Abnormal vehicle identification method and device, electronic equipment, storage medium and product

Abstract

The application discloses an abnormal vehicle identification method and device, electronic equipment, storage medium and product. The abnormal vehicle identification method comprises the following steps: determining an abnormal identification rule according to a target feature of a target vehicle, wherein the target vehicle is a vehicle contained in historical vehicle abnormal data; and identifying whether a vehicle to be processed is an abnormal vehicle according to the abnormal identification rule. The application takes the vehicle contained in the historical vehicle abnormal data as the target vehicle, analyzes the target feature of the target vehicle, determines the abnormal identification rule, and then automatically identifies whether the vehicle to be processed is the abnormal vehicle according to the abnormal identification rule, so that the automatic execution of the abnormal vehicle identification process is realized, and the efficiency of the vehicle abnormal identification is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an abnormal vehicle identification method, device, electronic device, storage medium, and product. Background Technology

[0002] The introduction of various new technologies has led to frequent vehicle malfunctions in new energy vehicles. After a vehicle malfunction occurs, it is particularly important to identify whether the malfunction is an isolated problem or a batch problem. Therefore, how to identify whether other vehicles are malfunctioning based on the problems of the actual malfunctioning vehicles is a technical problem that urgently needs to be solved.

[0003] Current methods for identifying anomalous vehicles typically rely on manual analysis of the characteristics of actual anomalous vehicles, using these characteristics to identify whether other vehicles are also anomalous. However, this method is manual, leading to low efficiency, and the manually selected features may not actually be those causing the vehicle's anomalousness, resulting in low accuracy. Summary of the Invention

[0004] The purpose of this application is to provide an abnormal vehicle identification method, device, electronic device, storage medium, and product that can solve the problems of low efficiency and accuracy in abnormal vehicle identification.

[0005] In a first aspect, embodiments of this application provide an abnormal vehicle identification method, the method comprising: Anomaly identification rules are determined based on the target characteristics of the target vehicle, wherein the target vehicle refers to the vehicle contained in the historical vehicle anomaly data; The anomaly identification rules are used to determine whether the vehicle to be processed is an abnormal vehicle.

[0006] Optionally, before determining the anomaly identification rule based on the target features of the target vehicle, the method further includes: determining the degree of anomaly of the candidate features of the target vehicle, and selecting the target features from the candidate features based on the degree of anomaly.

[0007] Optionally, the step of filtering target features from candidate features based on the degree of anomaly includes: filtering target features from candidate features based on the degree of anomaly and an anomaly threshold; The method further includes: if the number of identified abnormal vehicles is greater than a number threshold, lowering the abnormality threshold and returning to the step of filtering target features from the candidate features based on the degree of abnormality and the abnormality threshold.

[0008] Optionally, before determining the degree of anomaly of the candidate features of the target vehicle, the method further includes: using a large language model to generate structured target information based on the initial target information, wherein the target information includes the vehicle identifier of the target vehicle, the anomaly time point of the target vehicle, and the vehicle data table identifier. Determining the degree of anomaly of the candidate features of the target vehicle includes: determining the degree of anomaly of the candidate features of the target vehicle based on the structured target information.

[0009] Optionally, determining the degree of anomaly of the candidate features of the target vehicle includes: Based on the feature values ​​of the candidate features of the target vehicle at the target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point, a first anomaly parameter of the candidate features of the target vehicle is determined; the target time point is a plurality of time points prior to the anomaly time point of the target vehicle, and the first anomaly parameter includes a first outlier count and / or a first outlier magnitude statistical value. The degree of anomalousness of the candidate feature is determined based on the first anomalous parameter.

[0010] Optionally, determining the anomaly identification rule based on the target features of the target vehicle includes: Based on the feature value of the target feature of the target vehicle at the target time point and the feature value of the target feature of the reference vehicle at the target time point, a second anomaly parameter of the target feature of the target vehicle within each time window is determined; the target time point is a plurality of time points before the anomaly time point of the target vehicle, and the second anomaly parameter includes a second outlier count and / or a second outlier magnitude statistical value. The anomaly identification rule is determined based on the time window and the largest second anomaly parameter.

[0011] Optionally, the method further includes: pushing an abnormal notification corresponding to the abnormal vehicle to the target user and / or the identified abnormal vehicle.

[0012] Secondly, embodiments of this application provide an apparatus for identifying abnormal vehicles, the apparatus comprising: The first determining module is used to determine anomaly identification rules based on the target characteristics of the target vehicle, wherein the target vehicle refers to the vehicle contained in the historical vehicle anomaly data. The identification module is used to identify whether the vehicle to be processed is an abnormal vehicle according to the anomaly identification rules.

[0013] Optionally, the device further includes: The second determining module is used to determine the degree of anomaly of the candidate features of the target vehicle; The filtering module is used to filter out target features from the candidate features based on the degree of anomaly.

[0014] Optionally, the filtering module is specifically used to filter out target features from the candidate features based on the degree of anomaly and the anomaly threshold; The device further includes an adjustment module, used to lower the abnormality threshold and return to the filtering module when the number of identified abnormal vehicles exceeds the number threshold.

[0015] Optionally, the device further includes: a generation module, used to generate structured target information based on the initial target information using a large language model, the target information including the vehicle identifier of the target vehicle, the abnormal time point of the target vehicle, and the vehicle data table identifier; The second determining module is specifically used to determine the degree of anomaly of the candidate features of the target vehicle based on the structured target information.

[0016] Optionally, the second determining module includes: The first parameter determination unit is used to determine a first anomaly parameter of the candidate feature of the target vehicle based on the feature value of the candidate feature of the target vehicle at the target time point and the feature value of the candidate feature of the reference vehicle at the target time point; the target time point is a plurality of time points before the anomaly time point of the target vehicle, and the first anomaly parameter includes a first outlier count and / or a first outlier magnitude statistical value. The degree determination unit is used to determine the degree of abnormality of the candidate feature based on the first abnormality parameter.

[0017] Optionally, the first determining module includes: The second parameter determination unit is used to determine a second abnormal parameter of the target feature of the target vehicle within each time window based on the feature value of the target feature of the target vehicle at the target time point and the feature value of the target feature of the reference vehicle at the target time point; the target time point is a plurality of time points before the abnormal time point of the target vehicle, and the second abnormal parameter includes a second outlier count and / or a second outlier magnitude statistical value. The rule determination unit is used to determine the anomaly identification rule based on the time window and the largest second anomaly parameter.

[0018] Optionally, the device further includes a notification module for pushing abnormal notifications corresponding to the abnormal vehicles to the target user and / or the identified abnormal vehicles.

[0019] Thirdly, embodiments of this application provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the abnormal vehicle identification method as described in any of the preceding claims.

[0020] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the abnormal vehicle identification method as described in any of the preceding claims.

[0021] Fifthly, embodiments of this application provide a computer program product storing a program or instructions, which, when executed by a processor, implement the abnormal vehicle identification method as described in any of the preceding claims.

[0022] Sixthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the abnormal vehicle identification method as described in any of the preceding claims.

[0023] In this embodiment of the application, vehicles contained in historical vehicle anomaly data are used as target vehicles. By analyzing the target features of the target vehicles, anomaly identification rules can be determined. Then, the anomaly identification rules can be used to automatically identify whether the vehicle to be processed is an anomaly vehicle, thereby realizing the automatic execution of the anomaly vehicle identification process and improving the efficiency of vehicle anomaly identification.

[0024] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some drawings of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of an abnormal vehicle identification method according to an embodiment of this application; Figure 2 This is a flowchart of another abnormal vehicle identification method according to an embodiment of this application; Figure 3 This is a schematic diagram of an abnormal vehicle identification process according to an embodiment of this application; Figure 4 This is a structural block diagram of an abnormal vehicle identification device according to an embodiment of this application; Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application; Figure 6 This is a structural block diagram of a readable storage medium according to an embodiment of this application. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0029] The abnormal vehicle identification method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0030] Example 1: Reference Figure 1 The diagram shows a flowchart of an abnormal vehicle identification method according to an embodiment of this application.

[0031] like Figure 1 As shown, the abnormal vehicle identification method may include the following steps: Step 101: Determine the anomaly identification rules based on the target characteristics of the target vehicle, where the target vehicle refers to the vehicle included in the historical vehicle anomaly data.

[0032] In this embodiment, vehicles included in historical vehicle anomaly data are used as target vehicles; that is, target vehicles refer to vehicles that have historically experienced anomalies. Anomaly identification rules (i.e., the anomaly identification rules corresponding to the anomaly type of the target vehicle) can be determined based on the target vehicle's target characteristics. The specific processing procedure for this step will be described in detail in the following embodiments.

[0033] Step 102: Identify whether the vehicle to be processed is an abnormal vehicle according to the anomaly identification rules.

[0034] According to the anomaly identification rules, anomaly identification can be performed on the vehicles to be processed (referring to vehicles for which no anomalies have been found yet), thereby identifying whether the vehicles to be processed are abnormal vehicles (the anomaly type is the anomaly type corresponding to the anomaly identification rules).

[0035] For example, the anomaly identification rule may include, but is not limited to, information such as the conditions that the target features need to meet. For a vehicle to be processed, the target features of the vehicle to be processed can be obtained, and then the target features of the vehicle to be processed can be matched with the anomaly identification rule. If the match is successful, the vehicle to be processed can be determined to be an abnormal vehicle.

[0036] Example 2: In one alternative implementation, before determining the anomaly identification rule based on the target features of the target vehicle, the method further includes: determining the degree of anomaly of the candidate features of the target vehicle, and selecting the target features from the candidate features based on the degree of anomaly.

[0037] In this embodiment of the application, for each type of vehicle anomaly, features associated with that anomaly type can be determined based on business knowledge related to that anomaly type, and these features can be used as candidate features corresponding to that anomaly type.

[0038] For example, for battery system anomalies, features such as battery voltage fluctuation range, number of charging cycles, individual cell temperature difference, and abnormal charging state decay rate can be selected as candidate features corresponding to the battery system anomalies. For motor system anomalies, features such as motor winding temperature, motor speed fluctuation, abnormal output torque value, and motor current peak value can be selected as candidate features corresponding to the motor system anomalies. For electronic control system anomalies, features such as electronic control unit error codes, control signal response delay, and frequency of abnormal on / off states in high-voltage power distribution circuits can be selected as candidate features corresponding to the electronic control system anomalies. Of course, related environmental features can also be selected as corresponding candidate features. Specific handling can be based on actual experience, and this embodiment does not impose any restrictions on this.

[0039] In this embodiment, a vehicle data table corresponding to each type of vehicle anomaly can be constructed, and a vehicle data table identifier (such as name, number, etc.) can be configured for the vehicle data table. The vehicle data table is stored in a database for subsequent data retrieval.

[0040] For example, the vehicle data table corresponding to the anomaly type may include, but is not limited to, the vehicle identifiers of each vehicle (such as VIN (Vehicle Identification Number) etc.), the feature values ​​of each candidate feature of each vehicle under this anomaly type at each time point (the time point is also the time point when the candidate feature is collected, and the unit of the time point can be days, hours, etc.), and so on.

[0041] In this embodiment of the application, for each type of anomaly, the abnormal vehicle under that anomaly type can be identified according to the abnormal vehicle identification method, and the abnormal vehicle identification method is the same for each type of anomaly.

[0042] In this embodiment of the application, for a target vehicle, the degree of abnormality of the candidate features of the target vehicle can be determined.

[0043] For example, the anomaly type of the target vehicle can be obtained, and then the degree of anomaly of the candidate features of the target vehicle can be determined based on the data in the vehicle data table corresponding to that anomaly type. The specific processing procedure for this step will be described in detail in the following embodiments.

[0044] In this embodiment of the application, after determining the degree of abnormality of the candidate features of the target vehicle, the target feature is selected from the candidate features based on the degree of abnormality.

[0045] For example, target features can be selected from the candidate features based on the degree of anomaly and the anomaly threshold. For instance, candidate features with an anomaly degree greater than the anomaly threshold can be selected as target features. The specific processing procedure for this step will be described in detail in the following embodiments.

[0046] In this embodiment, by determining the degree of abnormality of candidate features of the target vehicle, the target features that truly cause the vehicle abnormality are selected based on the degree of abnormality, making the abnormality identification rules determined based on the target features more accurate, thereby improving the accuracy of vehicle abnormality identification.

[0047] Example 3: Reference Figure 2 The diagram shows a flowchart of another abnormal vehicle identification method according to an embodiment of this application.

[0048] like Figure 2 As shown, the abnormal vehicle identification method may include the following steps: Step 201: Determine the degree of anomaly of the candidate features of the target vehicle.

[0049] Step 202: Select target features from the candidate features based on the degree of anomaly and the anomaly threshold.

[0050] In this embodiment of the application, after determining the degree of abnormality of each candidate feature of the target vehicle, the degree of abnormality of each candidate feature is compared with the abnormality threshold, and the candidate feature with the degree of abnormality greater than the abnormality threshold is taken as the target feature.

[0051] The degree of anomaly of a candidate feature refers to the quantified value of how much the candidate feature deviates from the normal pattern in the target vehicle. The specific value of the anomaly threshold can be set according to actual needs; this embodiment does not impose any restrictions on it.

[0052] Step 203: Determine anomaly identification rules based on the target characteristics of the target vehicle, and identify whether the vehicle to be processed is an abnormal vehicle based on the anomaly identification rules.

[0053] Step 204: Determine whether the number of identified abnormal vehicles exceeds the number threshold. If yes, proceed to step 205; otherwise, proceed to step 206.

[0054] Step 205: If the number of identified abnormal vehicles exceeds the number threshold, lower the abnormal threshold and return to step 202.

[0055] In this embodiment of the application, after identifying whether the vehicle to be processed is an abnormal vehicle according to the anomaly identification rules, it is further determined whether the number of identified abnormal vehicles is greater than the number threshold.

[0056] If the number of identified abnormal vehicles exceeds the number threshold, it indicates that a large number of abnormal vehicles have been identified, and the anomaly identification rules can be considered to be too lenient. This may result in some of the vehicles not being truly abnormal. Therefore, the anomaly threshold can be lowered, and the process can return to the step of filtering target features from the candidate features based on the degree of anomaly and the anomaly threshold (the lowered anomaly threshold). The filtering of target features, the determination of anomaly identification rules, and the identification of abnormal vehicles can be performed again.

[0057] Step 206: Generate a list of abnormal vehicles.

[0058] If the number of identified abnormal vehicles is less than or equal to the number threshold, the identification of abnormal vehicles can be stopped and an abnormal vehicle list can be generated. This abnormal vehicle list may include the vehicle identifier of the identified abnormal vehicles, the feature values ​​of the target features of the abnormal vehicles, etc.

[0059] In this embodiment, by lowering the anomaly threshold when the number of identified abnormal vehicles exceeds the quantity threshold, more target features can be filtered out, thereby making the anomaly identification rules determined based on the target features more rigorous, and thus further improving the accuracy of abnormal vehicle identification.

[0060] Example 4: In one optional implementation, before determining the degree of anomalousness of the candidate features of the target vehicle, the method further includes: generating structured target information based on the initial target information using a Large Language Model (LLM). The structured target information is machine-readable, thereby ensuring that subsequent code can be called. The target information may include, but is not limited to: the vehicle identifier of the target vehicle, the anomalous time point of the target vehicle, and the vehicle data table identifier, etc.

[0061] For example, a natural language text including the initial target information can be constructed, and the natural language text and prompts can be input into a large language model. The prompts are used to guide the large language model to perform natural language understanding and structured parsing of the input natural language text. Under the guidance of the prompts, the large language model performs natural language understanding and structured parsing of the input natural language text, and outputs structured target information.

[0062] Accordingly, the process of determining the degree of anomalousness of candidate features of the target vehicle includes: determining the degree of anomalousness of candidate features of the target vehicle based on the structured target information.

[0063] For example, based on the structured target information, relevant data can be queried from the vehicle data table, and then the degree of anomaly of the candidate features of the target vehicle can be determined based on the queried data. The specific processing procedure will be described in detail in subsequent embodiments.

[0064] In this embodiment, by utilizing a large language model to convert natural language target information into structured target information, the human only needs to provide the natural language target information, eliminating the need to write the structured target information, thus simplifying the processing and enhancing the automation effect.

[0065] Example 5: In one alternative implementation, the process of determining the degree of anomalousness of candidate features of the target vehicle may include the following steps A1 to A2: Step A1: Based on the feature values ​​of the candidate features of the target vehicle at the target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point, determine the first abnormal parameter of the candidate features of the target vehicle.

[0066] In this embodiment, the feature values ​​of the candidate features of the target vehicle at a target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point are first obtained. Then, based on the feature values ​​of the candidate features of the target vehicle at the target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point, a first anomalous parameter of the candidate features of the target vehicle is determined. The target time point is a plurality of time points prior to the anomalous time point of the target vehicle. The reference vehicle includes at least some other vehicles besides the target vehicle.

[0067] For example, based on the vehicle identifier of the target vehicle, the abnormal time point of the target vehicle, and the vehicle data table identifier, the vehicle data table corresponding to the vehicle data table identifier is queried, and the feature value of the candidate feature of the target vehicle at the target time point and the feature value of the candidate feature of the reference vehicle at the target time point are queried from the vehicle data table.

[0068] For example, the process of determining a first anomalous parameter of a candidate feature of a target vehicle based on the feature values ​​of the candidate features of the target vehicle at the target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point may include: for each candidate feature, calculating the normal feature value range of the candidate feature at each target time point based on the feature values ​​of the candidate features of the target vehicle at the target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point; for each target time point, if the feature value of the candidate feature of the target vehicle at the target time point exceeds the normal feature value range of the candidate feature at the target time point, then determining that the candidate feature of the target vehicle is an outlier at the target time point, and calculating the outlier magnitude of the candidate feature of the target vehicle at the target time point; counting the number of outliers of the candidate feature of the target vehicle at all target time points as a first outlier count, counting the outlier magnitude statistics of the candidate feature of the target vehicle at all target time points as a first outlier magnitude statistics, and using the first outlier count and / or the first outlier magnitude statistics as the first anomalous parameter of the candidate feature of the target vehicle.

[0069] For example, the three sigma criterion can be used to calculate the mean and standard deviation of the candidate feature at the target time point based on the feature value of the candidate feature of the target vehicle at the target time point and the feature value of the candidate feature of the reference vehicle at the target time point. The range between the lower limit of the difference between the mean and three times the standard deviation and the upper limit of the sum of the mean and three times the standard deviation can be used as the normal feature value range at the target time point.

[0070] For example, the outlier magnitude refers to the sigma multiple by which a data point deviates from the mean. The outlier magnitude of the candidate feature of the target vehicle at the target time point is calculated as follows: the difference between the feature value of the candidate feature of the target vehicle at the target time point and the mean value corresponding to the target time point is calculated, and the ratio between the difference and the standard deviation corresponding to the target time point is taken as the outlier magnitude of the candidate feature of the target vehicle at the target time point.

[0071] For example, the outlier magnitude statistics of the candidate features of the target vehicle can be the sum of the outlier magnitudes of the candidate features of the target vehicle at all target time points, or the average of the outlier magnitudes of the candidate features of the target vehicle at all target time points, and so on.

[0072] Step A2: Determine the degree of abnormality of the candidate feature based on the first abnormality parameter of the candidate feature.

[0073] In this embodiment of the application, the first abnormality parameter of the candidate feature is positively correlated with the degree of abnormality of the candidate feature. That is, the larger the first abnormality parameter of the candidate feature, the greater the degree of abnormality of the candidate feature.

[0074] For example, if the first anomaly parameter includes the first outlier count, then the first outlier count can be determined as the degree of anomaly.

[0075] For example, if the first anomaly parameter includes a first outlier magnitude statistic, then the first outlier magnitude statistic can be determined as the degree of anomaly.

[0076] For example, if the first anomaly parameter includes a first outlier count and a first outlier magnitude statistic, then the weighted sum of the first outlier count and the first outlier magnitude statistic can be determined as the degree of anomaly.

[0077] In this embodiment, the first outlier count and the first outlier magnitude statistics can more accurately describe the anomaly, and therefore the degree of anomaly determined based on the first outlier count and / or the first outlier magnitude statistics is more accurate.

[0078] Example 6: In one alternative implementation, the process of determining anomaly identification rules based on the target characteristics of the target vehicle may include the following steps B1 to B2: Step B1: Based on the feature value of the target feature of the target vehicle at the target time point and the feature value of the target feature of the reference vehicle at the target time point, determine the second abnormal parameter of the target feature of the target vehicle within each time window.

[0079] In this embodiment, following the method described in step A1 above, based on the feature value of the target feature of the target vehicle at the target time point and the feature value of the target feature of the reference vehicle at the target time point, it is possible to obtain whether the target feature of the target vehicle is an outlier at each target time point, and the outlier magnitude when the target feature of the target vehicle is an outlier at the target time point. In this embodiment, a time window can be set to determine a second anomaly parameter of the target feature of the target vehicle within each time window. The second anomaly parameter includes a second outlier count and / or a second outlier magnitude statistical value.

[0080] For example, for each time window, the number of outliers of the target feature of the target vehicle within the time window is counted as the second outlier count, and the outlier magnitude of the target feature of the target vehicle within the time window is counted as the second outlier magnitude statistical value. The second outlier count and / or the second outlier magnitude statistical value are used as the second abnormal parameter of the target feature of the target vehicle within the time window.

[0081] Step B2: Determine the anomaly identification rule based on the time window and the largest second anomaly parameter.

[0082] In this embodiment of the application, the largest second abnormal parameter can be selected from the second abnormal parameters within each time window, and the target feature reaching the largest second abnormal parameter within the time window is used as the abnormal identification rule.

[0083] In this embodiment of the application, by setting a time window, the second abnormal parameter of the target feature can be statistically analyzed within a continuous time period, thereby enabling a more accurate description of the abnormal situation of the target feature.

[0084] Example 7: In one optional implementation, after identifying whether the vehicle to be processed is an abnormal vehicle according to the anomaly identification rules, the method further includes pushing the anomaly notification corresponding to the abnormal vehicle to the target user and / or the identified abnormal vehicle, so as to promptly remind the user of the vehicle's abnormal situation.

[0085] Reference Figure 3 The diagram illustrates an abnormal vehicle identification process according to an embodiment of this application.

[0086] like Figure 3As shown, the abnormal vehicle identification process may include: inputting initial target information (including the target vehicle's vehicle identifier, the abnormal time point of the target vehicle, and the vehicle data table identifier); using a feature analysis agent to first call the LLM to generate structured target information based on the initial target information, and then using the FastAPI (Fast Application Programming Interface)... The Interface (API) passes the structured target information to pre-developed Python code. The Python code determines the degree of anomalousness of candidate features for the target vehicle and filters out target features based on this degree. A rule-based algorithm agent constructs anomaly identification rules based on the target vehicle's features, and uses these rules to identify whether a vehicle is anomalous, resulting in a list of anomalous vehicles. When there are too many anomalous vehicles (the number exceeds a threshold), the algorithm automatically optimizes the agent to re-filter target features, redetermines the anomaly identification rules, and re-identifies whether a vehicle is anomalous, resulting in another list of anomalous vehicles. After determining the list of anomalous vehicles, the corresponding anomaly notifications are automatically pushed to after-sales personnel. These personnel can then initiate the repair process and push notifications to vehicle users, allowing them to be promptly informed of vehicle anomalies. Anomalous vehicles can display notifications on their dashboards or other screens, achieving a closed-loop repair process.

[0087] In this embodiment, a Workflow Agent is introduced to integrate LLM, FastAPI, and database technologies. This enables conversational input of initial target information, followed by automatic feature analysis, rule construction, and algorithm optimization by the Agent, ultimately identifying abnormal vehicles. Utilizing target features with higher anomaly levels ensures algorithm effectiveness and prevents omissions of abnormal vehicles. The conversational approach facilitates automatic feature analysis, rule construction, and algorithm optimization, automatically identifying abnormal vehicles and significantly improving efficiency. This streamlined process, from algorithm development to early warning push and after-sales support, achieves end-to-end automation.

[0088] It should be noted that the abnormal vehicle identification method involved in the above embodiments may include at least one of Embodiments 1 to 7. For example, Embodiment 1 can be implemented as an independent embodiment, Embodiment 1+2 can be implemented as an independent embodiment, Embodiment 1+2+3 can be implemented as an independent embodiment, Embodiment 1+2+4 can be implemented as an independent embodiment, Embodiment 1+2+3+4 can be implemented as an independent embodiment, Embodiment 1+2+5 can be implemented as an independent embodiment, Embodiment 1+2+3+5 can be implemented as an independent embodiment, Embodiment 1+2+4+5 can be implemented as an independent embodiment, Embodiment 1+2+3+4+5 can be implemented as an independent embodiment, and Embodiment 1+6 can be implemented as an independent embodiment. Examples 1+2+6 can be implemented as independent embodiments; Examples 1+2+3+6 can be implemented as independent embodiments; Examples 1+2+4+6 can be implemented as independent embodiments; Examples 1+2+3+4+6 can be implemented as independent embodiments; Examples 1+2+5+6 can be implemented as independent embodiments; Examples 1+2+3+5+6 can be implemented as independent embodiments; Examples 1+2+4+5+6 can be implemented as independent embodiments; Examples 1+2+3+4+5+6 can be implemented as independent embodiments; Examples 1+7 can be implemented as independent embodiments; Examples 1+2... +7 can be implemented as an independent embodiment, embodiment 1+2+3+7 can be implemented as an independent embodiment, embodiment 1+2+4+7 can be implemented as an independent embodiment, embodiment 1+2+3+4+7 can be implemented as an independent embodiment, embodiment 1+2+5+7 can be implemented as an independent embodiment, embodiment 1+2+3+5+7 can be implemented as an independent embodiment, embodiment 1+2+4+5+7 can be implemented as an independent embodiment, embodiment 1+2+3+4+5+7 can be implemented as an independent embodiment, embodiment 1+6+7 can be implemented as an independent embodiment, embodiment 1+2+6+ 7 can be implemented as an independent embodiment, and embodiments 1+2+3+6+7 can be implemented as independent embodiments, embodiments 1+2+4+6+7 can be implemented as independent embodiments, embodiments 1+2+3+4+6+7 can be implemented as independent embodiments, embodiments 1+2+5+6+7 can be implemented as independent embodiments, embodiments 1+2+3+5+6+7 can be implemented as independent embodiments, embodiments 1+2+4+5+6+7 can be implemented as independent embodiments, and so on, but are not limited to these, and will not be listed one by one here.

[0089] It should be noted that the abnormal vehicle identification method provided in this application embodiment can be executed by an abnormal vehicle identification device, or a control module within the abnormal vehicle identification device for executing the abnormal vehicle identification method. This application embodiment uses the execution of the abnormal vehicle identification method by an abnormal vehicle identification device as an example to illustrate the abnormal vehicle identification method provided in this application embodiment.

[0090] Reference Figure 4 The diagram shows a structural block diagram of an abnormal vehicle identification device according to an embodiment of this application.

[0091] like Figure 4 As shown, the abnormal vehicle identification device may include the following modules: The first determining module 401 is used to determine anomaly identification rules based on the target characteristics of the target vehicle, wherein the target vehicle refers to the vehicle contained in the historical vehicle anomaly data. The identification module 402 is used to identify whether the vehicle to be processed is an abnormal vehicle according to the anomaly identification rules.

[0092] Optionally, the device further includes: The second determining module is used to determine the degree of anomaly of the candidate features of the target vehicle; The filtering module is used to filter out target features from the candidate features based on the degree of anomaly.

[0093] Optionally, the filtering module is specifically used to filter out target features from the candidate features based on the degree of anomaly and the anomaly threshold; The device further includes an adjustment module, used to lower the abnormality threshold and return to the filtering module when the number of identified abnormal vehicles exceeds the number threshold.

[0094] Optionally, the device further includes: a generation module, used to generate structured target information based on the initial target information using a large language model, the target information including the vehicle identifier of the target vehicle, the abnormal time point of the target vehicle, and the vehicle data table identifier; The second determining module is specifically used to determine the degree of anomaly of the candidate features of the target vehicle based on the structured target information.

[0095] Optionally, the second determining module includes: The first parameter determination unit is used to determine a first anomaly parameter of the candidate feature of the target vehicle based on the feature value of the candidate feature of the target vehicle at the target time point and the feature value of the candidate feature of the reference vehicle at the target time point; the target time point is a plurality of time points before the anomaly time point of the target vehicle, and the first anomaly parameter includes a first outlier count and / or a first outlier magnitude statistical value. The degree determination unit is used to determine the degree of abnormality of the candidate feature based on the first abnormality parameter.

[0096] Optionally, the first determining module 401 includes: The second parameter determination unit is used to determine a second abnormal parameter of the target feature of the target vehicle within each time window based on the feature value of the target feature of the target vehicle at the target time point and the feature value of the target feature of the reference vehicle at the target time point; the target time point is a plurality of time points before the abnormal time point of the target vehicle, and the second abnormal parameter includes a second outlier count and / or a second outlier magnitude statistical value. The rule determination unit is used to determine the anomaly identification rule based on the time window and the largest second anomaly parameter.

[0097] Optionally, the device further includes a notification module for pushing abnormal notifications corresponding to the abnormal vehicles to the target user and / or the identified abnormal vehicles.

[0098] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0099] The abnormal vehicle identification device in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0100] The abnormal vehicle identification device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0101] The abnormal vehicle identification device provided in this application embodiment can realize each process implemented by the abnormal vehicle identification device in any of the above-mentioned method embodiments. To avoid repetition, it will not be described again here.

[0102] Optionally, embodiments of this application also provide an electronic device.

[0103] Reference Figure 5 The diagram shows a structural block diagram of an electronic device according to an embodiment of this application.

[0104] like Figure 5 As shown, the electronic device 11 includes a processor 111, a memory 112, and a program or instruction 1121 stored in the memory and executable on the processor. When the program or instruction 1121 is executed by the processor 111, it implements the various processes of any of the above-described embodiments of the abnormal vehicle identification method and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0105] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0106] Optionally, embodiments of this application also provide a readable storage medium.

[0107] Reference Figure 6 The diagram shows a structural block diagram of a readable storage medium according to an embodiment of this application.

[0108] like Figure 6 As shown, a program or instruction 211 is stored on the readable storage medium 21. When the program or instruction 211 is executed by the processor, it implements the various processes of any of the above abnormal vehicle identification method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0109] The processor may be the processor in the electronic device described in the above embodiments.

[0110] Optionally, this application provides a computer program product that stores programs or instructions. When the programs or instructions are executed by a processor, they implement the various processes of the above-described abnormal vehicle identification method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0111] Optionally, this application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described abnormal vehicle identification method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0112] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0113] The processors mentioned above may include, but are not limited to: Central Processing Unit (CPU), Network Processor (NP), Digital Signal Processor (DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0114] The aforementioned readable storage media include computer-readable storage media, which may include, but are not limited to: read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), electronically erasable programmable read-only memory (EEPROM), hard disk, floppy disk, flash memory, etc.

[0115] The various embodiments in this specification are related to each other and are described in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other.

[0116] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant data protection laws and regulations of the locality and with authorization from the owner of the relevant device.

[0117] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0118] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0119] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms. The functional units in the various embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0120] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0121] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for identifying abnormal vehicles, characterized in that, The method includes: Anomaly identification rules are determined based on the target characteristics of the target vehicle, wherein the target vehicle refers to the vehicle contained in the historical vehicle anomaly data; The anomaly identification rules are used to determine whether the vehicle to be processed is an abnormal vehicle.

2. The method according to claim 1, characterized in that, Before determining the anomaly identification rules based on the target characteristics of the target vehicle, the method further includes: Determine the degree of anomalousness of the candidate features of the target vehicle, and select the target features from the candidate features based on the degree of anomalousness.

3. The method according to claim 2, characterized in that, The step of selecting target features from candidate features based on the degree of anomaly includes: selecting target features from candidate features based on the degree of anomaly and an anomaly threshold; The method further includes: if the number of identified abnormal vehicles is greater than a number threshold, lowering the abnormality threshold and returning to the step of filtering target features from the candidate features based on the degree of abnormality and the abnormality threshold.

4. The method according to claim 2 or 3, characterized in that, Before determining the degree of anomaly of the candidate features of the target vehicle, the method further includes: using a large language model to generate structured target information based on the initial target information, wherein the target information includes the vehicle identifier of the target vehicle, the anomaly time point of the target vehicle, and the vehicle data table identifier. Determining the degree of anomaly of the candidate features of the target vehicle includes: determining the degree of anomaly of the candidate features of the target vehicle based on the structured target information.

5. The method according to any one of claims 2 to 4, characterized in that, Determining the degree of anomaly of the candidate features of the target vehicle includes: Based on the feature values ​​of the candidate features of the target vehicle at the target time point and the feature values ​​of the candidate features of the reference vehicle at the target time point, a first anomaly parameter of the candidate features of the target vehicle is determined; the target time point is a plurality of time points prior to the anomaly time point of the target vehicle, and the first anomaly parameter includes a first outlier count and / or a first outlier magnitude statistical value. The degree of anomalousness of the candidate feature is determined based on the first anomalous parameter.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining the anomaly identification rules based on the target characteristics of the target vehicle includes: Based on the feature value of the target feature of the target vehicle at the target time point and the feature value of the target feature of the reference vehicle at the target time point, a second anomaly parameter of the target feature of the target vehicle within each time window is determined; the target time point is a plurality of time points before the anomaly time point of the target vehicle, and the second anomaly parameter includes a second outlier count and / or a second outlier magnitude statistical value. The anomaly identification rule is determined based on the time window and the largest second anomaly parameter.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Push the abnormal notification corresponding to the abnormal vehicle to the target user and / or the identified abnormal vehicle.

8. An abnormal vehicle identification device, characterized in that, The device includes: The first determining module is used to determine anomaly identification rules based on the target characteristics of the target vehicle, wherein the target vehicle refers to the vehicle contained in the historical vehicle anomaly data. The identification module is used to identify whether the vehicle to be processed is an abnormal vehicle according to the anomaly identification rules.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the abnormal vehicle identification method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the abnormal vehicle identification method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product stores a program or instructions, which, when executed by a processor, implement the abnormal vehicle identification method as described in any one of claims 1 to 7.

Images