 that orders the favored search results based on the relevance of the location components of the search results and the configured route of the vehicle 5810 .

In an embodiment, vehicle 5810 includes a system for automating at least one control parameter of vehicle 5810 . In embodiments, vehicle 5810 is at least a semi-autonomous vehicle. In an embodiment, vehicles 5810 are auto-routed. In an embodiment, vehicle 5810 is a self-driving vehicle.

In embodiments, the rider interface 58208 is comprised of at least one of a touch screen, virtual assistant, entertainment system interface, communication interface, and navigation interface.

In an embodiment, favorable search results are ordered by the search result display ranking circuit 58210 such that results proximate to the established route are displayed before other results. In embodiments, the in-vehicle search criteria are based on a set of in-vehicle search ranking parameters. In an embodiment, ranking parameters are observed only in relation to the set of in-vehicle searches. In embodiments, the search system 58207 adapts the search result generation circuitry 58209 to prioritize search results that correlate with in-vehicle activity. In embodiments, search results correlated to in-vehicle behavior are determined through a comparison of rider behavior before and after performing the search. In an embodiment, the search system further comprises a machine learning circuit 58212 that facilitates training the search result generation circuit 58209 from a set of search results for a plurality of searchers based on an in-vehicle rider behavioral model and a set of search result generation parameters. .

Aspects provided herein include an in-vehicle network search system 58207 of a vehicle 5810, the search system 58207 including: A lidar interface 58208 that allows a rider 58120 of a vehicle 5810 to engage with the search system 5810 and search results based on detecting whether the vehicle 5810 is in self-driving or autonomous mode or is being driven by an active driver. and a search result display ranking circuit 58210 that orders the search results based on the relevance of the location component of the search results to the vehicle's 5810 configured route. In embodiments, search results vary based on whether the user (eg, rider 58120) is a driver of vehicle 5810 or a passenger of vehicle 5810. FIG.

In an embodiment, vehicle 5810 includes a system for automating at least one control parameter of vehicle 5810 . In embodiments, vehicle 5810 is at least a semi-autonomous vehicle. In an embodiment, vehicles 5810 are auto-routed. In an embodiment, vehicle 5810 is a self-driving vehicle.

In embodiments, the rider interface 58208 is comprised of at least one of a touch screen, virtual assistant, entertainment system interface, communication interface, and navigation interface.

In the embodiment, the search result display order determining circuit 58210 orders the search results so that results close to the set route are displayed before other results.

In an embodiment, the search criteria used by the search result generator circuit 58209 are based on the ranking parameters of the set of in-vehicle searches. In an embodiment, ranking parameters are observed only in relation to the set of in-vehicle searches. In an embodiment, the search system 58207 adapts the search result generation circuitry 58209 to prioritize search results that correlate to in-vehicle activity. In embodiments, search results correlated to in-vehicle behavior are determined through a comparison of rider behavior before and after conducting a search. In an embodiment, the search system 58207 further comprises a machine learning circuit 58212 that facilitates learning the search result generation circuit 58209 from a plurality of searcher search result sets and search result generation parameter sets based on in-vehicle rider behavior models. .

Aspects provided herein include an in-vehicle network search system 58207 of a vehicle 5810, the search system 58207 has a rider interface 58208 that enables a rider 58120 of the vehicle 5810 to engage with the search system 58207, a user (e.g., rider 58120), and a search result display ranking circuit 58210 that ranks the search results based on the relevance of the location components of the search results. A search result generation circuit 58209 that varies the search results based on whether the rider 58120) is the driver of the vehicle or a passenger of the vehicle, and the relevance of the location components of the search results to the set route of the vehicle 5810. a search result display ranking circuit 58210 for ordering the search results based on.

In an embodiment, vehicle 5810 includes a system for automating at least one control parameter of vehicle 5810 . In embodiments, vehicle 5810 is at least a semi-autonomous vehicle. In an embodiment, vehicles 5810 are auto-routed. In an embodiment, vehicle 5810 is a self-driving vehicle.

In embodiments, the rider interface 58208 is comprised of at least one of a touch screen, virtual assistant, entertainment system interface, communication interface, and navigation interface.

In embodiments, the search results are ordered by the search result display ranking circuit 58210 such that results proximate to the established route are displayed before other results. In an embodiment, the search criteria used by search result generation circuitry 58209 are based on a set of in-vehicle search ranking parameters. In an embodiment, ranking parameters are observed only in relation to the set of in-vehicle searches.

In embodiments, the search system 58204 adapts the search result generation circuitry 58209 to prioritize search results that correlate with in-vehicle activity. In embodiments, search results correlated to in-vehicle behavior are determined through a comparison of rider behavior before and after performing the search. In an embodiment, the search system 58207 further comprises a machine learning circuit 58212 that facilitates training the search result generation circuit 58209 from a plurality of searcher search result sets and search result generation parameter sets based on the in-vehicle rider behavior model. .

Referring to FIG. 59, an architecture for transport system 60100 is depicted, showing certain exemplary components and arrangements associated with certain embodiments described herein. System 60100 includes vehicle 60104, which includes various mechanical components such as powertrain, suspension system, steering system, braking system, fuel system, charging system, seat, combustion engine, electric vehicle driveline, transmission, gearset, etc. , electrical, and software components and systems. A vehicle may have a vehicle user interface that includes a set of interfaces including a steering system, buttons, levers, touch screen interfaces, audio interfaces, and the like. The vehicle may have a set of sensors 60108 (including cameras), such as for providing input to the expert/artificial intelligence systems described throughout this disclosure. Sensors 60108 and/or external information may be used to inform expert systems/artificial intelligence (AI) systems 60112 and include energy utilization status, maintenance status, component status, user experience status, and others as described herein. May be used to indicate or track one or more vehicle conditions 60116, such as vehicle operating conditions. The AI system 60112 takes as input a wide range of vehicle parameters, such as from on-board diagnostic systems, telemetry systems, and other software systems, as well as from sensors 60108, and from external systems, and uses one or more of the vehicle 60104 Components may be controlled. Data from sensors 60108 , including data relating to vehicle state 60116 , may be transmitted over network 60120 to cloud computing platform 60124 for storage in memory 60126 and processing. In embodiments, cloud computing platform 60124 and all elements located or operating therewith may be embodied separately from the remaining elements of system 60100 . Modeling application 60128 on cloud computing platform 60124 includes code and functions operable to generate and manipulate digital twin 60136 of vehicle 60104 when executed by processor 60132 on cloud computing platform 60124 . The digital twin 60136 represents, among other things about the vehicle and its environment, the operational state of the vehicle 60104 through a virtual model. A user device 60140 connected to the cloud computing platform 60124 and the vehicle 60104 via a network 60120 interacts with the modeling application 60128 and other software on the cloud computing platform 60124, such as via a digital twin 60136, to the vehicle 60104 may receive data from and control its operation. The interface 60144 on the user device 60140 can be used by drivers, riders, third party observers, vehicle owners, fleet operators/owners of vehicles, traffic safety personnel, vehicle designers, digital twin development engineers, etc. One or more vehicle states 60116 can be displayed using a digital twin 60136 to a user associated with the vehicle. In embodiments, user device 60140 may receive a particular view of data about vehicle 60104 as the data is processed by one or more applications on cloud computing platform 60124 . For example, the user device 60140 may, as the data is processed by one or more applications, such as the digital twin 60136, the vehicle, its interiors, subsystems and components, the environment in the vicinity of the vehicle, the navigation views, the maintenance times, the vehicle 60104, the vehicle, its interior, the Specific views of the data may be received, including graphical views such as lines, safety test views, and the like. As another example, the user device 60140 uses one or more applications hosted by the cloud computing platform 60124 to allow the user to enter commands into the digital twin 60136, the vehicle 60104, the modeling application 60128, etc. An enabling graphical user interface may be displayed.

In embodiments, the cloud computing platform 60124 may include multiple servers or processors that are geographically distributed and connected together via a network. In embodiments, the cloud computing platform 60124 may include an AI system 60130 coupled to or contained within the cloud computing platform 60124 .

In embodiments, cloud computing platform 60124 includes a database management system for creating, monitoring, and controlling access to data in databases 60118 coupled to or contained within cloud computing platform 60124. It's okay. Cloud computing platform 60124 may also include services that developers can use to build or test applications. Cloud computing platform 60124 may allow user device 60140 to be remotely configured and/or controlled via interface 60144 . The cloud computing platform 60124 also stores and analyzes data periodically collected from the user equipment 60140 and provides analysis, insight to the user, including the manufacturer, driver or owner of the user equipment 140 via the interface 60144. and may facilitate the provision of warnings.

In embodiments, instead of cloud computing platform 60124, on-premises servers may be used to host digital twin 60136.

In embodiments, the network 60120 may be of conventional type, wired or wireless, and may have many different configurations, including star configurations, token ring configurations, or other configurations. Additionally, the network 60120 may include a local area network (LAN), a wide area network (WAN) (e.g., the Internet), or other interconnected data paths over which multiple devices and/or entities may communicate. good. In some embodiments, network 60120 may include a peer-to-peer network. Network 60120 may also be coupled to or include portions of telecommunications networks for transmitting data in a variety of different communication protocols. In some embodiments, the network 60120 supports short messaging service (SMS), multimedia messaging service (MMS), hypertext transfer protocol (HTTP), direct data connection, wireless application protocol (WAP), email, DSRC, Including a Bluetooth(R) communication network or a cellular communication network for transmitting and receiving data, including via full-duplex radio communication or the like. Network 60120 may also include a mobile data network, which may include 3G, 4G, 5G, LTE, LTE-V2X, VoLTE, or any other mobile data network or combination of mobile data networks. Additionally, network 60120 may include one or more IEEE 802.11 wireless networks.

In embodiments, the digital twin 60136 of the vehicle 60104 combines real-time and historical operational data to create virtual representations of the vehicle's 60104 hardware, software, and processes, including structural models, mathematical models, physical process models, software process models, etc. It is a copy. In embodiments, the digital twin 60136 encompasses the hierarchy and functional relationships between the vehicle and various components and subsystems and may be represented as a system of systems. Therefore, we consider the digital twin 60136 of a vehicle 60104 to encompass digital twins of vehicle subsystems such as vehicle interior layout, electrical and fuel subsystems, as well as digital twins of components such as engine, brakes, fuel pumps and alternators. be able to.

The digital twin 60136 includes, but is not limited to, the passenger environment, the driver and passengers in the vehicle, the environment in proximity to the vehicle including nearby vehicles, infrastructure, and, for example, sensors in the vehicle and sensors located in proximity to the vehicle. Methods and systems may be included to represent other aspects of the vehicle environment, such as other objects detectable through the vehicle, such as other vehicles, traffic control infrastructure, pedestrian safety infrastructure, and the like.

In embodiments, the digital twin 60136 of the vehicle 60104 is configured to simulate the behavior of the vehicle 60104 or any part or environment thereof. In embodiments, the digital twin 60136 may be configured to communicate with the user of the vehicle 60104 through a range of communication channels such as voice, text, gestures, and the like. In embodiments, the digital twin 60136 may be configured to communicate with digital twins of other entities, including digital twins of users, nearby vehicles, traffic lights, pedestrians, and the like.

In embodiments, the digital twin is linked to the user's identity such that the digital twin is automatically provided for viewing and configuration via the identified user's mobile device. For example, when a user purchases a vehicle and installs a mobile application provided by the manufacturer, the digital twin is preconfigured to be viewed and controlled by the user.

In embodiments, the digital twin is integrated with an identity management system, and the ability to view, modify, and configure the digital twin is governed by an authentication and authorization system that parses the set of identities and roles managed by the identity management system. make it

FIG. 60 is a schematic diagram of a digital twin system 60200 integrated with an identity and access management system 60204, according to certain embodiments described herein. Identity manager 60208 in identity and access management system 60204 manages various identities, attributes and roles of users of digital twin system 200 . The access manager 60212 in the identity and access management system 60204 evaluates user attributes and regulates user access levels based on access policies to provide access to authenticated users. Identity Manager 60208 includes Credential Management 60216 , User Management 60220 and Provisioning 60224 . Credential Management 60216 manages sets of user credentials such as usernames, passwords, biometrics, encryption keys. User Management 60220 manages user IDs and profile information including various attributes, role definitions, preferences, etc. of each user. Provisioning 60224 creates, manages and maintains user rights and privileges, including those related to accessing resources of the digital twin system. Access Manager 60212 includes Authentication 60228 , Authorization 60232 and Access Policy 60236 . Authentication 60228 verifies the user's identity by matching the credentials provided by the user with those stored in Credential Management 60216 and provides access to the digital twin system for the verified user. Authorization 60232 parses a set of identities and roles to determine each user's entitlements, including the ability to view, modify, and configure digital twins. Authorization 60232 may be performed by matching resource access requests from users to access policies 60236 . Database 60118 may store data regarding all user directories, identities, roles, attributes, authorizations, etc. of identity and access management system 60204 . Roles may include driver, manufacturer, dealer, rider, owner, service department, and the like. In an example of role-based digital twin authenticated access, the manufacturer role is authorized to access content and views related to vehicle wear, maintenance status, service needs, quality inspections, etc. (e.g., worn recommend tire changes, adjust vehicle operating parameter limits such as maximum speed for heavily worn tires), and may not allow access to other content, such as content that may be considered sensitive by the vehicle owner. unknown. In embodiments, access to content by specific roles may be configured by a set of rules, by the manufacturer, by the vehicle owner, or the like.

61 is a schematic diagram of an interface 60300 of the digital twin system presented on the user device of the driver of the vehicle 60104. FIG. The interface 60300 includes multiple modes such as a graphical user interface (GUI) mode 60304 , an audio mode 60308 and an augmented reality (AR) mode 60312 . Additionally, the digital twin 60136 may be configured to communicate with the user via multiple communication channels such as voice, text, gestures, and the like. The GUI mode 60304 may provide the driver with various graphs and charts, diagrams and tables representing the operational state of one or more of the vehicle 60104 or its components. The voice mode 60308 may provide the driver with a voice interface for communicating with the digital twin 60136, whereby the digital twin receives queries from the driver regarding the vehicle 60104, generates responses to the queries, and provides such responses. can be communicated to the driver. Augmented Reality (AR) Mode 60312 presents the user with an Augmented Reality (AR) view that uses the front-facing camera of the User Device 60140 and augments the screen with one or more elements from the digital twin 60136 of the vehicle 60104. may The digital twin 60136 may present the user with a converged view of the world, where the physical view is augmented with computer graphics including images, animations, videos, route-related text, road signs, and the like.

The interface 60300 presents the driver with a set of views, each showing one or more operating states, aspects, parameters, etc. of the vehicle 60104 or its components, subsystems or environment. Dview 60316 presents the driver with a three-dimensional rendering of a model of vehicle 60104 . A driver can select one or more components in the 3D view to see a 3D model of the component, including relevant data about the component. Navigation view 60320 may display a digital twin within the navigation screen that allows the driver to view real-time navigation parameters. The navigation view may provide the driver with information regarding traffic conditions, time to destination, route to destination and preferred routes, road conditions, weather conditions, parking, landmarks, traffic lights, and the like. In addition, the Navigation View 60320 provides drivers with increased situational awareness by establishing communication and exchanging real-time information with nearby vehicles (V2V), pedestrians (V2P) and infrastructure (V2I). good too. Energy view 60324 shows fuel or battery status of vehicle 60104 including utilization and battery health. Value view 60328 shows the state of vehicle 60104 and the blue book value based on the state. Such information is useful, for example, when selling vehicle 60104 on the used car market. Service Views 60332 may present information and views related to wear and failure of vehicle 60104 components and predict the need for service, repair or replacement based on current and historical operating condition data. A world view 60336 may show the vehicle 60104 immersed in a virtual reality (VR) environment.

The digital twin 60136 uses an artificial intelligence system 60112 (including various expert systems, neural networks, teacher (including attached learning systems, machine learning systems, deep learning systems, and any other system) may be utilized.

FIG. 62 is a schematic diagram illustrating interaction between a driver and a digital twin using one or more views and modes of an interface according to an exemplary embodiment of the present disclosure; A driver 60244 of vehicle 60104 interacts with digital twin 60136 using interface 60300 to at least obtain knowledge of the environment not readily available to an in-vehicle navigation system, e.g. from a real-world vehicle to a virtual operating environment. may be deployed in virtual vehicle operating environments that interact with other digital twins that may have real-time or near-real-time traffic activity, road conditions, etc. that can be communicated to each digital twin within the request. The digital twin 60136 shows not only the position of the vehicle 60104 on the map, but also the expected route of the nearby vehicle (e.g., a nearby vehicle that is routed to take the next exit, but the nearby vehicle is still in the exit lane). the driver's propensity for such nearby vehicles (e.g., whether the driver tends to change lanes without using turn signals, etc.) A navigation view 60320 may be displayed to the driver 60244 that may also show candidate routes. The digital twin 60136 can also use voice modes 60308, such as to interact with the driver 60244 and provide assistance such as navigation. In embodiments, the digital twin may respond to driver queries using a combination of GUI mode 60304 and voice mode. In an embodiment, the digital twin 60136 determines nearby vehicles, pedestrians, traffic lights, toll booths, road signs, refueling systems to determine their behavior, coordinate traffic, and gain 3600 non-line-of-sight awareness of the environment. may interact with digital twins of infrastructure elements including, charging systems, etc. In embodiments, the digital twin 60136 may use a combination of 802.11p/dedicated short range communications (DSRC) and cellular V2X for interaction with infrastructure elements. In embodiments, the digital twin 60136 may detect upcoming sharp left or right turns that the digital twin 60136 may recognize based on the behavior of other digital twins in multiple digital twin virtual operating environments to help prevent accidents. may notify driver 60244 about In an embodiment, the digital twin 60136 can interact with the digital twins of nearby vehicles to identify any instances of sudden deceleration or lane changes and provide warnings to the driver 60244 about the same. In embodiments, the digital twin 60136 may interact with the digital twins of nearby vehicles to identify any potential driving hazards and notify the driver 60244 about the same. In embodiments, the digital twin 60136 may utilize external sensor data and traffic information to model the driving environment and optimize the driving route for the driver 60244. As an example of driving route optimization, the digital twin 60136 found that moving into the exit lane behind a nearby vehicle is more dangerous than the driver of a vehicle waiting to move into the exit lane further up the road. It may be determined that the probability of avoiding the driving state is high. In an embodiment, the digital twin 60136 interacts with the digital twin of a traffic light to choose a route with minimal stops or when bio You can suggest taking a break. In an embodiment, the digital twin 60136 assists drivers in finding empty parking spaces nearby by interacting with other twins to obtain information and/or spaces that may open soon. may warn the driver about In an embodiment, the digital twin 60136 may reach out to law enforcement or the police in any emergency or distress, such as an accident or crime that may be detected through the interaction of the digital twin with the vehicle 60104, etc. good. In embodiments, the digital twin 60136 advises the driver regarding driving speed or behavior based on predicted changes in driving conditions occurring or likely to occur ahead, such as unexpected deceleration in traffic around blind curves. You may For example, the digital twin 60136 may advise the driver to reduce driving speed to a safe range of 20-40 km/h when the weather changes from 'fog' to 'rain'. In an embodiment, the digital twin 60136 diagnoses such problems and then provides options for correcting them and/or the vehicle 60104 to mitigate the likelihood that such problems continue or worsen. Assists driver 60244 in resolving any problems with vehicle 60104 by suggesting adjusting operating parameters or modes. For example, driver 60244 can ask digital twin 60136 about the potential reason for rattling noises emanating from vehicle 60104 . In an embodiment, the digital twin 60136 may receive an indication of the rattle from audio sensors deployed in/with the vehicle (e.g., passenger compartment, engine compartment, etc.) and may provide a driver and /or positively suggest possible actions for any passenger (eg, fix a vibrating metal object against the window of the vehicle 60104). Twins may interact with drivers 60244 to dissect data, search for correlations, formulate diagnoses, and resolve potential problems. In embodiments, the digital twin 60136 may communicate with other algorithms accessible by and/or through the platform 60124 that may perform noise analysis, etc. in such examples. For example, the Digital Twin 60136, through any of the means described herein, may determine that the noise is caused by faulty vehicle door hydraulic pressure, and it may determine the specific door hydraulic pressure to correct the problem. You can download and install software updates that can tweak your Alternatively, the noise may be attributed to an exhaust system malfunction and replaced by replacing the catalytic converter. Twin can then proceed to resolve the issue by ordering a new catalytic converter using an e-commerce website and/or contacting a repair shop near vehicle 60104.

FIG. 63 is a schematic diagram of a digital twin system interface presented on a user device of a manufacturer 60240 of a vehicle 60104, according to various embodiments of the present disclosure. As shown, the interface provided to manufacturer 60240 is different than that displayed to driver 60244 of vehicle 60104 . The manufacturer 60240 is presented with a view of the digital twin 60136 aligned with the manufacturer's role and needs, and can provide useful information, for example, to make modifications to a vehicle assembly line or vehicle in operation. However, some parts of the manufacturer's interface may be similar to that of the driver's interface. For example, 3D view 60516 presents manufacturer 60240 with a three-dimensional rendering of a model of vehicle 60104 as well as various components and associated data. Design view 60520 includes digital data describing design information for vehicle 60104 and its individual vehicle components. For example, the design information includes CAD (Computer-Aided Design) data of the vehicle 60104 or its individual vehicle components. The design view allows the manufacturer 60240 to view the vehicle 60104 under a wide variety of representations, rotate in three dimensions allowing it to be viewed from any desired angle, and view the exact dimensions and shapes of vehicle components. make it possible to provide In embodiments, the design view allows the manufacturer 60240 to use simulation methods to optimize and drive the design of the vehicle and its parts and subsystems. In an embodiment, Design View 60520 enables Manufacturer 60240 in determining the optimal system architecture for new vehicle models through generative design techniques. The assembly view 60524 allows the manufacturer 60240 to implement a prescribed model of how the vehicle will work and optimize the performance of the vehicle 60104 and its components and subsystems. Manufacturer 60240 can use views to create integrated workflows by combining design, modeling, engineering, and simulation. This may allow the manufacturer 60240 to predict how the vehicle will perform before committing to expensive changes in the manufacturing process. As an example, when manufacturer 60240 produces a new model of hybrid vehicle, it can evaluate the impact of different transmission, fuel type, and engine displacement options on metrics such as fuel economy and retail price. The simulation in assembly view 60524 may then provide manufacturer 60240 with different fuel mileage and retail prices based on the combination of transmission, fuel type, and engine displacement used in the simulation. Manufacturer 60240 may use such simulations to make business decisions, for example, to determine the combination of transmission, fuel type, and engine displacement to use in a given model for a given segment of customers. can be used. Quality View 60528 is used by Manufacturer 60240 to test components in real-world conditions and to generate "what-if" scenarios that help Manufacturer 60240 avoid costly quality and recall related issues. , making it possible to run millions of simulations. For example, manufacturer 60240 can run quality scenarios to determine the impact of different hydraulic fluid options on braking effectiveness in hard braking situations and select the most effective option. Real Time Analysis Views 60532 are used to build a wide range of charts, graphs and models to help Manufacturers 60240 calculate a wide range of metrics and visualize the impact of changes in vehicle and component parameters on driving performance. data analysis may be performed. Service & Maintenance View 60536 may present information related to wear and failure of vehicle 60104 components and predict the need for service, repair or replacement based on current and historical operating condition data. This view may also assist the manufacturer 60240 in performing data analysis and developing projections regarding the remaining useful life of one or more components of the vehicle 60104.

FIG. 64 depicts a scenario in which manufacturer 60240 uses the quality view of the digital twin interface to run simulations and generate what-if scenarios for vehicle quality testing according to an exemplary embodiment. . The digital twin interface may provide the manufacturer 60240 with a list to choose from among various vehicle condition related options. For example, states may include speed 60604, acceleration 60608, climate 60612, road grade 60616, driving 60620, and transmission 60624. The manufacturer 60240 may be provided with graphical menus for selecting different values for a given state. The digital twin 60136 may then use this combination of vehicle states to run simulations to predict the behavior of the vehicle 60104 in given scenarios. In an embodiment, the digital twin 60136 may display the trajectory taken by the vehicle 60104 in case of hard braking and may also provide a minimum safe distance from other vehicles driving in front of the vehicle 60104. In embodiments, the digital twin 60136 may display the behavior of the vehicle 60104 in the event of a sudden tire burst, as well as the effect on occupants or other vehicles. In embodiments, the digital twin 60136 may generate a large set of realistic accident scenarios and then reliably simulate the vehicle's 60104 response in such scenarios. In embodiments, the digital twin 60136 may display the trajectory taken by the vehicle 60104 in the event of a brake failure and the effect on the occupants or other vehicles. In embodiments, the digital twin 60136 may communicate with the digital twins of other vehicles in close proximity to help prevent collisions. In embodiments, the digital twin 60136 may predict the time-to-collision (TTC) from other vehicles at a given distance from the vehicle 60104 . In embodiments, the digital twin 60136 may determine crash safety and rollover characteristics of the vehicle 60104 in the event of a crash. In embodiments, the digital twin 60136 may analyze the structural impact of a head-on collision of the vehicle 60104 to determine occupant safety. In embodiments, the digital twin 60136 may analyze the structural effects of a sideways crash on the vehicle 60104 to determine occupant safety.

FIG. 65 is a schematic diagram showing an interface 700 of the digital twin system presented on a user device of a dealer 60702 of a vehicle 60104. As shown in FIG. As shown, the interface provided to Dealer 60702 differs from that provided to Driver 60244 and Manufacturer 60240 of Vehicle 60104 . Dealer 60702 is shown a view of digital twin 60136 aligned with the dealer's role and needs, and can provide useful information, for example, to provide a superior sales and customer experience. However, some parts of the dealer's interface may be similar to those of the manufacturer's or driver's interface. For example, 3D view 60716 presents dealer 60702 with a three-dimensional rendering of a model of vehicle 60104 as well as various components and associated data. The performance tuning view 60720 allows the dealer 60702 to modify the vehicle 60104 to personalize the vehicle's characteristics according to the driver's or rider's preferences. For example, a vehicle may be tuned to provide better fuel economy, produce more power, or provide better handling and cruising. The performance tuning view 60720 may allow the dealer 60702 to modify or tune the performance of one or more components such as engine, body, suspension. Configurator View 60724 assists potential customers in configuring various components and materials of the vehicle, including engines, wheels, interiors, exteriors, colors, accessories, etc., by dealers 60702 based on the prospect's preferences. make it possible. The configurator view 60724 assists the dealer 60702 in determining different possible configurations of the vehicle, selecting a configuration based on potential customer preferences, and then calculating a price for the selected configuration. Test drive view 60728 may enable dealer 60702 to allow potential customers to virtually test drive a new or used vehicle using digital twin 60136. Verification View 60732 enables used car dealers to use digital twins to provide potential customers with verification of the condition of a used car. The Service & Maintenance View 60736 presents information related to wear and failure of vehicle 60104 components and can predict the need for service, repair or replacement based on current and historical operating condition data. This view may also assist dealers 60702 in performing data analysis and developing projections regarding the remaining useful life of one or more components of vehicle 60104 .

FIG. 66 depicts interaction between dealership 60702 and digital twin 60136 using one or more views for the purpose of personalizing the experience of potential customers purchasing vehicle 60104, in accordance with an illustrative embodiment. It is a figure explaining. The digital twin 60136 allows the dealer 60702 to interactively select one or more components or options to configure the vehicle based on customer preference as well as component availability and compatibility make it possible. In addition, the Digital Twin 60136 allows dealers 60702 to modify the performance of the vehicle 60104 in line with customer preferences, as well as test drive the customized vehicle before the customer ultimately purchases the same. make it possible to

Dealer 60702 of vehicle 60104 uses configurator view 60724 of interface 60700 to interact with digital twin 60136 to request assistance in configuring the vehicle for the customer. Digital twin 60136 may display to dealer 60702 GUI 60704 of configurator view 60724 showing all different options available for one or more components. Dealer 60702 then selects one or more components using drop-down menus or adds one or more components using drag-and-drop operations, depending on customer preference. A vehicle can be constructed using In the exemplary embodiment, the digital twin GUI view 60704 displays vehicle grade 60804, engine 60808, seat 60812, color 60816 and wheel 60820 options.

Digital Twin 60136 may check compatibility between one or more components selected by Dealer 60702 and model of vehicle 60104 using a predefined database set of valid relationships . In embodiments, certain combinations of components may not be compatible with a given grade of vehicle and Dealer 60702 may be advised of the same. For example, a grade EX represents the base model of the vehicle and may not offer the option of leather seats. Similarly, grade ZX means a premium model of the vehicle and may not be offered with a CVT engine, fabric seats and 20-inch aluminum wheels. In an embodiment, dealer 60702 is only shown compatible combinations by the configurator view. And the digital twin's configurator view allows dealers 60702 to configure complete vehicles by adding sets of compatible components and subsystems. Once configured, the digital twin 60136 calculates the price 60824 of the assembled vehicle based on the price of the individual components and presents the same to the dealer 60702.

In embodiments, the digital twin 60136 may also use voice mode 60708 to interact with the dealer 60702 and provide assistance with configuration. In embodiments, the digital twin 136 may use a combination of GUI mode 60704 and voice mode 60708 to respond to dealer inquiries.

In embodiments, the digital twin 60136 may also allow the dealer 60702 to assist the customer in tuning the performance of the vehicle using the performance tuning view 60720. Dealer 60702 may be presented with different modes 60828, including Sport, Fuel Efficient, Outdoor, and Comfort, and may select one of them to tune vehicle 60104 performance accordingly.

Similarly, the digital twin 60136 provides a view of one or more operational states, aspects, parameters, etc. of the vehicle 60104, or its components, subsystems, or environment, based on the owner's requirements. may be presented to A fleet monitoring view may allow the owner to track and monitor the movement/route/status of one or more vehicles. A driver behavior monitoring view may allow the owner to monitor instances of unsafe or unsafe driving by the driver. The insurance view can assist the owner in determining a vehicle insurance policy quote based on the condition of the vehicle. The compliance view can show the vehicle's compliance status with respect to emissions/pollutants and other regulatory mandates based on the vehicle's condition.

Similarly, the digital twin 60136 may present a rider of the vehicle 60136 with a view showing aspects relevant to the rider. For example, the rider may be provided with an experience optimization view that allows the rider to select an experience mode to personalize the riding experience based on the rider's preferences/riding objectives. A rider can select from one or more experience modes including comfort mode, sport mode, high efficiency mode, work mode, entertainment mode, sleep mode, relax mode, and long travel mode.

FIG. 67 is a diagram illustrating a service and maintenance view presented to a vehicle user including a driver 60244, a manufacturer 60240, and a dealer 60702 of a vehicle 60104, according to an exemplary embodiment. The service & maintenance view provided by the digital twin allows a user, such as dealer 60702, to monitor the health of one or more components or subsystems of vehicle 60104. The view shows some major components including engine 60904, steering 60908, battery 60912, exhaust & emissions 60916, tires 60920, shock absorbers 60924, brake pads 60928 and gearbox 60932. Dealer 60702 can click on a component's icon to view detailed data and diagnostics associated with that component. For example, digital twin 60136 may present analysis related to parameters such as vibration 60936 and temperature 60940 as well as historical vehicle data 60944 and real-time series sensor data 948 to dealer 60702 . The digital twin 60136 can also perform a health scan to find no engine health issues and present a "0 issues detected" message to the dealer 60702. The digital twin 60136 may also allow the dealer 60702 to perform a full health scan on the complete vehicle (rather than a component-by-component scan). The digital twin may assist Dealer 60702 in diagnosing and resolving issues. In this example, the digital twin detected two issues during a full health scan: a loose shock absorber and a faulty spark plug wire.

In embodiments, the digital twin 60136 may also help predict when one or more components of the vehicle should undergo maintenance. The Digital Twin 60136 predicts expected wear and failure of vehicle 60104 components by examining historical and current operational data, thereby reducing the risk of unscheduled downtime and the need for scheduled maintenance. can be reduced. Instead of over-maintaining the vehicle 60104, any problems predicted by the digital twin 60136 may be addressed in a proactive or just-in-time manner to avoid costly downtime, repair or replacement. .

The digital twin 60136 may collect on-board data, including real-time sensor data regarding components that may be communicated via the vehicle's 60104 CAN network. Digital twin 60136 may also collect historical or other data regarding vehicle statistics and maintenance, including data regarding repairs and repair diagnostics, from database 60118 .

The predictive analytics driven by the artificial intelligence system 60112 deconstructs the data, searches for correlations and employs predictive modeling to determine the condition of the vehicle 60104, the need for maintenance of one or more components and Predict remaining useful life.

The cloud computing platform 60124 uses artificial intelligence (various experts described throughout this disclosure) for condition monitoring, anomaly detection, failure prediction, and predictive maintenance of one or more components of the vehicle 60104 using the digital twin 60136. system, artificial intelligence system, neural network, supervised learning system, machine learning system, deep learning system, and any other system); , may include a system that trains on a training set of data.

In an embodiment, the cloud computing platform 60124 uses the digital twin 60136 to train the artificial intelligence system 60112 to perform predictive maintenance on the vehicle 60104 vehicle maintenance collected from data sources on a set of vehicle activities. It may also include a system for learning on a training set of results, parameters, and data.

In embodiments, the artificial intelligence system 60112 can train models such as predictive models (eg, various types of neural networks, classification-based models, regression-based models, and other machine learning models). In embodiments, training may be supervised, semi-supervised, or unsupervised. In embodiments, training may be performed using training data that may be collected or generated for training purposes.

An exemplary artificial intelligence system trains a vehicle predictive maintenance model. A predictive maintenance model may be a model that receives vehicle-related data and outputs one or more predictions or answers regarding the remaining life of vehicle 60104 . Learning data can be collected from multiple sources including vehicle or component specifications, environmental data, sensor data, operational information, and results data. The Artificial Intelligence System 60112 takes raw data, preprocesses it, and applies machine learning algorithms to generate predictive maintenance models. In embodiments, artificial intelligence system 60112 may store predictive models in a model data store within database 60118 .

The artificial intelligence system 60112 may train multiple predictive models to answer different predictive maintenance questions. For example, a classification model may be trained to predict failure within a given time window and a regression model may be trained to predict the remaining useful life of the vehicle 60104 or one or more components. good.

In embodiments, training may be based on feedback received by the system, also referred to as "reinforcement learning." In embodiments, the artificial intelligence system 60112 may receive a set of circumstances that led to the prediction (e.g., vehicle attributes, model attributes, etc.) and results related to the vehicle, and may update the model according to the feedback. good.

In embodiments, the artificial intelligence system 60112 uses clustering algorithms to identify hidden failure patterns in failure data and develop models for detecting uncharacteristic or anomalous behavior of one or more components. You can train. Failure data across multiple vehicles and their historical records may be clustered to understand how different patterns correlate with specific wear-down behaviors and develop maintenance plans to resonate with failures.

In embodiments, the artificial intelligence system 60112 may output a score for each possible prediction corresponding to each possible outcome of the prediction. For example, when using a predictive model that is used to determine the likelihood that a vehicle 60104 or one or more components will fail in the next week, the predictive model will give a score for the "fail" outcome and a "failure It may also output the score for the "never" result. The artificial intelligence system 60112 may then select the result with the higher score as the prediction. Alternatively, the system 60112 may output their respective scores to the requesting system. In an embodiment, the output from system 60112 includes probabilities of prediction accuracy.

FIG. 68 is an exemplary method used by the digital twin 60136 to detect vehicle 60104 failures and predict any future failures, according to an exemplary embodiment.

At 61002 , multiple streams of vehicle-related data from multiple data sources are received by digital twin 60136 . This includes vehicle specifications such as mechanical properties, data from maintenance records, operating data collected from sensors 60112, and historical data including failure data from multiple vehicles running at different times and under different operating conditions. included. At 61004, the raw data is cleaned by removing missing or noisy data that may occur due to some technical issues with the vehicle 60104 during data collection. At 61006, one or more models are selected for training with the digital twin 60136. Model selection is based on the types of data available in the digital twin 60136 and the desired results of the model. For example, failure data from the vehicle may not be available, or there may be only a limited number of failure data sets due to regular maintenance being performed. In such cases, classification or regression models may not work well, and clustering models may be the best fit. As another example, a fault detection model may be selected if the desired outcome of the model is to determine the current state of the vehicle and detect any faults, while the desired outcome is to determine future faults. , a remaining useful life prediction model may be selected. At 61008, one or more models are trained using the training data set and tested for performance using the test data set. At 61010, the learned model is used for failure detection and future failure prediction of vehicle 60104 on production data.

FIG. 69 is an exemplary embodiment showing deployment of digital twin 60136 to perform predictive maintenance of vehicle 60104. FIG. Digital twin 60136 receives data from database 60118 in real time or near real time. Database 60118 may store different types of data in different data stores. For example, the vehicle data store 61102 may store data related to vehicle identification and attributes, vehicle condition and event data, data from maintenance records, past driving data, notes from vehicle service engineers, and the like. Sensor data store 61104 may store sensor data from driving, including data from temperature, pressure, and vibration sensors, which may be stored as signals or time series data. The failure data store 61106 may store failure data from the vehicle 60104, including failure data for components or similar vehicles at different times and under different driving conditions. Model data store 61108 may store data associated with different prediction models, including failure detection models and remaining life prediction models.

The digital twin 60136 works with an artificial intelligence system to select one or more models based on the type and quality of data available and the desired answer or outcome. For example, if the intended use of the digital twin 60136 is to simulate what-if scenarios and predict how the vehicle will behave under such scenarios, the physical model 61110 is chosen. obtain. A fault detection and diagnostic model 61112 may be selected to determine the current state of health of the vehicle 60104 and any fault conditions. A simple fault detection model may use one or more condition indicators to distinguish between normal and faulty behavior, and may have thresholds for the condition indicators that, when exceeded, indicate a fault condition. good. A more complex model may train a classifier to compare values of one or more condition indicators to values associated with fault conditions and return probabilities that one or more fault conditions exist.

Remaining useful life (RUL) prediction models 61114 are used to predict future failures and may include degradation models 61116, survival models 61118 and similarity models 61120. An exemplary RUL prediction model may fit the time evolution of the condition indicator and predict how long it will take for the condition indicator to cross some threshold indicative of failure. Another model can compare the time evolution of the condition indicator with measured or simulated time series from similar systems that have gone into failure.

In embodiments, a combination of one or more of these models may be selected by the digital twin 60136.

The artificial intelligence system 60112 may include machine learning processes 61122, clustering processes 61124, analysis processes 61126, and natural language processes 61128. Machine learning process 61122 cooperates with digital twin 60136 to train one or more models as identified above. An example of such a machine-learned model is the RUL prediction model 61114. Model 61114 may be trained using training data set 61130 from database 60118 . The performance of model 61114 and classifier may then be tested using test data set 61132 .

A clustering process 61124 may be performed to identify failure patterns hidden in the failure data in order to train models for detecting uncharacteristic or aberrant behavior. Failure data across multiple vehicles and their historical records may be clustered to understand how different patterns correlate with specific wear behaviors. The analysis process 61126 performs data analysis on various data to identify insights and predict outcomes. Natural language processes 61128 work with digital twin 60136 to communicate achievements and results to the user of vehicle 60104 .

Outcomes 60234 may be in the form of modeling results 61136 , warnings and alarms 61138 , or remaining useful life (RUL) predictions 61140 . The digital twin 60136 may communicate with the user via multiple communication channels such as voice, text, gestures, etc. to communicate the outcome 61134.

In embodiments, the model may then be updated or enhanced based on the model results 61134. For example, the artificial intelligence system 60112 may receive the sequence of conditions and outcomes that led to the prediction of failure and may update the model based on the feedback.

FIG. 70 is a flow chart illustrating a method for generating a digital twin of a vehicle, according to certain embodiments of the present disclosure. At 61202, a request from a user, such as an owner, lessee, driver, fleet operator/owner, mechanic, etc., associated with a vehicle 60104 is sent through an interface provided on the vehicle 60104 or a user device 60140 carried by the user, such as Received by vehicle 60104 to provide vehicle 60104 status information. At 61204, the digital twin 60136 of the vehicle 60104 is processed by one or more processors based on one or more inputs regarding vehicle status from on-board diagnostic systems, telemetry systems, sensors located on the vehicle, and systems external to the vehicle. generated using At 61206, the user is presented through an interface with a version of vehicle 60104 state information determined by using vehicle 60104's digital twin 60136 as described above.

FIG. 71 is a perspective view illustrating an alternative architecture for a transportation system including a vehicle and a digital twin system, according to various embodiments of the present disclosure; The vehicle 60104 includes an edge intelligence system 61304 that provides 5G connectivity to systems external to the vehicle 60104, internal connectivity to the vehicle's 60104 array of sensors 60108 and data sources, and an onboard artificial intelligence system 60112. The edge intelligence system 61304 can also communicate with the artificial intelligence system 60130 of the digital twin system 60200 hosted on the cloud computing platform 60124. The digital twin system 60200 can be input from the edge intelligence system 61304 via an application programming interface (API).

The edge intelligence system 61304 helps provide specific intelligence locally at the vehicle 60104 instead of relying on cloud-based intelligence. This may include, for example, tasks that require low overhead computation and/or tasks that run under low latency conditions. This helps the system to perform reliably in limited network bandwidth situations and avoid dropouts.

FIG. 72 is a diagram illustrating a digital twin representing a combined set of states for both the vehicle and the vehicle's driver, according to certain embodiments of the present disclosure.

An integrated vehicle and driver twin 61404 may be created, such as by integrating the digital twin of the vehicle 60104 and the digital twin of the driver. In an embodiment, such an integration would normalize the 3D models used by each twin to represent a consistent scale, and link them via an API to provide periodic updates of each twin (current operating state of the vehicle and driver current physiological state, posture, etc.).

The integrated vehicle and driver twin can then work with the edge intelligence system 1304 to construct a vehicle experience based on the combined vehicle state 60116 and driver state 61408.

FIG. 73 is a schematic diagram illustrating scenarios in which an integrated vehicle and driver digital twin may configure the vehicle experience, according to an exemplary embodiment.

In an exemplary scenario, the integrated vehicle and driver twin 61404 has a set of IR cameras that track pupil size and eyelid movement, and sensors that track driver 60244's (slack) posture and (slowed) reaction time. Based on inputs from the set of 60108, it may be determined that the driver's state is "sleepy." The Twin can also determine that the vehicle is "unstable" based on tracking speed, lateral position, turn angle, and course of travel. Integrated vehicle and driver twin 61404 may communicate with driver 60244 to warn driver 60244 of the potential safety hazards of driving in such conditions. Alternatively, the integrated vehicle and driver twin 61404 can be activated by one or more steps to wake the driver, such as turning on the music or turning up the volume, and/or by switching the vehicle to autopilot or autosteer mode. Steps may be taken to ensure driver and vehicle safety.

As another example, the integrated vehicle and driver twin can use information about vehicle state (e.g., fuel level) and driver state (e.g., time since driver last ate) to determine preferred fuel provider A point suggestion function may be activated that suggests detours along the scheduled route to good dining places that pass near the .

In embodiments, a combined vehicle-rider twin may be created, such as by combining the digital twin of the vehicle 60104 with the digital twin of the rider. In an embodiment, such an integration would normalize the 3D models used by each of the twins to represent a consistent scale, and link them via an API to provide periodic updates of each twin (including the vehicle's current operating state and This may be achieved by obtaining the rider's current physiological state, posture, etc.).

In an embodiment, when a second rider enters the vehicle, the combined vehicle-rider twin is updated.

In embodiments, an integrated vehicle and rider twin can work with an edge intelligence system 61304 to configure a vehicle experience based on combined vehicle and rider states.

For example, the combined vehicle-rider twin may determine that the rider status is "fatigued" based on inputs such as from one or more sensors 60108. In an embodiment, a sheet-integrated, sensor-equipped fabric wrapped around a portion of the rider's body may assist the twin in determining rider status. It may also be determined that the twin includes high traffic congestion and damaged road conditions where the vehicle condition is high. Twins may operate seat-integrated robotic exoskeleton elements to provide functional support to the rider, including arm, leg, back, and neck/head support. Alternatively, the twin may activate seat-integrated, sensor-enabled cloth electro-stimulation elements wrapped around parts of the rider's body, including torso, legs, etc., to provide relaxation and comfort to the rider. .

As another example, an integrated vehicle and rider twin may determine that the rider state is "stunned" based on input from one or more sensors 60108, or the like. In an embodiment, a sheet-integrated, sensor-equipped fabric wrapped around a portion of the rider's body may assist the twin in determining rider status. Also, the twin may determine that the vehicle conditions include rain conditions. The twin is a sheet-integrated, sensor-enabled fabric heating element or mid-infrared (penetrating heat) wrapped around parts of the rider's body, including torso, legs, etc., to provide warmth and comfort to the rider. may be activated.

In embodiments, a digital twin is network-recognized (e.g., by having a network-recognized device identifier, such as the device identifier of a mobile phone, laptop, tablet, or other computing device) and/or Or it can represent a set of items contained in a vehicle, such as those identified by in-vehicle sensors such as cameras, including those that use computer vision for object recognition. The digital twin may thus provide the user's view of the vehicle's internal content depicting the presence or absence of the item so that the user can confirm the same. This may include finding lost items, checking the existence of items necessary for travel (such as reconciliation with packing lists, including digital packing lists), sports equipment, food, carrying seats, umbrellas, or other accessories or personal belongings of the user. can be useful for confirming the existence of items in In embodiments, a digital twin of a vehicle may be integrated with, or information from, a set of digital twins representing other items, including items of personal belongings of the user of the digital twin. In embodiments, an application, such as a mobile application, such as by or linked to a vehicle manufacturer or dealer, includes vehicle accessories and a typical set of items typically transported or stored on the vehicle. may be provided for tracking a user's personal items, including items, via a series of digital twins each representing some or all of the items. Users may identify an Item by name or description, by linking to an Item (e.g., by linking to an identifier on an e-commerce site (or a communication from such site, such as a confirmation email indicating a purchase)). You may be prompted to enter the item by capturing a picture of the item, by capturing the item's QR code, barcode, etc., or by other technology. based (e.g., by obtaining dimensions, images, and other attributes from relevant data sources such as e-commerce sites or providers) or based on actual images (structured light, LIDAR, or other may be represented by a set of digital twins that may be sized based on dimensional information captured during image capture, such as using inference techniques.In mobile applications, users track their personal belongings. You can indicate your wishes, in this case tag-based systems (e.g. RFID systems), label-based systems (e.g. QR systems), sensor-based systems (e.g. using cameras and other sensors), network-based systems A location tracking system (such as an IoT system) can track the location of a personal property, hi embodiments, the location information from the location tracking system may represent the user's vehicle, the location within the user's vehicle, An item can be represented in a set of digital twins such as (in a vehicle digital twin), a location in a user's home (such as in a home digital twin), a location in a user's workplace (such as in a workplace digital twin), etc. Embodiments In , a user can select an item within a mobile application, such as from a list or menu, or via a search function, and the mobile application retrieves the appropriate digital twin, based on the item's current location. The item will be displayed within the digital twin.

Referring to Figure 74, the artificial intelligence system 65248 is a machine for performing analysis, simulation, decision-making and forecasting related to one or more data processing, data analysis, simulation generation and simulation analysis of transportation A learning model 65102 may be defined. Machine learning models 65102 are algorithms and/or statistical models that perform specific tasks without the use of explicit instructions, relying instead on patterns and inference. Machine learning model 65102 builds one or more mathematical models based on training data to make predictions and/or decisions without being explicitly programmed to perform a specific task. The machine learning model 65102 may receive sensor data input, including event data 65124 and state data 65702 associated with one or more of the transportation entities, as learning data. The sensor data input to the machine learning model 65102 trains the machine learning model 65102 to perform analysis, simulation, decision-making, and prediction regarding one or more of data processing, data analysis, simulation creation, and simulation analysis of transportation entities. May be used to perform creation. The machine learning model 65102 may also use input data from users or users of information technology systems. Machine learning models 65102 may include artificial neural networks, decision trees, support vector machines, Bayesian networks, genetic algorithms, any other suitable form of machine learning models, or combinations thereof. Machine learning model 65102 may be learned through supervised learning, unsupervised learning, reinforcement learning, self-learning, feature learning, sparse dictionary learning, anomaly detection, association rules, combinations thereof, or any other suitable algorithm for learning. It may be configured to learn.

The artificial intelligence system 65248 may also define a digital twin system 65330 to create digital replicas of one or more transportation entities. One or more digital replicas of the transport entity may use substantially real-time sensor data to provide a substantially real-time virtual representation of the transport entity, one of the one or more transport entities. A simulation of the above possible future states is provided. A digital replica exists simultaneously with the vehicle or vehicles being replicated. A digital replica is a copy of both the physical elements and characteristics of the vehicle or vehicles being replicated and, in embodiments, the dynamics of the vehicle or vehicles being replicated throughout a lifestyle. Or provide multiple simulations. A digital replica is a virtual extrapolation of sensor data, for example in the design stage before one or more vehicles are constructed or manufactured, or during or after the construction or manufacture of one or more vehicles. to simulate the conditions of one or more vehicles to provide a virtual simulation of the vehicles. For example, during high stress, after a period of time where component wear may be an issue, during maximum throughput operation, after one or more virtual or planned improvements have been made to one or more vehicles, or any other suitable hypothetical situation, and so on. In some embodiments, the machine learning model 65102 predicts possible improvements to one or more transportation entities, predicts when one or more components of one or more transportation entities may fail. , and/or suggest possible improvements to one or more of the transport entities, such as changes in timing settings, placement, components, or any other suitable modifications to the transport entities, for simulation with the digital replica; Virtual situations may be predicted automatically. A digital replica enables simulation of one or more vehicles during both their design and operational stages, as well as simulation of virtual operating conditions and configurations for one or more vehicles. to Digital replicas can include nearly any temperature, wear, light, vibration, etc. within, on, and around each component of one or more transport entities, as well as, in some embodiments, within one or more transport entities. By facilitating the observation and measurement of type metrics, it allows for immense analysis and simulation of one or more transportation entities. In some embodiments, machine learning model 65102 may process sensor data, including event data 65124 and state data 65702, to define simulation data for use by digital twin system 65330. The machine learning model 65102, for example, receives state data 65702 and event data 65124 associated with a particular one of the plurality of transit modes, and performs a series of operations on the state data 65702 and event data 65124. , the state data 65702 and event data 65124 can be formatted into a format suitable for use by the digital twin system 65330 in creating a digital replica of the transit system. For example, one or more transport entities may include robots configured to augment products on adjacent assembly lines. The machine learning model 65102 may collect data from one or more sensors located on, near, in, and/or around the robot. The machine learning model 65102 may perform operations on sensor data, process the sensor data into simulation data, and output the simulation data to the digital twin system 65330. The Digital Twin Simulation 65330 may use the simulation data to create one or more digital replicas of the robot, where the simulation measures, for example, temperature, wear, speed, rotation, and vibration of the robot and its components. Including metrics. The simulation may be a substantially real-time simulation, allowing a human user of information technology to view the simulation of the robot, its associated metrics, and the metrics associated with its components in substantially real-time. to be able to The simulation may be in a predictive or hypothetical situation, where a human user of information technology may interact with the predictive or hypothetical simulation of the robot, its associated metrics, and its components. allow you to browse.

In some embodiments, the machine learning model 65102 and the digital twin system 65330 process the sensor data and create a digital replica of a set of transits for multiple transits to enable the design of related groups of transits, in real-time. Simulations, predictive simulations, and/or virtual simulations may be facilitated. A digital replica of a fleet of vehicles is used to provide a substantially real-time virtual representation of the fleet of vehicles and to provide a simulation of one or more possible future states of the fleet of vehicles. can use real-time sensor data for A digital replica exists concurrently with the set of vehicles being replicated. The digital replica provides one or more simulations of both the physical elements and characteristics of the replicated transit set and its dynamics in a lifestyle-wide embodiment of the replicated transit set. One or more simulations, such as a wireframe virtual representation of one or more transport entities that can be viewed on a monitor, using augmented reality (AR) devices, or using virtual reality (VR) devices , may include visual simulations. The visual simulation can be manipulated by a human user of the information technology system, such as by zooming or highlighting components of the simulation and/or providing an exploded view of one or more vehicles. It can be. Digital replicas allow virtual extrapolation of sensor data, e.g., at the design stage before one or more vehicles are constructed or fabricated, or during or after construction or fabrication of one or more vehicles. A virtual simulation of the transporter ensemble may be provided by simulating the state of the transporter ensemble with . For example, during high stress, after a period of time where component wear may be an issue, during maximum throughput operation, after one or more virtual or planned improvements have been made to the vehicle set, or any other appropriate hypothetical situations of In some embodiments, the machine learning model 65102 predicts possible improvements to the set of transport entities, predicts when one or more components of the set of transport entities may fail, and/or or automatically predict virtual situations for simulation with digital replicas, such as suggesting possible improvements to the set of transport entities, such as timing, placement, components, or any other suitable changes to the transport entities. You may The digital replica enables the simulation of the fleet of vehicles during both the design and operational phases of the fleet of vehicles, and enables the simulation of virtual operational conditions and configurations of the fleet of vehicles. The digital replicas can be of almost any type of metric, including temperature, wear, light, vibration, etc. within, on, and around each component of the set of transport entities, as well as in some embodiments, within the set of transport entities. allows for immense analysis and simulation of one or more transport entities by facilitating the observation and measurement of . In some embodiments, machine learning model 65102 may process sensor data, including event data 65124 and state data 65702, to define simulation data for use by digital twin system 65330. The machine learning model 65102, for example, receives state data 65702 and event data 65124 associated with a particular transportation entity of a plurality of transportation entities, performs a series of operations on the state data 65702 and event data 65124 to State data 65702 and event data 65124 can be formatted in a format suitable for use by digital twin system 65330 in creating a digital replica of a set of transportation entities. For example, a set of transport entities may include a die machine configured to place the product on a conveyor belt, a conveyor belt configured to place the product on the die machine, and a conveyor belt as the product moves along the assembly line. A plurality of robots configured to add parts to the product may be included. The machine learning model 65102 may collect data from one or more sensors located on, near, in, and/or around each of the die machine, conveyor belt, and plurality of robots. The machine learning model 65102 may perform operations on sensor data to process the sensor data into simulation data and output the simulation data to the digital twin system 65330. The Digital Twin Simulation 65330 may use the simulation data to create one or more digital replicas of the die machine, the conveyor belt, and the plurality of robots, the simulation including the die machine, the conveyor belt, and the plurality of robots and including, for example, indicators such as temperature, wear, speed, rotation, and vibration of those components. The simulation may be a substantially real-time simulation in which a human user of information technology can substantially simulate a die machine, a conveyor belt, and a plurality of robots, metrics therefor, and metrics about their components. can be viewed in real time. A simulation may be a predictive or hypothetical situation in which a human user of information technology is asked to describe a die machine, a conveyor belt, and a plurality of robots, metrics associated therewith, and metrics associated with their components. It may be possible to view predictive or virtual simulations.

In some embodiments, the machine learning model 65102 may prioritize collection of sensor data for use in one or more digital replica simulations of the transit system. The machine learning model 65102 learns using sensor data and user input, thereby learning what types of sensor data are most effective in creating one or more digital replica simulations of transportation facilities. may For example, the machine learning model 65102 may find that a particular transport entity has dynamic characteristics such as component wear and throughput that are affected by temperature, humidity, and load. The machine learning model 65102 may, through machine learning, prioritize the collection of sensor data related to temperature, humidity, and load, and convert the prioritized types of sensor data into simulation data for output to the digital twin system 65330. processing may be given priority. In some embodiments, the machine learning model 65102 is simulated transport such that more and/or better data of the preferred type can be used in the transport simulation via its digital replica. It may be suggested to users of information technology systems to implement more and/or different sensors of preferred types in information technology near and around the body.

In some embodiments, the machine learning model 65102 determines what type of sensor data is processed into simulation data for transmission to the digital twin system 65330 based on one or both of the modeling objectives and the quality or type of sensor data. It may be configured to learn to determine what to do. Modeling goals may be objectives set by the user of the information technology system or may be predicted or learned by the machine learning model 65102 . Examples of modeling goals include creating digital replicas that can show the throughput dynamics of an assembly line, such as conveyor belts, assembly machines, one or more products, and other configurations of the transportation ecosystem. It may include collection, simulation, and modeling of element heat, power, component wear, and other metrics. A machine learning model 65102 learns to determine what types of sensor data need to be processed into simulation data for transmission to the digital twin system 65330 in order to implement such a model. may be configured. In some embodiments, the machine learning model 65102 analyzes what type of sensor data is being collected, the quality and quantity of the sensor data being collected, and what the sensor data being collected represents. may be processed into simulation data for use by the digital twin system 65330 in achieving modeling goals, depending on which types of sensor data are relevant and/or not relevant to achieving modeling goals. Decisions, predictions, analyzes and/or determinations may be made to prioritize, improve and/or achieve the quality and quantity of sensor data available.

In some embodiments, an information technology system user may input modeling goals into the machine learning model 65102 . The machine learning model 65102 may learn to analyze the training data and output suggestions to users of information technology systems regarding what types of sensor data are most relevant to achieving modeling goals, e.g. Sensor data related to the achievement of modeling goals may be output, such as one or more types of sensors positioned in, above, or near. Or, sensors near the transport entity or transport entities involved in achieving the modeling goal are sufficient and/or not sufficient to achieve the modeling goal, add, remove, or rearrange sensors, etc. Different configurations of sensor types output suggestions to users of information technology systems as to how the machine learning model 65102 and digital twin system 65330 may better achieve modeling goals. In some embodiments, the machine learning model 65102 may be used to adjust collection rate, processing, storage, sampling rate, bandwidth allocation, bit rate, and other parameters of sensor data collection to achieve or better achieve modeling goals. attribute may be automatically incremented or decremented. In some embodiments, the machine learning model 65102 is used to optimize collection rate, processing, storage, sampling rate, bandwidth allocation, bit rate, and sensor data collection to achieve or better achieve modeling goals. Suggestions or predictions related to increasing or decreasing other attributes may be made to users of information technology systems. In some embodiments, the machine learning model 65102 uses sensor data, simulation data, previous, current, and/or future digital replica simulations of one or more vehicles of the plurality of vehicles to Modeling goals may be automatically generated and/or suggested. In some embodiments, modeling goals automatically created by the machine learning model 65102 may be automatically implemented by the machine learning model 65102. In some embodiments, the modeling goals automatically created by the machine learning model 65102 are suggested to users of the information technology system, and modified by the user, such as after modifications have been made to the modeling goals suggested by the user. It may be performed only after acceptance and/or partial acceptance.

In some embodiments, a user may enter one or more modeling goals, for example, by entering one or more modeling commands into an information technology system. The one or more modeling commands may include, for example, commands for creating a digital replica simulation of a transportation entity or set of transportation entities for the machine learning model 65102 and the digital twin system 65330, where the digital replica simulation is It may include commands for one or more of real-time simulation and virtual simulation. Modeling commands may include, for example, what type of sensor data to use, the sampling rate of the sensor data, and other parameters of the sensor data used in one or more digital replica simulations. In some embodiments, the machine learning model 65102 may be configured to predict modeling commands, such as by using previous modeling commands as learning data. The machine learning model 65102 may be used, for example, to facilitate one or more simulations of transportation that may be useful for transportation management and/or to identify potential transportation problems or possible improvements to transportation. Predictive modeling commands may be suggested to users of information technology systems so that they can be easily identified.

In some embodiments, the machine learning model 65102 may be configured to evaluate a set of one or more virtual simulations of transportation entities. A set of virtual simulations is performed by the machine learning model 65102 and by the digital twin system 65330, as a result of one or more modeling commands, as a result of one or more modeling objectives, by one or more modeling commands, by the machine learning model 65102. It may be generated by prediction or by a combination thereof. The machine learning model 65102 may evaluate the set of virtual simulations based on one or more user-defined metrics, one or more metrics defined by the machine learning model 65102, or a combination thereof. In some embodiments, the machine learning model 65102 may evaluate each of the virtual simulations of the set of virtual simulations independently of each other. In some embodiments, the machine learning model 65102 analyzes the virtual simulations of the set of virtual simulations, for example, by ranking the virtual simulations or creating a hierarchy of virtual simulations based on one or more metrics. may be evaluated in relation to each other.

In some embodiments, the machine learning model 65102 is the output of the machine learning model 65102 and one or more model interpretations to facilitate human understanding of information and insights related to cognition and processes of the machine learning model 65102. may include a probability system, i.e., by one or more model interpretability systems, the machine learning model 65102 is outputting "what" as well as "why" its output, and which process is Make it human-readable as to what led to 65102 formulating the output. The one or more model interpretability systems are also used by human users to improve and guide the training of the machine learning model 65102, to help debug the machine learning model 65102, to help recognize biases in the machine learning model 65102. can be used. One or more model interpretable systems include Linear Regression, Logistic Regression, Generalized Linear Models (GLM), Generalized Additive Models (GAM), Decision Trees, Decision Rules, RuleFit, Naive-Bay-Classifier Bayes Classifier). K-Nearest Neighbor Algorithm, Partial Dependence Plot, Individual Conditional Expectation (ICE), Cumulative Local Effects (ALE) Plot, Feature Interaction, Permuted Feature Importance, Global Surrogate Model, Local Surrogate (LIME) Model, Scoped Rules , that is, Anchor, Shapely. e. Anchors, Shapley values, Shapley additive explanations (SHAP), feature visualization, network dissection, or any other suitable machine learning interpretability implementation. In some embodiments, one or more model interpretability systems may include a model dataset visualization system. A model dataset visualization system is configured to automatically provide a human user of an information technology system with visual analysis associated with sensor data, simulation data, and the distribution of values of data nodes of a machine learning model 65102. be.

In some embodiments, the machine learning model 65102 may include and/or implement an embedded model interpretable system such as a Bayesian Case Model (BCM) or Glassbox. The Bayes-Case model uses Bayes-Case-based inference, prototype classification, and clustering to facilitate human understanding of data such as sensor data, simulation data, and data nodes of the machine learning model 65102. In some embodiments, the model interpretability system uses glassbox interpretability such as Gaussian processes to facilitate human comprehension of data such as sensor data, simulation data, and data nodes of the machine learning model 65102. may include and/or implement a method of

In some embodiments, the machine learning model 65102 may include and/or implement testing with concept activation vectors (TCAVs). TCAV predicts that the machine learning model 65102 "runs", "does not run", "powered", "unpowered" from examples by a process that involves defining concepts, determining concept activation vectors, and computing directional derivatives. , "robot", "human", "truck", or "ship" to learn human-interpretable concepts. By learning human interpretable concepts, objects, states, etc., TCAV enables the machine learning model 65102 to describe transportation entities and the data collected therefrom in a form easily understood by human users of information technology systems. may allow outputting useful information related to

In some embodiments, the machine learning model 65102 is an artificial neural network, e.g., "learns" to perform a task by considering examples and without being explicitly programmed with task-specific rules. and/or may include a connectionist system configured to. The machine learning model 65102 may be based on a collection of connected units and/or nodes that can act like artificial neurons that can emulate neurons in a biological brain in some way. Each unit and/or node may have one or more connections to other units and/or nodes. Units and/or nodes transmit information, eg, one or more signals, to other units and/or nodes, process signals received from other units and/or nodes, and transmit processed signals to other units and/or nodes. and/or may be configured to forward to a node. One or more of the units and/or nodes and connections between them may be assigned one or more numerical "weights." The assigned weights may be configured to facilitate learning, ie training, of the machine learning model 65102. The assigned weights may increase and/or decrease one or more signals between one or more units and/or nodes, and in some embodiments one or more of the weights may have one or more thresholds associated with . The one or more thresholds may be configured such that signals are transmitted between one or more units and/or nodes when the signals and/or collective signals exceed the thresholds. In some embodiments, units and/or nodes are assigned to multiple layers, and each layer can have one or both of inputs and outputs. The first layer may be configured to receive training data, transform at least a portion of the training data, and transmit the training data and a signal associated with the transform to the second layer. A final layer may be configured to output an estimate, conclusion, product, or other result of processing one or more inputs by the machine learning model 65102 . Each of the layers may perform one or more types of transformations, and one or more signals may pass through one or more layers one or more times. In some embodiments, the machine learning model 65102 employs deep learning and is configured to include one or more hidden layers such as deep neural networks, deep belief networks, recursive neural networks, and/or It may be modeled and/or configured at least in part as a convolutional neural network.

In some embodiments, the machine learning model 65102 is a decision tree, e.g., a tree-based prediction configured to identify one or more observations based on an input and determine one or more conclusions. It may be and/or include a model. Observations may be modeled as one or more "branches" of the decision tree, and conclusions may be modeled as one or more "leaves" of the decision tree. In some embodiments, the decision tree may be a classification tree. A classification tree may include one or more leaves representing one or more class labels and one or more branches representing one or more connections of features configured to derive the class labels. In some embodiments, the decision tree may be a regression tree. Regression trees may be constructed such that one or more of the target variables may take continuous values.

In some embodiments, the machine learning model 65102 is a support vector machine, e.g., a set of related supervised learning methods configured for use in one or both of classification and regression-based modeling of data. may also include and/or include The support vector machine may be configured to predict whether new examples fall into one or more categories, the one or more categories being configured during training of the support vector machine.

In some embodiments, the machine learning model 65102 performs regression analysis to determine and/or estimate relationships between one or more inputs and one or more features of the one or more inputs. may be configured to execute Regression analysis may include linear regression, and the machine learning model 65102 may calculate a single straight line that best fits the input data according to one or more mathematical criteria.

In embodiments, inputs to a machine learning model 65102 (such as a regression model, Bayesian network, supervised model, or other type of model) are processed using machine learning algorithms to test the effect of various inputs on the accuracy of the model 65102. It may be tested, such as by using a test data set that is independent of the data set used to create and/or train the model. For example, inputs to a regression model may be removed, including single inputs, pairs of inputs, triplets, etc., to determine whether the absence of inputs causes a significant deterioration in the success of model 65102. good. This can assist in recognizing inputs that are actually correlated (eg, linear combinations of the same underlying data), overlapping inputs, or similar inputs. A comparison of the model's success identifies the input (out of several similar ones) that produces the least "noise" in the model, has the lowest cost and the most impact on the model's effectiveness, and so on. , it may be useful to select among alternative input datasets that provide similar information. Therefore, input variation and testing of the effect of input variation on model effectiveness can be used to prune or enhance model performance for any of the machine learning systems described throughout this disclosure.

In some embodiments, the machine learning model 65102 may be and/or include a Bayesian network. A Bayesian network may be a probabilistic graphical model constructed to represent a set of random variables and conditional independence of the set of random variables. Bayesian networks may be constructed to represent random variables and conditional independence via directed acyclic graphs. A Bayesian network may include one or both of a dynamic Bayesian network and an influence diagram.

In some embodiments, the machine learning model 65102 is supervised learning, i.e. one or more configured to build a mathematical model of a training data set comprising one or more inputs and a desired output May be defined via multiple algorithms. Training data may consist of a set of training examples, each of which has one or more inputs and a desired output, ie, a supervisory signal. Each of the training examples may be represented in the machine learning model 65102 by an array and/or a vector, ie a feature vector. Learning data may be represented by matrices in the machine learning model 65102 . Machine learning model 65102 may learn one or more functions through iterative optimization of an objective function, thereby learning to predict outputs associated with new inputs. When optimized, the objective function may provide the machine learning model 65102 with the ability to accurately determine outputs for inputs other than those included in the training data. In some embodiments, the machine learning model 65102 may be defined via one or more supervised learning algorithms such as active learning, statistical classification, regression analysis, and similarity learning. Active learning may involve the machine learning model 65102 interactively interrogating users and/or information sources to label new data points with desired outputs. Statistical classification involves identifying, by a machine learning model 65102, to which set of subcategories, or subpopulations, a new observation belongs, based on a training set of data containing observations with known categories. It's okay. Regression analysis may involve estimating the relationship between a dependent variable, or outcome variable, and one or more independent variables, or predictors, covariates, and/or features, via a machine learning model 65102. Similarity learning may involve learning from examples by a machine learning model 65102 using a similarity function, which measures how similar or related two objects are. is designed to

In some embodiments, the machine learning model 65102 uses unsupervised learning, i.e., to build a mathematical model of a dataset containing only inputs by finding structures in the data such as groupings or clusterings of data points. may be defined via one or more algorithms configured to In some embodiments, the machine learning model 65102 may learn from test data that has not been labeled, classified, or categorized, ie training data. The unsupervised learning algorithm may include learning by machine learning model 65102 by identifying commonalities in training data and reacting based on the presence or absence of identified commonalities in new data. good. In some embodiments, machine learning model 65102 may generate one or more probability density functions. In some embodiments, the machine learning model 65102 follows one or more pre-specified criteria, such as following a similarity metric factored in by internal compactness, segregation, estimated density, and/or graph connectivity. It may be learned by performing a cluster analysis, such as assigning sets of values to subsets, or clusters.

In some embodiments, the machine learning model 65102 may be defined via semi-supervised learning, i.e., one or more algorithms that use training data where some training examples may lack training labels. good. Semi-supervised learning may be weakly supervised learning, and training labels may be noisy, restrictive, and/or inaccurate. Noisy, limited, and/or inaccurate training labels may be cheaper and/or less labor intensive to generate, and thus the machine learning model 65102 may be less costly and/or labor intensive. allows us to train on a larger set of training data with .

In some embodiments, the machine learning model 65102 is one or more algorithms, such as one or more algorithms using dynamic programming techniques such that the machine learning model 65102 can be trained by taking actions in the environment to maximize cumulative reward. may be defined via reinforcement learning of In some embodiments, the training data is represented as a Markov decision process.

In some embodiments, the machine learning model 65102 may be defined via self-learning, and the machine learning model 65102 uses external reward and external instruction, such as by employing a crossbar adaptive array (CAA). is configured to train using training data without The CAA may compute behavioral and/or emotional decisions about the outcome situation in a crossbar fashion, thereby driving machine learning model 65102 teaching through interactions between cognition and emotion.

In some embodiments, the machine learning model 65102 performs feature learning, i.e., to find increasingly accurate and/or appropriate representations of one or more inputs provided during training, e.g., in training data. It may be defined via one or more designed algorithms. Feature learning may include learning via principal component analysis and/or cluster analysis. Feature learning algorithms may include attempts by machine learning models 65102 to transform input training data such that the transformed input training data is useful while preserving the input training data. In some embodiments, the machine learning model 65102 may be configured to transform the input training data prior to performing one or more classifications and/or predictions on the input training data. Thus, the machine learning model 65102 may be configured to reconstruct input training data from one or more unknown data-generating distributions without necessarily matching an improbable configuration of the input training data according to the distribution. . In some embodiments, feature learning algorithms may be performed by machine learning model 65102 in a supervised, unsupervised, or semi-supervised manner.

In some embodiments, the machine learning model 65102 is defined through anomaly detection, i.e., by identifying rare and/or outlier instances of one or more items, events and/or observations. may Rare and/or outlier instances may be identified by the instances being significantly different from the majority pattern and/or characteristics of the training data. Unsupervised anomaly detection may involve detection of anomalies in an unlabeled training data set by the machine learning model 65102 under the assumption that the majority of the training data is "normal". Supervised anomaly detection may involve training on a dataset in which at least a portion of the training data is labeled as "normal" and/or "abnormal".

In some embodiments, the machine learning model 65102 may be defined via robot learning. Robot learning is the generation of one or more curricula by machine learning model 65102, a curriculum is a sequence of learning experiences, through exploration guided by machine learning model 65102 and social interaction with humans by machine learning model 65102. may include cumulative acquisition of new skills through Acquisition of new skills may be facilitated by one or more guidance mechanisms such as active learning, maturation, motor synergy, and/or imitation.

In some embodiments, the machine learning model 65102 may be defined via association rule learning. Association rule learning can involve discovering relationships between variables in the database by machine learning models 65102 to identify strong rules using some measure of "interestingness." Related rule learning may involve identifying, learning, and/or evolving rules for storing, manipulating, and/or applying knowledge. The machine learning model 65102 may be configured to learn by identifying and/or utilizing a set of relational rules, which collectively represent the knowledge captured by the machine learning model 65102. Relational rule learning may include one or more of a learning classifier system, inductive logic programming, and an artificial immune system. A learning classifier system is an algorithm that may combine a discovery component, such as one or more genetic algorithms, with a learning component, such as one or more algorithms for supervised learning, reinforcement learning, or unsupervised learning. be. Inductive logic programming is rule learning by a machine learning model 65102 using logic programming to express one or more of input examples, background knowledge, and hypotheses determined by the machine learning model 65102 during training. may include The machine learning model 65102 is configured to derive a hypothetical logic program encompassing all positive examples given an encoding of known background knowledge and a set of examples represented as a logic database of facts. good too.

Having thus described several aspects and embodiments of the present technology, it is to be appreciated various alterations, modifications, and improvements will readily occur to those skilled in the art. Such alterations, modifications, and improvements are intended to be within the spirit and scope of the technology described herein. For example, those skilled in the art will readily envision various other means and/or structures for performing the functions and/or obtaining the results and/or advantages described herein. All such variations and/or modifications are considered within the scope of the embodiments described herein.

Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific embodiments described herein. It is therefore to be understood that the foregoing embodiments are presented by way of illustration only and that within the scope of the appended claims and equivalents thereof, inventive embodiments may be practiced otherwise than as specifically described. want to be Moreover, any combination of two or more of the features, systems, articles, materials, kits, and/or methods described herein may be combined such that such features, systems, articles, materials, kits, and/or methods are mutually exclusive. included within the scope of this disclosure if not inconsistent with.

The embodiments described above may be implemented in any of a number of ways. One or more aspects and embodiments of the present application involving execution of a process or method are defined as a program executable by a device (e.g., a computer, processor, or other device) to perform or control the process or method. You can use commands.

As used herein, the term system means one or more computing devices, processors, modules, software, firmware, or circuits that operate independently or distributed to perform one or more functions. can be defined as any combination of A system can include one or more subsystems.

In this regard, the various inventive concepts are coded into one or more programs that, when executed on one or more computers or other processors, perform methods that implement one or more of the various embodiments described above. computer-readable storage medium (or plurality of computer-readable storage media) (e.g., computer memory, one or more floppy disks, compact disks, optical disks, magnetic tapes, flash memory, field programmable gate arrays, or other semiconductor device, or other tangible computer storage medium).

A computer-readable medium or medium may be transported such that a program or programs stored thereon can be loaded into one or more different computers or other processors to implement various of the aspects described above. It may be possible. In some implementations, a computer-readable medium may be a non-transitory medium.

The term "program" or "software" as used herein means any type of computer code or computer-implemented code that can be employed to program a computer or other processor to perform the various aspects as described above. Used in a generic sense to refer to a set of possible instructions. Furthermore, according to one aspect, one or more computer programs that, when executed, perform the methods of the present application need not reside on a single computer or processor to implement the various aspects of the present application. It should be understood that the implementation may be distributed in a modular fashion among a number of different computers or processors.

Computer-executable instructions may be in many forms, such as program modules, executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Typically the functionality of the program modules may be combined or distributed as desired in various embodiments.

Also, data structures may be stored in computer-readable media in any suitable form. For ease of illustration, data structures may be shown having fields that are related via position within the data structure. Such relationships may similarly be achieved by allocating storage for fields having positions within the computer-readable medium that convey the relationship between the fields. However, any suitable mechanism may be used to establish relationships between information in fields of data structures, such as the use of pointers, tags, or other mechanisms for establishing relationships between data elements.

Also, as described, some aspects may be embodied in one or more methods. Acts performed as part of a method may be ordered in any suitable manner. Thus, although illustrated as sequential acts in an exemplary embodiment, embodiments may be constructed in which acts are performed in a different order than illustrated, including performing some acts simultaneously.

Accordingly, the disclosure should not be considered limited to the particular embodiments described above. Various modifications, equivalent processes, and numerous structures to which this disclosure may be applied will be readily apparent to those skilled in the art to which this disclosure is directed upon review of this disclosure.

Although detailed embodiments of the present disclosure are disclosed herein, it is to be understood that the disclosed embodiments are merely exemplary of the disclosure, which may be embodied in various forms. Accordingly, specific structural and functional details disclosed herein are not to be construed as limiting, but merely as a basis for the claims and substantially any appropriate modifications that may be made by one of ordinary skill in the art. The detailed structure is to be construed as a representative basis for teaching various adaptations of the present disclosure.

While only certain embodiments of the disclosure have been shown and described, it will be appreciated that many changes and modifications can be made thereto without departing from the spirit and scope of the disclosure as set forth in the following claims. , will be apparent to those skilled in the art. All patent applications and patents (both foreign and domestic) and all other publications referenced herein are hereby incorporated in their entirety to the fullest extent permitted by law.

The methods and systems described herein can be deployed in part or in whole through machines executing computer software, program code and/or instructions on processors. The present disclosure may be embodied as a method on a machine, as a system or apparatus as part of or associated with a machine, or as a computer program product embodied in a computer readable medium executing on one or more of the machines. may In embodiments, the processor may be part of a server, cloud server, client, network infrastructure, mobile computing platform, stationary computing platform, or other computing platform. Processors include central processing units (CPUs), general purpose processing units (GPUs), logic boards, chips (e.g. graphics chips, video processing chips, data compression chips, etc.), chipsets, controllers, system-on-chips (e.g. RF systems on-chip, AI system-on-chip, video processing system-on-chip, etc.), integrated circuits, application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), approximate computation processors, quantum computation processors, parallel computation processors, neural networks processor, or other type of processor. A processor is a signal processor, digital processor, data processor, embedded processor, microprocessor, or coprocessor that can directly or indirectly facilitate the execution of program code or program instructions stored thereon (mathematical coprocessor, graphics co-processor, communication co-processor, video co-processor, AI co-processor, etc.). Further, a processor may enable execution of multiple programs, threads, and code. Threads may be executed concurrently to improve processor performance and facilitate concurrent operation of applications. As an implementation, the methods, program code, program instructions, etc. described herein may be implemented in one or more threads. Threads may spawn other threads that may have assigned priorities associated with them, and the processor may assign priority based on instructions provided in the program code or based on any other order. These threads may run. A processor, or any machine utilizing one, may include non-transitory memory for storing methods, code, instructions and programs as described herein and elsewhere. A processor may access non-transitory storage media through an interface that can store methods, code, and instructions such as those described herein and elsewhere. Storage media associated with processors for storing methods, programs, codes, program instructions or other types of instructions executable by a computing or processing device include CD-ROMs, DVDs, memory, hard disks, flash drives, RAM , ROM, cache, network-attached storage, server-based storage, etc., but not limited to.

A processor may include one or more cores, which may increase the speed and performance of multiprocessors. In embodiments, a process may be a dual-core processor, quad-core processor, other chip-level multiprocessor, etc. that combines two or more independent cores (sometimes called dies).

The methods and systems described herein can be used on servers, clients, firewalls, gateways, hubs, routers, switches, infrastructure-as-a-service, platforms-as-a-service, or other such computers. and/or may be deployed in part or in whole through a machine running computer software on networking hardware or systems. The software includes file servers, print servers, domain servers, internet servers, intranet servers, cloud servers, infrastructure as service servers, platform as service servers, web servers, secondary servers, host servers, distributed servers, failover servers, backups. It may be associated with a server, which may include other variants such as servers, server farms, and the like. Servers are among the interfaces that allow access to other servers, clients, machines, and devices through memory, processors, computer-readable media, storage media, ports (physical and virtual), communication devices, and wired or wireless media. May contain one or more. A method, program, or code described herein may be executed by a server. Additionally, other devices required for performing methods as described herein may be considered part of the infrastructure associated with the server.

Servers may provide interfaces to other devices, including clients, other servers, printers, database servers, print servers, file servers, communication servers, distributed servers, social networks, and the like. Additionally, this coupling and/or connection may facilitate remote execution of programs over a network. Networking some or all of these devices may facilitate parallel processing of a program or method at one or more locations without departing from the scope of this disclosure. Additionally, any of the devices connected to the server via an interface may include at least one storage medium capable of storing methods, programs, code and/or instructions. A central repository may provide program instructions to be executed on different devices. In this implementation, the remote repository may serve as a storage medium for program code, instructions, and programs.

Software programs may be associated with clients, which may include file clients, print clients, domain clients, Internet clients, intranet clients, and other variations such as secondary clients, host clients, distributed clients, and the like. A client may include memory, processors, computer-readable media, storage media, ports (physical and virtual), communication devices, and interfaces that may access other clients, servers, machines, and devices through wired or wireless media. may include one or more of Any method, program, or code described herein may be executed by a client. In addition, other equipment required for execution of methods as described herein can be considered part of the infrastructure associated with the client.

Clients may provide interfaces to other devices, including servers, other clients, printers, database servers, print servers, file servers, communication servers, distributed servers, and the like. Additionally, this coupling and/or connection may facilitate remote execution of programs over a network. Networking some or all of these devices may facilitate parallel processing of a program or method at one or more locations without departing from the scope of this disclosure. Additionally, any of the devices attached to the client via an interface may include at least one storage medium capable of storing methods, programs, applications, code and/or instructions. A central repository may provide program instructions to be executed on different devices. In this implementation, the remote repository may serve as a storage medium for program code, instructions, and programs.

The methods and systems described herein may be deployed in part or in whole through a network infrastructure. A network infrastructure may include computing devices, servers, routers, hubs, firewalls, clients, personal computers, communication devices, routing devices, and other active and passive devices, modules and/or components known in the art. may include elements such as Computing and/or non-computing device(s) associated with the network infrastructure may include storage media such as flash memory, buffers, stacks, RAM, ROM, etc., among other components. The processes, methods, program code, instructions described herein and elsewhere may be performed by one or more of the network infrastructure elements. The methods and systems described herein can be of any type, including those involving software as a service (SaaS), platform as a service (PaaS), and/or infrastructure as a service (IaaS) characteristics. may be adapted for use in private, community, or hybrid cloud computing networks or cloud computing environments.

The methods, program codes, and instructions described herein and elsewhere may be implemented in a cellular network having multiple cells. A cellular network may be either a frequency division multiple access (FDMA) network or a code division multiple access (CDMA) network. A cellular network may include mobile devices, cell sites, base stations, repeaters, antennas, towers, and the like. Cellular networks may be GSM, GPRS, 3G, 4G, 5G, LTE, EVDO, mesh, or other network types.

The methods, program codes, and instructions described herein and elsewhere may be implemented on or through mobile devices. Mobile devices may include navigation devices, cell phones, mobile personal digital assistants, laptops, palmtops, netbooks, pagers, e-book readers, music players, and the like. These devices may include, among other components, storage media such as flash memory, buffers, RAM, ROM, and one or more computing devices. A computing device associated with the mobile device may be capable of executing program codes, methods, and instructions stored thereon. Alternatively, mobile devices may be configured to execute instructions in cooperation with other devices. Mobile devices may communicate with a base station interfaced with a server and configured to execute program code. A mobile device may communicate over a peer-to-peer network, mesh network, or other communication network. The program code may be stored in storage media associated with the servers and executed by computing devices embedded within the servers. A base station may include a computing device and a storage medium. A storage medium may store program code and instructions that are executed by a computing device associated with the base station.

Computer software, program code, and/or instructions can be stored and/or accessed on machine-readable media, including: computer components, devices, and digital data used in computing for a period of time; Recording media; semiconductor storage known as random access memory (RAM); more permanent mass storage, such as forms of magnetic storage such as optical discs, hard disks, tapes, drums, cards; processor registers, cash meters, volatile memory , non-volatile memory; optical storage such as CDs, DVDs; removable media such as flash memory (e.g. USB sticks and keys), floppy disks, magnetic tapes, paper tapes, punch cards, stand-alone RAM disks, Zip drives, removable mass storage, offline, etc. dynamic memory, static memory, read/write storage, mutable storage, read-only, random access, sequential access, location addressable, file addressable, content addressable, network attached storage, storage area network, barcode, magnetic ink, Such as network attached storage, network storage, NVME access storage, PCIE attached storage, distributed storage, and other computer memory.

The methods and systems described herein may transform physical and/or intangible items from one state to another. The methods and systems described herein may also transform data representing physical and/or intangible items from one state to another.

Elements described and depicted herein, including flowcharts and block diagrams in the figures, imply logical boundaries between the elements. However, in accordance with software or hardware engineering practice, the depicted elements and their functionality may be represented as monolithic software structures, as stand-alone software modules, or as modules employing external routines, code, services, etc., or any combination thereof. As such, it may be implemented in a machine through computer executable code using a processor capable of executing program instructions stored therein, and all such implementations may fall within the scope of the present disclosure. Examples of such machines include personal digital assistants, laptops, personal computers, mobile phones, other portable computing devices, medical equipment, wired or wireless communication devices, transducers, chips, calculators, satellites, tablet PCs, electronic Books, gadgets, electronic devices, devices, artificial intelligence, computing devices, network appliances, servers, routers, etc. may include, but are not limited to. Further, the elements depicted in flowcharts or block diagrams, or other logical components, can be implemented by machines capable of executing program instructions. Thus, while the foregoing drawings and description illustrate functional aspects of the disclosed system, the specific arrangement of software for implementing those functional aspects may be explicitly described or contextualized. No inference should be drawn from these statements unless it is clear from Likewise, it is understood that the various steps identified and described above may vary and the order of steps may be adapted to suit a particular application of the techniques disclosed herein. Will. All such variations and modifications are intended to fall within the scope of this disclosure. As such, the depiction and/or description of an order for various steps does not imply a particular order of execution for those steps unless required by a particular application or explicitly stated or apparent from context. should not understand.

The methods and/or processes described above, and the steps associated therewith, may be implemented in hardware, software, or any combination of hardware and software suitable for a particular application. The hardware may include general purpose computers and/or special purpose computing devices or specific computing devices or specific aspects or components of specific computing devices. The processes may be implemented in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices, along with internal and/or external memory. The process may also, or alternatively, be embodied in an application specific integrated circuit, programmable gate array, programmable array logic, or any other device or combination of devices that may be configured to process electronic signals. Additionally, it will be appreciated that one or more of the processes may be embodied as computer-executable code executable on a machine-readable medium.

Computer-executable code uses structured programming languages such as C, object-oriented programming languages such as C++, or other high-level or low-level programming languages (including assembly language, hardware description languages, database programming languages and techniques). and may be stored, compiled, or stored for execution on one of the above devices, as well as processors, processor architectures, or heterogeneous combinations of different hardware and software, or other machines capable of executing program instructions. may be interpreted. Computer software may employ virtualization, virtual machines, containers, dock facilities, porters, and other features.

Thus, in one aspect, the above-described methods and combinations thereof may be embodied in computer-executable code that performs its steps when executed on one or more computing devices. In another aspect, the method may be embodied in a system that performs its steps, may be distributed among devices in any number of ways, or all of the functionality may reside on a dedicated stand-alone device or other hardware device. may be integrated into In another aspect, means for performing the steps associated with the processes described above may include any of the hardware and/or software described above. All such permutations and combinations are intended to fall within the scope of this disclosure.

Although the present disclosure has been disclosed in connection with the preferred embodiments shown and described in detail, various modifications and improvements thereto will become readily apparent to those skilled in the art. Accordingly, the spirit and scope of the present disclosure are not to be limited by the foregoing examples, but are to be understood in the broadest sense permitted by law.

The use of the terms "a" and "an" and "the" and similar references in the context of describing the present disclosure (especially in the context of the claims below) may be otherwise indicated herein or otherwise apparent from the context. shall be construed to cover both the singular and the plural unless inconsistent with The terms “consisting of,” “having,” “including,” and “including” shall be construed as open-ended terms (i.e., meaning “including, but not limited to”) unless otherwise indicated. . Recitation of ranges of values herein is merely intended to serve as a shorthand method for referring individually to each separate value falling within the range, unless otherwise indicated herein; Values are incorporated herein as if individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples or exemplary language (e.g., "such as") provided herein is merely intended to better illuminate the present disclosure and unless otherwise claimed, does not limit the scope of The term "set" can include a set having a single member. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the disclosure.

While the foregoing written descriptions enable those skilled in the art to make and use what is presently considered to be the best mode thereof, those skilled in the art will readily recognize variations, modifications, and variations of the specific embodiments, methods, and examples herein. It will be understood and understood that combinations and equivalents exist. Accordingly, the present disclosure should not be limited by the above-described embodiments, methods, and examples, but should be limited by all embodiments and methods within the scope and spirit of the present disclosure.

All documents referenced in this document are hereby incorporated by reference as if fully set forth herein.

Claims (215)

A system for presenting a set of operating states of the vehicle to a user of the vehicle, comprising:
a portion of the vehicle having vehicle operating conditions;
a digital twin system that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
and an interface for said digital twin system for presenting said vehicle operating conditions to said user of said vehicle. 2. The system of claim 1, wherein the vehicle operating state is a vehicle maintenance state. 2. The system of claim 1, wherein the vehicle operating conditions are vehicle energy utilization conditions. 2. The system of claim 1, wherein the vehicle operating conditions are vehicle navigation conditions. 2. The system of claim 1, wherein the vehicle operating conditions are vehicle component conditions. 2. The system of claim 1, wherein the vehicle operating conditions are vehicle driver conditions. The system of claim 1, wherein inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. 2. The system of claim 1, further comprising an identity management system for managing a set of identities and roles for users of said vehicle. 9. The identity management system includes functionality for viewing, modifying, and configuring the digital twin system, wherein the functionality is based on identities from the set of identities of the user of the vehicle. System as described. The system of claim 1, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to systems external to the vehicle. The system of claim 1, wherein the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to the vehicle's set of sensors and data sources. The system of claim 1, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to an in-vehicle artificial intelligence system. 11. The system of claim 10, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. 11. The system of claim 10, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of driver-user usage activities. 11. The system of claim 10, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of rider-user usage activities. Further, a first neural for detecting the detected state of well-being of the rider user on board the vehicle through analysis of data collected from sensors located on the vehicle to collect physiological state of the rider user. a network;
a second neural network for optimizing operating parameters of the vehicle in response to the detected state of satisfaction of the rider-user to achieve a preferred state of satisfaction of the rider-user. Item 1. The system according to item 1. 4. The detected state of satisfaction of the rider user is the detected emotional state of the rider user, and the preferred state of satisfaction of the rider user is the preferred emotional state of the rider user. 17. The system according to 16. 17. The system of claim 16, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 17. The system of claim 16, wherein at least one of said neural networks is a hybrid neural network and includes a convolutional neural network. 17. The system of claim 16, wherein the second neural network optimizes the operating parameters based on correlations between vehicle operating conditions and rider satisfaction of the rider user. 16. The second neural network optimizes the operating parameters in real-time in response to the detection of the detected satisfaction state of the rider user by the first neural network. System as described. The first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. 17. The system of Claim 16. The operating parameters that are optimized include the route of the vehicle, the in-vehicle audio content, the speed of the vehicle, the acceleration of the vehicle, the deceleration of the vehicle, the proximity of objects along the route, and other parameters along the route. 17. The system of claim 16, wherein the system of claim 16, wherein the system influences at least one of the following: A method for presenting a set of vehicle states to a user of a vehicle, comprising:
obtaining parameter data for one or more components of the vehicle from one or more inputs;
updating a digital twin system of the vehicle with the parameter data to generate one or more operational states of the vehicle; and
providing an interface for presenting the one or more operational states of the vehicle to the user of the vehicle. 25. The method of claim 24, wherein the one or more vehicle operating states comprise one or more of a vehicle maintenance state, a vehicle energy utilization state, a vehicle navigation state, a vehicle component state, or a vehicle driver state. Method. 25. The method of claim 24, wherein inputs for the digital twin system include one or more of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. Further comprising managing a set of user identities and roles of the vehicle and configuring the digital twin system based on identities from the set of user identities of the vehicle. 25. The method of claim 24, wherein further configured to have one or more of a 5G connection to systems external to the vehicle, an internal 5G connection to the vehicle's set of sensors and data sources, or a 5G connection to an in-vehicle artificial intelligence system. 25. The method of claim 24, comprising inputting into the digital twin system via an API from the vehicle's edge intelligence system. 29. The method of claim 28, further comprising automatically configuring the digital twin system with an artificial intelligence system based on a training set of usage activities by a set of digital twin users. Further detecting the rider user boarding the vehicle by analyzing data collected from sensors deployed on the vehicle to collect physiological conditions of the rider user using a first neural network. detecting a satisfied state of satisfaction and, using a second neural network, operating the vehicle in response to the detected state of satisfaction of the rider user so as to achieve a preferred state of satisfaction of the rider user. 25. The method of claim 24, comprising optimizing parameters. 4. The detected state of satisfaction of the rider user is the detected emotional state of the rider user, and the preferred state of satisfaction of the rider user is the preferred emotional state of the rider user. 30. The method of claim 30. 25. The method of claim 24, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 31. The method of claim 30, wherein at least one of said neural networks is a hybrid neural network and comprises a convolutional neural network. 31. The method of claim 30, wherein the optimization of said operating parameters in said second neural network is based on a correlation between vehicle operating conditions and rider user satisfaction of said rider user. . 30. Optimizing said operating parameters in said second neural network in response to said detection of said detected satisfaction state of said rider user by said first neural network. described method. further comprising using the first neural network to form one or more connected nodes forming a directed cycle, wherein the first neural network processes data between the connected nodes; 31. The method of claim 30, further facilitating bi-directional flow of . The operating parameters that are optimized include the vehicle's path, in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the path, and 31. The method of claim 30, wherein at least one of approaching another vehicle is affected. A computer-implemented method for generating a digital twin of a vehicle, comprising:
receiving, via an interface, a request from a user of the vehicle to display status information of the vehicle;
generating, using one or more processors, a digital twin representation of the vehicle based on one or more user inputs based on the state information of the vehicle; and
using the interface to display the status information of the vehicle using the digital twin representation of the vehicle. 39. The method of claim 38, wherein the state information of the vehicle includes one or more of vehicle maintenance state, vehicle energy utilization state, vehicle navigation state, vehicle component state, or vehicle driver state. 39. The method of claim 38, wherein the user input for the digital twin representation includes one or more of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. . Further comprising managing a set of user identities and roles of the vehicle, and constructing the digital twin representation based on identities from the set of user identities of the vehicle. 39. The method of claim 38. further configured to have one or more of 5G connectivity to systems external to the vehicle, internal 5G connectivity to a set of sensors and data sources in the vehicle, or 5G connectivity to an in-vehicle artificial intelligence system. 39. The method of claim 38, comprising inputting the digital twin representation via an API from an edge intelligence system of the vehicle. 43. The method of claim 42, further comprising automatically constructing the digital twin representation with an artificial intelligence system based on a training set of usage activities by a set of digital twin users. A system for presenting a set of vehicle operating conditions to a vehicle driver, comprising:
a portion of a vehicle having a vehicle operating state;
a digital twin system that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
and an interface for said digital twin system for presenting said vehicle operating conditions to said driver of said vehicle. 45. The system of claim 44, wherein said interface for said digital twin system provides said driver with a 3D view showing a three-dimensional rendering of a model of said vehicle. 4. The interface for the digital twin system provides the driver with a navigational view for improved situational awareness through real-time information exchange with nearby vehicles, pedestrians, and infrastructure. 44. The system of claim 44. 45. The method of claim 44, wherein the interface for the digital twin system provides the driver with an energy view for determining battery/fuel status within the vehicle, including utilization and battery health. system. 45. The system of claim 44, wherein the interface for the digital twin system provides the driver with a value view for displaying the vehicle status and blue book values based on the vehicle status. system. The interface for the digital twin system provides a service and maintenance view for showing wear and failure of components of the vehicle and predicting the need for service, repair, or replacement based on conditions of the vehicle's condition. 49. A system according to claim 48, characterized in that it provides to the driver. 45. The system of claim 44, wherein the interface for the digital twin system provides the driver with a world view to show the vehicle immersed in a virtual reality (VR) environment. 45. The system of claim 44, wherein the vehicle operating state is a vehicle maintenance state. 45. The system of claim 44, wherein the vehicle operating conditions are vehicle energy utilization conditions. 45. The system of claim 44, wherein the vehicle operating state is a vehicle navigation state. 45. The system of claim 44, wherein the vehicle operating conditions are vehicle component conditions. 45. The system of claim 44, wherein the vehicle operating conditions are vehicle driver conditions. 45. The system of claim 44, wherein inputs for the digital twin system include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. 45. The system of claim 44, further comprising an identity management system for managing a set of identities and roles for users of said vehicle. 57. The identity management system includes functionality for viewing, modifying, and configuring the digital twin system, wherein the functionality is based on identities from the set of identities of the user of the vehicle. System as described. 45. The system of claim 44, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to systems external to the vehicle. 45. The system of claim 44, wherein the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to the vehicle's set of sensors and data sources. 45. The system of claim 44, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to an in-vehicle artificial intelligence system. 62. The system of claim 61, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. 62. The system of claim 61, wherein said digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by said driver. 62. The system of claim 61, wherein said digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by said driver. Further, a first neural network for detecting a detected state of well-being of the driver in the vehicle through analysis of data collected from sensors deployed in the vehicle to collect the physiological state of the driver. and,
45. A second neural network for optimizing operating parameters of the vehicle in response to the detected state of well-being of the driver to achieve a preferred state of well-being of the driver. System as described. 66. The system of claim 65, wherein the detected state of satisfaction of the driver is a detected emotional state of the driver and the preferred state of satisfaction of the driver is a preferred emotional state of the driver. . 66. The system of claim 65, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 66. The system of claim 65, wherein at least one of said neural networks is a hybrid neural network and includes a convolutional neural network. 66. The system of claim 65, wherein said second neural network optimizes said operating parameters based on correlations between vehicle operating conditions and driver satisfaction conditions of said driver. 66. The method of claim 65, wherein said second neural network optimizes said operating parameters in real-time in response to said detection of said detected well-being of said driver by said first neural network. system. The first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. 66. A system according to claim 65. The operating parameters that are optimized include the vehicle's path, in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the path, and 66. The system of claim 65, wherein at least one of approaching another vehicle is affected. A system for presenting a set of vehicle operating conditions to a vehicle manufacturer, comprising:
a vehicle having a vehicle operating state;
a digital twin system that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
and an interface for said digital twin system for presenting said vehicle operating conditions to said manufacturer of said vehicle. The interface for the digital twin system provides a design view for the manufacturer to inform the manufacturer in determining part of the optimal system architecture for a new vehicle model through generative design techniques. 74. The system of claim 73, wherein: The interface for the digital twin system converts a portion of the assembly view into the manufacturing assembly view to allow the manufacturer to run a reference model to optimize performance of the vehicle and its components and subsystems. 74. The system of claim 73, provided to a merchant. The interface is characterized by providing the manufacturer with a portion of the quality view to enable the manufacturer to perform simulations for quality testing of the vehicle and its components under real-world conditions. 74. The system of claim 73, wherein The interface enables the manufacturer to perform data analysis to calculate a wide range of metrics, build charts, graphs, and models to visualize the effects of changing parameters of the vehicle and its components on vehicle performance. 74. The system of claim 73, providing the manufacturer with a real-time analytical view for doing so. 74. The system of claim 73, wherein the interface for the digital twin system provides the manufacturer with a 3D view showing a three-dimensional rendering of the model of the vehicle. 12. The interface for the digital twin system provides the manufacturer with an energy view for determining battery/fuel status within the vehicle, including utilization and battery health. 73. The system of claim 73. 74. The method of claim 73, wherein the interface for the digital twin system provides the manufacturer with a value view for displaying the vehicle's condition and blue book value based on the vehicle's condition. system. The interface for the digital twin system provides a service and maintenance view for showing wear and failure of components of the vehicle and predicting the need for service, repair, or replacement based on conditions of the vehicle's condition. 74. The system of claim 73, provided to the manufacturer. 74. The system of claim 73, wherein the vehicle operating state is a vehicle maintenance state. 74. The system of claim 73, wherein the vehicle operating conditions are vehicle energy utilization conditions. 74. The system of claim 73, wherein the vehicle operating state is a vehicle navigation state. 74. The system of claim 73, wherein the vehicle operating conditions are vehicle component conditions. 74. The system of claim 73, wherein the vehicle operating condition is a vehicle driver condition. 73. The one or more inputs for the digital twin system comprise at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. System as described. 74. The system of claim 73, further comprising an identity management system for managing a set of identities and roles of users of said vehicle for whom consent for communication has been granted to said manufacturer. 88. The identity management system includes functionality for viewing, modifying, and configuring the digital twin system, wherein the functionality is based on identities from the set of identities of the user of the vehicle. System as described. 74. The system of claim 73, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to systems external to the vehicle. 74. The system of claim 73, wherein the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to the vehicle's set of sensors and data sources. 74. The system of claim 73, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to an in-vehicle artificial intelligence system. 74. The system of claim 73, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. 74. The system of claim 73, wherein said digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by one of said driver or said manufacturer. and a first neural network for detecting a detected state of well-being of the user on board the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the user; ,
73. A second neural network for optimizing operating parameters of the vehicle in response to the detected state of well-being of the user to achieve a preferred state of well-being of the user. System as described. 96. The system of claim 95, wherein the detected state of satisfaction of the user is a detected emotional state of the user and the preferred state of satisfaction of the user is the preferred emotional state of the user. . 96. The system of claim 95, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 96. The system of Claim 95, wherein at least one of said neural networks is a hybrid neural network and includes a convolutional neural network. 96. The system of claim 95, wherein said second neural network optimizes said operating parameters based on correlations between vehicle operating conditions and said user's satisfaction conditions. 96. The method of claim 95, wherein said second neural network optimizes said operating parameters in real-time in response to said detection of said detected satisfaction state of said user by said first neural network. system. The first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. 96. A system according to claim 95. The operating parameters that are optimized include the vehicle's path, in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the path, and 96. The system of claim 95, wherein at least one of approaching another vehicle is affected. A system for presenting a set of vehicle operating conditions to a vehicle dealer, comprising:
a vehicle having a vehicle operating state;
a digital twin system that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
and an interface for said digital twin system for presenting said vehicle operating conditions to said dealer of said vehicle. The interface provides the dealer with a configurator view for configuring a vehicle based on potential customer preferences by selecting compatible component and subsystem combinations from a set of available components. 104. The system of claim 103, wherein: The interface provides the dealer with a performance tuning view for changing or adjusting characteristics of one or more components to personalize the performance of the vehicle based on driver or rider preferences. 104. The system of claim 103, wherein: 106. The system of claim 105, wherein one of said components is an engine of said vehicle. 106. The system of claim 105, wherein one or more of said components are suspensions of said vehicle. 106. The system of claim 105, wherein one of said components is the body of said vehicle. 104. The system of claim 103, wherein the interface provides the dealer with a test drive view for enabling a potential customer of the vehicle to virtually test drive the vehicle. 110. The system of claim 109, wherein said vehicle is a used vehicle. 104. The system of claim 103, wherein the interface provides the dealer with a proof view for enabling the dealer to provide proof regarding the condition of the vehicle to potential customers. . 112. The system of claim 111, wherein said vehicle is a used vehicle. 103. The interface provides the dealer with a portion of a quality view that enables the dealer to run simulations to quality test the vehicle and its components in real-world conditions. System as described. 104. The system of claim 103, wherein the interface for the digital twin system provides the dealer with a 3D view showing a three-dimensional rendering of the model of the vehicle. 104. The method of claim 103, wherein the interface for the digital twin system provides the dealer with a value view for displaying the condition of the vehicle and the value of the blue book based on the condition of the vehicle. system. The interface for the digital twin system provides a service and maintenance view for showing wear and failure of components of the vehicle and predicting the need for service, repair, or replacement based on conditions of the vehicle's condition; 104. The system of claim 103, providing to the dealer. 104. The system of claim 103, wherein the vehicle operating state is a vehicle maintenance state. 104. The system of claim 103, wherein the vehicle operating conditions are vehicle energy utilization conditions. 104. The system of claim 103, wherein the vehicle operating state is a vehicle navigation state. 104. The system of claim 103, wherein the vehicle operating conditions are vehicle component conditions. 104. The system of claim 103, wherein the vehicle operating conditions are vehicle driver conditions. 4. The one or more inputs for the digital twin system comprise at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. 103. The system of claim 103. 104. The system of claim 103, further comprising an identity management system for managing a set of identities and roles of users of said vehicle for whom consent for communication has been given to said dealer. 123. Claim 123, wherein said identity management system includes functionality for viewing, modifying and configuring said digital twin system, said functionality being based on an identity from said set of identities of said user of said vehicle. System as described. 104. The system of claim 103, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to systems external to the vehicle. 104. The system of claim 103, wherein the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to the vehicle's set of sensors and data sources. 104. The system of claim 103, wherein a digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to an in-vehicle artificial intelligence system. 128. The system of Claim 127, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. 128. The system of claim 127, wherein the digital twin system is automatically configured by the artificial intelligence system based on a training set of usage activities by one of the driver or the dealer. and a first neural network for detecting a detected state of well-being of the user on board the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the user; ,
103. A second neural network for optimizing operating parameters of the vehicle in response to the detected state of satisfaction of the user to achieve a preferred state of satisfaction of the user. System as described. 131. The system of claim 130, wherein the detected state of satisfaction of the user is a detected emotional state of the user, and the preferred state of satisfaction of the user is a preferred emotional state of the user. . 131. The system of claim 130, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 131. The system of claim 130, wherein at least one of said neural networks is a hybrid neural network and includes a convolutional neural network. 131. The system of claim 130, wherein the second neural network optimizes the operating parameters based on correlations between vehicle operating conditions and the user's satisfaction. 131. The method of claim 130, wherein said second neural network optimizes said operating parameters in real time in response to said detection of said detected satisfaction state of said user by said first neural network. system. The first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. 131. The system of claim 130, wherein the system. The operating parameters that are optimized include the vehicle's path, in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the path, and 131. The system of claim 130, wherein at least one of approaching another vehicle is affected. A system for presenting a vehicle owner with a set of vehicle operating conditions, comprising:
a vehicle having a vehicle operating state;
a digital twin system that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
and an interface for a digital twin system for presenting the vehicle operating conditions to the owner of the vehicle. 139. The method of claim 138, wherein said interface for said digital twin system provides said owner with a fleet monitoring view for tracking and monitoring movements/routes/status of one or more vehicles. system. The interface for the digital twin system is characterized by providing the owner with a driver behavior monitoring view to enable the owner to monitor instances of unsafe or unsafe driving by the driver. 139. The system of claim 138. A claim wherein the interface for the digital twin system provides an insurance view to the owner to assist the owner in determining a vehicle insurance quote based on vehicle condition. 139. The system of Clause 138. The interface for the digital twin system is characterized by providing the owner with a compliance view to indicate compliance status with respect to emissions/pollutants and other regulatory mandates based on the state of the vehicle. 139. The system of Claim 138. The interface provides the owner with a performance tuning view for changing or adjusting characteristics of one or more components to personalize the performance of the vehicle based on the owner's preferences. 139. The system of claim 138, wherein: 144. The system of claim 143, wherein one of said components is an engine of said vehicle. 144. The system of claim 143, wherein one or more of said components are suspensions of said vehicle. 144. The system of claim 143, wherein one of said components is a body of said vehicle. 139. The system of claim 138, wherein said interface for said digital twin system provides said owner with a 3D view showing a three-dimensional rendering of a model of said vehicle. 139. Claim 138, wherein the interface for the digital twin system provides the owner with a value view for displaying the condition of the vehicle and the value of the blue book based on the condition of the vehicle. system. The interface for the digital twin system provides a service and maintenance view for showing wear and failure of components of the vehicle and predicting the need for service, repair, or replacement based on conditions of the vehicle's condition. 139. The system of claim 138, providing to the owner. 139. The system of claim 138, wherein the vehicle operating state is a vehicle maintenance state. 139. The system of claim 138, wherein the vehicle operating conditions are vehicle energy utilization conditions. 139. The system of claim 138, wherein the vehicle operating state is a vehicle navigation state. 139. The system of claim 138, wherein the vehicle operating conditions are vehicle component conditions. 139. The system of claim 138, wherein the vehicle operating condition is a vehicle driver condition. 4. The one or more inputs for the digital twin system comprise at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to the vehicle. 138. The system of claim 138. 139. The system of claim 138, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to systems external to the vehicle. 139. The system of claim 138, wherein the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to the vehicle's set of sensors and data sources. 139. The system of claim 138, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to an in-vehicle artificial intelligence system. 159. The system of Claim 158, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. 159. The system of Claim 158, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activity by the owner. and a first neural network for detecting a detected state of well-being of the user on board the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the user; ,
138, comprising: a second neural network for optimizing operating parameters of the vehicle in response to the detected state of well-being of the user to achieve a preferred state of well-being of the user; System as described. 162. The system of claim 161, wherein the detected state of satisfaction of the user is a detected emotional state of the user, and the preferred state of satisfaction of the user is the preferred emotional state of the user. . 162. The system of Claim 161, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 162. The system of Claim 161, wherein at least one of said neural networks is a hybrid neural network, comprising a convolutional neural network. 162. The system of claim 161, wherein said second neural network optimizes said operating parameters based on correlations between vehicle operating conditions and said user's satisfaction conditions. 162. The method of claim 161, wherein said second neural network optimizes said operating parameters in real time in response to said detection of said detected satisfaction state of said user by said first neural network. system. The first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. 162. The system of claim 161, wherein the system. The operating parameters that are optimized include the vehicle's path, in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the path, and 162. The system of claim 161, wherein at least one of proximity to other vehicles is affected. A system for presenting a set of vehicle operating conditions to a rider of the vehicle, comprising:
a vehicle having a vehicle operating state;
a digital twin system that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
and an interface for said digital twin system for presenting said vehicle operating conditions to said rider of said vehicle. 4. The interface as claimed in claim 1, wherein the interface provides the rider with an experience optimization view for allowing the rider to select an experience mode for personalizing the riding experience based on the rider's preferences. 169. The system of Clause 169. 171. The system of Claim 170, wherein the experience mode includes a comfort mode. 171. The system of Claim 170, wherein the experiential mode includes a sports mode. 171. The system of Claim 170, wherein the sensory mode comprises a high efficiency mode. 171. The system of Claim 170, wherein the experience mode comprises a work mode. 171. The system of Claim 170, wherein the experiential mode comprises an entertainment mode. 171. The system of Claim 170, wherein the experience mode includes a sleep mode. 171. The system of Claim 170, wherein the experience mode includes a relaxation mode. 171. The system of Claim 170, wherein the experiential mode comprises a long-distance travel mode. A system for presenting a set of vehicle operating conditions to a vehicle user, comprising:
a vehicle having a vehicle operating state;
a digital twin that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
an interface for the digital twin to present the vehicle operating conditions to the user of the vehicle;
an identity management system that manages a set of user identities and roles of the vehicle and determines the ability to view, modify, and configure the digital twin based on analysis of the set of identities and roles. characterized system. 180. The system of claim 179, wherein the vehicle operating state is a vehicle maintenance state. 180. The system of claim 179, wherein the vehicle operating conditions are vehicle energy utilization conditions. 180. The system of claim 179, wherein the vehicle operating state is a vehicle navigation state. 180. The system of claim 179, wherein the vehicle operating conditions are vehicle component conditions. 180. The system of claim 179, wherein the vehicle operating condition is a vehicle driver condition. 180. The system of claim 179, wherein inputs for said digital twin include at least one of an on-board diagnostic system, a telemetry system, a vehicle-mounted sensor, or a system external to said vehicle. 180. The system of claim 179, further comprising an identity management system for managing a set of identities and roles for users of said vehicle. 186. Claim 186, wherein said identity management system includes functionality for viewing, modifying, and configuring said digital twin system, said functionality being based on an identity from said set of identities of said user of said vehicle. System as described. 180. The system of claim 179, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to systems external to the vehicle. 180. The system of claim 179, wherein the digital twin system is input via an API from the vehicle's edge intelligence system that provides internal 5G connectivity to the vehicle's set of sensors and data sources. 180. The system of claim 179, wherein the digital twin system is input via an API from an edge intelligence system of the vehicle that provides 5G connectivity to an in-vehicle artificial intelligence system. 191. The system of Claim 190, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activities by a set of digital twin users. 191. The system of claim 190, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of driver-user usage activities. 191. The system of Claim 190, wherein the digital twin system is automatically configured by an artificial intelligence system based on a training set of usage activity by rider users. Further, a first neural for detecting the detected state of well-being of the rider user on board the vehicle through analysis of data collected from sensors deployed on the vehicle to collect the physiological state of the rider user. a network;
a second neural network for optimizing operating parameters of the vehicle in response to the detected state of satisfaction of the rider-user to achieve a preferred state of satisfaction of the rider-user. 180. The system of Clause 179. 4. The detected state of satisfaction of the rider user is the detected emotional state of the rider user, and the preferred state of satisfaction of the rider user is the preferred emotional state of the rider user. 194. The system according to 194. 195. The system of Claim 194, wherein the first neural network is a recurrent neural network and the second neural network is a radial basis function neural network. 195. The system of Claim 194, wherein at least one of said neural networks is a hybrid neural network, comprising a convolutional neural network. 195. The system of Claim 194, wherein the second neural network optimizes the operating parameters based on correlations between vehicle operating conditions and rider satisfaction of the rider user. 194. Claim 194, wherein said second neural network optimizes said operating parameters in real-time in response to said detection of said detected satisfaction state of said rider user by said first neural network. System as described. The first neural network includes a plurality of connected nodes forming a directed cycle, the first neural network further facilitating bi-directional flow of data between the connected nodes. 195. The system of claim 194, wherein the system. The operating parameters that are optimized include the vehicle's path, in-vehicle audio content, the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, proximity to objects along the path, and 195. The system of claim 194, wherein at least one of approaching another vehicle is affected. A system for presenting a set of vehicle operating conditions to a vehicle user, comprising:
a vehicle having a vehicle operating state;
a digital twin that receives vehicle parameter data from one or more inputs to determine the vehicle operating condition;
an interface for the digital twin to present the vehicle operating conditions to the user of the vehicle;
A system, wherein the digital twin is linked to a user's identity such that the digital twin is automatically provided for display and configuration via the identified user's mobile device. A system for configuring a vehicle experience based on a set of vehicle operating conditions and a set of rider user experience conditions, comprising:
a vehicle having a vehicle operating state;
a rider having a user experience state;
a digital twin system that receives vehicle parameter data and rider user experience data from one or more inputs to determine a composite state of the vehicle and the rider and configure the vehicle experience based on the composite state; A system comprising: A system for configuring a vehicle experience based on a set of vehicle operating conditions and a set of driver user experience conditions, comprising:
a vehicle having a vehicle operating state;
a driver having a user experience state;
a digital twin system that receives vehicle parameter data and driver user experience data from one or more inputs for determining a coupling state between the vehicle and the driver and setting the vehicle experience based on the coupling state; A system comprising: 205. The system of claim 204, wherein the vehicle operating conditions comprise vehicle physical conditions. 205. The system of claim 204, wherein the vehicle operating conditions comprise vehicle maintenance conditions. 205. The system of claim 204, wherein the vehicle operating conditions comprise vehicle energy utilization conditions. 205. The system of claim 204, wherein the vehicle operating conditions comprise vehicle component conditions. 205. The system of claim 204, wherein the vehicle operating conditions comprise vehicle environmental conditions. 205. The system of claim 204, wherein said driver user experience states include driver physiological states. 205. A system according to claim 204, wherein said driver user experience states include driver psychological states. 205. The system of claim 204, wherein said driver user experience states include driver physical states. 205. The system of claim 204, wherein said driver user experience states include driver position states. 205. The system of claim 204, wherein said driver user experience states include driver emotional states. 205. The system of Claim 204, wherein the vehicle is an autonomous vehicle.

Images