Ride-hailing scenario mining method, mining device, electronic device, and storage medium

Abstract

This application proposes a method, device, electronic device, and storage medium for mining vehicle usage scenarios. The method includes: acquiring vehicle network data from multiple vehicles; dividing the vehicle network data into behavioral data and scenario data, and constructing behavioral tag sets and scenario tag sets based on the behavioral data and scenario data, respectively; combining the scenario tags in the scenario tag sets to generate multiple combined scenario tags, and constructing a combined scenario tag set based on the multiple combined scenario tags; determining the behavior trigger rate for each combined scenario tag based on the behavioral tag set and the combined scenario tag set; and updating the scenario knowledge base based on the behavior trigger rate of each combined scenario tag. Based on this, this application achieves quantitative identification and management of scenarios at different lifecycle stages, enabling the scenario knowledge base to automatically and continuously iterate and enrich itself along with the real evolution of user behavior.

Description

Technical Field

[0001] This application relates to the field of scene mining technology, specifically to a method, mining device, electronic device, and storage medium for mining vehicle usage scenes. Background Technology

[0002] With the popularization of vehicle-to-everything (V2X) technology, vehicles generate massive amounts of operational and interactive data during daily use. Mining and understanding meaningful usage scenarios from this data is crucial for improving vehicle intelligence and enhancing the user experience.

[0003] Currently, common scenario mining methods, such as time-series-based clustering analysis or anomaly detection algorithms, typically focus on finding statistically significant similarities or outliers in the data. However, the results of these methods often lack clear business semantics, making it difficult to explain which specific actual driving scenarios the discovered patterns correspond to. This results in inherently weak interpretability. Furthermore, these methods often remain at the "discovery" and "identification" stage of scenarios, lacking effective mechanisms for quantitative evaluation and continuous management. This not only leads to subsequent scenario utilization and knowledge base updates often relying on manual experience-based judgment, resulting in a passive, delayed, and inefficient process, but also makes it difficult to systematically guide and cultivate valuable scenarios. Summary of the Invention

[0004] In view of the above, it is necessary to propose a method, device, electronic equipment and storage medium for mining vehicle usage scenarios, so as to solve the technical problems that existing scenario mining methods have inherent defects of weak interpretability and lack an effective mechanism for quantitative evaluation and continuous management of scenarios.

[0005] In a first aspect, this application provides a method for mining vehicle usage scenarios. The method includes: acquiring vehicle network data from multiple vehicles; dividing the vehicle network data into behavioral data and scenario data, and constructing a behavioral tag set and a scenario tag set based on the behavioral data and the scenario data, respectively; combining the scenario tags in the scenario tag set to generate multiple combined scenario tags, and constructing a combined scenario tag set based on the multiple combined scenario tags; determining the behavior trigger rate for each of the multiple combined scenario tags based on the behavioral tag set and the combined scenario tag set; and updating the scenario knowledge base based on the behavior trigger rate of each combined scenario tag.

[0006] In the vehicle usage scenario mining method of this application embodiment, firstly, the original vehicle network data is divided into behavioral tags and scenario tags with clear business meanings. Scenario tags are then combined to define complex situations, transforming the analysis object from incomprehensible underlying signals into semantic content directly corresponding to user operations and vehicle status. Next, by calculating the behavioral trigger rate of each combined scenario tag, user cognition and response to the scenario are transformed into continuous statistical indicators. This establishes an objective and continuous quantitative indicator for vehicle usage scenarios, accurately reflecting the awareness, acceptance, or maturity of usage scenarios among multiple users. This transforms scenario management from subjective qualitative judgment to data-driven quantitative analysis. Finally, the scenario knowledge base is updated based on the behavioral trigger rate, automatically identifying mature scenarios and more accurately locating potentially valuable scenarios in the ambiguous cognitive stage and incubation stage. This achieves quantitative identification and management of scenarios at different lifecycle stages. Based on this, this application can automatically incorporate stable scenarios into the scenario knowledge base, enabling the knowledge base to automatically and continuously iterate and enrich itself along with the real evolution of user behavior. This significantly reduces manual maintenance costs and improves the timeliness and practicality of the scenario knowledge base.

[0007] In some embodiments of this application, determining the behavior trigger rate for each of the multiple combined scene tags based on the behavior category tag set and the combined scene tag set includes: constructing a scene matrix by treating each combined scene tag in the combined scene tag set as a row and the unique identifier of each of the multiple vehicles as a column; for each element in the scene matrix, if a user of any vehicle triggers at least one behavior in the behavior category tag set when any vehicle satisfies the combined scene tag in the element, then the element is marked as a first preset value; otherwise, it is marked as a second preset value; for each row of the scene matrix representing a combined scene tag, the proportion of the number of unique identifiers corresponding to the elements marked as the first preset value to the total number of all unique identifiers in the scene matrix is ​​calculated as the behavior trigger rate of the combined scene tag.

[0008] In some embodiments of this application, updating the scene knowledge base based on the behavior trigger rate of each combined scene tag includes: determining a target scene classified as a positive domain based on the behavior trigger rate of each combined scene tag; comparing the target scene with existing scenes in the scene knowledge base to determine whether the target scene is the same as the existing scenes; if the target scene is different from the existing scenes, storing the target scene in the scene knowledge base.

[0009] In some embodiments of this application, before updating the scene knowledge base based on the behavior trigger rate of each combined scene tag, the method further includes: dividing the scene data into objective scene data and behavioral scene data; marking the new function data generated by the vehicle within a first preset time period after listing in the behavioral scene data as new function scene tags; obtaining the historical behavior data of the multiple vehicles, and performing clustering processing on the users of the multiple vehicles based on the historical behavior data to obtain multiple user groups with similar behavioral characteristics.

[0010] In some embodiments of this application, determining the target scenario to be classified as a positive domain based on the behavior trigger rate of each combined scene tag includes: if the behavior trigger rate of any combined scene tag is greater than or equal to a first threshold and less than a second threshold, and the any combined scene tag contains the new function scenario, classifying the any combined scene tag as a new domain; for the combined scene tags in the new domain, recommending the new function marked as a new function scenario tag to each user in the same user group, and generating a usage introduction for the new function; if, after an interval of a second preset time, the behavior trigger rate of the combined scene tags in the new domain is greater than or equal to a third threshold, classifying the combined scene tags in the new domain as the positive domain, wherein the third threshold is greater than the second threshold.

[0011] In some embodiments of this application, determining the target scene to be classified as a positive domain based on the behavior trigger rate of the combined scene tags further includes: if the behavior trigger rate of any combined scene tag is greater than or equal to the second threshold and less than the third threshold, classifying the any combined scene tag as a boundary domain; for the combined scene tags in the boundary domain, recommending the function with the highest operation frequency among the same user group to users in the same user group who have not performed any operation; if, after an interval of a third preset time, the behavior trigger rate of the combined scene tags in the boundary domain is greater than or equal to the third threshold, classifying the combined scene tags in the boundary domain as the positive domain; if, after an interval of the third preset time, the behavior trigger rate of the combined scene tags in the boundary domain is still less than the third threshold, and the combined scene tags in the boundary domain include the new function scene tag, classifying the combined scene tags in the boundary domain as the new domain.

[0012] In some embodiments of this application, determining the target scene to be classified as a positive domain based on the behavior trigger rate of the combined scene tags further includes: if the behavior trigger rate of any one of the combined scene tags is greater than or equal to the third threshold, classifying the any one of the combined scene tags as the positive domain.

[0013] Secondly, this application also provides a vehicle usage scenario mining device, the device comprising: an acquisition module for acquiring vehicle network data of multiple vehicles; a segmentation module for segmenting the vehicle network data into behavioral data and scenario data, and constructing a behavioral tag set and a scenario tag set based on the behavioral data and the scenario data respectively; a composition module for combining scenario tags in the scenario tag set to generate multiple combined scenario tags, and constructing a combined scenario tag set based on the multiple combined scenario tags; a determination module for determining the behavior trigger rate for each of the multiple combined scenario tags based on the behavioral tag set and the combined scenario tag set; and an update module for updating the scenario knowledge base based on the behavior trigger rate of each combined scenario tag.

[0014] Thirdly, this application also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the vehicle usage scenario mining method described in the above embodiments.

[0015] Fourthly, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the vehicle usage scenario mining method described in the above embodiments.

[0016] Understandably, the vehicle usage scenario mining device of the second aspect, the electronic device of the third aspect, and the computer-readable storage medium of the fourth aspect all correspond to the vehicle usage scenario mining method of the first aspect. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding vehicle usage scenario mining method provided above, and will not be repeated here. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for mining vehicle usage scenarios provided in an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating a method for mining vehicle usage scenarios provided in another embodiment of this application.

[0019] Figure 3 This is a schematic diagram of the functional modules of a vehicle usage scenario mining device provided in an embodiment of this application.

[0020] Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application.

[0021] Explanation of main component symbols Electronic devices 10 Memory 11 Processor 12 Vehicle usage scenario mining device 100 Get Module 110 Module 120 Module 130 Determine module 140 Update module 150 The following detailed description, in conjunction with the accompanying drawings, will further illustrate this application. Detailed Implementation

[0022] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0023] To provide a clearer understanding of the embodiments of the present invention, the invention will be described in detail below with reference to the accompanying drawings and specific examples. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0024] Please see Figure 1 This is a flowchart illustrating a method for mining vehicle usage scenarios provided in an embodiment of this application.

[0025] The vehicle usage scenario mining method in this application embodiment can be applied to... Figure 4 In the one or more vehicles shown, specifically, the vehicle includes an electronic device 10, which is used to execute the vehicle usage scenario mining method. The electronic device 10 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0026] Among them, electronic equipment 10 can be vehicle-mounted equipment, such as body control module (BCM) or vehicle control unit (VCU).

[0027] Specifically, the method for mining vehicle usage scenarios includes the following steps. Depending on different needs, the order of some steps in this flowchart can be changed, and some steps can be omitted.

[0028] S10: Acquire vehicle network data from multiple vehicles.

[0029] In some embodiments of this application, vehicle network data includes physical operation data and user interaction data. Physical operation data refers to vehicle status information conforming to enterprise data standards, i.e., vehicle enterprise standard signals, such as driving speed, longitudinal acceleration, steering wheel angle, outside temperature, and windshield wiper status. User interaction data refers to the logs of behavioral events during user interaction with the vehicle system, i.e., vehicle system user behavior tracking points.

[0030] Specifically, the electronic device 10 can synchronously collect two types of time-series data with the intelligent driving cloud platform through a vehicle-to-everything (V2X) data platform deployed in the cloud: physical operation data and user interaction data.

[0031] S11: Divide vehicle network data into behavioral data and scenario data, and construct behavioral tag sets and scenario tag sets based on behavioral data and scenario data respectively.

[0032] Specifically, the electronic device 10 defines discrete events (i.e., behavioral data generated by user subjective operations) that are actively initiated by the user through vehicle technology systems such as physical controls, voice commands, and touch interfaces, resulting in changes in vehicle status or activation of functions, as behavioral data, such as adjusting vehicle speed or turning on the air conditioning. Furthermore, by performing pattern matching, event decoding, and parameter parsing on the behavioral data, it maps the behavioral data into standardized behavioral tags, such as setting the target speed for adaptive cruise control or activating intelligent parking assistance. All behavioral tags constitute the behavioral tag set S1.

[0033] Electronic device 10 defines scene features in the vehicle network data that describe the vehicle's operating environment, system status, and contextual characteristics as scene-type data, such as in-vehicle temperature range, road type, presence of obstacles, vehicle driving mode, navigation status, and in-vehicle lighting. Furthermore, by applying logical judgment rules, state machine models, and feature extraction algorithms to the scene-type data, it maps the scene-type data into standardized scene-type labels, such as: external ambient temperature ≥ 35°C, current road type = urban congested section, and a vehicle cutting in front at close range. All scene-type labels constitute the scene-type label set S2.

[0034] S12: Combine the scene tags in the scene tag set to generate multiple combined scene tags, and form a combined scene tag set based on the multiple combined scene tags.

[0035] In some embodiments of this application, if all N scene class tags in the scene class tag set S2 are combined pairwise, N×N-level combined scene tags can be formed. All combined scene tags constitute the combined scene tag set S2.1. Each combined scene tag represents a complex situation where multiple scenes are simultaneously true, for example, external temperature > 30°C and road type = highway.

[0036] S13: Based on the set of behavior tags and the set of combined scene tags, determine the behavior trigger rate for each combined scene tag among multiple combined scene tags.

[0037] In some embodiments of this application, the vehicle usage scenario mining method further includes: constructing a scenario matrix M by using each combined scenario label in the combined scenario label set S2.1 as a row and the unique identifier of each vehicle among multiple vehicles as a column: For each element in the scene matrix M, if, under the condition that any vehicle satisfies the combined scene tags in the element, the user of any vehicle triggers at least one behavior in the set of behavior tags, then the element is marked with a first preset value (e.g., 1); otherwise, it is marked with a second preset value (e.g., 0). For each row of the combined scene tags represented by the scene matrix, the proportion of the number of unique identifiers corresponding to the elements marked with the first preset value to the total number of unique identifiers in the scene matrix is ​​calculated as the behavior trigger rate of the combined scene tags.

[0038] Among these, the unique identifier for a vehicle can be the Vehicle Identification Number (VIN), which is a unique identification code for the vehicle, equivalent to the vehicle's "ID number." In all aspects of vehicle-to-everything (V2X) data tracking, the VIN serves as the core index for accurately identifying and associating vehicle information.

[0039] Specifically, each combined scene tag in the combined scene tag set S2.1 (e.g., external temperature > 30°C and time = afternoon) is treated as a row in the scene matrix M, and a unique row index i is assigned to each combined scene tag. The VIN of each vehicle in the combined scene tag set S2.1 is treated as a column in the scene matrix M, and a unique column index m is assigned to each vehicle. Thus, a two-dimensional scene matrix M with dimension i × m is constructed. For any element M(i, m) in the scene matrix M, the value is determined according to the following rules: Electronic device 10 traverses the scene class data tags in the scene class tag set S2 for each vehicle m (corresponding to VIN m). When vehicle m is in a situation that meets all the scene conditions defined by combined scene tag i, it further queries whether the user of vehicle m has triggered at least one behavior class data (e.g., turning on the air conditioner) in the behavior class tag set S1 within the same time period. If both the "scene occurrence" and "behavior trigger" conditions are met simultaneously, then element M(i, m) is marked as 1; otherwise, element M(i, m) is marked as 0. For each combined scene tag i, the proportion of the number of VINs corresponding to the element marked as 1 to the total number of VINs in the scene matrix M is the behavior trigger rate Pi of the combined scene tag.

[0040] In the above embodiments, the scenario matrix M encapsulates the full correlation of which specific vehicles (columns) produced which response behaviors (1 / 0 identifiers) under what complex scenarios (rows), in a structured and quantitative form. It transforms qualitative business descriptions into computable mathematical objects, objectively revealing the behavioral differences of different users in the same scenario from a group perspective (for example, in a high-temperature scenario, some users' behavior vector values ​​are 1 [turn on the air conditioner], while others are 0 [open the car window]). This provides a core data foundation for subsequent scenario awareness statistical calculations (for example, calculating the proportion of "1" in each row, i.e., the behavior trigger rate Pi) and the implementation of the three-branch decision domain division.

[0041] S14: Update the scene knowledge base based on the behavior trigger rate of each combined scene tag.

[0042] In some embodiments of this application, the vehicle usage scenario mining method of this application further includes: determining the target scenario classified as a positive domain based on the behavior trigger rate of each combined scenario tag; comparing the target scenario with existing scenarios in the scenario knowledge base to determine whether the target scenario is the same as the existing scenarios; if the target scenario is different from the existing scenarios, storing the target scenario in the scenario knowledge base.

[0043] In some embodiments of this application, if the target scene is the same as an existing scene, the target scene is stored in the scene class tag set S2 to enter the next iteration.

[0044] It should be noted that the process of determining the target scenario classified as positive based on the behavior trigger rate of each combined scene tag will be discussed later. Figure 2 The details are explained in detail therein, and to avoid repetition, they will not be repeated here.

[0045] In this embodiment, firstly, the raw vehicle network data is divided into behavioral tags and scenario tags with clear business meanings. Scenario tags are then combined to define complex situations, transforming the analysis object from incomprehensible underlying signals into semantic content directly corresponding to user operations and vehicle status. Next, by calculating the behavioral trigger rate for each combined scenario tag, user cognition and response to the scenario are transformed into continuous statistical indicators. This establishes an objective and continuous quantitative indicator for vehicle usage scenarios, accurately reflecting the awareness, acceptance, or maturity of usage scenarios among multiple users. This transforms scenario management from subjective qualitative judgment to data-driven quantitative analysis. Finally, the scenario knowledge base is updated based on the behavioral trigger rate, automatically identifying mature scenarios and more accurately locating potentially valuable scenarios in the ambiguous cognitive stage and incubation stage. This achieves quantitative identification and management of scenarios at different lifecycle stages. Based on this, this application can automatically incorporate stable scenarios into the scenario knowledge base, allowing the knowledge base to automatically and continuously iterate and enrich itself along with the real evolution of user behavior. This significantly reduces manual maintenance costs and improves the timeliness and practicality of the scenario knowledge base.

[0046] Please see Figure 2 This is a flowchart illustrating a method for mining vehicle usage scenarios provided in another embodiment of this application.

[0047] Specifically, the method for mining vehicle usage scenarios includes the following steps. Depending on different needs, the order of some steps in this flowchart can be changed, and some steps can be omitted.

[0048] S20: Acquire vehicle network data from multiple vehicles.

[0049] It should be noted that the specific implementations of steps S20 and S10 are the same, and to avoid repetition, this application will not repeat them here.

[0050] S21: Divide vehicle network data into behavioral data and scenario data, and construct behavioral tag sets and scenario tag sets based on behavioral data and scenario data respectively.

[0051] It should be noted that the specific implementations of steps S21 and S11 are the same, and to avoid repetition, this application will not repeat them here.

[0052] S22: Divide scenario-based data into objective scenario-based data and behavioral scenario-based data, and mark the new function data generated by the vehicle within the first preset time period after its launch, which is included in the behavioral scenario-based data, as new function scenario tags.

[0053] In some embodiments of this application, the electronic device 10 defines the features in the scene tag set S2 that are automatically determined based on vehicle sensor signals, environmental perception data and system status through predefined rules (such as threshold judgment, geofencing, time window) and do not depend on real-time user operation as objective scene data, such as in-vehicle temperature range, time, road type, whether there are obstacles, rainfall, whether there are vehicles or pedestrians, and whether there are faults in various parts of the vehicle.

[0054] In some embodiments of this application, the electronic device 10 defines the features in the scene tag set S2 that represent the user's continuous and patterned setting status of the vehicle system or function as behavioral scene data, such as vehicle driving mode, whether navigation is in progress, and interior lights.

[0055] In some embodiments of this application, the electronic device 10 queries the launch timestamp of any behavioral scenario data associated with a function in the scenario tag set S2. If the difference between the launch timestamp and the current time is less than or equal to a first preset duration T1 (e.g., T1 = 90 days, T1 is an adjustment parameter), a new function scenario identifier is added to any behavioral scenario data, such as marked as "intelligent fragrance system = enabled (new function)", which is used to distinguish and prioritize the processing of scenarios related to the new function in the subsequent vehicle use scenario mining process.

[0056] S23: Obtain historical behavior data of multiple vehicles, and based on the historical behavior data, cluster users of multiple vehicles to obtain multiple user groups with similar behavioral characteristics.

[0057] In some embodiments of this application, the electronic device 10 extracts historical behavior data of multiple vehicles over the most recent N1 natural days. This historical behavior data includes, but is not limited to, timestamps, location trajectories, vehicle speed sequences, air conditioning settings, and charging events. Further extraction includes: spatiotemporal features: daily travel time distribution (e.g., peak commuting time), frequent stops, trip chain patterns, average driving radius, etc.; driving behavior features: calculating dynamic indicators such as average speed, frequency of rapid acceleration / deceleration, and percentage of high-speed cruising; and energy consumption preference features: statistically analyzing the median air conditioning setting temperature, seat heating usage frequency, charging time preferences, etc., and constructing a high-dimensional feature vector for each vehicle, followed by standardization to eliminate the influence of dimensions. Finally, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to control clustering density through neighborhood radius and minimum sample size. The DBSCAN algorithm automatically identifies core points, boundary points, and noise points, outputting N2 types of user groups.

[0058] In other embodiments, the clustering algorithm can be replaced with GMM, OPTICS, etc., and the clustering effect can be evaluated by contour coefficient, DB index, etc.

[0059] S24: Combine the scene tags in the scene tag set to generate multiple combined scene tags, and form a combined scene tag set based on the multiple combined scene tags.

[0060] It should be noted that the specific implementations of steps S24 and S12 are the same, and to avoid repetition, this application will not repeat them here.

[0061] S25: Based on the set of behavior tags and the set of combined scene tags, determine the behavior trigger rate for each combined scene tag among multiple combined scene tags.

[0062] It should be noted that the specific implementations of steps S25 and S13 are the same, and to avoid repetition, this application will not repeat them here.

[0063] S26: If the behavior trigger rate of any combined scene tag is greater than or equal to the third threshold, then any combined scene tag is classified as a positive domain.

[0064] Specifically, if the proportion of VINs equal to 1 in any combined scene label i is greater than or equal to the third threshold R3, then any combined scene label i is classified as a positive domain.

[0065] S27: If the behavior trigger rate of any combined scene tag is greater than or equal to the first threshold and less than the second threshold, and any combined scene tag contains a new function scene, then any combined scene tag is classified as a new domain.

[0066] Specifically, if in any combined scene label i, the proportion of VINs equal to 1 is greater than or equal to the first threshold R1 and less than the second threshold R2, then any combined scene label i is classified as a new domain.

[0067] Among them, the third threshold R3 > the second threshold R2 > the first threshold R1, and R1, R2, and R3 are all adjustable parameters.

[0068] S271: For combined scene tags in the newly added domain, recommend the new function marked as the new function scene tag to each user in the same user group, and generate a usage introduction for the new function.

[0069] Specifically, for the combined scene tag i in the newly added domain, combined with the user group clustered in step S23, the new function marked as the new function scene tag is recommended to each user in the user group, and the usage of the new function is introduced.

[0070] S272: If, after a second preset time interval, the behavior trigger rate of the combined scene tags in the newly added domain is greater than or equal to the third threshold, the combined scene tags in the newly added domain will be classified as positive domains.

[0071] Specifically, if, after a second preset time interval T2, the proportion of VINs equal to 1 in any of the newly added combined scene labels i is greater than or equal to the third threshold R3, then any combined scene label i will be classified as a positive domain.

[0072] S28: If the behavior trigger rate of any combined scene label is greater than or equal to the second threshold and less than the third threshold, then divide any combined scene label into a boundary domain.

[0073] Specifically, if in any combined scene label i, the proportion of VINs equal to 1 is greater than or equal to the second threshold R2 and less than the third threshold R3, then any combined scene label i is divided into a boundary region.

[0074] S281: For combined scene tags in the boundary domain, recommend the most frequently used functions among users of the same user group to users of the same user group who have not performed any operations.

[0075] Specifically, for the combined scene label i in the boundary domain, combined with the user groups clustered in step S23, if some users in the same user group have performed certain operations and some users have not performed any operations, then the function with the highest operation frequency in the same user group is recommended to the users in the same user group who have not performed any operations.

[0076] S282: If, after a third preset time interval, the behavior trigger rate of the combined scene tags in the boundary domain is greater than or equal to the third threshold, the combined scene tags in the boundary domain will be classified as positive domains.

[0077] Specifically, if, after a third preset time interval T3, the proportion of VINs equal to 1 in any combined scene label i in the boundary domain is greater than or equal to the third threshold R3, then any combined scene label i is classified as a positive domain.

[0078] In some embodiments of this application, if after a third preset time interval T3, the behavior trigger rate of the combined scene label i in the boundary domain is still less than the third threshold R3, and the combined scene label i in the boundary domain contains a new function scene label, the combined scene label i in the boundary domain is divided into a new domain.

[0079] Specifically, if, after a third preset time interval T3, the proportion of VINs equal to 1 in any combined scene label i in the boundary domain is still less than the third threshold R3, and any combined scene label i contains a new function scene label, then any combined scene label i will be classified as a new domain.

[0080] S29: If the behavior trigger rate of any combined scene tag is less than the first threshold, or if, after a third preset time interval, the behavior trigger rate of any combined scene tag in the boundary domain is still less than the third threshold, and no new function scene tag is included in any combined scene tag in the boundary domain, then any combined scene tag is divided into a negative domain and the combined scene tags in the negative domain are discarded.

[0081] In some embodiments of this application, if the proportion of VINs equal to 1 in any combined scene label i is less than the first threshold R1, or, after an interval of a third preset time period T3, the proportion of VINs equal to 1 in any combined scene label i in the boundary domain is still less than the third threshold R3, and any combined scene label i does not contain a new function scene label, then any combined scene label is divided into a negative domain.

[0082] S30: Compare the target scene, which is divided into positive domains, with the existing scenes in the scene knowledge base to determine whether the target scene and the existing scenes are the same.

[0083] In some embodiments of this application, if the target scene is the same as an existing scene, the electronic device 10 returns to the execution step S20 and stores the target scene in the scene class tag set S2 to enter the next iteration, thereby realizing the continuous optimization of the scene knowledge base.

[0084] In some embodiments of this application, if the target scene is different from the existing scene, the electronic device 10 continues to execute step S31.

[0085] S31: Store the target scene in the scene knowledge base.

[0086] Specifically, when the target scenario differs from the existing scenario, it indicates that the target scenario is a newly added maternity leave. The target scenario is then manually reviewed and named, and then stored in the scenario knowledge base.

[0087] In the vehicle usage scenario mining method of this application embodiment, the scenario knowledge base is updated based on the behavior trigger rate. This allows for the automatic and real-time classification of massive scenarios into positive, boundary, new, and negative domains. It not only identifies mature scenarios but also accurately locates potentially valuable scenarios in the cognitive ambiguity stage (boundary domain) and the incubation stage (new domain), thereby achieving quantitative identification and management of scenarios at different lifecycle stages. Based on this, this application can automatically incorporate stable scenarios into the scenario knowledge base and implement personalized guidance or feature promotion for scenarios in the boundary and new domains. Then, it re-evaluates the scenario status based on the data feedback after guidance, enabling the scenario knowledge base to automatically and continuously iterate and enrich itself along with the real evolution of user behavior. This significantly reduces manual maintenance costs and improves the timeliness and practicality of the scenario knowledge base.

[0088] Please see Figure 4 This is a schematic diagram of the functional modules of a vehicle scenario mining device 100 provided in an embodiment of this application.

[0089] In this embodiment, based on the above... Figure 1 Using the same concept as the vehicle usage scenario mining method in the illustrated embodiments, this application also provides a vehicle usage scenario mining device 100, which can be used to execute the above-described vehicle usage scenario mining method. For ease of explanation, the schematic diagram of the vehicle usage scenario mining device 100 embodiment only shows the parts related to the embodiments of this application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation on the vehicle usage scenario mining device 100, and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0090] Specifically, the vehicle usage scenario mining device 100 provided in this application embodiment includes an acquisition module 110, a segmentation module 120, a composition module 130, a determination module 140, and an update module 150. The acquisition module 110 is used to acquire vehicle network data of multiple vehicles; the segmentation module 120 is used to segment the vehicle network data into behavioral data and scenario data, and construct behavioral tag sets and scenario tag sets based on the behavioral data and scenario data, respectively; the composition module 130 is used to combine the scenario tags in the scenario tag set to generate multiple combined scenario tags, and construct a combined scenario tag set based on the multiple combined scenario tags; the determination module 140 is used to determine the behavior trigger rate for each of the multiple combined scenario tags based on the behavioral tag set and the combined scenario tag set; the update module 150 is used to update the scenario knowledge base based on the behavior trigger rate of each combined scenario tag.

[0091] Specific limitations regarding the vehicle usage scenario mining device 100 can be found in the limitations of the vehicle usage scenario mining method described above, and will not be repeated here. Each module in the aforementioned vehicle usage scenario mining device 100 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor 12 in the electronic device 10 in hardware form, or stored in the memory 11 of the electronic device 10 in software form, so that the processor 12 can call and execute the operations corresponding to each module.

[0092] Please see Figure 4 This is a schematic diagram of the hardware structure of an electronic device 10 provided in an embodiment of this application.

[0093] The electronic device 10 provided in this application embodiment includes, but is not limited to, a memory 11, a processor 12, and a computer program stored in the memory 11 and capable of running on the processor 12, such as a vehicle usage scenario mining program. When the computer program is executed by the processor 12, it implements the vehicle usage scenario mining method as described in the above embodiment.

[0094] Figure 4 Only the electronic device 10 with memory 11 and processor 12 is shown. It will be understood by those skilled in the art that... Figure 4 The structure shown does not constitute a limitation on the electronic device 10, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0095] In some embodiments of this application, the electronic device 10 can be communicatively connected to devices such as desktop computers, laptops, handheld computers, and cloud servers.

[0096] In some embodiments of this application, the electronic device 10 can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0097] In some embodiments of this application, the electronic device 10 may further include network devices and / or client devices. These network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, and a cloud server based on cloud computing, consisting of a large number of hosts or network servers.

[0098] In some embodiments of this application, the network where the electronic device 10 is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0099] In some embodiments of this application, the memory 11 stores multiple computer-readable instructions to implement a vehicle usage scenario mining method, and the processor 12 can execute multiple instructions to achieve: acquiring vehicle network data of multiple vehicles; dividing the vehicle network data into behavioral data and scenario data, and constructing behavioral tag sets and scenario tag sets based on the behavioral data and scenario data respectively; combining the scenario tags in the scenario tag set to generate multiple combined scenario tags, and constructing a combined scenario tag set based on the multiple combined scenario tags; determining the behavior trigger rate for each combined scenario tag among the multiple combined scenario tags based on the behavioral tag set and the combined scenario tag set; and updating the scenario knowledge base based on the behavior trigger rate of each combined scenario tag.

[0100] Specifically, the processor 12's implementation method for the above instructions can be found in [reference needed]. Figure 1 , Figure 2 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0101] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 10 and does not constitute a limitation on the electronic device 10. The electronic device 10 can be a bus topology or a star topology. The electronic device 10 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, the electronic device 10 may also include input / output devices, network access devices, etc.

[0102] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 4The symbol is represented by only one arrow, but this does not mean that there is only one bus or one type of bus. The bus is configured to implement communication between memory 11 and at least one processor 12, etc.

[0103] It should be noted that electronic device 10 is only an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0104] In some embodiments of this application, the processor 12 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 12 is the control unit of the electronic device 10, connecting various components of the electronic device 10 via various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a vehicle usage scenario mining program) and calls data stored in the memory 11 to perform various functions of the electronic device 10 and process data.

[0105] The processor 12 executes the operating system of the electronic device 10 and various installed applications. The processor 12 executes these applications to implement the steps described in each of the above embodiments of the vehicle usage scenario mining method, for example... Figure 1 , Figure 2 The steps are shown.

[0106] For example, a computer program may be divided into one or more modules / units, one or more of which are stored in memory 11 and executed by processor 12 to complete this application. One or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in electronic device 10. For example, the computer program may be divided into an acquisition module 110, a partitioning module 120, a construction module 130, a determination module 140, and an update module 150.

[0107] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute a portion of a vehicle usage scenario mining method according to various embodiments of this application.

[0108] If the modules / units integrated in the electronic device 10 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0109] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory, and other types of memory.

[0110] This application also provides a computer-readable storage medium (not shown), which stores computer-readable instructions. These computer-readable instructions are executed by a processor in an electronic device 10 to implement a vehicle usage scenario mining method according to any of the above embodiments.

[0111] Specifically, computer-readable storage media can be non-volatile or volatile. Computer-readable storage media include flash memory, portable hard drives, multimedia cards, card-type memories (e.g., SD memory, DX memory, etc.), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, memory 11 can be an internal storage unit of electronic device 10, such as the portable hard drive of electronic device 10. In other embodiments, memory 11 can also be an external storage device of electronic device 10, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on electronic device 10. Memory 11 can be used not only to store application software and various types of data installed on electronic device 10, such as the code of a vehicle usage scenario mining program, but also to temporarily store data that has been output or will be output.

[0112] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0113] In the embodiments of this application, it should be noted that, unless otherwise explicitly specified and limited, "multiple" means two or more.

[0114] In the embodiments of this application, it should be noted that, unless otherwise expressly specified and limited, the word "for example" is used to indicate an example, illustration, or description. Any embodiment or design scheme described as "for example" in the embodiments of this application should not be construed as being better or more advantageous than other embodiments or design schemes. Specifically, the use of the word "for example" is intended to present the relevant concepts in a specific manner.

[0115] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0116] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more features.

[0117] In the description of this application, it should be noted that, unless otherwise explicitly stated and limited, "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Furthermore, the character " / " in this application generally indicates that the preceding and following related objects have an "or" relationship.

[0118] Unless otherwise specified, all steps in this application may be performed sequentially or randomly. For example, if a method includes steps A and B, it means that the method may include steps A and B performed sequentially, or it may include steps B and A performed sequentially. For example, if a method may also include step C, it means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or it may include steps A, C, and B, or it may include steps C, A, and B, etc.

[0119] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0121] In the various embodiments of this application, the functional modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0122] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the specification may also be implemented by a single unit or device through software or hardware.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for mining vehicle usage scenarios, characterized in that, The method includes: Acquire vehicle network data from multiple vehicles; The vehicle network data is divided into behavioral data and scenario data, and behavioral tag sets and scenario tag sets are constructed based on the behavioral data and scenario data, respectively. The scene tags in the scene category tag set are combined to generate multiple combined scene tags, and a combined scene tag set is formed based on the multiple combined scene tags; Based on the set of behavior tags and the set of combined scene tags, determine the behavior trigger rate for each of the multiple combined scene tags; The scene knowledge base is updated based on the behavior trigger rate of each combined scene tag.

2. The method for mining vehicle usage scenarios as described in claim 1, characterized in that, The step of determining the behavior trigger rate for each of the multiple combined scene tags based on the behavior category tag set and the combined scene tag set includes: Construct a scene matrix by using each combined scene tag in the combined scene tag set as a row and the unique identifier of each vehicle in the plurality of vehicles as a column; For each element in the scene matrix, if a user of any vehicle triggers at least one behavior in the set of behavior tags when any vehicle satisfies the combined scene tags in the element, then the element is marked as a first preset value; otherwise, it is marked as a second preset value. For each row in the scene matrix representing a combined scene tag, the proportion of the number of unique identifiers corresponding to the elements marked with the first preset value to the total number of all unique identifiers in the scene matrix is ​​calculated, and this proportion is used as the behavior trigger rate of the combined scene tag.

3. The method for mining vehicle usage scenarios as described in claim 1, characterized in that, The step of updating the scene knowledge base based on the behavior trigger rate of each combined scene tag includes: Based on the behavior trigger rate of each combined scene label, the target scene is determined to be classified into the positive domain. The target scene is compared with existing scenes in the scene knowledge base to determine whether the target scene is the same as the existing scenes; If the target scene is different from the existing scene, the target scene is stored in the scene knowledge base.

4. The method for mining vehicle usage scenarios as described in claim 3, characterized in that, Before updating the scene knowledge base based on the behavior trigger rate of each combined scene tag, the method further includes: The scenario data is divided into objective scenario data and behavioral scenario data; The new function data generated by the vehicle within the first preset time period after its launch, contained in the behavioral scenario data, are marked as new function scenario tags; Historical behavior data of the multiple vehicles is obtained, and users of the multiple vehicles are clustered based on the historical behavior data to obtain multiple user groups with similar behavioral characteristics.

5. The method for mining vehicle usage scenarios as described in claim 4, characterized in that, The determination of the target scene classified into a positive domain based on the behavior trigger rate of each combined scene label includes: If the behavior trigger rate of any combined scene tag is greater than or equal to the first threshold and less than the second threshold, and the combined scene tag contains the new function scene, the combined scene tag is classified as a new domain. For the combined scene tags in the newly added domain, the new function marked as the new function scene tag is recommended to each user in the same user group, and a usage introduction of the new function is generated; If, after a second preset time interval, the behavior trigger rate of the combined scene tags in the newly added domain is greater than or equal to the third threshold, the combined scene tags in the newly added domain are classified into the positive domain, wherein the third threshold is greater than the second threshold.

6. The method for mining vehicle usage scenarios as described in claim 5, characterized in that, The step of determining the target scene classified as a positive domain based on the behavior trigger rate of the combined scene tags also includes: If the behavior trigger rate of any combined scene tag is greater than or equal to the second threshold and less than the third threshold, the any combined scene tag is divided into a boundary domain; For the combined scene tags in the boundary domain, the functions with the highest operation frequency among the same user groups are recommended to users in the same user group who have not performed any operation. If, after a third preset time interval, the behavior trigger rate of the combined scene tags in the boundary domain is greater than or equal to the third threshold, the combined scene tags in the boundary domain will be divided into the positive domain. If, after the third preset time interval, the behavior trigger rate of the combined scene tags in the boundary domain is still less than the third threshold, and the combined scene tags in the boundary domain contain the new function scene tags, then the combined scene tags in the boundary domain are classified as the new domain.

7. The method for mining vehicle usage scenarios as described in claim 5, characterized in that, The step of determining the target scene classified as a positive domain based on the behavior trigger rate of the combined scene tags also includes: If the behavior trigger rate of any of the combined scene tags is greater than or equal to the third threshold, then the combined scene tag is classified into the positive domain.

8. A device for exploring vehicle usage scenarios, characterized in that, The device includes: The acquisition module is used to acquire vehicle network data from multiple vehicles; The segmentation module is used to divide the vehicle network data into behavioral data and scenario data, and to construct behavioral tag sets and scenario tag sets based on the behavioral data and scenario data, respectively. The composition module is used to combine the scene tags in the scene category tag set to generate multiple combined scene tags, and to form a combined scene tag set based on the multiple combined scene tags. The determination module is used to determine the behavior trigger rate for each of the multiple combined scene tags based on the behavior category tag set and the combined scene tag set; The update module is used to update the scene knowledge base based on the behavior trigger rate of each combined scene tag.

9. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the vehicle usage scenario mining method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle usage scenario mining method as described in any one of claims 1 to 7.

Images