Driver Behavior Portrait Method, Device, Electronic Device and Readable Storage Medium

Abstract

The present application provides a driver behavior profiling method, apparatus, electronic device, and readable storage medium. The method includes: obtaining national standard vehicle historical records and enterprise standard vehicle historical records stored by data collection date; identifying first type events in the national standard vehicle historical records to obtain event elements of the first type events, where the event elements include vehicle identification codes, event start times, and event end times; associating the first type events with the national standard vehicle historical records or enterprise standard vehicle historical records according to the event elements of the first type events, and calculating event metrics of the first type events according to the association results; identifying second type events in the first type events, and calculating event metrics of the second type events; and performing driver behavior profiling according to the event metrics of the first type events and the event metrics of the second type events. By adopting the technical solution of the present application, vehicle user behavior profiling can be performed more accurately.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a method, apparatus, electronic device, and readable storage medium for driver behavior profiling. Background Art

[0002] User profiling is an effective tool for outlining user characteristics, analyzing user needs, and determining product optimization goals. In addition to analyzing static information such as basic user data in user profiling, the interaction behavior between users and products is of greater significance for optimization goals. Therefore, how to describe user behavior and how to construct user behavior tags are very basic and core tasks in user profiling.

[0003] In the business of electric vehicle user profiling, the reported data are mostly the data directly reported by sensors during the operation of electric vehicles, such as heartbeat data. Therefore, there is a lack of accurate definition and classification of user behavior, and it is impossible to directly describe user behavior according to the event model, thus unable to meet the requirements of vehicle user behavior profiling for electric vehicles and unable to accurately profile vehicle user behavior. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, electronic device, and computer-readable storage medium for driver behavior profiling to solve the problem of inaccurate vehicle user behavior profiling.

[0005] In a first aspect of the embodiments of this application, a method for driver behavior profiling is provided. The method includes: obtaining national standard vehicle historical records and enterprise standard vehicle historical records stored by date of data collection; identifying first-type events in the national standard vehicle historical records to obtain event elements of the first-type events, where the event elements include vehicle identification numbers, event start times, and event end times; associating the first-type events with the national standard vehicle historical records or the enterprise standard vehicle historical records according to the event elements of the first-type events, and calculating event metrics of the first-type events according to the association results; identifying second-type events in the first-type events, and calculating event metrics of the second-type events; and performing driver behavior profiling according to the event metrics of the first-type events and the event metrics of the second-type events.

[0006] In the second aspect of the embodiments of the present application, a driver behavior portrait device is provided. The device includes: a data acquisition module for acquiring national standard vehicle historical records and enterprise standard vehicle historical records stored by date of data acquisition; a first identification module for identifying first type events in the national standard vehicle historical records to obtain event elements of the first type events, where the event elements include vehicle identification codes, event start times, and event end times; an index calculation module for associating the first type events with the national standard vehicle historical records or the enterprise standard vehicle historical records according to the event elements of the first type events, and calculating event indexes of the first type events according to the association results; a second identification module for identifying second type events in the first type events and calculating event indexes of the second type events; and a portrait module for performing driver behavior portraits according to the event indexes of the first type events and the event indexes of the second type events.

[0007] In the third aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0008] In the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] The beneficial effects of the embodiments of the present application compared with the prior art at least include: The technical solution of the embodiments of the present application constructs a two-layer event model suitable for electric vehicle user behavior portraits by identifying first type events in the national standard vehicle historical records to obtain event indexes of the first type events, and further identifying second type events in the first type events to obtain event indexes of the second type events. By performing driver behavior portraits according to the event indexes of the first type events and the event indexes of the second type events and combining the two layers of events, driver behavior portraits can be made more accurately. Description of the Drawings

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0011] Figure 1 It is a flowchart of a driver behavior portrait method provided by an embodiment of the present application;

[0012] Figure 2It is a schematic flowchart of constructing a double-layer event model provided by an embodiment of the present application;

[0013] Figure 3 It is a schematic structural diagram of a driver behavior portrait device provided by an embodiment of the present application;

[0014] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0015] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0016] In related technologies, to perform user portrait, it is necessary to collect user behavior data. In common APP (Application) services such as e-commerce, video, and news, the data source of user behavior is the data reported by APP buried points. These APP services started early and have a high maturity, and their behavior buried point data is quite comprehensive. Various behaviors have been clearly defined and classified at the buried point stage. Therefore, in such services, the corresponding behavior reported data can be directly used to construct an event model to describe when, where, under what circumstances, in what way, and what behavior the user generates. For example, common events in e-commerce services include "login", "click to browse", "click to place an order", and "favorite", etc.

[0017] In the electric vehicle user portrait service, for the behavior analysis of users' vehicle use, generally, data such as VHR (Vehicle History Record) and T-BOX (Telematics-BOX) are used as data sources. Since the electric vehicle service is in the process of development and improvement, the buried point reported data cannot directly describe user behavior according to the event model, and the electric vehicle service often needs to statistically analyze with process events with a relatively long duration such as driving trips and charging processes. Therefore, various small events also need to be considered during the period when the process event occurs.

[0018] Therefore, the existing method of directly constructing a single-layer event model based on the buried point reported behavior data cannot meet the requirements of electric vehicle user behavior portrait.

[0019] To solve the above technical problems, an embodiment of the present application provides a driver behavior portrait solution.

[0020] The method and device for driver behavior profiling according to the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0021] Figure 1 It is a schematic flowchart of a method for driver behavior profiling provided by an embodiment of the present application. The method provided by the embodiment of the present application can be executed by any electronic device with computer processing capabilities, such as a terminal or a server. As Figure 1 shown, the driver behavior profiling method includes:

[0022] Step S101, obtain the national standard vehicle historical records and enterprise standard vehicle historical records stored by date of data collection.

[0023] Step S102, identify the first type of events in the national standard vehicle historical records, and obtain the event elements of the first type of events. The event elements include vehicle identification number, event start time, and event end time.

[0024] Specifically, the VIN (Vehicle Identification Number) consists of 17 characters, including the vehicle manufacturer, year, model, body type and code, engine code, and assembly location, and is the identity identifier of the vehicle. In the embodiments of the present application, the first type of events can also be referred to as major events. Major events can include driving trips and charging processes, and are not limited thereto. The national standard vehicle historical records are vehicle historical records collected according to the national standard, and the enterprise standard vehicle historical records are vehicle historical records collected according to the enterprise's self-defined standards.

[0025] Step S103, associate the first type of events with the national standard vehicle historical records or enterprise standard vehicle historical records according to the event elements of the first type of events, and calculate the event metrics of the first type of events according to the association results.

[0026] Step S104, identify the second type of events in the first type of events, and calculate the event metrics of the second type of events.

[0027] Specifically, the second type of events includes at least any one of the following: rapid acceleration, rapid deceleration, speeding, sharp turn, and collision. In the embodiments of the present application, the second type of events can also be referred to as minor events. Minor events can include rapid acceleration, rapid deceleration, sharp turn, and collision, and are not limited thereto. In step S104, the second type of events can be identified according to the national standard vehicle historical records and enterprise standard vehicle historical records associated with the first type of events.

[0028] Step S105, perform driver behavior profiling according to the event metrics of the first type of events and the event metrics of the second type of events.

[0029] Before step S101, the national standard vehicle historical records and enterprise standard vehicle historical records can be collected and persisted respectively; receive the national standard vehicle historical records and enterprise standard vehicle historical records reported in real time from the distributed publish-subscribe message system, and write the national standard vehicle historical records and enterprise standard vehicle historical records into the distributed file storage system.

[0030] Specifically, when collecting and persisting the national standard VHR data and enterprise standard VHR data reported by vehicles respectively, Flink can be used to consume and report the VHR data from Kafka in real time and write it into an HDFS (Hadoop Distributed File System) file. Among them, Flink is an open-source stream processing framework for distributed systems and requires computing resources to execute applications. Kafka is a high-throughput distributed publish-subscribe message system that can process all action stream data of consumers on websites. HDFS is a component of the distributed system infrastructure Hadoop.

[0031] During the real-time writing process of writing VHR data into the HDFS file, data parsing and simple data cleaning can be performed. After writing the VHR data into the HDFS file, the VHR data can be partitioned by the data collection date and loaded by associating with an external partitioned table of HIVE. Among them, HIVE is a data warehouse tool based on Hadoop, used for data extraction, transformation, and loading, which is a mechanism that can store, query, and analyze large-scale data stored in Hadoop.

[0032] In step S102, the national standard vehicle historical records can be grouped according to the vehicle identification number, and the grouped national standard vehicle historical records can be sorted in ascending order according to the data collection timestamp. Then, according to the identification and division rules of different first-type events, the first-type events are divided based on the national standard vehicle historical records to obtain the event elements of the first-type events. Among them, different first-type events include driving events or charging events. Then, the event elements of the first-type events are stored in different tables according to the event type of the first-type events and partitioned according to the event date.

[0033] Specifically, the national standard VHR data can be used to identify and divide the first-type events. The national standard GB / T32960 details the requirements and standards for the collection of electric vehicle historical records. Therefore, the national standard VHR data has the advantages of strong universality and easy data parsing. Using the national standard VHR data to identify and divide the first-type events and adopting a unified calculation caliber can greatly reduce the impact caused by data differences between different vehicle models and greatly reduce the difficulty of the system in accessing new vehicle models.

[0034] In the embodiments of the present application, the recognition and division rules for driving events may be as follows: when vcu_ready (vehicle status) = 1, the vehicle is in the "driving state". The first continuously reported driving state is the start of the trip, and the last continuously reported one is the end of the trip. The recognition and division rules for charging events may be as follows: when bms_vehicleChargingStatus (charging status) = 1, the vehicle is in the "parked charging state". The first continuously reported parked charging state is the start of charging, and the last continuously reported one is the end of charging.

[0035] Specifically, when performing major event division, the national standard VHR data can be grouped according to the VIN first, and the grouped national standard VHR data can be sorted in ascending order according to the data collection timestamp. Further, major events can be divided according to the recognition and division rules for different major events, and the vehicle identification code, event start time, and event end time can be obtained. Finally, the event data such as the event elements of the obtained major events are saved in tables according to the event types of the major events and partitioned according to the date corresponding to the event start time.

[0036] In the embodiments of the present application, to eliminate the influence of short-time signal jumps in the reported data, after dividing the first type of events according to the recognition and division rules for different first type of events based on the national standard vehicle history records, events of the same type with the same vehicle identification code and an event time interval less than the first duration can be merged. Specifically, the first duration can be set to 5 minutes, and it is not limited thereto. The event time interval refers to the interval between the event end time of the previous event and the event start time of the next event. For example, when two charging events corresponding to the same vehicle identification code are recognized, and the interval between the event end time of the previous charging event and the event start time of the next charging event is 3 minutes, these two charging events can be merged into one charging event.

[0037] In step S103, the major event table obtained by recognizing major events can be used to associate the national standard VHR data and the enterprise standard VHR data. The calculation calibers of the same major event indicator are different. Among them, some indicators of the same major event are calculated from the national standard data, and some indicators of the same major event are calculated from the enterprise standard data. Therefore, it is necessary to use the major event table generated in step S102 to determine the three elements of VIN, event start time, and event end time to associate the national standard VHR data and the enterprise standard VHR data related to the major event.

[0038] In step S104, partial historical records corresponding to the first type of events in the national standard vehicle historical records and enterprise standard vehicle historical records can be obtained according to the association result; the partial historical records are grouped according to the vehicle identification number and the event start time, and the grouped partial historical records are sorted in ascending order of the data collection timestamp; the second type of events are divided according to the identification and division rules of different second type of events based on the partial historical records to obtain the event elements of the second type of events.

[0039] Because small events during vehicle use often occur along with large events and are often interrelated during analysis and investigation. Therefore, the process of dividing the second type of events according to the partial historical records is the process of identifying and dividing small events within large events.

[0040] When identifying and dividing small events, first, according to the large event calculation criteria, the large event table is associated with the national standard VHR data or enterprise standard VHR data, and the partial VHR data related to the large event corresponding to the association result is used as the VHR data for dividing the second type of events. This part of the VHR data is grouped according to the VIN and the large event start time, and sorted in ascending order of the collection time of the VHR data. Further, according to the identification and division rules of small events, the event elements of small events, that is, the event start time and event end time of small events, are calculated.

[0041] In the embodiments of the present application, the identification and division rules for small events corresponding to rapid acceleration and rapid deceleration can be:

[0042] The identification and division rule for rapid acceleration events: an event where the vehicle's longitudinal acceleration > \(3m / s^2\) 2 The identification and division rule for rapid deceleration events: an event where the vehicle's longitudinal acceleration < \(-3.5m / s^2\) 2 of the event.

[0043] In the embodiments of the present application, the relevant indicators for small events of rapid acceleration events and rapid deceleration events can be as shown in Table 1 below:

[0044] Table 1 Relevant indicators for small events

[0045]

[0046]

[0047] In step S105, calculations can be performed according to the event indicators of the second type of events, the calculation results are used as event indicators and added to the event indicators of the first type of events, and driver behavior portraits are created based on the event indicators of the first type of events after adding the calculation results.

[0048] Specifically, based on the relevant indicators of small events in Table 1, some of the indicators of large events as shown in Table 2 can be obtained. By summarizing some of the indicators of large events of driving events obtained from the relevant indicators of small events and the original indicators of large events of driving events, the indicators of driving events after adding event indicators as shown in Table 2 below can be obtained.

[0049] Table 2 Driving event indicators.

[0050]

[0051]

[0052] Specifically, in the embodiments of the present application, the large event indicators can include two parts. One is the conventional indicators directly counted and calculated under large events, such as duration, mileage, start and end addresses, average speed, etc. under driving events. The other is the indicators summarized and statistically analyzed from small events under large events, such as the number of hard accelerations, hard acceleration penalty points, overspeed duration, overspeed degree, etc. under driving events.

[0053] Generally speaking, the user portrait system performs higher-level statistical analysis based on the event indicator system composed of large events, that is, most of the portrait requirements can be realized. In some embodiments, if there are more refined portrait requirements for small events, small events can also be incorporated into the event system of the user portrait system for analysis.

[0054] Such as Figure 2 As shown, the technical solution of the embodiments of the present application constructs a two-layer model of driving events. The specific steps include:

[0055] Step S211, collect vehicle historical record data in real time.

[0056] Step S212, parse and clean the vehicle historical record data.

[0057] Step S213, persistently store the vehicle historical record data.

[0058] Step S214, identify large events in the national standard vehicle historical records.

[0059] Specifically, taking the large event of driving events as an example, in steps S211 to S214, national standard VHR and enterprise standard VHR data can be collected and persistently stored, and a driving event table, that is, a large event table, can be calculated and generated according to the driving event identification and division rules.

[0060] Step S221, associate national standard data.

[0061] Step S222, divide small events.

[0062] Step S223, calculate conventional indicators.

[0063] Step S224, count small event metrics.

[0064] Specifically, in steps S221 to S224, the driving event table can be used as the main table, associated with national standard VHR data, calculate the conventional metrics of driving events, and analyze and identify the metrics of two small events, sudden acceleration and sudden deceleration, under driving events.

[0065] Step S231, associate enterprise standard data.

[0066] Step S232, divide small events.

[0067] Step S233, calculate conventional metrics.

[0068] Step S234, count small event metrics.

[0069] Specifically, in steps S231 to S234, the driving event table can be used as the main table, associated with enterprise standard VHR data, calculate the conventional metrics of driving events, and analyze and identify the metrics of two small events, sudden acceleration and sudden deceleration, under driving events.

[0070] Step S241, summarize large event metrics. The metrics of large events can be summarized based on the large event table, conventional metrics, and small event metrics.

[0071] Specifically, the metrics of the summarized large events are used as driving events and added to the user portrait system for use. User tags can be generated after further upper-level calculation and analysis. Further, if more in-depth portrait analysis of small events is required, small events can also be directly added to the user portrait system, but the types of events in the portrait system need to be controlled to prevent the user portrait event system from being too complex.

[0072] The embodiment of this application proposes a solution for event recognition and division after obtaining national standard VHR data and enterprise standard VHR data. Combining the large events and small events obtained by associated division, a two-layer event model suitable for the user behavior portrait of electric vehicles is constructed.

[0073] Specifically, the technical solution of the embodiment of the present application performs event recognition after the vehicle reports data collection and persistence, solving the problem of insufficient event recognition in the data logging and reporting stage of electric vehicles. Using national standard VHR data for the recognition and classification of major events such as driving behavior and charging behavior effectively reduces the difficulty of user behavior profiling for multiple vehicle models. Designing a two-layer event model that combines major events and minor events can effectively abstract the characteristics of users' vehicle usage behavior, independently recognize and classify minor events within major events, accurately abstract the behavior characteristics of electric vehicles, and calculate the minor event and general indicators respectively within the scope of the major event according to the total-subtotal-total logic, and then summarize the "major event" indicators, thereby realizing the combination of the two layers of events in the index calculation link. In the event model usage stage, users can flexibly select events to access the user portrait system.

[0074] According to the driver behavior profiling method of the embodiment of the present application, by recognizing the first type of events in the national standard vehicle historical records, obtaining the event indicators of the first type of events, and further recognizing the second type of events in the first type of events, obtaining the event indicators of the second type of events, a two-layer event model applicable to electric vehicle user behavior profiling is constructed, and driver behavior profiling is performed according to the event indicators of the first type of events and the second type of events, and the two layers of events are combined, that is, driver behavior profiling can be performed more accurately.

[0075] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. The driver behavior profiling device described below can be mutually corresponding and referenced with the driver behavior profiling method described above. For the details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0076] Figure 3 It is a schematic diagram of a driver behavior profiling device provided by an embodiment of the present application. As Figure 3 shown, the driver behavior profiling device in the embodiment of the present application includes:

[0077] A data acquisition module 301, configured to acquire national standard vehicle historical records and enterprise standard vehicle historical records stored by date partition of data collection.

[0078] A first recognition module 302, configured to recognize the first type of events in the national standard vehicle historical records, and obtain the event elements of the first type of events, where the event elements include a vehicle identification code, an event start time, and an event end time.

[0079] An index calculation module 303, configured to associate the first type of events with the national standard vehicle historical records or the enterprise standard vehicle historical records according to the event elements of the first type of events, and calculate the event indicators of the first type of events according to the association result.

[0080] A second recognition module 304, configured to recognize a second type of event in the first type of event and calculate an event metric of the second type of event.

[0081] A portrait module 305, configured to perform driver behavior portrait according to the event metric of the first type of event and the event metric of the second type of event.

[0082] Since each functional module of the driver behavior portrait device in the exemplary embodiments of the present application corresponds to the steps of the exemplary embodiments of the above-mentioned driver behavior portrait method, for details not disclosed in the device embodiments of the present application, please refer to the embodiments of the above-mentioned driver behavior portrait method of the present application.

[0083] According to the driver behavior portrait device in the embodiments of the present application, by recognizing the first type of event in the national standard vehicle historical record, obtaining the event metric of the first type of event, and further recognizing the second type of event in the first type of event, obtaining the event metric of the second type of event, a two-layer event model applicable to the electric vehicle user behavior portrait is constructed. According to the event metrics of the first type of event and the second type of event, driver behavior portrait is performed, and the two layers of events are combined, so that driver behavior portrait can be performed more accurately.

[0084] Figure 4 It is a schematic diagram of an electronic device 4 provided in the embodiments of the present application. As Figure 4 shown, the electronic device 4 in this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of each module in the above-mentioned various device embodiments are implemented.

[0085] The electronic device 4 may be a desktop computer, a notebook, a palm computer, a cloud server, and other electronic devices. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art can understand that Figure 4 merely examples of the electronic device 4, which do not constitute a limitation to the electronic device 4, and may include more or fewer components than those shown in the figure, or different components.

[0086] The processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0087] The memory 402 can be an internal storage unit of the electronic device 4. For example, the hard disk or memory of the electronic device 4. The memory 402 can also be an external storage device of the electronic device 4. For example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 4. The memory 402 can also include both the internal storage unit and the external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.

[0088] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0089] When an integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. The computer program can include computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0090] The above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A driver behavior profiling method, characterized in that, The method includes: Obtaining the national standard vehicle historical records and enterprise standard vehicle historical records stored by data collection date partition; Identifying the first type of events in the national standard vehicle historical records to obtain the event elements of the first type of events, where the event elements include vehicle identification number, event start time, and event end time; Associating the first type of events with the national standard vehicle historical records or the enterprise standard vehicle historical records according to the event elements of the first type of events, and calculating the event indicators of the first type of events according to the association result; Identifying the second type of events in the first type of events, and calculating the event indicators of the second type of events; Performing driver behavior profiling according to the event indicators of the first type of events and the event indicators of the second type of events.

2. The method according to claim 1, characterized in that Identifying the first type of events in the national standard vehicle historical records includes: Grouping the national standard vehicle historical records by vehicle identification number, and arranging the grouped national standard vehicle historical records in ascending order of data collection timestamp; Dividing the first type of events according to the national standard vehicle historical records according to the identification and division rules of different first type of events to obtain the event elements of the first type of events, where the different first type of events include driving events or charging events; Storing the event elements of the first type of events in separate tables according to the event type of the first type of events and partitioning by event date.

3. The method according to claim 2, wherein After dividing the first type of events according to the national standard vehicle historical records according to the identification and division rules of different first type of events, the method further includes: merging the same type of events with the same vehicle identification number and an event time interval less than the first duration.

4. The method according to claim 1, wherein Identifying the second type of events in the first type of events includes: Obtaining the corresponding partial historical records of the first type of events in the national standard vehicle historical records and the enterprise standard vehicle historical records according to the association result; Grouping the partial historical records by the vehicle identification number and the event start time, and arranging the grouped partial historical records in ascending order of data collection timestamp; Dividing the second type of events according to the partial historical records according to the identification and division rules of different second type of events to obtain the event elements of the second type of events.

5. The method according to claim 1, wherein Performing driver behavior profiling according to the event indicators of the first type of events and the event indicators of the second type of events includes: Calculating according to the event indicators of the second type of events, and adding the calculation result as an event indicator to the event indicators of the first type of events; Performing driver behavior profiling according to the event indicators of the first type of events after adding the calculation result.

6. The method according to claim 1, characterized in that, The second type of events includes at least any one of the following: sudden acceleration, sudden deceleration, speeding, sharp turn, and collision.

7. The method according to claim 1, wherein Before obtaining the national standard vehicle historical records and the enterprise standard vehicle historical records stored by data collection date partition, the method further includes: Separately collecting and persisting the national standard vehicle historical records and the enterprise standard vehicle historical records; Receive the national standard vehicle historical records and the enterprise standard vehicle historical records reported in real time from the distributed publish-subscribe message system, and write the national standard vehicle historical records and the enterprise standard vehicle historical records into the distributed file storage system.

8. A driver behavior profiling device, characterized in that, The device includes: A data acquisition module, configured to acquire the national standard vehicle historical records and the enterprise standard vehicle historical records stored by date partition of data acquisition; A first identification module, configured to identify a first type of event in the national standard vehicle historical records to obtain event elements of the first type of event, where the event elements include a vehicle identification code, an event start time, and an event end time; An index calculation module, configured to associate the first type of event with the national standard vehicle historical records or the enterprise standard vehicle historical records according to the event elements of the first type of event, and calculate an event index of the first type of event according to the association result; A second identification module, configured to identify a second type of event in the first type of event and calculate an event index of the second type of event; A portrait module, configured to perform driver behavior portrait according to the event index of the first type of event and the event index of the second type of event.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images