CN113194138B - Travel management method and system based on AI deep learning - Google Patents
Travel management method and system based on AI deep learning Download PDFInfo
- Publication number
- CN113194138B CN113194138B CN202110467946.9A CN202110467946A CN113194138B CN 113194138 B CN113194138 B CN 113194138B CN 202110467946 A CN202110467946 A CN 202110467946A CN 113194138 B CN113194138 B CN 113194138B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- information
- acquiring
- client
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Abstract
The invention provides a trip management method and system based on AI deep learning, relating to the technical field of trip management, which is applied to a trip management system comprising a client, a cloud and an edge computing server, and comprises the following steps: the method comprises the steps that environmental information and vehicle information of a preset scene are collected in real time at an edge computing server side and are sent to a cloud end; identifying vehicle information at a cloud end, and acquiring associated data to perform data analysis so as to acquire vehicle management data; acquiring vehicle track data at the cloud according to the vehicle information, and predicting vehicle violation behaviors to acquire vehicle state information; monitoring the position of the vehicle, analyzing the vehicle position and the environmental information at the cloud end, and generating guide data containing a path according to an analysis result; the vehicle management data, the vehicle state information and the guiding data are sent to the client in real time, visual display is carried out on the client, and the problems that in the prior art, the travel service level is low and the travel efficiency is low are solved.
Description
Technical Field
The invention relates to the technical field of travel management, in particular to a travel management method and system based on AI deep learning.
Background
The progress of urbanization and the rapid increase of the number of motor vehicles, the traffic volume of urban roads is continuously increased, various traffic problems are highlighted, the urban traffic pressure is gradually increased, in recent years, the economic loss of the whole country is up to 2500 billions of yuan, which accounts for 2 percent of the GDP in the same year, the urban traffic accidents are frequent, and the traffic jam becomes a main factor which restricts the social and economic development and influences the quality of life.
However, the construction speed of the urban traffic infrastructure cannot keep up with the rapidly increasing traffic demand at present, and the conventional public traffic is atrophied, taxis and private cars are rapidly increased, the rail transit starts to start, and the traffic management technology level is low. And the urban traffic space is saturated due to the rapid and continuous increase of the vehicle holding capacity, and the normal traveling efficiency of residents is low directly caused by traffic jam.
With the development of the internet, particularly the mobile internet, social governance and synchronization put forward higher demands. The social governance mode is turning from one-way management to two-way interaction, from off-line to on-line fusion, and from pure government supervision to more attention on social cooperative governance, so that intelligent travel is provided. Therefore, an intelligent travel management method and system are lacked to solve the problems of low travel service level and low travel efficiency.
Disclosure of Invention
In order to overcome the technical defects, the invention aims to provide a travel management method and system based on AI deep learning, which are used for solving the problems of low travel service level and low travel efficiency.
The invention discloses a trip management method based on AI deep learning, which is applied to a trip management system comprising a client, a cloud and an edge computing server, and comprises the following steps:
the method comprises the steps that environmental information and vehicle information of a preset scene are collected in real time at an edge computing server side, and the environmental information and the vehicle information are sent to a cloud end;
identifying based on the vehicle information by adopting an image identification algorithm at the cloud, and acquiring associated data according to a vehicle identification result to perform data analysis so as to obtain a vehicle condition detection result and service recommendation data as vehicle management data;
obtaining vehicle track data according to the vehicle information at the cloud end, and predicting vehicle violation behaviors of the vehicle track based on the environment information to obtain vehicle state information;
monitoring the position of the vehicle in real time at an edge computing server, analyzing the position of the vehicle and the environmental information at the cloud side, and generating guide data containing a path according to an analysis result;
and sending the vehicle management data, the vehicle state information and the guiding data to a client in real time, and carrying out visual display at the client.
Preferably, the acquiring, at the edge computing server side, the environmental information and the vehicle information of the preset scene in real time includes the following steps:
adopting an access control system module and/or a face recognition module to collect people flow data in a preset scene in real time;
the method comprises the steps that a vehicle identification module is adopted to collect vehicle distribution data in a preset scene in real time;
static environment data in a preset database is obtained from a cloud end, the people flow data, the vehicle distribution data and the static environment data are associated, and the environment information and the vehicle information are obtained.
Preferably, the identifying is performed at the cloud end by adopting an image identification algorithm based on the vehicle information, and the associated data is acquired according to the vehicle identification result to perform data analysis so as to obtain vehicle condition detection data and service recommendation data vehicle management data, and the method comprises the following steps:
carrying out image recognition on the vehicle information to obtain license plate data and vehicle basic parameters;
adopting a pre-trained deep learning model to detect the vehicle condition of the vehicle information, and generating a processing scheme containing service recommendation data according to the vehicle condition detection result;
acquiring associated data, acquiring historical service data based on the associated data, updating the processing scheme based on the historical service data, and acquiring vehicle management data.
Preferably, the analyzing at the cloud end based on the vehicle position and the environment information, and generating guidance data including a route according to an analysis result includes the following:
acquiring static environment data from a preset database, and associating the environment information at the vehicle position with the static environment data to acquire real-time space data corresponding to the vehicle position;
and predicting the position of the vehicle according to the static environment data and the real-time space data to generate guiding data containing a path.
Preferably, before the predicting the vehicle position according to the static environment data and the real-time spatial data to generate the guidance data, the following is further included:
and the intelligent signal control system is connected with the intelligent signal control system, and the signal duration is adjusted based on the real-time spatial data through the intelligent signal control system.
Preferably, after the client performs the visual display, the method includes:
receiving a query instruction of a user on a client, acquiring data matched with the query instruction according to the query instruction on the vehicle management data, the vehicle state information or the guide data, and displaying the data on the client; wherein the query instruction comprises a gesture, audio, text, and an image.
The invention also provides a trip management system based on AI deep learning, which is characterized in that: the system comprises a client, a cloud server and an edge computing server;
the edge computing server includes:
the first acquisition module is used for acquiring environmental information and vehicle information of a preset scene in real time at the edge computing server;
wherein, the first acquisition module includes:
the access control system module and/or the face recognition sub-module are used for collecting people flow data in a preset scene;
the vehicle identification submodule is used for acquiring vehicle distribution data in a preset scene;
the processing submodule is used for acquiring static environment data in a preset database from a cloud end, associating the people flow data, the vehicle distribution data and the static environment data, and acquiring the environment information and the vehicle information;
the second acquisition module is used for monitoring the position of the vehicle in real time;
the first transmission module is used for sending the environment information, the vehicle track data and the vehicle position to a cloud server;
the cloud server includes:
the first processing module is used for identifying based on the vehicle information by adopting an image identification algorithm and acquiring associated data according to a vehicle identification result to perform data analysis so as to obtain a vehicle condition detection result and service recommendation data as vehicle management data;
wherein, the first processing module further comprises:
the recognition sub-module is used for carrying out image recognition on the vehicle information to acquire license plate data and vehicle basic parameters;
the monitoring submodule is used for detecting the vehicle condition of the vehicle information by adopting a pre-trained deep learning model and generating a processing scheme containing service recommendation data according to the vehicle condition detection result;
the scheme generation submodule is used for acquiring associated data, acquiring historical service data based on the associated data, updating the processing scheme based on the historical service data and acquiring vehicle management data;
the second processing module is used for acquiring vehicle track data according to the vehicle information, predicting vehicle violation behaviors of the vehicle track based on the environment information and acquiring vehicle state information;
the third processing module is used for analyzing based on the vehicle position and the environment information and generating guide data containing a path according to an analysis result;
the second transmission module is used for transmitting the vehicle management data, the vehicle state information and the guiding data to a client in real time;
the client comprises:
and the display module is used for receiving the vehicle management data, the vehicle state information and the guiding data and performing visual display on a client.
Preferably, the third processing module further comprises:
the processing submodule is used for acquiring static environment data from a preset database and associating the environment information under the vehicle position with the static environment data to acquire real-time space data corresponding to the vehicle position;
and the prediction sub-module is used for predicting the position of the vehicle according to the static environment data and the real-time space data so as to generate guide data containing a path.
Preferably, the client further comprises.
The query module is used for receiving a query instruction of a user on a client, acquiring data matched with the query instruction according to the query instruction on the vehicle management data, the vehicle state information or the guide data, and displaying the data on the client; wherein the query instruction comprises a gesture, audio, text and an image.
Preferably, the cloud server further includes:
and the regulation and control module is used for being connected with the intelligent signal control system and adjusting the signal duration based on the real-time spatial data through the intelligent signal control system.
After the technical scheme is adopted, compared with the prior art, the method has the following beneficial effects:
through the data transmission of the client, the cloud server and the edge calculation server, data are collected according to the edge calculation server, an AI-based deep learning model and big data analysis are adopted in the cloud server, vehicle management data, vehicle state information and guiding data are respectively generated based on the first processing module, the second processing module and the third processing module and fed back to the client, personalized routes and services are recommended to a user, guiding suggestions can be provided for vehicle tracks, parking and the like, the travel efficiency is improved, the integrity of closed-loop data of a travel platform is guaranteed, the big data analysis is more accurate, and the problems of low travel service level and low travel efficiency are effectively solved.
Drawings
Fig. 1 is a hardware schematic diagram of a first embodiment and a second embodiment of a travel management method and system based on AI deep learning according to the present invention;
fig. 2 is a flowchart of a first embodiment of a trip management method based on AI deep learning according to the present invention;
fig. 3 is a flowchart for embodying real-time collection of environmental information and vehicle information of a preset scene at an edge computing server in a first embodiment of the travel management method based on AI deep learning according to the present invention;
fig. 4 is a flowchart of vehicle management data for obtaining vehicle condition detection data and service recommendation data according to a first embodiment of the travel management method based on AI deep learning according to the present invention;
fig. 5 is a flowchart for representing analysis performed at the cloud based on vehicle position and environmental information, and generating guidance data including a route according to an analysis result in the first embodiment of the travel management method based on AI deep learning according to the present invention;
fig. 6 is a schematic block structure diagram of a second embodiment of the travel management system based on AI deep learning according to the present invention.
Reference numerals are as follows:
6. a trip management system; 61. a client; 611. a display module; 612. a query module; 62. a cloud server; 621. a first processing module; 6211. identifying a submodule; 6212. a monitoring submodule; 6213. a scheme generation submodule; 622. a second processing module; 623. a third processing module; 6231. a processing submodule; 6232. a prediction submodule; 6233. a second transmission module; 624. a regulation module; 63. an edge computing server; 631. a first acquisition module; 6311. the access control system module and/or the face recognition sub-module; 6312. a vehicle identification submodule; 6313. a processing submodule; 632. a second acquisition module; 633. a first transmission module.
Detailed Description
The advantages of the invention are further illustrated in the following description of specific embodiments in conjunction with the accompanying drawings.
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if," as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination," depending on the context.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection through an intermediate medium, and those skilled in the art will understand the specific meaning of the terms as they are used in the specific case.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
The first embodiment is as follows: the embodiment discloses a trip management method based on AI deep learning, which is applied to a trip management system 6 comprising a Client 61, a cloud server 62 and an edge computing server 63, referring to fig. 1, wherein the Client comprises but is not limited to APP, WEB, client and vehicle-mounted terminals respectively facing to users, merchants and government departments, the cloud clothes can cover various trip management aspects such as communities, transportation, public security and parking lots, and mainly comprises functional services such as trip law enforcement, audit and control, analysis and study, trip induction, operation and maintenance supervision, command and dispatch, situation monitoring, vehicle tracks, personnel tracks, data analysis, report generation, chat friend-making service, old and weak supervision, security assurance, reservation service, payment service, convenience life service, other life services, car owners, vehicles, vehicle navigation service, trip peripheral service, vehicle recommendation service, road condition release service and the like, the edge computing server is used for acquiring data of reading, transportation, public security and parking lots, and specifically, referring to fig. 2:
s100: the method comprises the steps that environmental information and vehicle information of a preset scene are collected in real time at an edge computing server side, and the environmental information and the vehicle information are sent to a cloud end;
in the above steps, in a preset scene, including but not limited to a community, a traffic intersection, a parking lot, and the like, the edge computing server is configured to collect real-time data, where the real-time data includes people stream data, vehicle distribution data, and the like, so as to reflect travel traffic in the preset scene, specifically, referring to fig. 3, the edge computing server collects environmental information and vehicle information of the preset scene in real time, and the method includes the following steps:
s110: adopting an access control system module and/or a face recognition module to collect people flow data in a preset scene in real time;
in the above steps, the access control system module is adopted to collect people flow data, the access control system module can be connected with the cloud server, vehicle data on the historical path data of the user fed back by the cloud server are received, and suggestions are given to the user, such as path change or trip mode change, so that the vehicle flow pressure is reduced, the vehicle jam condition is reduced, the number of people going out can be accumulated through the access control system module, the people flow data and the distribution condition of the people flow data under the current scene can be identified through the face identification module, and meanwhile, the preset database can be associated to perform personalized path recommendation.
S120: the method comprises the steps that a vehicle identification module is adopted to collect vehicle distribution data in a preset scene in real time;
in the above steps, the vehicle identification module may implement positioning and detection of the vehicle by using, for example, an object detection model, to obtain vehicle distribution data in the scene, such as a parking lot, as a specific example, and may also determine a usage situation of a current parking space in the parking lot for vehicle parking position suggestion for subsequent entering the parking lot.
S130: and acquiring static environment data in a preset database from the cloud, associating the people flow data, the vehicle distribution data and the static environment data, and acquiring environment information and vehicle information.
The total amount and distribution of the people flow and the vehicles can be obtained through the steps S110 and S120, and the current real-time environment data can be obtained by matching the corresponding distribution with the static environment data, wherein the static environment data is used as a map, is a map which is collected in advance and does not contain any people or vehicles and has detailed coordinates, and is matched and added in the static environment data according to the distribution coordinates of the people flow and the vehicles.
S200: identifying based on vehicle information by adopting an image identification algorithm at the cloud, and acquiring associated data according to a vehicle identification result to perform data analysis so as to obtain a vehicle condition detection result and service recommendation data as vehicle management data;
in the foregoing step S100, the real-time environment information is obtained, and vehicle identification can be performed at the cloud end to perform vehicle management on vehicles in each preset scene, referring to fig. 4, specifically, the vehicle information is identified at the cloud end by using an image identification algorithm, and associated data is obtained according to a vehicle identification result to perform data analysis, so as to obtain vehicle condition detection data and service recommendation data vehicle management data, which includes the following steps:
s210: carrying out image recognition on the vehicle information to obtain license plate data and vehicle basic parameters;
in the above steps, the image recognition may be implemented by using a pre-trained deep learning neural network model (which may be combined with the model in step S220 to form a processing model, or two models may be set to be processed separately), the basic parameters of the vehicle include, but are not limited to, vehicle type, vehicle body color, human face in the vehicle, and positions of various vehicles and vehicle accessories, the license plate data may be extracted by using a recognition algorithm for characters in the image, it should be noted that there is no license plate data, and at this time, the basic parameters of the vehicle are required to search for vehicle data of a type consistent with the vehicle in the preset vehicle model data, so as to improve the accuracy of the basic parameters of the vehicle.
S220: the method comprises the steps that a pre-trained deep learning model is adopted to detect vehicle conditions of vehicle information, and a processing scheme containing service recommendation data is generated according to a vehicle condition detection result;
in the above steps, the vehicle condition detection includes, but is not limited to, determining whether the vehicle has scratches, whether insurance is due, whether vehicle washing is needed, a brand of articles of daily use frequently used by a vehicle owner, whether the vehicle breaks rules and the like by using artificial intelligence and a big data technology, and generating a processing scheme according to a detection result.
S230: acquiring associated data, acquiring historical service data based on the associated data, updating a processing scheme based on the historical service data, and acquiring vehicle management data.
In the above steps, the obtained associated data is the user history data, including but not limited to service data, path data, etc., and a user profile may be generated according to the user history data to obtain service data preferred by the user, and the processing scheme generated in step S220 may be updated to improve the matching degree between the processing scheme and the user, so as to generate the processing scheme including the service recommendation data.
S300: acquiring vehicle track data according to the vehicle information at the cloud end, and predicting vehicle violation behaviors of the vehicle track based on the environment information to acquire vehicle state information;
in the steps, the cloud end receives the vehicle data in each scene collected by the edge computing server, so that the vehicle data in each scene can be collected to analyze each vehicle route, on one hand, the vehicle violation behaviors can be predicted by combining the current real-time environment information, the personnel track and the vehicle track can be tracked, and the violation behaviors can be effectively checked, illegal vehicles can be hit, and the occurrence rate of travel accidents can be reduced by the technical means; on the other hand, the vehicle route may be obtained to generate a route map of the vehicle, so as to obtain the route habits of the users and feed the obtained route habits back to the access control system in step S110, so as to remind the users and reduce traffic pressure.
S400: monitoring the position of the vehicle in real time at an edge computing server, analyzing the vehicle position and the environmental information at the cloud side, and generating guide data containing a path according to an analysis result;
in the above steps, the vehicle identification module collects vehicle distribution data in a preset scene in real time according to step S120, and may monitor and obtain a real-time vehicle position, where the guidance data including a route includes, but is not limited to, for example, replacement of a congested route, parking in a parking lot, and the like, and for example, if the vehicle identification module obtains that a congestion condition in a current route is serious (a preset threshold vehicle flow is exceeded, and vehicle distribution exceeds a preset condition at the same time), a preferred replacement route is sent to the client (a priority is set only according to a congestion condition of a road condition, that is, a congestion-free route is the highest priority), when the route is specific, the route is analyzed at the cloud based on the vehicle position and the environmental information, and guidance data including the route is generated according to an analysis result, referring to fig. 5, the following steps are included:
s410: acquiring static environment data from a preset database, and associating environment information under the vehicle position with the static environment data to acquire real-time space data corresponding to the vehicle position;
in the steps, the vehicle position map under the current scene can be obtained by matching and filling the vehicle data under the static environment data, so that the construction of the parking lot and the unified and effective management of the berth are reasonably planned, and the resources of static traffic and dynamic traffic are integrated.
S420: the vehicle position is predicted from the static environmental data and the real-time spatial data to generate guidance data including a route.
As described above, the prediction includes, but is not limited to, changing of a congested route, parking lot parking route, etc., which may assist city management such as adjustment of traffic light time, etc., and effective utilization of resources, and thus before predicting a vehicle position based on static environment data and real-time spatial data to generate guidance data, the following is further included:
and the intelligent signal control system is connected with the intelligent signal control system, and the signal duration is adjusted based on real-time spatial data through the intelligent signal control system.
In the above steps, the control signal can be sent out through the cloud server, so that the intelligent signal control system can adjust the signal duration in time, the guidance system can shunt the vehicle by combining the flow data, the road congestion is further relieved, and the problem of low traveling efficiency is solved.
S500: and sending the vehicle management data, the vehicle state information and the guiding data to the client in real time, and carrying out visual display at the client.
In the steps, a user can know the current real-time environment information through the vehicle management data so as to reasonably plan a route, a merchant can adjust a business strategy, a management department can adjust an intelligent signal control system according to the real-time environment information to relieve the congestion situation, meanwhile, the person track can be tracked according to the vehicle state information, the violation behaviors are effectively checked, illegal vehicles are hit, the occurrence rate of travel accidents is reduced, the vehicle condition of the user can be personally reminded, a processing scheme is provided, the user can avoid a congested road section according to the guiding data so as to relieve traffic pressure, or the user is guided to park, the construction of a parking lot is reasonably planned, and the unified and effective management of parking spaces is realized.
In addition, in order to further increase the application range of the system, the method increases the interaction function with the client, and specifically includes, after the client performs the visual display: receiving a query instruction of a user on a client, acquiring data matched with the query instruction according to the query instruction on vehicle management data, vehicle state information or guide data, and displaying the data on the client; the query instruction comprises a gesture, audio, characters and an image.
In the above steps, according to the query instruction sent by the user, as an example: and inquiring whether the XX road section is unblocked, and analyzing the traffic flow condition of the current road section and the positions of all vehicles according to the environmental information to determine the unblocked condition of the current road section. The query instruction includes but is not limited to a gesture, audio, text and an image, that is, the user can send the query instruction by clicking or specifying the gesture, voice call and the like, and the query instruction is realized by adopting a corresponding acquisition algorithm and module.
In the embodiment, data transmission through the client, the cloud server and the edge computing server is realized, the cloud server adopts an AI-based deep learning model and big data analysis, the travel efficiency is improved, data sharing is more convenient, and the cloud side realizes interconnection and cooperation. Data acquisition, application service, platform service and service independently greatly ensure the integrity of trip platform closed-loop data, also ensure the independent characteristic of each service, make full use of each platform data transmission to carry out planning and design, make all data can be in coordination with the linkage, big data analysis is more accurate, and the problem of low trip service level and low trip efficiency is solved.
Example two: the embodiment also provides a travel management system 6 based on AI deep learning, referring to fig. 1 and fig. 6, including a Client 61, a cloud server 62 and an edge computing server 63, where the Client includes but is not limited to APP, WEB, client and vehicle-mounted terminal respectively facing to a user, a merchant and a government administration department.
Specifically, the edge calculation server 63 includes:
the first collecting module 631 is configured to collect, in real time, environment information and vehicle information of a preset scene at the edge computing server; wherein, the first collecting module 631 comprises:
the access control system module and/or the face identification submodule 6311 are/is configured to collect people stream data in a preset scene;
the vehicle identification submodule 6312 is configured to collect vehicle distribution data in a preset scene;
the processing submodule 6313 is configured to obtain static environment data in a preset database from the cloud, associate the pedestrian flow data, the vehicle distribution data and the static environment data, and obtain environment information and vehicle information;
a second acquisition module 632, configured to monitor the vehicle position in real time;
the first transmission module 633 is used for sending the environmental information, the vehicle track data and the vehicle position to the cloud server;
The cloud server 62 includes:
the first processing module 621 is configured to perform identification based on vehicle information by using an image identification algorithm, and acquire associated data according to a vehicle identification result to perform data analysis, so as to acquire a vehicle condition detection result and service recommendation data as vehicle management data; wherein the first processing module 621 further includes:
the recognition sub-module 6211 is configured to perform image recognition on the vehicle information, and acquire license plate data and vehicle basic parameters;
the monitoring submodule 6212 is configured to perform vehicle condition detection on the vehicle information by using a pre-trained deep learning model, and generate a processing scheme including service recommendation data according to a vehicle condition detection result;
a scenario generation submodule 6213 configured to acquire the associated data, acquire historical service data based on the associated data, update a processing scenario based on the historical service data, and acquire vehicle management data;
the second processing module 622 is configured to obtain vehicle track data according to the vehicle information, predict a vehicle violation behavior of the vehicle track based on the environmental information, and obtain vehicle state information;
a third processing module 623, configured to perform analysis based on the vehicle position and the environmental information, and generate guidance data including a route according to an analysis result;
in a preferred embodiment, the third processing module further comprises:
the processing submodule 6231 is configured to obtain static environment data from a preset database, and associate environment information at the vehicle position with the static environment data to obtain real-time spatial data corresponding to the vehicle position;
a prediction sub-module 6232 is configured to predict the vehicle position according to the static environment data and the real-time spatial data to generate guidance data including a route.
The second transmission module 6233 is configured to send the vehicle management data, the vehicle status information, and the guidance data to the client in real time;
in a preferred implementation, the cloud server 62 further includes:
and the regulation and control module 624 is used for being connected with the intelligent signal control system and adjusting the signal duration based on the real-time spatial data through the intelligent signal control system.
The cloud server covers various aspects of trip management such as communities, transportation, parking lots and the like, and mainly comprises but is not limited to trip enforcement, inspection and control, analysis and study, trip guidance, operation and maintenance supervision, other life services, vehicle owner figures, vehicle figures, trip navigation services and the like. Meanwhile, construction of a parking lot and unified effective management of berths are reasonably planned by utilizing trip platform data, resources of static traffic and dynamic traffic are integrated, urban management such as adjustment of traffic light time and effective utilization of resources are assisted, security and protection arrangement and control are provided for management departments, convenient smart life services can be brought for users, parking spaces are found, parking spaces are reserved, and the like, meanwhile, management efficiency and benefit are improved for operation units by comprehensive data support, and operation cost is greatly reduced.
The client 61 includes:
the display module 611 is configured to receive the vehicle management data, the vehicle status information, and the guidance data and perform a visual display at the client.
In a preferred embodiment, the client further includes:
the query module 612 is configured to receive a query instruction of a user on a client, acquire data matched with the query instruction from vehicle management data, vehicle state information, or guidance data according to the query instruction, and display the data on the client; the query instruction comprises gestures, audio, characters and images.
The client is used for receiving various pushed information (voice, text, video, images and the like) sent by the cloud server, displaying the information by using the display module 611 so that the client can conveniently obtain suggestions for traveling in time, meanwhile, the client can transmit the information such as voice, video, text and images to the cloud platform by using the query door module 612, and the cloud server 62 gives corresponding responses. The intelligent platform provides data support and intelligent service for the parking lot, the community and management departments, for example, the platform is connected with parking lot information data and community user data for uploading, and the platform performs analysis and evidence obtaining and the like, so that the function of each end is fully exerted, and perfect and convenient travel service is provided for users, and the full utilization of resources is also guaranteed.
In this embodiment, the client can be implemented as a terminal of various forms. For example, the terminal described in the present invention may include an intelligent terminal such as a mobile phone, a smart phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, etc., and a fixed terminal such as a digital TV, a desktop computer, etc. In the following, it is assumed that the terminal is an intelligent terminal. However, it will be understood by those skilled in the art that the configuration according to the embodiment of the present invention can be applied to a fixed type terminal in addition to elements particularly used for moving purposes.
It should be noted that the embodiments of the present invention have been described in terms of preferred embodiments, and not by way of limitation, and that those skilled in the art can make modifications and variations of the embodiments described above without departing from the spirit of the invention.
Claims (10)
1. A trip management method based on AI deep learning is applied to a trip management system comprising a client, a cloud and an edge computing server, and is characterized by comprising the following steps:
the method comprises the steps that environmental information and vehicle information of a preset scene are collected in real time at an edge computing server side, and the environmental information and the vehicle information are sent to a cloud end;
identifying the vehicle information at the cloud by adopting an image identification algorithm, and acquiring associated data according to a vehicle identification result to perform data analysis so as to acquire a vehicle condition detection result and service recommendation data as vehicle management data;
obtaining vehicle track data at the cloud according to the vehicle information, and predicting vehicle violation behaviors of the vehicle track based on the environment information to obtain vehicle state information;
monitoring the position of a vehicle in real time at an edge computing server, analyzing the vehicle position and the environmental information at a cloud side, and generating guide data containing a path according to an analysis result;
the vehicle management data, the vehicle state information and the guiding data are sent to a client in real time, and visual display is carried out on the client;
the method for acquiring the environmental information and the vehicle information of the preset scene in real time at the edge computing server comprises the following steps:
the method comprises the steps that the edge computing server collects people stream data and vehicle distribution data in a preset scene, static environment data in a preset database are obtained from a cloud end, the people stream data, the vehicle distribution data and the static environment data are correlated, and environment information and vehicle information of a real-time space are obtained.
2. A travel management method according to claim 1, wherein the edge computing server collects traffic data and vehicle distribution data in a preset scene, and the method comprises the following steps:
adopting an access control system module and/or a face recognition module to collect people flow data in a preset scene in real time;
and a vehicle identification module is adopted to collect vehicle distribution data in a preset scene in real time.
3. A travel management method according to claim 1, wherein the cloud side adopts an image recognition algorithm to perform recognition based on the vehicle information, and obtains associated data according to a vehicle recognition result to perform data analysis so as to obtain vehicle condition detection data and service recommendation data vehicle management data, and the method comprises the following steps:
carrying out image recognition on the vehicle information to obtain license plate data and vehicle basic parameters;
adopting a pre-trained deep learning model to detect the vehicle condition of the vehicle information, and generating a processing scheme containing service recommendation data according to the vehicle condition detection result;
acquiring associated data, acquiring historical service data based on the associated data, updating the processing scheme based on the historical service data, and acquiring vehicle management data.
4. A travel management method according to claim 1, wherein the analyzing at the cloud based on the vehicle position and the environment information, and generating guidance data including a route according to an analysis result includes the following:
acquiring static environment data from a preset database, and associating the environment information at the vehicle position with the static environment data to acquire real-time space data corresponding to the vehicle position;
and predicting the position of the vehicle according to the static environment data and the real-time space data to generate guiding data containing a path.
5. A travel management method according to claim 4, further comprising, before said predicting the vehicle position from the static environment data and the real-time spatial data to generate guidance data, the steps of:
and the intelligent signal control system is connected with the intelligent signal control system, and the signal duration is adjusted based on the real-time spatial data through the intelligent signal control system.
6. A travel management method according to claim 1, wherein after the client performs the visual display, the method includes:
receiving a query instruction of a user on a client, acquiring data matched with the query instruction according to the query instruction on the vehicle management data, the vehicle state information or the guide data, and displaying the data on the client; wherein the query instruction comprises a gesture, audio, text and an image.
7. The utility model provides a trip management system based on AI deep learning which characterized in that: the system comprises a client, a cloud server and an edge computing server;
the edge computing server includes:
the first acquisition module is used for acquiring environmental information and vehicle information of a preset scene in real time at the edge computing server; wherein the first acquisition module comprises:
the access control system module and/or the face recognition sub-module are used for collecting people flow data in a preset scene;
the vehicle identification submodule is used for acquiring vehicle distribution data in a preset scene;
the processing submodule is used for acquiring static environment data in a preset database from a cloud end, associating the people flow data, the vehicle distribution data and the static environment data, and acquiring the environment information and the vehicle information;
the second acquisition module is used for monitoring the position of the vehicle in real time;
the first transmission module is used for sending the environment information, the vehicle track data and the vehicle position to a cloud server;
the cloud server includes:
the first processing module is used for identifying based on the vehicle information by adopting an image identification algorithm and acquiring associated data according to a vehicle identification result to perform data analysis so as to acquire a vehicle condition detection result and service recommendation data as vehicle management data;
wherein, the first processing module still includes:
the recognition submodule is used for carrying out image recognition on the vehicle information to acquire license plate data and vehicle basic parameters; the monitoring submodule is used for detecting the vehicle condition of the vehicle information by adopting a pre-trained deep learning model and generating a processing scheme containing service recommendation data according to a vehicle condition detection result;
the scheme generation submodule is used for acquiring associated data, acquiring historical service data based on the associated data, updating the processing scheme based on the historical service data and acquiring vehicle management data;
the second processing module is used for acquiring vehicle track data according to the vehicle information, predicting vehicle violation behaviors of the vehicle track based on the environment information and acquiring vehicle state information;
the third processing module is used for analyzing based on the vehicle position and the environment information and generating guide data containing a path according to an analysis result;
the second transmission module is used for transmitting the vehicle management data, the vehicle state information and the guiding data to a client in real time;
the client comprises:
and the display module is used for receiving the vehicle management data, the vehicle state information and the guiding data and performing visual display on a client.
8. A travel management system according to claim 7, wherein said third processing module further comprises:
the processing submodule is used for acquiring static environment data from a preset database and associating the environment information under the vehicle position with the static environment data to acquire real-time space data corresponding to the vehicle position;
and the prediction sub-module is used for predicting the vehicle position according to the static environment data and the real-time space data so as to generate guide data containing a path.
9. A travel management system according to claim 7, wherein the client further comprises:
the query module is used for receiving a query instruction of a user on a client, acquiring data matched with the query instruction according to the query instruction on the vehicle management data, the vehicle state information or the guide data, and displaying the data on the client; wherein the query instruction comprises a gesture, audio, text, and an image.
10. A travel management system according to claim 8, wherein the cloud server further comprises:
and the regulation and control module is used for being connected with the intelligent signal control system and adjusting the signal duration based on the real-time spatial data through the intelligent signal control system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110467946.9A CN113194138B (en) | 2021-04-28 | 2021-04-28 | Travel management method and system based on AI deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110467946.9A CN113194138B (en) | 2021-04-28 | 2021-04-28 | Travel management method and system based on AI deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113194138A CN113194138A (en) | 2021-07-30 |
| CN113194138B true CN113194138B (en) | 2022-10-18 |
Family
ID=76979955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110467946.9A Active CN113194138B (en) | 2021-04-28 | 2021-04-28 | Travel management method and system based on AI deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113194138B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114360267B (en) * | 2021-11-25 | 2023-10-10 | 广东唯普汽车电子商务股份有限公司 | Cloud detection system-based vehicle condition detection method and device and cloud detection system |
| CN114430424A (en) * | 2021-12-31 | 2022-05-03 | 联通智网科技股份有限公司 | Method and device for processing big data of Internet of vehicles and storage medium |
| CN114694416A (en) * | 2022-03-24 | 2022-07-01 | 东风汽车集团股份有限公司 | Violation vehicle avoidance method and avoidance system based on cloud server |
| CN114860976B (en) * | 2022-04-29 | 2023-05-05 | 长沙公交智慧大数据科技有限公司 | Image data query method and system based on big data |
| CN115440047A (en) * | 2022-09-14 | 2022-12-06 | 甘肃新视能科技有限公司 | Intelligent traffic system based on cloud side end fusion technology |
| CN116153090B (en) * | 2022-10-25 | 2024-03-29 | 浙江特锐讯智能科技有限公司 | Full-track accurate license plate recognition management method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106681250A (en) * | 2017-01-24 | 2017-05-17 | 浙江大学 | Cloud-based intelligent car control and management system |
| CN111915896A (en) * | 2020-08-17 | 2020-11-10 | 重庆电子工程职业学院 | Intelligent traffic system and method based on Internet of things |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1716335A (en) * | 2005-08-04 | 2006-01-04 | 河南雪城科技股份有限公司 | Real time information investigation system for road traffic |
| US9288270B1 (en) * | 2011-04-22 | 2016-03-15 | Angel A. Penilla | Systems for learning user preferences and generating recommendations to make settings at connected vehicles and interfacing with cloud systems |
| CN105180952A (en) * | 2015-08-06 | 2015-12-23 | 北汽福田汽车股份有限公司 | Vehicle navigation method and navigation system |
| CN107967817A (en) * | 2017-11-17 | 2018-04-27 | 张慧 | Intelligent managing system for parking lot and method based on multi-path camera deep learning |
| CN108364494B (en) * | 2018-02-26 | 2023-11-10 | 郑清辉 | Intelligent road traffic management method, system and platform |
| CN110455302B (en) * | 2018-05-08 | 2023-10-20 | 奥迪股份公司 | Navigation system control method, device, computer equipment and storage medium |
| CN110930703A (en) * | 2019-11-26 | 2020-03-27 | 陕西坤翔互联网科技有限公司 | Intelligent static traffic control service system and method |
| CN112466144A (en) * | 2021-02-03 | 2021-03-09 | 华睿交通科技有限公司 | Road network traffic situation management and control system |
-
2021
- 2021-04-28 CN CN202110467946.9A patent/CN113194138B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106681250A (en) * | 2017-01-24 | 2017-05-17 | 浙江大学 | Cloud-based intelligent car control and management system |
| CN111915896A (en) * | 2020-08-17 | 2020-11-10 | 重庆电子工程职业学院 | Intelligent traffic system and method based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113194138A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113194138B (en) | Travel management method and system based on AI deep learning | |
| CN111091720B (en) | Congestion road section identification method and device based on signaling data and floating car data | |
| CN108242149A (en) | A kind of big data analysis method based on traffic data | |
| CN111862606B (en) | Illegal operating vehicle identification method based on multi-source data | |
| CN114067560B (en) | Highway epidemic prevention and control non-inductive personnel detection and vehicle trajectory tracking system | |
| CN104508719A (en) | Driving assistance system and driving assistance method | |
| CN103594000A (en) | Parking space search platform based on mobile network services | |
| CN106652523B (en) | Intelligent traffic system based on real-time reservation and processing of roads | |
| WO2014201895A1 (en) | System and method for predicting arrival time of vehicle | |
| CN102855599B (en) | Intelligent bus system | |
| CN103606299A (en) | Parking space information sharing method based on smart phones | |
| CN110705848A (en) | Comprehensive traffic service evaluation method and device based on individual trip chain | |
| CN111653092A (en) | Bus route is wisdom public transit management monitored control system in coordination | |
| CN114693495B (en) | Smart city public traffic management method, Internet of things system, device and medium | |
| CN111785073A (en) | Parking lot guidance system based on human factor | |
| CN113393137B (en) | Scheduling sharing system based on Internet of vehicles | |
| Namiot et al. | On bikes in smart cities | |
| CN113468243A (en) | Subway passenger flow analysis and prediction method and system | |
| CN113542364B (en) | Bus and network appointment linkage intelligent traffic system | |
| CN114338785A (en) | Accompanying type travel service system | |
| CN106355872A (en) | Intelligent public transport management system and application | |
| CN112712699A (en) | Intelligent urban road congestion charging system management method | |
| Link et al. | Combining GPS tracking and surveys for a mode choice model: Processing data from a quasi-natural experiment in Germany | |
| CN111612927A (en) | Expressway reservation traffic system | |
| CN117592788B (en) | Bus running risk identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |