CN114638666A

CN114638666A - Method and device for processing Internet of vehicles data

Info

Publication number: CN114638666A
Application number: CN202210260943.2A
Authority: CN
Inventors: 付振; 王明月; 李涵; 张洪军; 李振洋; 邵天东; 吕欢欢
Original assignee: FAW Group Corp
Current assignee: FAW Group Corp
Priority date: 2022-03-11
Filing date: 2022-03-11
Publication date: 2022-06-17

Abstract

The disclosure provides a method and a device for processing Internet of vehicles data. Wherein, the method can comprise the following steps: in the driving process of at least one vehicle to be monitored, the vehicle networking information of the vehicle to be monitored is collected, wherein the vehicle networking information at least comprises: journey information of a vehicle to be monitored; calling a generation driving program identification model deployed at a vehicle-mounted edge end; analyzing the car networking information by adopting a driving program generation identification model, and acquiring the target driving program generation characteristic of the vehicle to be monitored; acquiring a driving demand replacement identification model based on the driving behavior characteristics of the target generation; adopting a designated driving request of a designated driving demand identification model; uploading the designated driving request of the vehicle to be monitored to the cloud end platform, wherein at least one user end is allowed to obtain the designated driving request of the vehicle to be monitored, and the request is pushed by the cloud end platform.

Description

Method and device for processing Internet of vehicles data

Technical Field

The disclosure relates to the field of data processing, and in particular to a method and a device for processing data of a vehicle networking.

Background

At present, the recommendation of the designated driving service is mainly based on user history information, a history behavior of providing the designated driving service for the user by a platform is obtained, the possibility that the user needs designated driving is presumed according to the frequency of the behavior, and then a related service content push or a coupon is sent to the user through an Application program (APP). The recommendation method has the technical problems that the user requirements cannot be accurately identified, and the service push efficiency is low.

Aiming at the technical problems that the user requirements cannot be accurately identified and the service pushing efficiency is low, an effective solution is not provided at present.

Disclosure of Invention

The embodiment of the invention provides a method and a device for processing Internet of vehicles data, which at least solve the technical problems that user requirements cannot be accurately identified and service pushing efficiency is low.

According to an aspect of the embodiments of the present invention, a method for processing data in a vehicle networking system is provided, including: in the driving process of at least one vehicle to be monitored, the vehicle networking information of the vehicle to be monitored is collected, wherein the vehicle networking information at least comprises: journey information of a vehicle to be monitored; calling a generation driving program identification model deployed at a vehicle-mounted edge end; analyzing the car networking information by adopting a driving program generation identification model, and acquiring the target driving program generation characteristic of the vehicle to be monitored; acquiring a replacement driving demand identification model based on the target generation driving behavior characteristics; adopting a designated driving demand identification model to determine a designated driving request of a vehicle to be monitored; uploading the designated driving request of the vehicle to be monitored to the cloud end platform, wherein at least one user end is allowed to obtain the designated driving request of the vehicle to be monitored, and the request is pushed by the cloud end platform.

Optionally, the method further comprises: the method comprises the steps of collecting internet-of-vehicles data of a plurality of vehicles in a historical time period, wherein the historical time period at least comprises a driving generation time period for generating driving generation behavior information, and the internet-of-vehicles data at least comprises the following steps: designated driving travel data generated in designated driving time periods; training the machine learning model based on the designated driving journey data to generate a designated driving journey identification model; the method for determining the designated driving request of the vehicle to be monitored by adopting the designated driving demand recognition model comprises the following steps: acquiring designated driving sample data based on the characteristic of the target designated driving, wherein the designated driving sample data at least comprises at least one of the following data: travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period; training the machine learning model based on designated driving sample data to generate a designated driving demand recognition model, wherein the designated driving demand recognition model is used for recognizing corresponding designated driving demand characteristics based on the travel information of the vehicle to be recognized.

Optionally, after uploading the designated driving request of the vehicle to be monitored to the cloud-end platform, the method further includes: detecting whether a designated driving request is received by a cloud platform; if a designated driving request is received, calling driver information of at least one registered designated driving driver; determining whether a designated driver in an idle state exists based on driver information of the designated driver; determining at least one target designated driver based on a pushing rule, and calling equipment information of the target designated driver, wherein the pushing rule is used for determining pushing priorities of a plurality of designated drivers; and pushing the designated driving request to equipment held by the target designated driving driver based on the equipment information of the target designated driving driver.

According to another aspect of the embodiments of the present invention, there is provided a device for processing data of a vehicle networking system, including: the collection module is used for collecting the car networking information of the vehicles to be monitored in the driving process of at least one vehicle to be monitored, wherein the car networking information at least comprises: journey information of a vehicle to be monitored; the calling module is used for calling a driving program generation identification model deployed at a vehicle-mounted edge end; the first acquisition module is used for analyzing the Internet of vehicles information by adopting a driving program generation identification model and acquiring target driving program generation characteristics of the vehicle to be monitored; the second acquisition module is used for acquiring a driving demand replacement identification model based on the driving behavior characteristics of the target generation; the determining module is used for determining a designated driving request of the vehicle to be monitored by adopting a designated driving demand identifying model; the uploading module is used for uploading the designated driving request of the vehicle to be monitored to the cloud end platform, wherein at least one user end is allowed to acquire the designated driving request of the vehicle to be monitored, and the request is pushed by the cloud end platform.

Optionally, the apparatus further comprises: the collection module is used for collecting vehicle networking data of a plurality of vehicles in a historical time period, wherein the historical time period at least comprises a driving generation time period for generating driving generation behavior information, and the vehicle networking data at least comprises: designated driving travel data generated in designated driving time periods; the first training module is used for training the machine learning model based on the driving program generation data to generate a driving program generation identification model; the acquisition module is used for acquiring designated driving sample data based on the target designated driving behavior characteristics, wherein the designated driving sample data at least comprises at least one of the following data: travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period; the second training module is used for training the machine learning model based on the designated driving sample data to generate a designated driving demand recognition model, wherein the designated driving demand recognition model is used for recognizing corresponding designated driving demand characteristics based on the travel information of the vehicle to be recognized.

Optionally, the apparatus further comprises: the detection module is used for detecting whether the cloud platform receives a designated driving request; the calling module is used for calling the driver information of at least one registered designated driver if the designated driver request is received; the determining module is used for determining whether the designated driver in an idle state exists or not based on driver information of the designated driver; the processing module is used for determining at least one target designated driver based on a pushing rule and calling equipment information of the target designated driver, wherein the pushing rule is used for determining pushing priorities of a plurality of designated drivers; the pushing module is used for pushing the designated driving request to equipment held by the target designated driving driver based on the equipment information of the target designated driving driver.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium. The computer readable storage medium comprises a stored program, wherein when the program is executed by a processor, the program controls a device where the computer readable storage medium is located to execute the method for processing the vehicle networking data according to the embodiment of the invention.

According to another aspect of the embodiment of the invention, a processor is further provided, and the processor is used for running the program, wherein when the program runs, the method for processing the internet of vehicles data according to the embodiment of the invention is executed.

According to another aspect of the embodiments of the present invention, there is also provided a vehicle including: the car networking data processing method is achieved.

In the embodiment of the invention, historical behavior information of designated driving service provided for a user by a current platform is acquired, data in a time period corresponding to the user is acquired in internet of vehicles data as a sample, designated driving behavior characteristics are acquired, then the designated driving behavior characteristics are identified based on the internet of vehicles data, a large amount of designated driving behavior sample data are acquired, a designated driving service demand identification model of the user is trained based on the data, the designated driving demand which possibly exists in the user is identified, finally, model identification calculation is carried out at a vehicle-mounted edge end, real-time designated driving service demand identification is realized, meanwhile, user position data does not need to be uploaded to a cloud end, the safety of user privacy data is ensured, the accurate identification of the user is realized, the service pushing efficiency is greatly improved, the safety of the user privacy data is ensured, and the technical problems that the user demand cannot be accurately identified and the service pushing efficiency is low are solved, the technical effects of accurately identifying the user requirements and improving the service pushing efficiency are achieved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of a method of processing Internet of vehicles data according to an embodiment of the disclosure;

FIG. 2 is a schematic illustration of a flow of a drive generation identification scheme according to an embodiment of the disclosure;

fig. 3 is a schematic diagram of a flow of a designated driving demand identification scheme according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a flow of a model function edge-end implementation according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of a device for processing internet of vehicles data according to an embodiment of the disclosure.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

The following describes a method for processing car networking data according to an embodiment of the present disclosure.

Vehicle networking data: the System comprises two parts of gray data and color data, wherein the gray mainly refers to various sensor signals of the vehicle, including vehicle speed, vehicle door opening state, trunk door opening state, Global Positioning System (GPS) information and the like; the color data includes various kinds of APPs and functional data, such as navigation information, used by the user at the vehicle.

The identification scheme comprises the following steps: the method is characterized by mainly comprising user navigation Information (the destination is a frequently-visited place or a home address of a user) and Information Point (POI for short) analysis of a position of a travel starting Point (a commercial place exists near the starting Point), characteristics before the driving course starts (a trunk is opened, the number of opened doors and the like), driving behaviors of the driving course (speed, acceleration rate, relatively conservative style) and the like.

And performing characteristic construction based on the characteristics of the designated driving journey, inputting the acquired designated driving service information as sample data into a machine learning model for training, and then identifying the journey information with the same characteristics in the data by using the journey information of a large number of vehicles, namely the part of the journey is the designated driving journey.

The method comprises the steps of obtaining travel information of a previous section adjacent to a designated driving travel, inputting corresponding sample travel characteristics into a machine learning model for training, deploying a trained model to a vehicle-mounted edge end for calculation, feeding back identification results of the designated driving service possibly existing in a user to a cloud end when the model identifies the travel information with the same characteristics, and then accurately pushing related services to the user through an APP.

Fig. 1 is a flowchart of a method for processing internet of vehicles data according to an embodiment of the present disclosure, and as shown in fig. 1, the method may include the following steps:

step S101, in the running process of at least one vehicle to be monitored, acquiring the vehicle networking information of the vehicle to be monitored, wherein the vehicle networking information at least comprises: and the travel information of the vehicle to be monitored.

In the technical scheme provided in the above step S101 of the present disclosure, in the driving process of at least one vehicle to be monitored, the vehicle networking information of the vehicle to be monitored is collected, for example, various sensor signals of the vehicle and various APPs and functional data used by the user in the vehicle machine, such as navigation information, in the period before and after a batch of designated driving service are acquired by combining with platform data.

In this embodiment, the internet of vehicles data may include two parts, namely, gray data and color data, wherein the gray data mainly refers to various sensor signals of the vehicle, including vehicle speed, door opening state, trunk door opening state, GPS information, and the like; the color data includes various kinds of APPs and functional data, such as navigation information, used by the user at the vehicle.

In this embodiment, the trip information of the vehicle to be monitored may be information of a designated driving trip of the vehicle to be monitored, and the designated driving trip information may be acquired through history information of a designated driving application or some manual identification method.

In this embodiment, the car networking information includes at least: the travel information of the vehicle to be monitored, for example, after acquiring vehicle networking data of the vehicle in a period before and after a batch of designated driving service by combining platform data, related user information is firstly eliminated, and designated driving travel data is analyzed.

And step S102, calling a driving program generation identification model deployed at the vehicle-mounted edge end.

In the technical solution provided by the above step S102 of the present disclosure, the generation driving program identification model deployed at the vehicle-mounted edge is called, for example, after the generation driving program identification model is trained, the generation driving program identification model is deployed at the vehicle-mounted edge, and the model is called to perform generation driving program identification.

In this embodiment, before invoking the driving assistance program generation recognition model deployed at the vehicle-mounted edge end, the generation of the driving assistance program generation recognition model may be performed, for example, by manually selecting some data with high probability of being driving assistance programs, inputting the driving assistance program generation data into the machine learning model for training, and then generating the driving assistance program generation recognition model.

And step S103, analyzing the vehicle networking information by adopting a driving program generation identification model, and acquiring the target driving program generation characteristic of the vehicle to be monitored.

In the technical solution provided in the above step S103 of the present disclosure, the driving information of the vehicle network may be analyzed by using a driving information generation recognition model, and target driving characteristics of the vehicle to be monitored are obtained, for example, a characteristic structure is performed based on characteristics of a driving information generation, the obtained driving information generation is used as characteristic data, the characteristic data is input to a machine learning model for training, after the driving information generation recognition model is obtained, the driving information of a large number of vehicles is used as data, and the driving information with the same characteristics is recognized, that is, the part of the driving information is a driving information generation.

In this embodiment, the analysis of the car networking information by using the driving program generation recognition model can be performed at the cloud, and the target driving characteristic of the vehicle to be monitored can be obtained.

In this embodiment, the method may include: the method comprises the steps of identifying characteristics of travel information in the internet of vehicles information input into the driving assistant identification model, and judging whether travel information identical to the characteristics in sample data used for training the driving assistant identification model exists or not.

In this embodiment, the driver's ride generation identification model may be trained by analyzing common features of the driver's ride generation data to form feature data.

And step S104, obtaining a driving demand identification model based on the driving characteristic of the target generation.

In the technical solution provided in the above step S104 of the present disclosure, if it is recognized that the target driving behavior characteristic exists in the vehicle to be monitored, the driving demand identification model is replaced, for example, when the model recognizes the travel information with the same characteristic, the driving demand identification model is called.

And step S105, determining a designated driving request of the vehicle to be monitored by adopting a designated driving demand identification model.

In the technical solution provided in the above step S105 of the present disclosure, a designated driving request of the vehicle to be monitored may be determined by using a designated driving demand identification model, for example, when a user arrives near a destination, it is identified whether the user has a designated driving demand, and a designated driving service is pushed for the user who may need designated driving.

In this embodiment, the designated driving demand recognition model may be deployed at a vehicle-mounted intelligent terminal, and user location information may be acquired at the vehicle-mounted intelligent terminal, so that only one piece of result information is uploaded, and user privacy information is not uploaded to the cloud, that is, when a user is currently requested by a designated driving service, the cloud can control to issue recommendation information of the service to a user side, and the privacy of the user is effectively protected while accurate recommendation is performed.

And step S106, uploading the designated driving request of the vehicle to be monitored to a cloud platform, wherein at least one user side is allowed to obtain the designated driving request of the vehicle to be monitored, which is pushed by the cloud platform.

In the technical scheme provided in the above step S106 of the present disclosure, the designated driving request of the vehicle to be monitored is uploaded to the cloud platform, for example, after the model identifies the travel information with the same characteristics, the identification result of the designated driving service requirement possibly existing in the user is fed back to the cloud, and then the APP is used to accurately push the relevant service to the user.

In this embodiment, prior to generating the second drive-on request for the vehicle to be monitored, the method may include: and uploading the identification result to the cloud.

In this embodiment, after generating the ride-on request for the vehicle to be monitored, the method may include: and pushing the service of the designated driving request through the APP.

Through the steps S101 to S106, historical behavior information of designated driving service provided for a user by the current platform is obtained, data in a time period corresponding to the user is obtained from the vehicle networking data to serve as a sample, designated driving behavior characteristics are obtained, then, the designated driving behavior characteristics are identified based on the vehicle networking data, a large amount of designated driving behavior sample data are obtained, a designated driving service demand identification model is trained based on the data, the designated driving demand which possibly exists in the user is identified, finally, model identification calculation is carried out at a vehicle-mounted edge end, real-time designated driving service demand identification is realized, meanwhile, user position data do not need to be uploaded to a cloud end, the safety of user privacy data is ensured, the accurate identification of the user is realized, the service pushing efficiency is greatly improved, the safety of the user privacy data is ensured, and the technical problems that the user demand cannot be accurately identified and the service pushing efficiency is low are solved, the technical effects of accurately identifying the user requirements and improving the service pushing efficiency are achieved.

The above-described method of this embodiment is described in further detail below.

As an optional implementation, in step S102, before invoking the driver identification model deployed at the vehicle-mounted edge terminal, the method further includes: the method comprises the following steps of collecting internet-of-vehicles data of a plurality of vehicles in a historical time period, wherein the historical time period at least comprises a driving generation time period for generating driving generation behavior information, and the internet-of-vehicles data at least comprises the following steps: the designated driving travel data is generated in the designated driving time period; training the machine learning model based on the designated driving journey data to generate a designated driving journey identification model; the method for determining the designated driving request of the vehicle to be monitored by adopting the designated driving demand recognition model comprises the following steps: acquiring designated driving sample data based on the characteristics of target designated driving behaviors, wherein the designated driving sample data at least comprises at least one of the following data: travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period; training the machine learning model based on the designated driving sample data to generate a designated driving demand identification model, wherein the designated driving demand identification model is used for identifying corresponding designated driving demand characteristics based on the travel information of the vehicle to be identified.

In the embodiment, the internet-of-vehicles data of a plurality of vehicles in a historical time period is collected, for example, the internet-of-vehicles data of vehicles in a period before and after a batch of designated driving service is obtained, relevant user information is firstly eliminated, designated driving journey data is analyzed, and the method is characterized by mainly comprising user navigation information (the destination is a user frequent place or a family address) and interest point analysis of the position of a journey starting point (a business place exists near the starting point), characteristics before the designated driving journey starts (trunk opening, door opening number and the like), driving behaviors of the designated driving journey (speed, acceleration rate, relatively conservative style) and the like.

In this embodiment, the machine learning model may be trained based on the driving assistance travel data to generate a driving assistance travel recognition model, for example, after common features of the driving assistance travel data are analyzed, feature data is formed, and then the feature data is used to train the driving assistance travel recognition model, which is used to screen a large amount of driving assistance travel data from historical data of the vehicle to be monitored, where the driving assistance travel data may be travel data representing driving assistance travel.

For example, a small amount of historical driving travel information can be acquired through the driving service APP, the travel characteristics of the analyzer, such as whether a plurality of people take a car (a single person can get rid of driving), whether the vehicle storage of the driver is distinguished through the state of a trunk switch, indexes such as speed and acceleration change rate are calculated through a series of signals such as speed and acceleration, the overall driving style of the driving travel is evaluated, whether the driving travel starting point is located in a commercial area or not is judged through a GPS signal, a relevant characteristic structure is completed based on the part of historical data, the training of a cost formation recognition model is performed, after the training of the model is completed, the model screens a large amount of driving travel data from mass internet-of-vehicles data in the cloud, a travel section before the driving travel is acquired based on a corresponding time section, namely, a travel section of a user going to the commercial place, it may be characterized by a fixed time period to reach the destination (business, etc.) as opposed to a normal weekday to reach the destination (home).

In this embodiment, the designated driving sample data is obtained based on the target designated driving behavior as a characteristic, for example, after the designated driving journey data is analyzed, the characteristic construction is performed based on the characteristic of the designated driving journey, and the obtained designated driving service information is taken as the sample data, wherein the designated driving sample data at least includes at least one of the following: the travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period.

In this embodiment, the main features of the designated driving sample data may include: a travel time zone (non-operating time), navigation information, a travel end position (a place where a business is located near), a travel route (a route different from a daily travel route, not a return route from a company), and the like.

In this embodiment, the machine learning model may be trained based on the driving generation sample data to generate the driving generation requirement recognition model, for example, the driving generation requirement recognition model may be trained by using sample data, the sample data may be travel data of a user driving to a restaurant or an entertainment place before the driving generation travel data used for training the driving generation requirement recognition model, and the corresponding sample travel characteristics are input into the machine learning model to be trained to generate the driving generation requirement recognition model.

As an optional implementation manner, at least one type of driving assistant characteristic information is extracted from driving assistant travel data generated in a driving assistant time period, characteristic construction is performed on the basis of the driving assistant characteristic information, and a part of samples in the driving assistant travel data are generated, wherein the driving assistant travel data comprises at least one of the following data: the method comprises the following steps of navigation information, interest point analysis data of the position of a starting point of the driving program generation, vehicle equipment use characteristics before the driving program generation starts, and driving behavior information in the driving program generation.

In this embodiment, the navigation information may be a frequent location or home address destined for the user.

In this embodiment, the point of interest analysis data for the location of the origin of the driver's ride may be the presence of a business location near the origin.

In this embodiment, the vehicle device usage characteristic before the start of driving schedule may be trunk opening, door opening number, or the like.

In this embodiment, the driving behavior information in the designated driving journey may be speed, acceleration rate, style relatively conservative, and the like.

As an optional implementation manner, at least one type of designated driving feature information is extracted from the trip information in at least one adjacent time period adjacent to the designated driving time period, feature construction is performed on the basis of the designated driving feature information, and a part of samples in designated driving sample data are generated, wherein the trip information includes at least one of the following: the travel time period, the navigation information, the terminal position of the designated driving travel and the designated driving route.

In this embodiment, the trip time period may be a non-operating time.

In this embodiment, the navigation information and the end position of the valet travel may be a route and a position of a nearby business place.

In this embodiment, the drive-by driving route may be a route from a company to a business leisure instead of a return-to-home route from the company, unlike a daily driving route.

As an optional implementation manner, historical designated driving service information is obtained by accessing a designated driving service platform, and vehicle networking data of each vehicle in a historical time period is obtained based on matching in the historical designated driving service information, wherein the vehicle networking data further includes at least one of the following data: door open and close states of the vehicle, trunk open and close states, vehicle speed, vehicle acceleration, vehicle steering wheel angle, steering wheel angle speed, accelerator pedal opening, brake pedal opening, and vehicle navigation data.

In this embodiment, the door switch state of the vehicle can be used to distinguish whether a plurality of people take a car (a single person takes a car can exclude a designated drive).

In this embodiment, the trunk switch state may be used to distinguish vehicle deposits for designated drivers.

In this embodiment, vehicle speed, vehicle acceleration, vehicle steering wheel angle, steering wheel angle speed, accelerator pedal opening, brake pedal opening may be used to evaluate the overall driving style of the ride-on course.

In this embodiment, the vehicle navigation data may be used to determine whether the designated driving range start point is located in a commercial zone.

As an optional implementation manner, in step S105, after uploading the designated driving request of the vehicle to be monitored to the cloud-end platform, the method further includes: detecting whether a designated driving request is received by a cloud platform; if a designated driving request is received, calling driver information of at least one registered designated driving driver; determining whether a designated driver in an idle state exists based on driver information of the designated driver; determining at least one target designated driver based on a pushing rule, and calling equipment information of the target designated driver, wherein the pushing rule is used for determining pushing priorities of a plurality of designated drivers; and pushing the designated driving request to equipment held by the target designated driving driver based on the equipment information of the target designated driving driver.

In this embodiment, whether the cloud platform receives the designated driving request is detected, for example, after the designated driving request of the vehicle to be monitored is uploaded to the cloud platform, whether the cloud platform receives the designated driving request is detected.

In this embodiment, if the designated driving request is received, the driver information of the at least one registered designated driver is retrieved, for example, after the designated driving request is detected to be received by the cloud platform, the driver information (such as name, identification number, working state, current position and the like) of the at least one registered designated driver on the designated driving service platform is retrieved.

In this embodiment, whether the designated driver in the idle state exists is determined based on the driver information of the designated driver, for example, whether the designated driver in the idle state exists is determined according to the working state in the driver information of the at least one driver.

In this embodiment, at least one target designated driver is determined based on the pushing rules, and the device information of the target designated driver is retrieved, for example, the driver's favorable rating is ranked from high to low, the driver with the highest favorable rating is pushed as the priority based on the pushing rules, at least one designated driver with the highest favorable rating is determined, and the device information of the designated driver is retrieved.

In this embodiment, the designated driving request is pushed to the device held by the target designated driving driver based on the device information of the target designated driving driver, for example, after at least one designated driving driver with the highest rating is determined as the target driver, the designated driving request is pushed to the mobile phone held by the target designated driving driver through the mobile phone short message and/or the voice call interface of the designated driving service APP according to the registration information of the designated driving service APP in the mobile phone held by the target designated driving driver.

For example, the step one, identifying the driving behavior characteristic of the designated driver is to manually select a part of data (historical information of the driving application program or some manual methods) with a high probability of being the driving behavior of the designated driver, and analyze common characteristics in the part of data; step two, training a 'driving program generation recognition model' by using the characteristic data obtained by analysis in the step one, wherein the purpose of the model is to screen a large amount of driving program generation data (namely the driving program of a driver generation) from historical data; and step three, acquiring data of a previous journey (the journey of the user driving to a restaurant or an entertainment place) by using a large amount of data (namely the journey of the designated driver driving) obtained in the previous step, and training a designated driving demand identification model by using the journey data, wherein the model is used for identifying whether the user has designated driving demand when the user arrives near a destination, pushing designated driving service for the user possibly needing designated driving and the like.

In the embodiment of the disclosure, historical behavior information of a designated driving service is provided for a user by acquiring a current platform, data in a time period corresponding to the user is acquired in vehicle networking data and used as a sample, designated driving behavior characteristics are acquired, then the designated driving behavior characteristics are identified based on the vehicle networking data, a large amount of designated driving behavior sample data is acquired, a user designated driving service requirement identification model is trained based on data, designated driving requirements possibly existing in the user are identified, accurate identification of the user is achieved, service pushing efficiency is greatly improved, safety of user privacy data is guaranteed, the technical problem that the user requirements cannot be accurately identified and service pushing efficiency is low is solved, and the technical effects that the user requirements can be accurately identified and the service pushing efficiency is improved are achieved.

As a preferred embodiment, the user's override service may be divided into two phases, which are described below.

Stage one, a journey section when a user goes to a business place is characterized in that a fixed time period arrival destination (business place and the like) is different from a normal working day arrival destination (home), and the like;

and in the second stage, after the designated driver arrives at the designated place, the vehicle is started, the designated driver is sent to the section of the travel of the destination, the characteristics of opening a trunk door and the like exist at the beginning of the travel, and the characteristics of driving behavior in the travel are different from the driving behavior of the owner under the normal condition.

The recommendation of the designated driving service needs to be carried out after the travel section of the first stage is identified and before the second stage, and the final aim of the application is to identify the first stage.

The scheme of the application can be divided into three parts, which are introduced below respectively.

The first part is a driving course identification scheme, which is performed in the cloud, and the final purpose of the first part is to acquire a large number of driving courses (driving courses of the drivers, namely, the second stage) for next sample screening (screening courses from users to destinations, namely, the first stage).

The method comprises the steps of firstly obtaining a small amount of historical driving program information through a driving service APP (stage two), analyzing the stroke characteristics (distinguishing whether the vehicle is ridden by multiple persons (the driving can be eliminated by a single person) through the opening state of a vehicle door, distinguishing the storage of transportation tools of the driving driver in the state of a trunk switch, calculating indexes such as speed, acceleration rate and the like through a series of signals such as speed, acceleration rate and the like to evaluate the whole driving style of the driving program, judging whether a driving program starting point is located in a commercial area or not through a GPS signal, completing relevant characteristic structures based on the part of historical data, training a driving program recognition model, screening out a large amount of driving programs (far more than those obtained through the driving service APP and the like only) from mass vehicle networking data at the cloud end through the model after the training of the model is completed, and obtaining the stroke section before the driving program based on the corresponding time period, i.e., the travel segment sample data of phase one.

And the second part is a designated driving demand identification scheme, which is also carried out at the cloud, and the final purpose is to construct characteristics of a stage-trip section, and output a designated driving demand identification model for subsequent vehicle end deployment through training of a large amount of sample data.

The third part is deployment of a vehicle end and an integral recommendation strategy, a trained designated driving demand identification model is deployed to a vehicle-mounted intelligent terminal, and partial operations related to user position information acquisition are all performed at the vehicle end, user privacy information cannot be uploaded to a cloud end, only one piece of result information is uploaded to the cloud end, namely, a user currently has a designated driving service demand, the cloud end can control recommendation information of service to be issued to a user end, and the user privacy is effectively protected while accurate recommendation is performed.

It should be noted that, when the driving program generation identification model is trained based on the driving program generation information, because the manner of directly acquiring a large amount of driving program generation information relates to user privacy data, in the application, a small amount of historical driving program generation information is acquired through channels such as driving service APP (application) and the like, the travel characteristics of the historical driving program generation information are analyzed, and the relevant characteristic structure is completed based on the partial historical data to train the driving program generation identification model.

Example 2

The car networking data processing method of the present disclosure is further described below with reference to preferred embodiments.

Fig. 2 is a schematic diagram of a flow of a driving assistance program identification scheme according to an embodiment of the present disclosure, which, as shown in fig. 2, may include the following steps:

s201, acquiring historical designated driving service information;

s202, acquiring Internet of vehicles data in the designated driving journey time period;

s203, constructing a driving program generation characteristic;

s204, training a driving program identification algorithm model;

s205, acquiring a large number of designated driving trips;

in the embodiment, historical driving service information of a user is obtained from driving service providing platforms such as APP (application), vehicle internet of vehicles data in corresponding time periods are matched, sample data are obtained, main initial field signals comprise a vehicle door opening and closing state, a trunk opening and closing state, speed, acceleration, a steering wheel corner speed, an accelerator pedal opening degree, a brake pedal opening degree, GPS (global positioning system) and the like, and various signals are selected for the following main purposes: whether a plurality of persons ride the bus or not is distinguished through the opening state of the vehicle door (the designated driving can be eliminated by a single person riding the bus); the state of a trunk switch distinguishes the storage of transportation tools of a designated driver; a series of signals such as speed, acceleration and the like are used for calculating indexes such as speed, acceleration rate and the like and evaluating the integral driving style of a driving program; the GPS signal is used for judging whether the designated driving travel starting point is located in a commercial area.

And (2) completing corresponding feature construction (including but not limited to the four types) on the data to form sample data of the designated driving journey, performing model training as input of a machine learning model, acquiring journey data of all vehicles, constructing the same features, inputting the same features into the trained model, and outputting a result to indicate all journey sections identified as the designated driving journey to serve as input conditions of a subsequent model.

Through steps S201 to S205 in this embodiment, historical designated driving service information is acquired; acquiring Internet of vehicles data in designated driving travel time period; constructing a driving program generation characteristic; training a driving program generation recognition algorithm model; the method comprises the steps of obtaining a large number of designated driving travels, namely obtaining historical designated driving service information of a user from designated driving service providing platforms such as APP, matching vehicle internet of vehicles data in corresponding time intervals, obtaining sample data, selecting multiple signals for constructing multiple characteristics, training a machine learning model, inputting the travel data of all vehicles into the trained model, obtaining all travel sections of the designated driving travels, further solving the technical problem that the user requirements cannot be accurately identified, and achieving the technical effect that the user requirements can be accurately identified.

Fig. 3 is a schematic diagram of a flow of a designated driving demand identification scheme according to an embodiment of the present disclosure, and as shown in fig. 3, the scheme may include the following steps:

step S301, acquiring Internet of vehicles data in a period of time before a designated driving journey;

step S302, constructing corresponding stroke characteristics;

and step S303, training a designated driving demand recognition algorithm model.

In this embodiment, according to the time corresponding to a large number of driving courses of different generations, the information of the course adjacent to the driving course is obtained, and the signals of the relevant fields in the course, including time, GPS signals, navigation information, etc., are obtained, and the following characteristics are mainly constructed for each signal: the time is used for judging whether the time is working time or not; the GPS signal and the navigation information are used for judging whether the user drives on a home route or a common route (the route is set by the user or an algorithm identification result and is stored at the vehicle end); the GPS signal and navigation information are also used to determine whether a trip end point or the vicinity of a navigation address is located in a business district or the like.

And performing model training by taking sample data of travel designated driving demand identification after all data are subjected to relevant feature construction (including but not limited to the three types) as input of a machine learning model.

Through steps S301 to S303 in this embodiment, internet-of-vehicles data in a period of time before the designated driving trip is acquired; constructing corresponding stroke characteristics; the method comprises the steps of training a designated driving demand recognition algorithm model, namely acquiring travel information of an adjacent previous section of travel according to corresponding time of a large number of acquired designated driving travels, acquiring related field signals in the travel section, constructing various types of characteristics by selecting multiple signals, completing related characteristic construction on all data (including but not limited to the three types of signals), and performing model training by using the travel designated driving demand recognition sample data as input of a machine learning model, so that the designated driving demand is accurately recognized, the technical problem that user demands cannot be accurately recognized is solved, and the technical effect of accurately recognizing the user demands is achieved.

Fig. 4 is a schematic diagram of a flow of a model function edge implementation scheme according to an embodiment of the present disclosure, and as shown in fig. 4, the scheme may include the following steps:

step S401, deploying model edge terminals;

step S402, calculating the edge end of the model in real time;

step S403, calculating and uploading an edge end model to a cloud end;

and step S404, the APP sends the accurate recommendation information.

In this embodiment, after the model training is completed, the model is deployed to a vehicle-mounted intelligent terminal (including but not limited to an intelligent cabin, a gateway, and a vehicle-mounted internet terminal), gray and color data of the vehicle internet are obtained in real time, information such as a user home address and a common route stored in a vehicle end is obtained, data calculation and storage are completed in the vehicle end, only a result is sent to a cloud end, the cloud end sends a judgment result to an APP, and the user is subjected to designated driving service accurate pushing.

Through the steps S401 to S404 of the embodiment of the present disclosure, the model edge is deployed; calculating the edge end of the model in real time; calculating an uploading cloud by the edge end model; the APP sends accurate recommendation information, namely, the model is deployed to the vehicle-mounted intelligent terminal, the grey of the Internet of vehicles and color data are obtained in real time, the home address of a user stored at the vehicle end is obtained, information such as common routes is obtained, data calculation and storage are completed at the vehicle end, only the result is sent to the cloud end, the cloud end sends the judgment result to the APP, accurate identification of the user is achieved, service pushing efficiency is greatly improved, safety of user privacy data is ensured simultaneously, user demands cannot be accurately identified are further solved, the technical problem that service pushing efficiency is low is solved, the user demands can be accurately identified and the technical effect of service pushing efficiency is improved.

Example 3

The embodiment of the disclosure also provides a device for processing the internet of vehicles data, which is used for executing the method for processing the internet of vehicles data in the embodiment shown in fig. 1.

Fig. 5 is a schematic diagram of a device for processing data of a vehicle networking according to an embodiment of the present disclosure, and as shown in fig. 5, the device 50 for processing data of a vehicle networking may include: the device comprises an acquisition module 51, a calling module 52, an identification module 53, a generation module 54 and an uploading module 55.

The collection module 51 is configured to collect the vehicle networking information of the vehicle to be monitored in the driving process of at least one vehicle to be monitored, where the vehicle networking information at least includes: journey information of a vehicle to be monitored;

the calling module 52 is used for calling a designated driving identification model deployed at a vehicle-mounted edge end;

the first acquisition module 53 is used for analyzing the internet of vehicles information by adopting a designated driving identification model and acquiring target designated driving behavior characteristics of the vehicle to be monitored;

a second obtaining module 53, configured to obtain a substitute driving demand identification model based on the target generation driving behavior characteristics;

a determination module 54, configured to determine a designated driving request of a vehicle to be monitored by using a designated driving demand identification model;

the uploading module 55 is configured to upload the designated driving request of the vehicle to be monitored to the cloud platform, where at least one user side is allowed to obtain the designated driving request of the vehicle to be monitored pushed by the cloud platform.

In the above-mentioned processing apparatus of car networking data of this disclosure, the apparatus further includes: the device comprises a collection module, a first training module, an acquisition module and a second training module. The collection module is used for collecting vehicle networking data of a plurality of vehicles in a historical time period, wherein the historical time period at least comprises a driving generation time period for generating driving generation behavior information, and the vehicle networking data at least comprises: designated driving travel data generated in designated driving time periods; the first training module is used for training the machine learning model based on the driving program generation data to generate a driving program generation identification model; the acquisition module is used for acquiring designated driving sample data based on the target designated driving behavior characteristics, wherein the designated driving sample data at least comprises at least one of the following data: travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period; and the second training module is used for training the machine learning model based on the designated driving sample data to generate a designated driving demand identification model, wherein the designated driving demand identification model is used for identifying corresponding designated driving demand characteristics based on the travel information of the vehicle to be identified.

Optionally, the obtaining module further includes a first obtaining unit and a second obtaining unit. The first acquisition unit is used for extracting at least one type of designated driving characteristic information from designated driving travel data generated in a designated driving time period, performing characteristic construction based on the designated driving characteristic information, and generating a part of samples in designated driving sample data, wherein the designated driving travel data comprises at least one of the following data: navigation information, interest point analysis data of the position of the starting point of the driving program generation, vehicle equipment use characteristics before the driving program generation starts and driving behavior information in the driving program generation; the second acquisition unit is used for extracting at least one type of designated driving characteristic information from the travel information in at least one adjacent time period adjacent to the designated driving time period, performing characteristic construction based on the designated driving characteristic information, and generating a part of samples in designated driving sample data, wherein the travel information comprises at least one of the following items: the travel time period, the navigation information, the destination position of the driving travel and the driving route.

Optionally, the collection module further comprises a first collection unit. The first collection unit is used for obtaining historical designated driving service information by visiting the designated driving service platform, and obtaining the internet of vehicles data of each vehicle in a historical time period based on matching in the historical designated driving service information, wherein the internet of vehicles data further comprises at least one of the following data: door open and close states of the vehicle, trunk open and close states, vehicle speed, vehicle acceleration, vehicle steering wheel angle, steering wheel angle speed, accelerator pedal opening, brake pedal opening, and vehicle navigation data.

In the above-mentioned processing apparatus of car networking data of this disclosure, the apparatus further includes: the device comprises a detection module, a calling module, a determining module, a processing module and a pushing module. The detection module is used for detecting whether the cloud platform receives a designated driving request; the calling module is used for calling the driver information of at least one registered designated driver if the designated driver request is received; the determining module is used for determining whether the designated driver in an idle state exists or not based on the driver information of the designated driver; the processing module is used for determining at least one target designated driver based on a pushing rule and calling equipment information of the target designated driver, wherein the pushing rule is used for determining pushing priorities of a plurality of designated drivers; the pushing module is used for pushing the designated driving request to equipment held by the target designated driving driver based on the equipment information of the target designated driving driver.

In the above embodiments of the present disclosure, historical behavior information of a designated driving service provided for a user by a current platform is obtained, data in a time period corresponding to the user is obtained in internet of vehicles data as a sample, designated driving behavior characteristics are obtained, then the designated driving behavior characteristics are identified based on the internet of vehicles data, a large amount of designated driving behavior sample data is obtained, a designated driving service demand identification model of the user is trained based on the data, a designated driving demand which may exist in the user is identified, finally, model identification calculation is performed at a vehicle-mounted edge end, real-time designated driving service demand identification is realized, meanwhile, user position data does not need to be uploaded to a cloud end, safety of user privacy data is ensured, accurate identification of the user is realized, service pushing efficiency is greatly improved, safety of the user privacy data is ensured, and the technical problems that the user demand cannot be accurately identified and the service pushing efficiency is low are solved, the technical effects of accurately identifying the user requirements and improving the service pushing efficiency are achieved.

Example 4

According to an embodiment of the present invention, there is also provided a computer-readable storage medium. The computer readable storage medium comprises a stored program, wherein when the program is executed by a processor, the program controls a device where the computer readable storage medium is located to execute the method for processing the vehicle networking data according to the embodiment of the invention.

Example 5

According to the embodiment of the invention, the processor is used for running the program, wherein the processing method of the vehicle networking data is executed when the program runs.

Example 6

According to the embodiment of the disclosure, the disclosure further provides a vehicle, which comprises the vehicle networking data processing method of the embodiment of the disclosure.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described in detail in a certain embodiment.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or models, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A processing method of Internet of vehicles data is characterized by comprising the following steps:

the method comprises the following steps of collecting the Internet of vehicles information of at least one vehicle to be monitored in the running process of the vehicle to be monitored, wherein the Internet of vehicles information at least comprises the following steps: the travel information of the vehicle to be monitored;

calling a generation driving program identification model deployed at a vehicle-mounted edge end;

analyzing the car networking information by adopting the driving program generation identification model, and acquiring target driving generation characteristic of the vehicle to be monitored;

acquiring a driving replacement demand identification model based on the target generation driving behavior characteristics;

determining a designated driving request of the vehicle to be monitored by adopting the designated driving demand identification model;

uploading the designated driving request of the vehicle to be monitored to a cloud end platform, wherein at least one user end is allowed to obtain the designated driving request of the vehicle to be monitored, which is pushed by the cloud end platform.

2. The method of claim 1,

the method further comprises the following steps: acquiring Internet of vehicles data of a plurality of vehicles in historical time periods, wherein the historical time periods at least comprise driving generation time periods for which driving generation behavior information is generated, and the Internet of vehicles data at least comprises: the designated driving travel data is generated in the designated driving time period; training a machine learning model based on the designated driving journey data to generate the designated driving journey recognition model; acquiring a driving demand replacement identification model based on the target generation driving behavior characteristics, wherein the driving demand replacement identification model comprises the following steps: acquiring designated driving sample data based on the target designated driving behavior characteristics, wherein the designated driving sample data at least comprises at least one of the following data: travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period;

training a machine learning model based on the designated driving sample data to generate the designated driving demand recognition model, wherein the designated driving demand recognition model is used for recognizing corresponding designated driving demand characteristics based on the travel information of the vehicle to be recognized.

3. The method of claim 2, wherein at least one type of ride-on feature information is extracted from ride-on travel data generated within the ride-on time period, and feature construction is performed based on the ride-on feature information to generate a portion of the samples in the ride-on sample data, wherein the ride-on travel data comprises at least one of: the method comprises the following steps of navigation information, interest point analysis data of the position of a starting point of the driving program generation, vehicle equipment use characteristics before the driving program generation starts, and driving behavior information in the driving program generation.

4. The method of claim 2, wherein at least one type of ride-on feature information is extracted from travel information in at least one adjacent time period adjacent to the ride-on time period, and feature construction is performed based on the ride-on feature information to generate partial samples in the ride-on sample data, wherein the travel information comprises at least one of: the travel time period, the navigation information, the terminal position of the designated driving travel and the designated driving route.

5. The method of claim 2, wherein historical designated driving service information is obtained by accessing a designated driving service platform, and the internet of vehicle data for each vehicle in the historical time period is obtained based on a match in the historical designated driving service information, wherein the internet of vehicle data further comprises at least one of: door open and close states of the vehicle, trunk open and close states, vehicle speed, vehicle acceleration, vehicle steering wheel angle, steering wheel angle speed, accelerator pedal opening, brake pedal opening, and vehicle navigation data.

6. The method of any one of claims 1-5, wherein after uploading the designated drive request of the vehicle to be monitored to a cloud-end platform, the method further comprises:

detecting whether the cloud platform receives the designated driving request;

if the designated driving request is received, calling driver information of at least one registered designated driving driver;

determining whether a designated driver in an idle state exists based on the driver information of the designated driver;

determining at least one target designated driver based on a pushing rule, and calling equipment information of the target designated driver, wherein the pushing rule is used for determining pushing priorities of a plurality of designated drivers;

and pushing the designated driving request to equipment held by the target designated driving driver based on the equipment information of the target designated driving driver.

7. A device for processing Internet of vehicles data is characterized by comprising:

the collection module is used for collecting the vehicle networking information of the vehicle to be monitored in the running process of at least one vehicle to be monitored, wherein the vehicle networking information at least comprises: the travel information of the vehicle to be monitored;

the calling module is used for calling a designated driving identification model deployed at a vehicle-mounted edge end;

the first acquisition module is used for analyzing the internet of vehicles information by adopting the designated driving identification model and acquiring target designated driving behavior characteristics of the vehicle to be monitored;

the second acquisition module is used for acquiring a driving demand replacement identification model based on the target generation driving behavior characteristics;

the determining module is used for determining a designated driving request of the vehicle to be monitored by adopting the designated driving demand identification model;

the uploading module is used for uploading the designated driving request of the vehicle to be monitored to a cloud platform, wherein at least one user side is allowed to obtain the designated driving request of the vehicle to be monitored, and the designated driving request is pushed by the cloud platform.

8. The apparatus of claim 7, further comprising:

the vehicle networking management system comprises a collection module, a management module and a management module, wherein the collection module is used for collecting vehicle networking data of a plurality of vehicles in a historical time period, the historical time period at least comprises a driving generation time period for generating driving generation behavior information, and the vehicle networking data at least comprises: designated driving travel data generated in the designated driving time period;

the first training module is used for training a machine learning model based on the designated driving journey data to generate the designated driving journey recognition model;

the acquisition module is used for acquiring designated driving sample data based on the target designated driving behavior characteristics, wherein the designated driving sample data at least comprises at least one of the following data: travel information in at least one adjacent time period adjacent to the designated driving time period, and designated driving travel data generated in the designated driving time period;

and the second training module is used for training a machine learning model based on the designated driving sample data to generate a designated driving demand recognition model, wherein the designated driving demand recognition model is used for recognizing corresponding designated driving demand characteristics based on the travel information of the vehicle to be recognized.

9. The apparatus of claim 7, further comprising:

the detection module is used for detecting whether the cloud platform receives the designated driving request;

the calling module is used for calling the driver information of at least one registered designated driver if the designated driving request is received;

the determining module is used for determining whether the designated driver in an idle state exists or not based on the driver information of the designated driver;

the processing module is used for determining at least one target designated driver based on a pushing rule and calling equipment information of the target designated driver, wherein the pushing rule is used for determining pushing priorities of a plurality of designated drivers;

and the pushing module is used for pushing the designated driving request to equipment held by the target designated driving driver based on the equipment information of the target designated driving driver.

10. A vehicle comprising the method for processing Internet of vehicles data according to any one of claims 1 to 6.