User portrait obtaining method and device
By analyzing vehicle driving data using DBSCAN clustering algorithm, the problems of high cost and low efficiency of user portrait analysis in the prior art are solved, and fast and low-cost user portrait acquisition are achieved.
Patent Information
- Application Number
- CN202411543087.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-02-18
AI Technical Summary
The prior art requires a large number of label samples and high initial investment in user portrait analysis, resulting in high cost and low efficiency.
By obtaining the basic driving data indicators of each car and inputting them into the DBSCAN clustering algorithm, multiple user categories are obtained, and finally, using the user classification as the dimension, the average of the basic driving data indicators of users in each user classification is obtained. User portraits corresponding to each user category.
It realizes fast, simple and low-cost user portrait analysis, can quickly divide users into different types and draw user portraits, reducing the need for data annotation and early investment.
Smart Images
Figure CN119477404A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of big data technology, and in particular to a method and device for obtaining a user portrait. Background Art
[0002] Before the widespread use of the Internet of Vehicles, the main method for automobile manufacturers to analyze the main vehicle usage scenarios and vehicle usage habits of a certain user group was to conduct offline questionnaire surveys on users. The disadvantages of this method are obvious: high cost, small sample size, and strong subjectivity. As the Internet of Vehicles functions continue to become more popular, the scope and types of data collection are gradually enriched. The Internet of Vehicles big data provides a new solution for vehicle user portrait analysis.
[0003] In the prior art, a scene feature expansion network is constructed and trained based on manually labeled real scene features; the vehicle scene data is expanded based on the trained scene feature expansion network, which can complete the expansion of vehicle scene data with a small amount of labeled real scene data. This method requires the provision of existing sample labels for algorithm training, and has certain requirements for the number of vehicles owned by the enterprise, requiring a large amount of initial investment.
[0004] In summary, how to implement fast, simple and low-cost user portrait analysis is an urgent problem that technical personnel in this field need to solve. Summary of the invention
[0005] In view of this, the present application provides a method and device for obtaining a user portrait, aiming to achieve fast, simple and low-cost user portrait analysis.
[0006] In a first aspect, the present application provides a method for obtaining a user portrait, comprising:
[0007] Obtain basic driving data indicators for each vehicle; the basic driving data indicators include the average number of driving days per week, the average number of vehicle uses per day, the average daily driving mileage, the average mileage per trip, the average number of passengers per trip, the number of stops at various locations, and the number of passengers getting on and off at various locations;
[0008] Inputting the basic driving data index of each vehicle into the DBSCAN clustering algorithm to obtain multiple user classifications;
[0009] Taking the user classification as a dimension, the basic driving data indicators of users in each user classification are averaged to obtain user portraits corresponding to each user classification.
[0010] Optionally, the obtaining of basic driving data indicators of each vehicle includes:
[0011] Segmenting the vehicle travel of each vehicle to obtain travel data of each vehicle;
[0012] Identify the boarding and alighting behaviors of passengers in each vehicle trip to obtain passenger riding data of each vehicle;
[0013] Identifying the stop process of each vehicle to obtain the stop data of each vehicle;
[0014] Determine the vehicle use process related information data of each vehicle according to the travel data of each vehicle, the passenger riding data of each vehicle and the stop data of each vehicle;
[0015] According to the information data related to the vehicle use process of each vehicle, the basic driving data index of each vehicle is determined.
[0016] Optionally, the segmenting of the vehicle travel of each vehicle to obtain the travel data of each vehicle includes:
[0017] Get the vehicle's single engine ignition signal;
[0018] Determining the vehicle's single engine ignition signal as a vehicle trip start identifier;
[0019] According to the time sequence, the first engine shutdown signal after the single engine ignition signal of the vehicle is determined as the vehicle trip end mark;
[0020] The start and end times of the trip, the longitude and latitude, and the accumulated mileage of the vehicle are determined according to the vehicle trip start mark and the vehicle trip end mark.
[0021] Optionally, the identifying the boarding and alighting behaviors of passengers in each vehicle trip to obtain the passenger riding data of each vehicle includes:
[0022] If the vehicle is in the process of traveling and obtains a seat occupancy sensor activation signal, the occupancy sensor activation signal is determined as a seat start indicator;
[0023] If the vehicle has acquired the seat occupancy sensor activation signal at the start of the journey, determining the vehicle journey start mark as the seat occupancy start mark;
[0024] Searching backward in chronological order for a seat occupancy release signal closest to the seat's ride start mark;
[0025] determining the seat occupancy release signal as a passenger leaving mark of the seat;
[0026] If the vehicle does not obtain the seat occupancy release signal at the end of the journey, the vehicle journey end mark is determined as the passenger leaving mark of the seat.
[0027] Optionally, the identifying the stop process of each vehicle to obtain the stop data of each vehicle includes:
[0028] The stop data of the vehicle is determined according to the vehicle travel start mark and the vehicle travel end mark.
[0029] In a second aspect, the present application provides a user portrait acquisition device, comprising:
[0030] An acquisition module is used to acquire basic driving data indicators of each vehicle; the basic driving data indicators include the average number of driving days per week, the average number of vehicle usage per day, the average daily driving mileage, the average mileage per trip, the average number of passengers per trip, the number of stops at various locations, and the number of passengers getting on and off at various locations;
[0031] An input module, used for inputting the basic driving data index of each vehicle into a DBSCAN clustering algorithm to obtain multiple user classifications;
[0032] The processing module is used to take the user classification as a dimension, average the basic driving data indicators of users in each user classification, and obtain the user portraits corresponding to each user classification.
[0033] Optionally, the acquisition module includes:
[0034] A segmentation unit, used for segmenting the vehicle travel of each vehicle to obtain the travel data of each vehicle;
[0035] A first identification unit is used to identify the boarding and alighting behaviors of passengers in each vehicle trip to obtain the passenger riding data of each vehicle;
[0036] A second identification unit is used to identify the stop process of each vehicle and obtain the stop data of each vehicle;
[0037] A first determining unit is used to determine the vehicle use process related information data of each vehicle according to the travel data of each vehicle, the passenger riding data of each vehicle and the stop data of each vehicle;
[0038] The second determination unit is used to determine the basic driving data index of each vehicle according to the relevant information data of the vehicle use process of each vehicle.
[0039] Optionally, the segmentation unit includes:
[0040] A first acquisition subunit is used to acquire a single engine ignition signal of a vehicle;
[0041] A first determination subunit, configured to determine the vehicle single engine ignition signal as a vehicle trip start identifier;
[0042] A second determination subunit is used to determine, in chronological order, the first engine shutdown signal after the single engine ignition signal of the vehicle as a vehicle trip end mark;
[0043] The third determining subunit is used to determine the start and end time of the trip, the longitude and latitude, and the accumulated mileage of the vehicle according to the vehicle trip start mark and the vehicle trip end mark.
[0044] Optionally, the first identification unit includes:
[0045] a fourth determination subunit, configured to determine, if the vehicle is in the process of traveling and obtains a seat occupancy sensor activation signal, the occupancy sensor activation signal as a seat occupancy start indicator;
[0046] a fifth determining subunit, configured to determine the vehicle journey start flag as the seat occupancy start flag if the vehicle has acquired the seat occupancy sensor activation signal at the beginning of the journey;
[0047] A searching subunit, configured to search backward in chronological order for a seat occupancy release signal closest to the seat's occupancy start mark;
[0048] a sixth determining subunit, configured to determine the seat occupancy release signal as a passenger leaving mark of the seat;
[0049] The seventh determination subunit is used to determine the vehicle journey end mark as the passenger leaving mark of the seat if the vehicle does not obtain the seat occupancy release signal at the end of the journey.
[0050] Optionally, the second identification unit includes:
[0051] An eighth determining subunit is used to determine the stop data of the vehicle according to the vehicle journey start mark and the vehicle journey end mark.
[0052] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the user portrait acquisition method described in any one of the implementation methods in the first aspect of the embodiment of the present application.
[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes a user portrait acquisition method as described in any one of the implementation methods in the first aspect of the embodiment of the present application.
[0054] The present application provides a method for obtaining user portraits. When executing the method, the basic driving data indicators of each vehicle are first obtained, wherein the basic driving data indicators include the average number of driving days per week, the average number of vehicle uses per day, the average mileage per day, the average mileage per trip, the average number of people on the vehicle per trip, the number of stops at various types of locations, and the number of passengers getting on and off at various types of locations. The basic driving data indicators of each vehicle are then input into the DBSCAN clustering algorithm to obtain multiple user classifications. Finally, the basic driving data indicators of users in each user classification are averaged based on the user classification as a dimension to obtain the user portraits corresponding to each user classification. In this way, users of a certain user group are divided into several different types based on dimensions such as vehicle usage scenarios and vehicle usage habits, and user portraits of users of different types are drawn for user analysis. A fast, simple, and low-cost user portrait analysis is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0056] Figure 1 A flowchart of a method for obtaining a user portrait provided in an embodiment of the present application;
[0057] Figure 2 A flow chart of a user classification algorithm provided in an embodiment of the present application;
[0058] Figure 3 A schematic diagram of the structure of a user portrait acquisition device provided in an embodiment of the present application;
[0059] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0060] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The present application provides a method and device for obtaining user portraits, which are used in the field of big data technology. The above is only an example and does not limit the application field of the method and device name provided in the present application.
[0061] Before the widespread use of the Internet of Vehicles, the main method for automobile manufacturers to analyze the main vehicle usage scenarios and vehicle usage habits of a certain user group was to conduct offline questionnaire surveys on users. The disadvantages of this method are obvious: high cost, small sample size, and strong subjectivity. As the Internet of Vehicles functions continue to become more popular, the scope and types of data collection are gradually enriched. The Internet of Vehicles big data provides a new solution for vehicle user portrait analysis.
[0062] In the prior art, a scene feature expansion network is constructed and trained based on manually labeled real scene features; the vehicle scene data is expanded based on the trained scene feature expansion network, which can complete the expansion of vehicle scene data with a small amount of labeled real scene data. This method requires the provision of existing sample labels for algorithm training, and has certain requirements for the number of vehicles owned by the enterprise, requiring a large amount of initial investment.
[0063] After research, the inventor proposed the technical solution of this application. First, the basic driving data indicators of each vehicle are obtained, wherein the basic driving data indicators include the average number of driving days per week, the average number of vehicle usage per day, the average mileage per day, the average mileage per trip, the average number of passengers per trip, the number of stops at various types of locations, and the number of passengers getting on and off at various types of locations. Then, the basic driving data indicators of each vehicle are input into the DBSCAN clustering algorithm to obtain multiple user classifications. Finally, the basic driving data indicators of users in each user classification are averaged based on the user classification as a dimension to obtain the user portraits corresponding to each user classification. In this way, users of a certain user group are divided into several different types based on dimensions such as vehicle usage scenarios and vehicle usage habits, and user portraits of users of different types are drawn for user analysis. A fast, simple, and low-cost user portrait analysis is achieved.
[0064] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.
[0065] See also Figure 1 , Figure 1 A flowchart of a method for obtaining a user portrait provided in an embodiment of the present application includes:
[0066] S101: Obtain basic driving data indicators for each vehicle.
[0067] First, the vehicle's trip is segmented to obtain the vehicle's trip data, which includes but is not limited to the start and end time of the trip, longitude and latitude, and the vehicle's accumulated mileage. Specifically, the vehicle's single engine ignition signal is used as the vehicle's trip start mark. Then, the engine shutdown signal closest to the start mark is searched backward in chronological order as the vehicle's trip end mark. And a trip is determined based on the vehicle's trip start mark and the vehicle's trip end mark. And record the trip start and end time, longitude and latitude, and the vehicle's accumulated mileage and other information.
[0068] Next, the boarding and alighting behaviors of passengers during the trip are identified. Specifically, if the vehicle obtains a seat occupancy sensor activation signal during the trip, the occupancy sensor activation signal is determined as the seat's start mark. If the vehicle has obtained a seat occupancy sensor activation signal at the beginning of the trip, the vehicle's trip start mark is determined as the seat's start mark. The seat occupancy release signal closest to the seat's start mark is searched backward in chronological order, and the seat occupancy release signal is determined as the seat's passenger departure mark. If the vehicle does not obtain a seat occupancy release signal at the end of the trip, the vehicle's trip end mark is determined as the seat's passenger departure mark. The time, longitude and latitude, accumulated mileage and other information of the passenger's start and end of the trip are recorded.
[0069] The vehicle's stop process is identified. Specifically, the middle period between two adjacent trips is regarded as a vehicle stop process, and the end time and location of the previous trip and the start time and location of the next trip are respectively used as the start time, location and end time and location of the stop.
[0070] Next, the vehicle use process related data is obtained, specifically in the following way: the vehicle trip and the end time of the passenger boarding and alighting process are obtained by subtracting the start time from the end time to obtain the process time, and the cumulative mileage at the end of the trip is subtracted from the cumulative mileage at the beginning to obtain the trip distance. The latitude and longitude at the beginning and end of the trip and when the passengers board and alight are parsed into geographic information and classified into: residential areas, commercial buildings, large parking lots, airport stations, tourist attractions, commercial stores, etc. The start time, location, end time and location of the stop are used to determine the duration of the stop process, location information, etc.
[0071] Finally, the vehicle usage data indicators are processed using information data related to the vehicle usage process to obtain the average number of driving days per week, the average number of vehicle uses per day, the average daily mileage, the average mileage per trip, the average number of people on board per trip, the number of stops at various types of locations, and the number of passengers getting on and off at various locations.
[0072] S102: Input the basic driving data index of each vehicle into the DBSCAN clustering algorithm to obtain multiple user classifications.
[0073] The DBSCAN clustering algorithm is used for automatic classification of users. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm. Its main features are that it can find clusters of any shape and can handle noisy data. The DBSCAN algorithm defines a cluster as the largest set of density-connected points. It uses two parameters to describe the compactness of sample distribution in the neighborhood: eps: describes the neighborhood distance threshold of a certain sample. minSamples: describes the threshold of the number of samples in the neighborhood of a certain sample with a distance of eps. The basic steps of the algorithm are as follows: Determine the core sample points: For each point, if there are at least minSamples points in its eps neighborhood, then this point is a core sample point. Form a cluster: Starting from a core sample point, all density-connected points form a cluster. Density connection here means the set of points that can be reached from a core point through other core points. Identify noise: Points that are not in any cluster are considered noise. The main advantages of the DBSCAN algorithm include: Ability to discover clusters of arbitrary shapes: Unlike the traditional K-means algorithm, DBSCAN does not assume that the shape of the cluster is circular or spherical, so it can identify more complex data structures. Insensitive to noisy data: DBSCAN is able to exclude noisy data points from the cluster. No need to pre-specify the number of clusters: DBSCAN automatically determines the number of clusters based on the density characteristics of the data.
[0074] The processed data indicators are input into the algorithm to obtain each user classification, such as Figure 2 As shown, Figure 2 A flow chart of a user classification algorithm provided in an embodiment of the present application.
[0075] S103: Taking user classification as a dimension, average the basic driving data indicators of users in each user classification to obtain user portraits corresponding to each user classification.
[0076] Taking the user classification obtained in step S102 as a dimension, the average value of the car usage data indicators of users in each category is taken to obtain the user portrait of the category. The statistical results are shown in Table 1.
[0077] Table 1: User profile table for classified users
[0078]
[0079] In the embodiment of the present application, the basic driving data indicators of each vehicle are first obtained, wherein the basic driving data indicators include the average number of driving days per week, the average number of vehicle usage per day, the average mileage per day, the average mileage per trip, the average number of passengers on a single trip, the number of stops at various types of locations, and the number of passengers getting on and off at various types of locations. The basic driving data indicators of each vehicle are then input into the DBSCAN clustering algorithm to obtain multiple user classifications. Finally, the basic driving data indicators of users in each user classification are averaged based on the user classification as a dimension to obtain the user portraits corresponding to each user classification. In this way, users of a certain user group are divided into several different types based on dimensions such as vehicle usage scenarios and vehicle usage habits, and user portraits of users of different types are drawn for user analysis. A fast, simple, and low-cost user portrait analysis is achieved.
[0080] The above are some specific implementations of the user portrait acquisition method provided in the embodiment of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiment of the present application will be introduced from the perspective of functional modularization.
[0081] See also Figure 3 , Figure 3 A schematic diagram of the structure of a user portrait acquisition device provided in an embodiment of the present application, the user portrait acquisition device 300 includes:
[0082] The acquisition module 310 is used to acquire basic driving data indicators of each vehicle; the basic driving data indicators include the average number of driving days per week, the average number of vehicle usage per day, the average driving mileage per day, the average mileage per trip, the average number of passengers per trip, the number of stops at various locations, and the number of passengers getting on and off at various locations;
[0083] An input module 320, used for inputting the basic driving data index of each vehicle into a DBSCAN clustering algorithm to obtain multiple user classifications;
[0084] The processing module 330 is used to take the average value of the basic driving data indicators of users in each user category based on the user category as a dimension, and obtain the user portraits corresponding to each user category.
[0085] Optionally, the acquisition module 310 includes:
[0086] A segmentation unit, used for segmenting the vehicle travel of each vehicle to obtain the travel data of each vehicle;
[0087] A first identification unit is used to identify the boarding and alighting behaviors of passengers in each vehicle trip to obtain the passenger riding data of each vehicle;
[0088] A second identification unit is used to identify the stop process of each vehicle and obtain the stop data of each vehicle;
[0089] A first determining unit is used to determine the vehicle use process related information data of each vehicle according to the travel data of each vehicle, the passenger riding data of each vehicle and the stop data of each vehicle;
[0090] The second determination unit is used to determine the basic driving data index of each vehicle according to the relevant information data of the vehicle use process of each vehicle.
[0091] Optionally, the segmentation unit includes:
[0092] A first acquisition subunit is used to acquire a single engine ignition signal of a vehicle;
[0093] A first determination subunit, configured to determine the vehicle single engine ignition signal as a vehicle trip start identifier;
[0094] A second determination subunit is used to determine, in chronological order, the first engine shutdown signal after the single engine ignition signal of the vehicle as a vehicle trip end mark;
[0095] The third determining subunit is used to determine the start and end time of the trip, the longitude and latitude, and the accumulated mileage of the vehicle according to the vehicle trip start mark and the vehicle trip end mark.
[0096] Optionally, the first identification unit includes:
[0097] a fourth determination subunit, configured to determine, if the vehicle is in the process of traveling and obtains a seat occupancy sensor activation signal, the occupancy sensor activation signal as a seat occupancy start indicator;
[0098] a fifth determining subunit, configured to determine the vehicle journey start flag as the seat occupancy start flag if the vehicle has acquired the seat occupancy sensor activation signal at the beginning of the journey;
[0099] A searching subunit, configured to search backward in chronological order for a seat occupancy release signal closest to the seat's occupancy start mark;
[0100] a sixth determining subunit, configured to determine the seat occupancy release signal as a passenger leaving mark of the seat;
[0101] The seventh determination subunit is used to determine the vehicle journey end mark as the passenger leaving mark of the seat if the vehicle does not obtain the seat occupancy release signal at the end of the journey.
[0102] Optionally, the second identification unit includes:
[0103] An eighth determining subunit is used to determine the stop data of the vehicle according to the vehicle journey start mark and the vehicle journey end mark.
[0104] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.
[0105] like Figure 4 As shown, the computer device 01 is in the form of a general computing device. The components of the computer device 01 may include but are not limited to: one or more processors or processing units 03, a system memory 08, and a bus 04 connecting different system components (including the system memory 08 and the processing unit 03).
[0106] Bus 04 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.
[0107] The computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 01, including volatile and non-volatile media, removable and non-removable media.
[0108] The system memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. The computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 11 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 04 via one or more data medium interfaces. The memory 08 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0109] A program / utility 12 having a set (at least one) of program modules 13 may be stored, for example, in the memory 08, such program modules 13 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 13 generally perform the functions and / or methods of the embodiments described herein.
[0110] The computer device 01 may also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), one or more devices that enable a user to interact with the computer device 01, and / or any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via input / output (I / O) interface 06. Furthermore, the computer device 01 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via network adapter 05. Figure 4 As shown, the network adapter 05 communicates with other modules of the computer device 01 via the bus 04. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with computer device 01, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0111] The processor unit 03 executes various functional applications and data processing by running programs stored in the system memory 08, such as implementing a user portrait acquisition method provided in an embodiment of the present application.
[0112] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0113] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.
[0114] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.
[0115] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.
Claims
1. A method for obtaining a user portrait, characterized in that: include: Obtain basic driving data indicators for each vehicle; the basic driving data indicators include the average number of driving days per week, the average number of vehicle uses per day, the average driving mileage per day, the average mileage per trip, the average number of passengers per trip, the number of stops at various locations, and the number of passengers getting on and off at various locations; Inputting the basic driving data index of each vehicle into the DBSCAN clustering algorithm to obtain multiple user classifications; Taking the user classification as a dimension, the basic driving data indicators of users in each user classification are averaged to obtain user portraits corresponding to each user classification.
2. The method according to claim 1, characterized in that The basic driving data indicators of each vehicle are obtained, including: Segmenting the vehicle travel of each vehicle to obtain travel data of each vehicle; Identify the boarding and alighting behaviors of passengers in each vehicle trip to obtain passenger riding data of each vehicle; Identifying the stop process of each vehicle to obtain the stop data of each vehicle; Determine the vehicle use process related information data of each vehicle according to the travel data of each vehicle, the passenger riding data of each vehicle and the stop data of each vehicle; According to the information data related to the vehicle use process of each vehicle, the basic driving data index of each vehicle is determined.
3. The method according to claim 2, characterized in that The vehicle travel of each vehicle is segmented to obtain the travel data of each vehicle, including: Get the vehicle's single engine ignition signal; Determining the vehicle's single engine ignition signal as a vehicle trip start identifier; According to the time sequence, the first engine shutdown signal after the single engine ignition signal of the vehicle is determined as the vehicle trip end mark; The start and end times of the trip, the longitude and latitude, and the accumulated mileage of the vehicle are determined according to the vehicle trip start mark and the vehicle trip end mark.
4. The method according to claim 3, characterized in that The identification of the boarding and alighting behaviors of passengers in each vehicle trip to obtain the passenger riding data of each vehicle includes: If the vehicle is in the process of traveling and obtains a seat occupancy sensor activation signal, the occupancy sensor activation signal is determined as a seat start indicator; If the vehicle has acquired the seat occupancy sensor activation signal at the start of the journey, determining the vehicle journey start mark as the seat occupancy start mark; Searching backward in chronological order for a seat occupancy release signal closest to the seat's ride start mark; determining the seat occupancy release signal as a passenger leaving mark of the seat; If the vehicle does not obtain the seat occupancy release signal at the end of the journey, the vehicle journey end mark is determined as the passenger leaving mark of the seat.
5. The method according to claim 3, characterized in that: The step of identifying the stop process of each vehicle to obtain the stop data of each vehicle includes: The stop data of the vehicle is determined according to the vehicle travel start mark and the vehicle travel end mark.
6. A user portrait acquisition device, characterized in that: include: An acquisition module is used to acquire basic driving data indicators of each vehicle; the basic driving data indicators include the average number of driving days per week, the average number of vehicle usage per day, the average daily driving mileage, the average mileage per trip, the average number of passengers per trip, the number of stops at various locations, and the number of passengers getting on and off at various locations; An input module, used for inputting the basic driving data index of each vehicle into a DBSCAN clustering algorithm to obtain multiple user classifications; The processing module is used to take the user classification as a dimension, average the basic driving data indicators of users in each user classification, and obtain the user portraits corresponding to each user classification.
7. The device according to claim 6, characterized in that The acquisition module comprises: A segmentation unit, used for segmenting the vehicle travel of each vehicle to obtain the travel data of each vehicle; A first identification unit is used to identify the boarding and alighting behaviors of passengers in each vehicle trip to obtain the passenger riding data of each vehicle; A second identification unit is used to identify the stop process of each vehicle and obtain the stop data of each vehicle; A first determining unit is used to determine the vehicle use process related information data of each vehicle according to the travel data of each vehicle, the passenger riding data of each vehicle and the stop data of each vehicle; The second determination unit is used to determine the basic driving data index of each vehicle according to the relevant information data of the vehicle use process of each vehicle.
8. The device according to claim 7, characterized in that The segmentation unit comprises: A first acquisition subunit is used to acquire a single engine ignition signal of a vehicle; A first determination subunit, configured to determine the vehicle single engine ignition signal as a vehicle trip start identifier; A second determination subunit is used to determine, in chronological order, the first engine shutdown signal after the single engine ignition signal of the vehicle as a vehicle trip end mark; The third determining subunit is used to determine the start and end time of the trip, the longitude and latitude, and the accumulated mileage of the vehicle according to the vehicle trip start mark and the vehicle trip end mark.
9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the user portrait acquisition method according to any one of claims 1 to 5 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the user portrait acquisition method according to any one of claims 1 to 5.