Method and apparatus for processing internet of vehicles data

Abstract

The present disclosure provides a kind of vehicle networking data processing method and device. Wherein, the method can include: collecting the vehicle networking information of at least one vehicle to be monitored during the driving process of the vehicle to be monitored, wherein the vehicle networking information at least includes: the journey information of the vehicle to be monitored;Call the driving service journey identification model deployed in the vehicle-mounted edge terminal;Using the driving service journey identification model to analyze the vehicle networking information, obtain the target driving service behavior characteristics of the vehicle to be monitored;Based on the target driving service behavior characteristics, obtain the driving service demand identification model;Using the driving service request of the driving service demand identification model;Upload the driving service request of the vehicle to be monitored to the cloud platform, wherein at least one user terminal is allowed to obtain the driving service request of the vehicle to be monitored pushed by the cloud platform.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of data processing, and particularly relates to a method and device for processing Internet of Vehicles data. BACKGROUND

[0002] At present, the recommendation of driving service is mainly based on the historical information of the user, the historical behavior of the platform providing driving service for the user is obtained, the possibility of the user needing driving is inferred according to the frequency of the behavior, and then the related service content push or coupons are sent to the user through an application (APP).

[0003] At present, there is no effective solution to the technical problems of being unable to accurately identify user demand and low service push efficiency. SUMMARY

[0004] The embodiments of the present application provide a method and device for processing Internet of Vehicles data to at least solve the technical problems of being unable to accurately identify user demand and low service push efficiency.

[0005] According to an aspect of the embodiments of the present application, a method for processing Internet of Vehicles data is provided, comprising: collecting Internet of Vehicles information of a to-be-monitored vehicle during driving of the to-be-monitored vehicle, wherein the Internet of Vehicles information at least includes: travel information of the to-be-monitored vehicle; calling a driving trip identification model deployed on a vehicle-mounted edge side; analyzing the Internet of Vehicles information by using the driving trip identification model to obtain target driving behavior characteristics of the to-be-monitored vehicle; obtaining a driving demand identification model based on the target driving behavior characteristics; determining a driving request of the to-be-monitored vehicle by using the driving demand identification model; and uploading the driving request of the to-be-monitored vehicle to a cloud platform, wherein at least one user terminal is allowed to obtain the driving request of the to-be-monitored vehicle pushed by the cloud platform.

[0006] Optionally, the method further comprises: collecting Internet of Vehicles data of a plurality of vehicles in a historical time period, wherein the historical time period at least includes a driving time period in which driving behavior information is generated, and the Internet of Vehicles data at least includes: driving trip data generated in the driving time period; training a machine learning model based on the driving trip data to generate the driving trip identification model; and determining the driving request of the to-be-monitored vehicle by using the driving demand identification model, comprising: obtaining driving sample data based on the target driving behavior characteristics, wherein the driving sample data at least includes at least one of: travel information in at least one adjacent time period adjacent to the driving time period, and driving trip data generated in the driving time period; and training a machine learning model based on the driving sample data to generate the driving demand identification model, wherein the driving demand identification model is used to identify corresponding driving demand characteristics based on travel information of a to-be-identified vehicle.

[0007] Optionally, after uploading the chauffeur request of the to-be-monitored vehicle to the cloud platform, the method further comprises: detecting whether the chauffeur request is received by the cloud platform; if the chauffeur request is received, calling the driver information of the registered at least one chauffeur; determining whether there is an idle chauffeur based on the driver information of the chauffeur; determining at least one target chauffeur based on a push rule, and calling the equipment information of the target chauffeur, wherein the push rule is used to determine the push priority of a plurality of chauffeurs; and pushing the chauffeur request to the equipment held by the target chauffeur based on the equipment information of the target chauffeur.

[0008] According to another aspect of the embodiment of the present application, a vehicle networking data processing device is provided, comprising: a collection module configured to collect vehicle networking information of at least one to-be-monitored vehicle during driving of the to-be-monitored vehicle, wherein the vehicle networking information at least includes travel information of the to-be-monitored vehicle; a calling module configured to call a chauffeur travel identification model deployed on a vehicle-mounted edge terminal; a first acquisition module configured to acquire target chauffeur behavior characteristics of the to-be-monitored vehicle by using the chauffeur travel identification model to analyze the vehicle networking information; a second acquisition module configured to acquire a chauffeur demand identification model based on the target chauffeur behavior characteristics; a determination module configured to determine a chauffeur request of the to-be-monitored vehicle by using the chauffeur demand identification model; and an uploading module configured to upload the chauffeur request of the to-be-monitored vehicle to a cloud platform, wherein at least one user terminal is allowed to acquire the chauffeur request of the to-be-monitored vehicle pushed by the cloud platform.

[0009] Optionally, the device further comprises: a collection module configured to collect vehicle networking data of a plurality of vehicles in a historical time period, wherein the historical time period at least includes a chauffeur time period in which chauffeur behavior information is generated, and the vehicle networking data at least includes chauffeur travel data generated in the chauffeur time period; a first training module configured to train a machine learning model based on the chauffeur travel data to generate the chauffeur travel identification model; an acquisition module configured to acquire chauffeur sample data based on the target chauffeur behavior characteristics, wherein the chauffeur sample data at least includes at least one of the following: travel information in at least one adjacent time period adjacent to the chauffeur time period, and chauffeur travel data generated in the chauffeur time period; and a second training module configured to train the machine learning model based on the chauffeur sample data to generate the chauffeur demand identification model, wherein the chauffeur demand identification model is used to identify corresponding chauffeur demand characteristics based on travel information of a to-be-identified vehicle.

[0010] Optionally, the device further comprises a detection module configured to detect whether the cloud platform receives a ride request; a calling module configured to call driver information of the registered at least one ride driver if the ride request is received; a determination module configured to determine whether there is a ride driver in an idle state based on the driver information of the ride driver; a processing module configured to determine at least one target ride driver based on a push rule and call device information of the target ride driver, wherein the push rule is used to determine a push priority of a plurality of ride drivers; and a push module configured to push the ride request to a device held by the target ride driver based on the device information of the target ride driver.

[0011] According to another aspect of the embodiments of the present application, a computer readable storage medium is further provided. The computer readable storage medium comprises a stored program, wherein the program, when executed by a processor, controls a device where the computer readable storage medium is located to perform the vehicle networking data processing method of the embodiments of the present application.

[0012] According to another aspect of the embodiments of the present application, a processor is further provided, which is used to execute a program, wherein the program, when executed, performs the vehicle networking data processing method of the embodiments of the present application.

[0013] According to another aspect of the embodiments of the present application, a vehicle is further provided, which comprises a vehicle networking data processing method of the embodiments of the present application.

[0014] In the embodiments of the present application, by obtaining historical behavior information of the current platform providing ride service for users, and obtaining data of the user in a corresponding time period in the vehicle networking data as a sample, ride behavior characteristics are obtained, then the ride behavior characteristics are identified based on the vehicle networking data, a large amount of ride behavior sample data is obtained, a user ride service demand identification model is trained based on the data, the ride demand of the user is identified, finally, model identification calculation is performed on the vehicle edge side, real-time ride service demand identification is realized, at the same time, user location data does not need to be uploaded to the cloud, user privacy data security is ensured, accurate user identification is realized, service push efficiency is greatly improved, at the same time, user privacy data security is ensured, thereby solving the technical problems of being unable to accurately identify user demand and low service push efficiency, and achieving the technical effects of accurately identifying user demand and improving service push efficiency.

[0015] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0017] Figure 1 is a flowchart of a vehicle networking data processing method according to an embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of a flow of a chauffeur trip identification scheme according to an embodiment of the present disclosure;

[0019] Figure 3 is a schematic diagram of a flow of a chauffeur demand identification scheme according to an embodiment of the present disclosure;

[0020] Figure 4 is a schematic diagram of a flow of a model function edge end implementation scheme according to an embodiment of the present disclosure;

[0021] Figure 5 is a schematic diagram of a vehicle networking data processing apparatus according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] In order to make the personnel in the art better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units need not be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] Embodiment 1

[0025] The vehicle networking data processing method of the present disclosure embodiment is introduced below.

[0026] The Internet of Vehicles data includes gray data and color data. The gray data mainly refers to various sensor signals of the vehicle, including vehicle speed, door opening state, trunk door opening state, Global Position System (GPS) information, and the like. The color data includes various APPs and function data used by the user on the vehicle machine, such as navigation information.

[0027] The identification scheme is as follows: first, obtain the Internet of Vehicles data of the vehicle in the period before and after the driving service, eliminate the relevant user information, analyze the driving service data, and analyze the characteristics of the driving service data, including the user navigation information (the destination is the user's frequently visited place or home address), the POI analysis of the starting point (there are business places near the starting point), the characteristics before the driving service (the trunk is opened, the number of door openings, and the like), the driving behavior (the speed, the acceleration change rate, and the relatively conservative style), and the like.

[0028] Based on the above characteristics of the driving service, the feature is constructed, the obtained driving service information is used as sample data, the machine learning model is trained, a large amount of driving information of the vehicle is used as data, the driving information with the same characteristics is identified, and the driving information is the driving service.

[0029] The adjacent previous driving information of the driving service is obtained, the main characteristics include the driving time period (non-working time), the navigation information and the end point position (there are business places near the end point), the driving route (different from the daily driving route, not the route from the company to home), and the like, the corresponding sample driving characteristics are input into the machine learning model for training, the trained model is deployed to the vehicle edge end for calculation, when the same characteristics of the driving information are identified by the model, the identification result that the user may have the driving service demand is fed back to the cloud, and the APP is used to accurately push the related service to the user.

[0030] Figure 1 According to the embodiments of the present disclosure, a flowchart of a vehicle Internet data processing method is shown in FIG. 1. Figure 1 The method can include the following steps:

[0031] In step S101, the Internet of Vehicles information of the vehicle to be monitored is collected in the driving process of the vehicle to be monitored, wherein the Internet of Vehicles information at least includes the driving information of the vehicle to be monitored.

[0032] In the technical solution provided in the foregoing step S101 of the present disclosure, during the driving of the at least one to-be-monitored vehicle, the Internet of Vehicles information of the to-be-monitored vehicle is collected, for example, the various types of sensor signals and the various types of APPs and function data used by the user on the vehicle machine in the period before and after a batch of driving service are acquired in combination with platform data, such as navigation information.

[0033] In this embodiment, the Internet of Vehicles data can include two parts of gray data and color data, where the gray mainly refers to various types of sensor signals of the vehicle, including vehicle speed, door opening state, trunk door opening state, GPS information, etc.; and the color data includes various types of APPs and function data used by the user on the vehicle machine, such as navigation information, etc.

[0034] In this embodiment, the trip information of the to-be-monitored vehicle can be the information of the driving trip of the to-be-monitored vehicle, which can be obtained by the historical information of the driving application or some manual identification method.

[0035] In this embodiment, the Internet of Vehicles information at least includes: the trip information of the to-be-monitored vehicle, for example, after the Internet of Vehicles data of the vehicle in the period before and after a batch of driving service is acquired in combination with platform data, the relevant user information is first eliminated, and the driving trip data is analyzed, which mainly includes the user navigation information (the destination is a place frequently visited by the user or the home address) and the analysis of the interest point at the location of the starting point (there are commercial places near the starting point), the characteristics before the driving trip (the trunk is opened, the number of door openings, etc.), the driving behavior of the driving trip (speed, acceleration change rate, and relatively conservative style), etc.

[0036] Step S102, calling a driving trip identification model deployed on a vehicle-mounted edge side.

[0037] In the technical solution provided in the foregoing step S102 of the present disclosure, the driving trip identification model deployed on the vehicle-mounted edge side is called, for example, after the driving trip identification model is trained, it is deployed on the vehicle-mounted edge side, and the model is called to identify the driving trip.

[0038] In this embodiment, before the driving trip identification model deployed on the vehicle-mounted edge side is called, the driving trip identification model can be generated, for example, some data with high probability of driving trip is manually selected, the driving trip data is input into a machine learning model for training, and then the driving trip identification model is generated.

[0039] Step S103, using the driving trip identification model to analyze the Internet of Vehicles information, and obtaining the target driving behavior characteristics of the to-be-monitored vehicle.

[0040] In the technical solution provided in the step S103 of the present disclosure, the ride-hailing trip recognition model can be used to analyze the vehicle networking information and obtain the target ride-hailing behavior feature of the to-be-monitored vehicle. For example, the feature is constructed based on the characteristics of the ride-hailing trip, the obtained ride-hailing service information is used as the feature data, and the machine learning model is trained to obtain the ride-hailing trip recognition model. Then, the trip information of a large number of vehicles is used as the data, and the trip information with the same feature is identified, that is, the part of the trip is the ride-hailing trip.

[0041] In this embodiment, the ride-hailing trip recognition model can be used to analyze the vehicle networking information and obtain the target ride-hailing behavior feature of the to-be-monitored vehicle in the cloud.

[0042] In this embodiment, the method can include identifying the feature of the trip information in the vehicle networking information input into the ride-hailing trip recognition model and determining whether there is the same trip information as the feature in the sample data used to train the ride-hailing recognition model.

[0043] In this embodiment, the common feature of the ride-hailing trip data can be analyzed to form the feature data, and the ride-hailing trip recognition model is trained by using the feature data.

[0044] In step S104, a ride-hailing demand recognition model is obtained based on the target ride-hailing behavior feature.

[0045] In the technical solution provided in the step S104 of the present disclosure, if the target ride-hailing behavior feature of the to-be-monitored vehicle is identified, the ride-hailing demand recognition model is obtained. For example, when the model identifies the trip information with the same feature, the ride-hailing demand recognition model is called.

[0046] In step S105, the ride-hailing demand recognition model is used to determine the ride-hailing request of the to-be-monitored vehicle.

[0047] In the technical solution provided in the step S105 of the present disclosure, the ride-hailing demand recognition model can be used to determine the ride-hailing request of the to-be-monitored vehicle. For example, when the user arrives near the destination, it is identified whether the user has the ride-hailing demand, and the ride-hailing service is pushed to the user who may need the ride-hailing.

[0048] In this embodiment, the ride-hailing demand recognition model can be deployed on the vehicle-mounted intelligent terminal. The user location information can be obtained on the vehicle-mounted intelligent terminal. Thus, only one result information is uploaded to the cloud, and the user privacy information is not uploaded to the cloud. That is, when the user currently has the ride-hailing service demand, the cloud can control the recommendation information of the service to be issued to the user end, thereby accurately recommending the service and effectively protecting the privacy of the user.

[0049] In step S106, the ride-hailing request of the to-be-monitored vehicle is uploaded to the cloud platform, and at least one user end is allowed to obtain the ride-hailing request of the to-be-monitored vehicle pushed by the cloud platform.

[0050] In the technical solution provided in the above step S106 of the present disclosure, the chauffeur request of the vehicle to be monitored is uploaded to a cloud platform. For example, after the model identifies the same feature of the trip information, the identification result of the possible chauffeur service demand of the user is fed back to the cloud, and the related service is accurately pushed to the user through the APP.

[0051] In this embodiment, before generating the chauffeur request of the vehicle to be monitored, the method can include uploading the identification result to the cloud.

[0052] In this embodiment, after generating the chauffeur request of the vehicle to be monitored, the method can include pushing the service of the chauffeur request via the APP.

[0053] Through the above steps S101 to S106, by obtaining the historical behavior information of the chauffeur service provided by the current platform for the user, and obtaining the data of the user in the corresponding time period in the Internet of Vehicles data as a sample, the chauffeur behavior feature is obtained, then the chauffeur behavior feature is identified based on the Internet of Vehicles data, a large amount of chauffeur behavior sample data is obtained, the user chauffeur service demand identification model is trained based on the data, the possible chauffeur demand of the user is identified, finally, the model identification calculation is performed on the vehicle edge side, the real-time chauffeur service demand identification is realized, at the same time, the user location data does not need to be uploaded to the cloud, the user privacy data security is ensured, the user accurate identification is realized, the service pushing efficiency is greatly improved, at the same time, the user privacy data security is ensured, thereby solving the technical problems of being unable to accurately identify the user demand and low service pushing efficiency, and achieving the technical effects of accurately identifying the user demand and improving the service pushing efficiency.

[0054] The above method of this embodiment will be further described in detail.

[0055] As an optional implementation, before calling the chauffeur identification model deployed on the vehicle edge side in step S102, the method further includes: collecting the Internet of Vehicles data of a plurality of vehicles in a historical time period, wherein the historical time period at least includes a chauffeur time period in which chauffeur behavior information is generated, and the Internet of Vehicles data at least includes chauffeur trip data generated in the chauffeur time period; training a machine learning model based on the chauffeur trip data to generate a chauffeur trip identification model; determining the chauffeur request of the vehicle to be monitored by using the chauffeur demand identification model, including: based on the target chauffeur behavior feature, obtaining chauffeur sample data, wherein the chauffeur sample data at least includes at least one of the following: trip information in at least one adjacent time period adjacent to the chauffeur time period, and chauffeur trip data generated in the chauffeur time period; training a machine learning model based on the chauffeur sample data to generate a chauffeur demand identification model, wherein the chauffeur demand identification model is used to identify the corresponding chauffeur trip feature based on the trip information of the vehicle to be identified.

[0056] In this embodiment, a plurality of vehicle telematics data of vehicles in a historical time period is collected, for example, vehicle telematics data in a period before and after a batch of driving service is obtained, first, the relevant user information is eliminated, and the driving service trip data is analyzed, and the characteristics mainly include user navigation information (destination is a place frequently visited by the user or home address) and point of interest analysis of the location where the trip starts (there are business places near the starting point), characteristics before the driving service trip starts (trunk opening, number of door openings, etc.), driving behavior of the driving service trip (speed, acceleration change rate, relatively conservative style), etc.

[0057] In this embodiment, a machine learning model can be trained based on the driving service trip data to generate a driving service trip recognition model, for example, after analyzing the common characteristics of the driving service trip data, forming feature data, and then using the feature data to train the driving service trip recognition model, the driving service trip recognition model is used to filter a large amount of driving service trip data from the historical data of the vehicle to be monitored, which can be trip data representing the driving of the driving service driver.

[0058] For example, a small amount of historical driving service trip information can be obtained through the driving service APP, and the trip characteristics are analyzed, for example, whether it is a multi-person ride by distinguishing the door opening state (single-occupancy ride can be excluded from driving service), distinguishing the transportation tool of the driving service driver by the trunk opening and closing state, calculating indicators such as speed and acceleration change rate based on a series of signals such as speed and acceleration, which are used to evaluate the overall driving style of the driving service trip, and determining whether the starting point of the driving service trip is located in a business district based on GPS signals, based on this part of historical data to complete the construction of related characteristics, and train the recognition model, after the training of the model is completed, the model filters a large amount of driving service trip data from the massive telematics data in the cloud, and based on the corresponding time period, the trip segment before the driving service trip is obtained, that is, the trip segment of the user going to a business place, the characteristics of which can be different from the normal working day to arrive at the destination (home).

[0059] In this embodiment, based on the target driving service behavior characteristics, driving sample data is obtained, for example, after analyzing the driving service trip data, feature construction is performed based on the characteristics of the driving service trip, and the obtained driving service information is used as sample data, wherein the driving sample data at least includes at least one of the following: trip information in at least one adjacent time period adjacent to the driving time period, and driving service trip data generated in the driving time period.

[0060] In this embodiment, the main characteristics of the driving sample data can include: trip time period (non-working hours), navigation information and trip end location (there are business places nearby), driving route (different from the daily driving route, not the route from the company to home), etc.

[0061] In this embodiment, the machine learning model can be trained based on the sample data of the chauffeur, and a chauffeur demand identification model is generated, for example, the sample data used to train the chauffeur trip identification model is the trip data of the user driving to the restaurant or entertainment venue by himself before the chauffeur trip data, the corresponding sample trip features are input into the machine learning model for training, and the chauffeur demand identification model is generated.

[0062] As an optional implementation, at least one chauffeur feature information is extracted from the chauffeur trip data generated in the chauffeur time period, and feature construction is performed based on the chauffeur feature information to generate part of the samples in the chauffeur sample data, wherein the chauffeur trip data includes at least one of the following: navigation information, point of interest analysis data of the location where the chauffeur trip starts, vehicle equipment usage features before the chauffeur trip starts, and driving behavior information in the chauffeur trip.

[0063] In this embodiment, the navigation information can be a destination that is a user's favorite place or home address.

[0064] In this embodiment, the point of interest analysis data of the location where the chauffeur trip starts can be that there is a business place near the starting point.

[0065] In this embodiment, the vehicle equipment usage features before the chauffeur trip starts can be trunk opening, number of door opening, etc.

[0066] In this embodiment, the driving behavior information in the chauffeur trip can be speed, acceleration change rate, and relatively conservative style, etc.

[0067] As an optional implementation, at least one chauffeur feature information is extracted from the trip information in at least one adjacent time period adjacent to the chauffeur time period, and feature construction is performed based on the chauffeur feature information to generate part of the samples in the chauffeur sample data, wherein the trip information includes at least one of the following: trip time period, navigation information, end point location of the chauffeur trip, and chauffeur driving route.

[0068] In this embodiment, the trip time period can be non-working hours.

[0069] In this embodiment, the navigation information and the end point location of the chauffeur trip can be a route and a location with a business place nearby.

[0070] In this embodiment, the chauffeur driving route can be different from the daily driving route, which can be a route from the company to a business and leisure place, rather than a route from the company to home.

[0071] As an optional implementation, the historical driving service information is obtained by accessing the driving service platform, and Internet of Vehicles data of each vehicle in the historical time period is matched based on the historical driving service information, wherein the Internet of Vehicles data further includes at least one of the following: a vehicle door switch state, a trunk switch state, a vehicle speed, a vehicle acceleration, a vehicle steering wheel angle, a steering wheel angle speed, an accelerator pedal opening degree, a brake pedal opening degree, and vehicle navigation data.

[0072] In this embodiment, the vehicle door switch state can be used to distinguish whether multiple people are riding in the vehicle (single-occupancy vehicle can exclude driving).

[0073] In this embodiment, the trunk switch state can be used to distinguish the transportation tool of the driving driver.

[0074] In this embodiment, the vehicle speed, the vehicle acceleration, the vehicle steering wheel angle, the steering wheel angle speed, the accelerator pedal opening degree, and the brake pedal opening degree can be used to evaluate the overall driving style of the driving trip.

[0075] In this embodiment, the vehicle navigation data can be used to determine whether the starting point of the driving trip is located in a commercial area.

[0076] As an optional implementation, after the driving request of the vehicle to be monitored is uploaded to the cloud platform, the method further includes: detecting whether the cloud platform receives the driving request; if the driving request is received, calling the driver information of the registered at least one driving driver; based on the driver information of the driving driver, determining whether there is a driving driver in an idle state; based on the push rule, determining at least one target driving driver, and calling the equipment information of the target driving driver, wherein the push rule is used to determine the push priority of multiple driving drivers; based on the equipment information of the target driving driver, pushing the driving request to the equipment held by the target driving driver.

[0077] In this embodiment, whether the cloud platform receives the driving request is detected, for example, after the driving request of the vehicle to be monitored is uploaded to the cloud platform, whether the cloud platform receives the driving request is detected.

[0078] In this embodiment, if the driving request is received, the driver information of the registered at least one driving driver is called, for example, after it is detected that the cloud platform receives the driving request, the driver information (such as name, ID number, working state, and current location, etc.) of the at least one driving driver registered in the driving service platform is called.

[0079] In this embodiment, based on the driver information of the driving driver, it is determined whether there is a driving driver in an idle state, for example, according to the working state in the driver information of the at least one driver called, it is determined whether there is a driving driver in an idle state.

[0080] In this embodiment, based on the push rule, at least one target driver is determined, and the device information of the target driver is called, for example, the driver's praise rate is ranked from high to low, and the target driver with the highest praise rate is determined based on the push rule, and the device information of the target driver is called.

[0081] In this embodiment, based on the device information of the target driver, the driving request is pushed to the device held by the target driver, for example, after determining the at least one driver with the highest praise rate as the target driver, the driving request is pushed to the mobile phone held by the target driver through the mobile phone short message and / or the voice call interface of the driving service APP in the mobile phone according to the registration information of the driving service APP in the mobile phone of the target driver.

[0082] For example, step one, identify the "driving behavior characteristics", manually select a part of the data with high probability of driving (historical information of driving application or some manual methods), and analyze the common characteristics in this part of data; step two, use the characteristic data obtained in step one to train the "driving trip recognition model", the purpose of this model is to filter out a large amount of driving trip data (i.e. driving trip of driver) from historical data; step three, use the large amount of data (i.e. driving trip of driver) obtained in the last step to obtain the data of one of its previous trips (user's own driving trip to restaurant or entertainment place), and use this trip data to train the "driving demand recognition model", which is to identify whether the user has driving demand when he arrives near the destination, and push driving service to the user who may need driving service.

[0083] In the above embodiments of the present disclosure, by obtaining the historical behavior information of the user provided by the current platform for driving service, and obtaining the data of the user in the corresponding time period as a sample in the Internet of Vehicles data, the driving behavior characteristics are obtained, and then the driving behavior characteristics are recognized based on the Internet of Vehicles data, a large amount of driving behavior sample data is obtained, the user driving service demand recognition model is trained based on the data, the possible driving demand of the user is recognized, the user is accurately identified, the service push efficiency is greatly improved, the user privacy data is ensured to be safe, and the technical problems of unable to accurately identify the user demand and low service push efficiency are solved, and the technical effects of accurately identifying the user demand and improving the service push efficiency are achieved.

[0084] As a preferred embodiment, the user obtaining driving service can be divided into two stages, which will be introduced as follows.

[0085] Phase one, the journey segment when the user is on the way to the business place, characterized by fixed time period to arrive at the destination (business place, etc.) and normal working day to arrive at the destination (home) is different, etc.

[0086] Phase two, after the driver reaches the designated location, the vehicle is started, and the user is sent to the destination, and the journey is started with the characteristics of opening the trunk door, and the driving behavior in the journey is different from the normal driving behavior of the vehicle owner.

[0087] The recommendation of the chauffeur service needs to be made after the identification of the above-mentioned phase one journey segment and before phase two. The ultimate goal of the present application is to identify phase one.

[0088] The scheme of the present application can be divided into three parts, which will be introduced respectively as follows.

[0089] The first part is the chauffeur journey identification scheme, which is carried out in the cloud. The ultimate goal is to obtain a large number of chauffeur journeys (the journey segment of the chauffeur driving, i.e. the above-mentioned phase two) for the next step of sample screening (screening the journey segment of the user driving to the destination, i.e. phase one).

[0090] The specific method can be as follows: first, a small amount of historical chauffeur journey information (phase two) is obtained through channels such as chauffeur service APP, the journey characteristics are analyzed (whether multiple people are riding is distinguished by the state of the vehicle door (single person riding can be excluded from chauffeur); the state of the trunk opening and closing distinguishes the transportation tool of the chauffeur; a series of signals such as speed and acceleration are used to calculate the speed and acceleration change rate, which are used to evaluate the overall driving style of the chauffeur journey; the GPS signal is used to judge whether the starting point of the chauffeur journey is located in the business district, etc.), the relevant feature construction is completed based on this part of historical data, the training of the chauffeur journey identification model is carried out, after the training of the model is completed, a large number of chauffeur journeys (much more than obtained through channels such as chauffeur service APP) are screened from the massive Internet of Vehicles data in the cloud, and the journey segment before the chauffeur journey based on the corresponding time period is obtained, i.e. the journey segment sample data of phase one.

[0091] The second part is the chauffeur demand identification scheme, which is also carried out in the cloud. The ultimate goal is to construct the characteristics of phase one journey segment, and output the chauffeur demand identification model through the training of a large number of sample data, which is used for subsequent deployment on the vehicle side.

[0092] The third part is the deployment of the vehicle end and the overall recommendation strategy. The trained driving demand recognition model is deployed to the vehicle-mounted intelligent terminal, and the operation of obtaining the user location information is performed at the vehicle end, without uploading the user privacy information to the cloud end. Only a result information is uploaded to the cloud end, that is, the user currently has a driving service demand. The cloud end can control and issue a service recommendation information to the user end, thereby accurately recommending and effectively protecting the user privacy.

[0093] It should be noted that, when training the driving trip recognition model based on the driving trip information, the direct acquisition of a large amount of driving trip information involves user privacy data. In the present application, a small amount of historical driving trip information is acquired through a driving service APP and the like, the trip characteristics are analyzed, the related feature construction is completed based on the part of historical data, and the driving trip recognition model is trained.

[0094] Embodiment 2

[0095] The method for processing Internet of Vehicles data according to the present disclosure will be further described below in combination with preferred embodiments.

[0096] Figure 2 is a schematic diagram of a driving trip recognition scheme flow according to an embodiment of the present disclosure, as shown in Figure 2 The scheme can include the following steps:

[0097] S201, obtaining historical driving service information;

[0098] S202, obtaining Internet of Vehicles data in a driving trip time period;

[0099] S203, constructing driving trip features;

[0100] S204, driving trip recognition algorithm model training;

[0101] S205, obtaining a large number of driving trips;

[0102] In this embodiment, the user historical driving service information is acquired from a driving service providing platform such as an APP, the vehicle Internet of Vehicles data in a corresponding time period is matched, and sample data is obtained. The main initial field signals include a vehicle door opening and closing state, a trunk opening and closing state, a speed, an acceleration, a steering wheel angle, a steering wheel angle speed, an accelerator pedal opening degree, a brake pedal opening degree, a GPS, and the like. The main purpose of selecting each signal is to construct the following several types of features: whether a plurality of people are riding a vehicle is distinguished through the vehicle door opening and closing state (single-riding can be excluded from driving); the transportation tool of the driving driver is distinguished through the trunk opening and closing state; a series of signals such as the speed and the acceleration are used to calculate the speed and the acceleration change rate and the like, which are used to evaluate the overall driving style of the driving trip; and the GPS signal is used to judge whether the starting point of the driving trip is located in a commercial area.

[0103] The corresponding feature construction (including but not limited to the above four categories) is completed on the data to form sample data of the ride service trip, which is input into the model training of the machine learning model, the trip data of all vehicles is obtained, the same features are constructed, and the output result of the input into the trained model indicates that all trip segments identified as the ride service trip are marked as the input condition of the subsequent model.

[0104] Through steps S201 to S205 in this embodiment, historical ride service information is obtained, vehicle networking data in a ride service trip time period is obtained, ride service trip features are constructed, a ride service trip recognition algorithm model is trained, and a large number of ride service trips are obtained, that is, user historical ride service information is obtained from an APP or other ride service providing platform, vehicle networking data in a corresponding time period is matched, sample data is obtained, multiple signals are selected for constructing multiple features, a machine learning model is trained, and all trip data of all vehicles is input into the trained model to obtain all trip segments of the ride service trip, thereby solving the technical problem of being unable to accurately identify user demand and achieving the technical effect of being able to accurately identify user demand.

[0105] Figure 3 is a schematic diagram of a flow of a ride service demand recognition scheme according to an embodiment of the present disclosure, as shown in Figure 3 The scheme can include the following steps:

[0106] Step S301, vehicle networking data in a period of time before a ride service trip is obtained.

[0107] Step S302, corresponding trip features are constructed.

[0108] Step S303, a ride service demand recognition algorithm model is trained.

[0109] In this embodiment, according to a large number of ride service trips corresponding to a time period, adjacent previous trip information thereof is obtained, and related field signals in the trip segment are obtained, including time, GPS signals, navigation information, etc. The main purpose of selecting each signal is to construct the following several types of features: time is used to determine whether it is working time; GPS signals and navigation information are used to determine whether the user travels on a home route or a commonly used route (the route is set by the user or an algorithm recognition result, which is stored on the vehicle side); GPS signals and navigation information are also used to determine whether the trip end or the navigation address is located in a commercial area or the like.

[0110] After the related feature construction is completed on all data (including but not limited to the above three types), sample data of the ride service demand recognition is obtained, which is input into the model training of the machine learning model.

[0111] Through steps S301 to S303 in this embodiment, the Internet of Vehicles data in a period of time before the driving service is obtained, the corresponding driving characteristics are constructed, and the driving service demand recognition algorithm model is trained, that is, by obtaining the adjacent previous driving information and the related field signals in the driving period according to the obtained large amount of driving service corresponding time, a plurality of signals are selected to construct a plurality of characteristics, and after the related characteristics of the sample data of the driving service demand recognition are constructed (including but not limited to the above three types), the sample data is used as the input of the machine learning model for model training, the accurate recognition of the driving service demand is realized, the technical problem that the user demand cannot be accurately recognized is solved, and the technical effect that the user demand can be accurately recognized is achieved.

[0112] Figure 4 is a schematic diagram of a flow of a model function edge end implementation scheme according to an embodiment of the present disclosure, as Figure 4 shown, the scheme can include the following steps:

[0113] Step S401, model edge end deployment;

[0114] Step S402, model edge end real-time calculation;

[0115] Step S403, edge end model calculation uploading to the cloud;

[0116] Step S404, APP sends accurate recommendation information.

[0117] In this embodiment, after the model training is completed, the model is deployed to the vehicle-mounted intelligent terminal (including but not limited to the intelligent cabin, the gateway, the vehicle-mounted Internet terminal), the Internet of Vehicles gray and color data are obtained in real time, and the user home address, the commonly used route and other information stored in the vehicle end are obtained, the data calculation and storage are completed in the vehicle end, only the result is uploaded to the cloud, the cloud end downloads the judgment result to the APP, and the accurate push of the driving service to the user is realized.

[0118] Through the above steps S401 to S404 of the embodiment of the present disclosure, the model edge end is deployed, the model edge end is calculated in real time, the edge end model calculation is uploaded to the cloud, and the APP sends accurate recommendation information, that is, the model is deployed to the vehicle-mounted intelligent terminal, the Internet of Vehicles gray and color data are obtained in real time, and the user home address, the commonly used route and other information stored in the vehicle end are obtained, the data calculation and storage are completed in the vehicle end, only the result is uploaded to the cloud, the cloud end downloads the judgment result to the APP, the accurate recognition of the user is realized, the service push efficiency is greatly improved, the user privacy data security is ensured, and the technical problems that the user demand cannot be accurately recognized and the service push efficiency is low are solved, and the technical effects that the user demand can be accurately recognized and the service push efficiency is improved are achieved.

[0119] Embodiment 3

[0120] The embodiments of the present disclosure further provide a vehicle networking data processing method and a vehicle networking data processing device. Figure 1 The embodiments of the present disclosure further provide a vehicle networking data processing method and a vehicle networking data processing device.

[0121] Figure 5 FIG. 1 is a schematic diagram of a vehicle networking data processing device according to an embodiment of the present disclosure, as shown in the figure, the vehicle networking data processing device 50 can include an acquisition module 51, a calling module 52, a first acquisition module 53, a second acquisition module 54, a determination module 55, and an uploading module 56. Figure 5

[0122] The acquisition module 51 is configured to acquire vehicle networking information of a to-be-monitored vehicle during driving of the to-be-monitored vehicle, wherein the vehicle networking information at least includes travel information of the to-be-monitored vehicle.

[0123] The calling module 52 is configured to call a driver identification model deployed on a vehicle-mounted edge side.

[0124] The first acquisition module 53 is configured to analyze the vehicle networking information by using the driver identification model to obtain target driver behavior characteristics of the to-be-monitored vehicle.

[0125] The second acquisition module 54 is configured to obtain a driver demand identification model based on the target driver behavior characteristics.

[0126] The determination module 55 is configured to determine a driver request of the to-be-monitored vehicle by using the driver demand identification model.

[0127] The uploading module 56 is configured to upload the driver request of the to-be-monitored vehicle to a cloud platform, wherein at least one user terminal is allowed to obtain the driver request of the to-be-monitored vehicle pushed by the cloud platform.

[0128] In the above vehicle networking data processing device of the present disclosure, the device further includes a collection module, a first training module, an acquisition module, and a second training module. The collection module is configured to acquire vehicle networking data of a plurality of vehicles in a historical time period, wherein the historical time period at least includes a driver time period in which driver behavior information is generated, and the vehicle networking data at least includes driver travel data generated in the driver time period. The first training module is configured to train a machine learning model based on the driver travel data to generate a driver travel identification model. The acquisition module is configured to obtain driver sample data based on the target driver behavior characteristics, wherein the driver sample data at least includes at least one of the following: travel information in at least one adjacent time period adjacent to the driver time period, and the driver travel data generated in the driver time period. The second training module is configured to train the machine learning model based on the driver sample data to generate a driver demand identification model, wherein the driver demand identification model is used to identify corresponding driver travel characteristics based on travel information of a to-be-identified vehicle.​

[0129] Optionally, the acquisition module further comprises a first acquisition unit and a second acquisition unit. The first acquisition unit is configured to extract at least one driving service feature information from the driving service trip data generated in the driving service time period, and perform feature construction based on the driving service feature information to generate part of the samples in the driving service sample data. The driving service trip data comprises at least one of the following: navigation information, point of interest analysis data of a location where the driving service trip starts, vehicle equipment usage feature before the driving service trip starts, and driving behavior information in the driving service trip. The second acquisition unit is configured to extract at least one driving service feature information from the trip information in at least one adjacent time period adjacent to the driving service time period, and perform feature construction based on the driving service feature information to generate part of the samples in the driving service sample data. The trip information comprises at least one of the following: a trip time period, navigation information, a location where the driving service trip ends, and a driving service route.

[0130] Optionally, the collection module further comprises a first collection unit. The first collection unit is configured to acquire historical driving service information by accessing the driving service platform, and obtain vehicle networking data of each vehicle in a historical time period based on the historical driving service information. The vehicle networking data further comprises at least one of the following: a vehicle door opening and closing state, a trunk opening and closing state, a vehicle speed, a vehicle acceleration, a vehicle steering wheel angle, a steering wheel angle speed, an accelerator pedal opening degree, a brake pedal opening degree, and vehicle navigation data.

[0131] In the above-mentioned vehicle networking data processing device of the present disclosure, the device further comprises a detection module, a calling module, a determination module, a processing module, and a pushing module. The detection module is configured to detect whether the cloud platform receives a driving service request. The calling module is configured to call driver information of at least one registered driving service driver if the driving service request is received. The determination module is configured to determine whether there is a driving service driver in an idle state based on the driver information of the driving service driver. The processing module is configured to determine at least one target driving service driver based on a pushing rule, and call equipment information of the target driving service driver. The pushing rule is used to determine a pushing priority of a plurality of driving service drivers. The pushing module is configured to push the driving service request to equipment held by the target driving service driver based on the equipment information of the target driving service driver.

[0132] In the above-mentioned embodiments of the present disclosure, by acquiring historical behavior information of the current platform providing the user with a driving service, and acquiring data of the user in a corresponding time period in the Internet of Vehicles data as a sample, driving behavior characteristics are obtained, then, the driving behavior characteristics are identified based on the Internet of Vehicles data, a large amount of driving behavior sample data is obtained, a user driving service demand identification model is trained based on the data, the driving demand of the user is identified, finally, model identification calculation is performed on the vehicle-mounted edge side, real-time driving service demand identification is realized, at the same time, user location data does not need to be uploaded to the cloud, ensuring the safety of user privacy data, realizing accurate identification of the user, greatly improving the service pushing efficiency, at the same time ensuring the safety of user privacy data, thereby solving the technical problems of being unable to accurately identify the user demand and low service pushing efficiency, and achieving the technical effects of accurately identifying the user demand and improving the service pushing efficiency.

[0133] Embodiment 4

[0134] According to the embodiments of the present application, a computer readable storage medium is also provided. The computer readable storage medium includes a stored program, wherein when the program is run by a processor, it controls the device where the computer readable storage medium is located to execute the processing method of the Internet of Vehicles data of the embodiments of the present application.

[0135] Embodiment 5

[0136] According to the embodiments of the present application, a processor is also provided, which is used to run a program, wherein when the program is run, the processing method of the Internet of Vehicles data of the embodiments of the present application is executed.

[0137] Embodiment 6

[0138] According to the embodiments of the present disclosure, the present disclosure also provides a vehicle comprising the processing method of the Internet of Vehicles data of the embodiments of the present disclosure.

[0139] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0140] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0141] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented by other means. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division mode, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, units or models, which can be electrical or other forms.

[0142] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0143] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0144] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0145] The above is only the preferred embodiment of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method for processing Internet of Vehicles data, characterized in that, The method comprises the following steps: Collecting Internet of Vehicles information of the to-be-monitored vehicle during driving of the to-be-monitored vehicle, wherein the Internet of Vehicles information at least comprises: driving information of the to-be-monitored vehicle, and the driving information of the to-be-monitored vehicle at least comprises one of the following information: vehicle navigation information, interest point information of a location where a starting point of a journey is located, and driving behavior information of a driver of the to-be-monitored vehicle during driving of the to-be-monitored vehicle; Calling a driving-for-others journey recognition model deployed on a vehicle-mounted edge terminal, wherein the driving-for-others journey recognition model is obtained by training a machine learning model by using historical driving-for-others journey data of the to-be-monitored vehicle, and the historical driving-for-others journey data is used to indicate journey data of the to-be-monitored vehicle during driving of the to-be-monitored vehicle by the driver in a historical time period; Analyzing the Internet of Vehicles information by using the driving-for-others journey recognition model, determining journey information that is the same as a feature in the historical driving-for-others journey data used to train the driving-for-others journey recognition model, and determining a feature corresponding to the journey information as a target driving-for-others behavior feature of the to-be-monitored vehicle, wherein the target driving-for-others behavior feature is the journey information that has the same feature in the journey information of the to-be-monitored vehicle; Based on the target driving-for-others behavior feature, obtaining driving-for-others sample data, and training the machine learning model based on the driving-for-others sample data to generate a driving-for-others demand recognition model, wherein the driving-for-others sample data comprises: time periods of different driving-for-others services, journey information of a previous time period and a next time period of the time periods of the different driving-for-others services, and the historical driving-for-others journey data generated in a driving-for-others time period, and the driving-for-others demand recognition model is used to identify corresponding driving-for-others demand features based on journey information of a to-be-monitored vehicle; Identifying a driving-for-others request of the to-be-monitored vehicle by using the driving-for-others demand recognition model; Uploading the driving-for-others request of the to-be-monitored vehicle to a cloud platform, wherein at least one user terminal is allowed to obtain the driving-for-others request of the to-be-monitored vehicle pushed by the cloud platform.

2. The method of claim 1, wherein the method further comprises: 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-for-others time period in which driving-for-others behavior information is generated, and the Internet of Vehicles data at least comprises: the historical driving-for-others journey data generated in the driving-for-others time period, wherein the historical driving-for-others journey data at least comprises one of the following: user navigation information, interest point analysis of a location where a starting point of a journey is located, driving-for-others journey start feature, and driving-for-others journey driving behavior; and training a machine learning model based on the historical driving-for-others journey data in the Internet of Vehicles data in the historical time period to generate the driving-for-others journey recognition model. ​ 3. The method of claim 2, wherein, extract at least one driving feature information from the historical driving trip data generated in the driving time period, and perform feature construction based on the driving feature information to generate part of the samples in the driving sample data, wherein the historical driving trip data includes at least one of the following: navigation information, point of interest analysis data of the location where the driving trip starts, vehicle equipment usage features before the driving trip starts, and driving behavior information in the driving trip.

4. The method of claim 1, wherein, The trip information further includes at least one of the following: a trip time period, navigation information, and a destination location of the driving trip.

5. The method of claim 2, wherein, The historical driving service information is obtained by accessing a driving service platform, and the vehicle networking data of each vehicle in the historical time period is matched based on the historical driving service information, wherein the vehicle networking data further includes at least one of the following: a vehicle door opening and closing state, a trunk opening and closing state, a vehicle speed, a vehicle acceleration, a steering wheel angle, a steering wheel angle speed, an accelerator pedal opening degree, a brake pedal opening degree, and vehicle navigation data.

6. The method according to any one of claims 1 to 5, characterized in that, After uploading the driving request of the vehicle to be monitored to the cloud platform, the method further includes: detecting whether the cloud platform receives the driving request; if the driving request is received, calling the driver information of at least one registered driving driver; based on the driver information of the driving driver, determining whether there is a driving driver in an idle state; based on the push rule, determining at least one target driving driver, and calling the device information of the target driving driver, wherein the push rule is used to determine the push priority of a plurality of driving drivers; based on the device information of the target driving driver, pushing the driving request to the device held by the target driving driver.

7. A processing apparatus for Internet of Vehicles data, characterized in that, comprises: a collection module configured to collect vehicle networking information of at least one vehicle to be monitored during driving of the vehicle to be monitored, wherein the vehicle networking information includes at least one of the following information: vehicle navigation information, point of interest information of a location where a driving trip starts, and driving behavior information of a driving object of the vehicle to be monitored during driving of the vehicle to be monitored; a calling module configured to call a driving trip recognition model deployed on a vehicle-mounted edge side, wherein the driving trip recognition model is obtained by training a machine learning model using historical driving trip data of the vehicle to be monitored, and the historical driving trip data is used to indicate trip data of the vehicle to be monitored during driving of the vehicle to be monitored by the driving object in a historical time period; a determination module configured to analyze the vehicle networking information using the driving trip recognition model, determine trip information having the same features as the historical driving trip data used to train the driving recognition model, and determine the trip information corresponding to the features as target driving behavior features of the vehicle to be monitored, wherein the target driving behavior features are the trip information having the same features in the trip information of the vehicle to be monitored; The generation module is configured to obtain driving sample data based on the target driving behavior feature, and train the machine learning model based on the driving sample data to generate a driving demand identification model. The driving sample data includes time periods of different driving services, trip information of a previous time period and a next time period of the time periods of the different driving services, and the historical driving trip data generated in a driving time period. The driving demand identification model is configured to identify corresponding driving demand features based on trip information of a vehicle to be monitored. The identification module is configured to identify a driving request of the vehicle to be monitored by using the driving demand identification model. The uploading module is configured to upload the driving request of the vehicle to be monitored to a cloud platform, and allow at least one user terminal to obtain the driving request of the vehicle to be monitored pushed by the cloud platform.

8. The apparatus of claim 7, wherein, The device further includes: The collection module is configured to collect Internet of Vehicles data of a plurality of vehicles in a historical time period. The historical time period at least includes a driving time period in which driving behavior information is generated. The Internet of Vehicles data at least includes historical driving trip data generated in the driving time period. The first training module is configured to train a machine learning model based on the historical driving trip data to generate the driving trip identification model. The acquisition module is configured to obtain driving sample data based on the target driving behavior feature. The second training module is configured to train a machine learning model based on the driving sample data to generate the driving demand identification model.

9. The apparatus of claim 7, wherein, The device further includes: The detection module is configured to detect whether the cloud platform receives the driving request. The calling module is configured to call driver information of at least one registered driving driver if the driving request is received. The determination module is configured to determine whether there is a driving driver in an idle state based on the driver information of the driving driver. The processing module is configured to determine at least one target driving driver based on a pushing rule, and call device information of the target driving driver. The pushing rule is used to determine pushing priorities of a plurality of driving drivers. The pushing module is configured to push the driving request to a device held by the target driving driver based on the device information of the target driving driver.

10. A vehicle characterized by comprising: The processing method of the Internet of Vehicles data includes any one of claims 1-6.

Images