Method, device and non-volatile storage medium for generating vehicle trajectory analysis model

Abstract

The present application discloses a method, apparatus, and non-volatile storage medium for generating a vehicle trajectory judgment model. Among them, the method includes: obtaining vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; determining the scenario categories corresponding to the vehicle trajectory data; determining the target model parameter thresholds corresponding to the target vehicle trajectory judgment models under different scenario categories according to the vehicle trajectory data under different scenario categories; and determining the target vehicle trajectory judgment models under different scenario categories according to the target model parameter thresholds. The present application solves the technical problem that the vehicle trajectory cannot be efficiently analyzed in multiple scenario dimensions due to the strong singularity of the vehicle trajectory judgment algorithm in the related art.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular, to a method, apparatus, and non-volatile storage medium for generating a vehicle trajectory analysis model. Background Art

[0002] In recent years, with the continuous development of road traffic, it has brought more and greater challenges to traffic management. Against this background, the vehicle trajectory analysis technology based on video surveillance has gradually matured, and the vehicle trajectory analysis technology has gradually developed from the unified management of a single traffic department to all aspects of society such as individuals, enterprises, production, fire protection, and criminal investigation. Vehicle trajectory analysis is breaking through the boundaries of the industry and bringing great benefits to road traffic management analysis. With the popularization and improvement of the application of view big data, customer personalized needs are becoming more and more divergent. As a result, the difficulty of vehicle trajectory analysis is also increasing, mainly reflected in the vehicle trajectory analysis of different scenarios, different dimensions, and different granularities, which requires different depths of algorithm analysis. It is difficult to have an algorithm that can comprehensively consider all conditions such as scene dimensions and granularities. At present, the vehicle trajectory analysis algorithms in related technologies are often highly single, and they often cannot perform well in analyzing vehicle trajectory analysis tasks in multiple scene dimensions.

[0003] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0004] Embodiments of the present application provide a method, apparatus, and non-volatile storage medium for generating a vehicle trajectory analysis model, so as to at least solve the technical problem that the vehicle trajectory analysis algorithm in related technologies is highly single and cannot efficiently analyze vehicle trajectories in multiple scene dimensions.

[0005] According to one aspect of the embodiments of the present application, a method for generating a vehicle trajectory analysis model is provided, including: obtaining vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; determining the scene categories corresponding to the vehicle trajectory data; determining the target model parameter thresholds corresponding to the target vehicle trajectory analysis models in different scene categories according to the vehicle trajectory data in different scene categories; and determining the target vehicle trajectory analysis models in different scene categories according to the target model parameter thresholds.

[0006] Optionally, the step of determining the scene categories corresponding to the vehicle trajectory data includes: classifying the vehicle trajectory data through a preset scene classification algorithm to obtain the vehicle trajectory data in different scene categories; and determining the scene category labels of the vehicle trajectory data according to the scene categories corresponding to the vehicle trajectory data, where the scene categories include: community, school, village, and urban area.

[0007] Optionally, the steps of determining the target model parameter thresholds corresponding to the target vehicle trajectory analysis models for different scenario categories based on the vehicle trajectory data for different scenario categories include: for the vehicle trajectory data for each scenario category among different scenario categories, using a general vehicle trajectory analysis model to process the vehicle trajectory data in different dimensions to obtain a first data analysis result; filtering out the invalid data analysis results in the first data analysis result to obtain a second data analysis result; and determining the target model parameter thresholds for different scenario categories based on the second data analysis result.

[0008] Optionally, the vehicle trajectory data for different scenario categories includes the vehicle trajectory data in different dimensions for that scenario category, where the dimensions include: time, scenario, vehicle type, style, color.

[0009] Optionally, after the step of determining the target vehicle trajectory analysis models for different scenario categories based on the target model parameter thresholds, the method for generating a vehicle trajectory analysis model further includes: placing the target vehicle trajectory analysis model into the corresponding target operator bin in the vehicle trajectory analysis system, where the vehicle trajectory analysis system includes multiple operator bins, and each operator bin among the multiple operator bins is used to store the target vehicle trajectory analysis model for the same scenario category; when the vehicle trajectory analysis system receives new vehicle trajectory data, determining the scenario category corresponding to the new vehicle trajectory data; and determining the target vehicle trajectory analysis model corresponding to the new vehicle trajectory data based on the scenario category corresponding to the new vehicle trajectory data.

[0010] Optionally, the working modes of the vehicle trajectory analysis system include an offline working mode and an online working mode. Among them, in the offline working mode, the target vehicle trajectory analysis model is called through the interface of the vehicle trajectory analysis system; in the online working mode, the target vehicle trajectory analysis model is called in real time through a scheduling program and a configuration file.

[0011] Optionally, the architecture of the vehicle trajectory analysis system is a Lambda architecture.

[0012] According to another aspect of the embodiments of the present application, there is also provided a device for generating a vehicle trajectory analysis model, including: an acquisition module, configured to acquire vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; a classification module, configured to determine the scenario category corresponding to the vehicle trajectory data; a first processing module, configured to determine the target model parameter thresholds corresponding to the target vehicle trajectory analysis models for different scenario categories based on the vehicle trajectory data for different scenario categories; and a second processing module, configured to determine the target vehicle trajectory analysis models for different scenario categories based on the target model parameter thresholds.

[0013] According to another aspect of the embodiments of the present application, a non-volatile storage medium is further provided. A program is stored in the non-volatile storage medium. When the program runs, it controls the device where the non-volatile storage medium is located to execute the vehicle trajectory analysis model generation method.

[0014] According to another aspect of the embodiments of the present application, an electronic device is further provided, including: a memory and a processor. The processor is used to run the program stored in the memory. When the program runs, it executes the vehicle trajectory analysis model generation method.

[0015] In the embodiments of the present application, the method includes obtaining vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; determining the scenario category corresponding to the vehicle trajectory data; determining the target model parameter thresholds corresponding to the target vehicle trajectory analysis models in different scenario categories according to the vehicle trajectory data in different scenario categories; and determining the target vehicle trajectory analysis models in different scenario categories according to the target model parameter thresholds. By determining the target model parameter thresholds in the vehicle trajectory data of different scenario categories, and then determining the target vehicle trajectory analysis models in these scenario categories, the purpose of determining the vehicle trajectory analysis models in various scenario categories is achieved, thereby realizing the technical effect of efficiently analyzing vehicle trajectories in different scenario categories, and further solving the technical problem that it is impossible to efficiently analyze vehicle trajectories in multiple scenario dimensions due to the strong singularity of vehicle trajectory analysis algorithms in related technologies. Description of the Drawings

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0017] Figure 1 is a schematic diagram of a vehicle trajectory analysis model according to related technologies;

[0018] Figure 2 is a schematic diagram of an optional computer terminal device according to the embodiments of the present application;

[0019] Figure 3 is a schematic flowchart of a vehicle trajectory analysis model generation method according to the embodiments of the present application;

[0020] Figure 4 is a schematic diagram of a vehicle trajectory analysis model according to the embodiments of the present application;

[0021] Figure 5 is a schematic diagram of a vehicle trajectory analysis operator matching rule according to the embodiments of the present application;

[0022] Figure 6 It is a schematic structural diagram of a vehicle trajectory judgment model generation device according to an embodiment of the present application. Detailed implementation manners

[0023] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" 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 does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0025] In the related art, as Figure 1 shown, in order to process vehicle trajectory data in different scenarios, the data query vehicle driving record will be called, and the vehicle will be classified by single features such as body color and license plate number, the parameters will be adjusted, the judgment samples will be increased, and then it will be upgraded to the vehicle trajectory judgment operator warehouse (such as Figure 1 ). However, the drawbacks of the iteration and upgrade of this single-algorithm corresponding to vehicle trajectory judgment in multiple scenarios are often more obvious as the data increases, resulting in problems such as unclear judgment effect and poor user experience. To solve this problem, relevant solutions are provided in the embodiments of the present application, which will be described in detail below.

[0026] According to an embodiment of the present application, a method embodiment of a vehicle trajectory judgment model generation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described here can be executed in an order different from that here.

[0027] The method embodiments provided by the embodiments of the present application can be executed on a mobile terminal, a computer terminal or a similar computing device.Figure 2 A hardware block diagram of a computer terminal (or mobile device) for implementing a vehicle trajectory analysis model generation method is shown. As Figure 2 shown, the computer terminal 10 (or mobile device 10) may include one or more processors 102 (shown as 102a, 102b,..., 102n in the figure) (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may further include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply, and / or a camera. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above electronic device. For example, the computer terminal 10 may further include more or fewer components than Figure 1 shown, or have a different configuration from Figure 1 shown.

[0028] It should be noted that the above one or more processors 102 and / or other data processing circuits are generally referred to as "data processing circuits" herein. The data processing circuit may be embodied in software, hardware, firmware, or any combination thereof, in whole or in part. In addition, the data processing circuit may be a single independent processing module, or be incorporated in whole or in part into any one of the other elements in the computer terminal 10 (or mobile device). As involved in the embodiments of the present application, the data processing circuit is used for a processor control (such as the selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 may be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle trajectory analysis model generation method in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implements the vehicle trajectory analysis model generation method of the above application program. The memory 104 may include a high-speed random access memory, and may further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely set relative to the processor 102, and these remote memories may be connected to the computer terminal 10 through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display can be, for example, a touch-screen Liquid Crystal Display (LCD), which enables the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0032] Under the above operating environment, the embodiment of the present application provides a method for generating a vehicle trajectory analysis model, as Figure 3 shown, the method includes the following steps:

[0033] Step S302, obtain vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios;

[0034] Step S304, determine the scenario category corresponding to the vehicle trajectory data;

[0035] In the technical solution provided in step S304, the step of determining the scenario category corresponding to the vehicle trajectory data includes: classifying the vehicle trajectory data through a preset scenario classification algorithm to obtain the vehicle trajectory data under different scenario categories; determining the scenario category label of the vehicle trajectory data according to the scenario category corresponding to the vehicle trajectory data, where the scenario category includes: community, school, village, urban area.

[0036] Specifically, the vehicle data can be automatically classified by a scenario-based vehicle trajectory analysis algorithm, mainly divided into: community, school, village, urban area, etc., and tags are added to the vehicle data.

[0037] Step S306, determine the target model parameter thresholds corresponding to the target vehicle trajectory analysis models under different scenario categories according to the vehicle trajectory data under different scenario categories;

[0038] In the technical solution provided in step S306, the steps of determining the target model parameter thresholds corresponding to the target vehicle trajectory analysis models under different scenario categories based on the vehicle trajectory data under different scenario categories include: for the vehicle trajectory data under each scenario category among different scenario categories, using a general vehicle trajectory analysis model to process the vehicle trajectory data in different dimensions to obtain a first data analysis result; filtering out the invalid data analysis results in the first data analysis result to obtain a second data analysis result; and determining the target model parameter thresholds under different scenario categories based on the second data analysis result.

[0039] In some embodiments of the present application, the vehicle trajectory data under different scenario categories includes vehicle trajectory data in different dimensions under the scenario category, where the dimensions include: time, scenario, vehicle type, style, color.

[0040] Specifically, a general algorithm model can be used to analyze vehicle data in different dimensions (such as time, scenario, vehicle type, style, color, etc.), and the analysis results (pictures, confidence levels, targets, scenario labels) form a multi-dimensional vehicle trajectory analysis algorithm model. First, some invalid data is filtered through an intermediate result set to improve the confidence level of the algorithm.

[0041] Step S308: Determine the target vehicle trajectory analysis models under different scenario categories according to the target model parameter thresholds.

[0042] In the technical solution provided in step S308, when determining the target vehicle trajectory analysis models under different scenario categories according to the target model parameter thresholds, the thresholds of different dimensions of the vehicle trajectory analysis conditions under each scenario can be superimposed and analyzed based on a general algorithm model. The generated new algorithm model is assigned a scenario label according to the scenario information, and then the new algorithm models under different scenarios are uniformly scheduled through a data middle platform and updated into the corresponding vehicle trajectory analysis operator warehouse.

[0043] As an optional implementation manner, steps S302 - S308 can also be executed cyclically, so that the adaptability of the algorithm model to a specific scenario will be better. Through the above embodiments, the optimal matching of vehicle trajectory analysis & scenario & data is completed. For newly created vehicle data, its scenario is also classified, and the algorithm with the same label is adapted to ensure the implementation effect of the algorithm.

[0044] In some embodiments of the present application, after the step of determining the target vehicle trajectory analysis model under different scenario categories according to the target model parameter threshold, the method for generating the vehicle trajectory analysis model further includes: putting the target vehicle trajectory analysis model into the corresponding target operator bin in the vehicle trajectory analysis system, where the vehicle trajectory analysis system includes multiple operator bins, and each operator bin in the multiple operator bins is used to store the target vehicle trajectory analysis model under the same scenario category; when the vehicle trajectory analysis system receives new vehicle trajectory data, determining the scenario category corresponding to the new vehicle trajectory data; and determining the target vehicle trajectory analysis model corresponding to the new vehicle trajectory data according to the scenario category corresponding to the new vehicle trajectory data.

[0045] In some embodiments of the present application, the vehicle trajectory analysis system is as Figure 4 shown. It should be noted that the vehicle trajectory analysis operator bin in the system can be deployed as a separate service to the server, or it can be docked with the upper-layer platform application and integrated with the platform. First, when vehicle data is accessed from the front-end device, all data is stored in the database. In this application, it is preferably stored in the ClickHouse database. Then, it is necessary to perform dimensional stratification on the aggregated data to distinguish dimensions such as time, scenario, style, and vehicle speed. In the data calculation process, dimensional aggregation calculation is performed through multi-dimensional data indicators.

[0046] As an alternative implementation, when receiving new vehicle trajectory data, the process of the vehicle trajectory analysis system matching the corresponding vehicle trajectory analysis model is as Figure 5 shown. It can be seen from Figure 5 that when receiving new vehicle trajectory data, first, for the data accessed in each scenario, a specific scenario data set is generated. The data sets of all accessed scenarios are trained using the Kmeans clustering algorithm model. The data sets with high similarity are clustered into one type of data. Then, the linear regression algorithm is called for all data sets in the same type, and the Bayesian theorem is used to calculate the algorithm analysis operator parameter thresholds in each scenario, generating the vehicle analysis operator parameter thresholds for each type of data set. Finally, the training model and the result data set are trained and compared multiple times to obtain the most rigorous parameter thresholds and generate the vehicle analysis operator algorithms for different scenarios. For the subsequent accessed data sets, the automatic generation of the vehicle analysis operator for the data sets after data access can be realized. It should be noted that the operator described in the embodiments of the present application is the target vehicle trajectory analysis model.

[0047] In some embodiments of the present application, the user can also configure the vehicle trajectory analysis system. Specifically, the user can first select to enable the corresponding sub-services, such as spatio-temporal collision, same-travel vehicle, and cloned vehicle. Next is to select the respective implementations of the business real-time mode and the offline mode, as well as the specific data to be obtained during the analysis.

[0048] In some embodiments of the present application, the working modes of the vehicle trajectory analysis system include an offline working mode and an online working mode. Among them, in the offline working mode, the target vehicle trajectory analysis model is called through the interface of the vehicle trajectory analysis system; in the online working mode, the target vehicle trajectory analysis model is called in real time through the scheduling program and the configuration file.

[0049] In order to enable the vehicle trajectory analysis system to operate normally in both the offline working mode and the online working mode, the architecture of the vehicle trajectory analysis system is a Lambda architecture.

[0050] Specifically, in the embodiments of the present application, the Lambda architecture of data calculation in the big data system is adopted, that is, starting from the overall situation, the real-time mode and the offline mode are distinguished. First, when the data is being accessed, the data is uniformly accessed into a topic in Kafka. When the real-time mode is selected, the data will be consumed by Flink and then into other topics in Kafka, and finally saved in the ClickHouse database. In this mode, the vehicle trajectory analysis operator will perform specific task scheduling through service configuration; when the offline mode is selected, the data is directly saved into the intermediate result set of ClickHouse, and then multi-dimensional data aggregation calculation is performed according to the specific vehicle trajectory analysis algorithm. In this mode, the vehicle analysis operator will send the result to the front end through the front-end call interface.

[0051] By obtaining vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; determining the scenario categories corresponding to the vehicle trajectory data; determining the target model parameter thresholds corresponding to the target vehicle trajectory analysis models in different scenario categories according to the vehicle trajectory data in different scenario categories; and determining the target vehicle trajectory analysis models in different scenario categories according to the target model parameter thresholds. By determining the target model parameter thresholds in the vehicle trajectory data of different scenario categories, and then determining the target vehicle trajectory analysis models in this scenario category, the purpose of determining the vehicle trajectory analysis models in various scenario categories is achieved, thus realizing the technical effect of efficiently analyzing vehicle trajectories in different scenario categories, and further solving the technical problem of being unable to efficiently analyze vehicle trajectories in multiple scenario dimensions due to the strong singularity of vehicle trajectory analysis algorithms in related technologies.

[0052] In addition, the vehicle trajectory analysis model generation method provided in the embodiments of the present application can perform multi-dimensional analysis on vehicle trajectory analysis, and optimize the analysis algorithm according to different scenario dimensions. When optimizing the algorithm, targeted scenario analysis is performed by combining multi-dimensional conditions for analysis, and different versions of the same type of analysis operator in different scenarios are output, so as to realize targeted training optimization for vehicle trajectory analysis in a certain area or a certain time period. The algorithm of an analysis operator is configured into multiple optimized algorithms according to the actual scenario, changing the relationship between the vehicle trajectory analysis algorithm and the actual scenario from 1:N to M:N. Realize the refined management and scheduling of vehicle trajectory analysis, dimensions, and data, so that the vehicle trajectory analysis effect is highly matched with vehicle data, thereby achieving the effect of improving the accuracy of the algorithm and enhancing user satisfaction.

[0053] An embodiment of the present application provides a vehicle trajectory analysis model generation device. Figure 6 It is a schematic structural diagram of the device, as Figure 6 shown. The device includes: an acquisition module 60 for acquiring vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; a classification module 62 for determining the scenario category corresponding to the vehicle trajectory data; a first processing module 64 for determining the target model parameter threshold corresponding to the target vehicle trajectory analysis model in different scenario categories according to the vehicle trajectory data in different scenario categories; a second processing module 66 for determining the target vehicle trajectory analysis model in different scenario categories according to the target model parameter threshold.

[0054] In some embodiments of the present application, the steps of the classification module 62 determining the scenario category corresponding to the vehicle trajectory data include: classifying the vehicle trajectory data through a preset scenario classification algorithm to obtain vehicle trajectory data in different scenario categories; determining the scenario category label of the vehicle trajectory data according to the scenario category corresponding to the vehicle trajectory data, where the scenario categories include: community, school, village, urban area.

[0055] In some embodiments of the present application, the steps of the first processing module 64 determining the target model parameter threshold corresponding to the target vehicle trajectory analysis model in different scenario categories according to the vehicle trajectory data in different scenario categories include: using a general vehicle trajectory analysis model to process the vehicle trajectory data in different dimensions of each scenario category in different scenario categories to obtain a first data analysis result; filtering out the invalid data analysis results in the first data analysis result to obtain a second data analysis result; determining the target model parameter threshold in different scenario categories according to the second data analysis result.

[0056] In some embodiments of the present application, the vehicle trajectory data under different scenario categories includes vehicle trajectory data of different dimensions under the scenario category, where the dimensions include: time, scenario, vehicle type, style, and color.

[0057] In some embodiments of the present application, after the step of determining the target vehicle trajectory analysis model under different scenario categories according to the target model parameter threshold, the second processing module 66 is further configured to: put the target vehicle trajectory analysis model into the corresponding target operator bin in the vehicle trajectory analysis system, where the vehicle trajectory analysis system includes multiple operator bins, and each operator bin in the multiple operator bins is used to store the target vehicle trajectory analysis model under the same scenario category; when the vehicle trajectory analysis system receives new vehicle trajectory data, determine the scenario category corresponding to the new vehicle trajectory data; and determine the target vehicle trajectory analysis model corresponding to the new vehicle trajectory data according to the scenario category corresponding to the new vehicle trajectory data.

[0058] In some embodiments of the present application, the working mode of the vehicle trajectory analysis system includes an offline working mode and an online working mode. Among them, in the offline working mode, the target vehicle trajectory analysis model is called through the interface of the vehicle trajectory analysis system; in the online working mode, the target vehicle trajectory analysis model is called in real time through the scheduling program and the configuration file.

[0059] In some embodiments of the present application, the architecture of the vehicle trajectory analysis system is a Lambda architecture.

[0060] It should be noted that each module in the above vehicle trajectory analysis model generation device can be a program module (for example, a set of program instructions that implements a specific function), or a hardware module. For the latter, it can be presented in the following forms, but is not limited thereto: the presentation form of each of the above modules is a processor, or the functions of each of the above modules are implemented by a processor.

[0061] According to an embodiment of the present application, a non-volatile storage medium is provided. A program is stored in the non-volatile storage medium. When the program runs, it controls the device where the non-volatile storage medium is located to execute the following vehicle trajectory analysis model generation method: obtain vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles under different scenarios; determine the scenario category corresponding to the vehicle trajectory data; determine the target model parameter threshold corresponding to the target vehicle trajectory analysis model under different scenario categories according to the vehicle trajectory data under different scenario categories; and determine the target vehicle trajectory analysis model under different scenario categories according to the target model parameter threshold.

[0062] According to an embodiment of the present application, an electronic device is provided. The electronic device includes a memory and a processor, and the processor is configured to run a program stored in the memory. When the program runs, it executes the following method for generating a vehicle trajectory judgment model: obtaining vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; determining the scenario category corresponding to the vehicle trajectory data; determining the target model parameter thresholds corresponding to the target vehicle trajectory judgment models in different scenario categories based on the vehicle trajectory data in different scenario categories; and determining the target vehicle trajectory judgment models in different scenario categories based on the target model parameter thresholds.

[0063] In the above embodiments of the present application, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0064] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0065] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0066] In addition, in each embodiment of the present application, the functional units 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.

[0067] When the integrated unit 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, the technical solution of this application, in essence, or the part that contributes to the related technology, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several 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 methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0068] The above are only the preferred embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for generating a vehicle trajectory judgment model, characterized in that, Including: Obtain vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; Determine the scenario category corresponding to the vehicle trajectory data; Based on the vehicle trajectory data under different scenario categories, determine the target model parameter thresholds corresponding to the target vehicle trajectory analysis models under different scenario categories; Based on the target model parameter thresholds, determine the target vehicle trajectory analysis models under different scenario categories; Put the target vehicle trajectory analysis model into the corresponding target operator bin in the vehicle trajectory analysis system, where the vehicle trajectory analysis system includes multiple operator bins, and each operator bin in the multiple operator bins is used to store the target vehicle trajectory analysis model under the same scenario category; when the vehicle trajectory analysis system receives new vehicle trajectory data, determine the scenario category corresponding to the new vehicle trajectory data; based on the scenario category corresponding to the new vehicle trajectory data, determine the target vehicle trajectory analysis model corresponding to the new vehicle trajectory data.

2. The method for generating a vehicle trajectory analysis model according to claim 1, wherein The step of determining the scenario category corresponding to the vehicle trajectory data includes: Classify the vehicle trajectory data through a preset scenario classification algorithm to obtain the vehicle trajectory data under different scenario categories; Based on the scenario category corresponding to the vehicle trajectory data, determine the scenario category label of the vehicle trajectory data, where the scenario categories include: community, school, village, urban area.

3. The method for generating a vehicle trajectory analysis model according to claim 1, wherein, The step of determining the target model parameter thresholds corresponding to the target vehicle trajectory analysis models under different scenario categories based on the vehicle trajectory data under different scenario categories includes: Process the vehicle trajectory data under each scenario category in the different scenario categories using a general vehicle trajectory analysis model to obtain a first data analysis result for different dimensions of the vehicle trajectory data; Filter out the invalid data analysis results in the first data analysis result to obtain a second data analysis result; Based on the second data analysis result, determine the target model parameter thresholds under different scenario categories.

4. The method for generating a vehicle trajectory analysis model according to claim 3, wherein The vehicle trajectory data under different scenario categories includes vehicle trajectory data of different dimensions under this scenario category, where the dimensions include: time, scenario, vehicle type, style, color.

5. The method for generating a vehicle trajectory analysis model according to claim 1, wherein The working modes of the vehicle trajectory analysis system include an offline working mode and an online working mode, where In the offline working mode, call the target vehicle trajectory analysis model through the interface of the vehicle trajectory analysis system; In the online working mode, call the target vehicle trajectory analysis model in real time through a scheduling program and a configuration file.

6. The method for generating a vehicle trajectory analysis model according to claim 1, wherein The architecture of the vehicle trajectory analysis system is a Lambda architecture.

7. A vehicle trajectory analysis model generation device, characterized in that, Including: An acquisition module for obtaining vehicle trajectory data, where the vehicle trajectory data includes the running trajectory data of different vehicles in different scenarios; A classification module for determining the scenario category corresponding to the vehicle trajectory data; A first processing module, configured to determine target model parameter thresholds corresponding to target vehicle trajectory analysis models under different scenario categories according to the vehicle trajectory data under different scenario categories; A second processing module, configured to determine the target vehicle trajectory analysis models under different scenario categories according to the target model parameter thresholds; place the target vehicle trajectory analysis models into corresponding target operator bins in a vehicle trajectory analysis system, where the vehicle trajectory analysis system includes multiple operator bins, and each of the multiple operator bins is used to store the target vehicle trajectory analysis models under the same scenario category; when the vehicle trajectory analysis system receives newly added vehicle trajectory data, determine the scenario category corresponding to the newly added vehicle trajectory data; and determine the target vehicle trajectory analysis model corresponding to the newly added vehicle trajectory data according to the scenario category corresponding to the newly added vehicle trajectory data.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a program, wherein when the program runs, it controls the device where the non-volatile storage medium is located to execute the vehicle trajectory analysis model generation method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, Comprising: A memory and a processor, the processor is configured to run the program stored in the memory, wherein when the program runs, it executes the vehicle trajectory analysis model generation method according to any one of claims 1 to 6.

Images