Operation index anomaly detection method and equipment based on battery swap station, and medium

Abstract

The invention discloses an operation index anomaly detection method and device based on a battery swap station and a medium, belongs to the technical field of index anomaly detection, and is used for solving the problems that operation indexes of an existing battery swap station are uneven, unified data detection is difficult to realize, detection on abnormal value indexes is relatively single, and the detection efficiency is high. And a certain hysteresis error also exists. The method comprises the following steps: obtaining operation index data in a battery swap station index library; performing unified conversion processing on the operation index data in a related standardized data format to obtain unified index data; according to the historical index value set, performing comparison judgment of related abnormal indexes on the unified index data, and determining an abnormal value range in the unified index data; performing abnormity judgment on the current operation index data to obtain current abnormal index data and a corresponding abnormal index duration day number; and if the number of duration days of the abnormal index is greater than a first preset threshold value, performing range adjustment on the abnormal value range to obtain an optimized abnormal value range.

Description

[0001] This application claims priority from the invention patent application titled "An Abnormal Detection Method, Device, and Medium for Operation Indicators Based on Battery Swap Stations" with the application number 202311871769.6, which was filed with the China National Intellectual Property Administration on December 29, 2023. Technical Field

[0002] This application relates to the field of abnormal detection of indicators, and particularly to an abnormal detection method, device, and medium for operation indicators based on battery swap stations. Background Art

[0003] With the enhancement of environmental protection awareness and the transformation of the energy structure, electric vehicles, as a clean and sustainable transportation mode, have received extensive attention and promotion. Regarding the operation indicators of each battery swap station at the national, city, and regional city levels, it is difficult to achieve a unified evaluation of the relevant indicators, and the variation laws of the indicators cannot be quantified. For example, designing abnormal detection logic separately for a single indicator requires a large amount of work, and it is also difficult to unify the detection methods ultimately.

[0004] Currently, the operation indicators of existing vehicle battery swap stations are uneven, making it difficult to achieve unified data detection. Moreover, for the detection and judgment of abnormal indicators, it often only performs abnormal detection on a specific single indicator, unable to accurately identify the true abnormal values in various operation indicators comprehensively. At the same time, there is also a certain lag error in the detected abnormal value indicators, which is not conducive to the intelligent unified detection of operation indicators in vehicle battery swap stations. Summary of the Invention

[0005] The embodiments of this application provide an abnormal detection method, device, and medium for operation indicators based on battery swap stations to solve the following technical problems: The operation indicators of existing battery swap stations are uneven, making it difficult to achieve unified data detection. The detection of abnormal value indicators is relatively single, unable to accurately identify the true abnormal values in various operation indicators comprehensively, and there is also a certain lag error, etc.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] On the one hand, an embodiment of the present application provides an abnormal detection method for operation indicators based on a battery swapping station, including: obtaining operation indicator data in the operation indicator database of the battery swapping station based on a preset time interval; performing unified conversion processing on the operation indicator data in a standardized data format to obtain unified indicator data; comparing and judging the unified indicator data with respect to abnormal indicators according to a set of historical indicator values to determine the range of abnormal values in the unified indicator data; performing abnormal judgment on the current operation indicator data according to the range of abnormal values to obtain the current abnormal indicator data and the corresponding number of consecutive days of abnormal indicators; if the number of consecutive days of abnormal indicators is greater than a first preset threshold, adjusting the range of the abnormal value range to obtain an optimized abnormal value range.

[0008] In the embodiment of the present application, after converting the operation indicator data obtained from the battery swapping station into a unified data format and combining it with a set of historical abnormal indicator values, the current abnormal indicator values are compared and judged, so as to accurately identify the abnormal indicator values of each indicator type in the unified indicator data, then obtain the abnormal indicator values at the current time node, and perform model training on them, thereby obtaining the abnormal detection result data at all time nodes. It reduces the phenomenon of uneven operation indicators of the battery swapping station, realizes unified data detection, can comprehensively and accurately identify the true abnormal values in various operation indicators, reduces the problem of lag error of abnormal indicator values, and optimizes the abnormal detection method for operation indicators in the battery swapping station.

[0009] In a feasible implementation manner, obtaining operation indicator data in the operation indicator database of the battery swapping station based on a preset time interval specifically includes: accessing and publishing data collection instructions to battery swapping stations within a preset area through the data request instruction set of the battery swapping station management platform to obtain the access link of the operation indicator database in each battery swapping station; wherein, the operation indicator database contains various battery swapping data collected during the daily use of the battery swapping station; obtaining the operation indicator data at different time intervals in the operation indicator database according to the access link; wherein, the operation indicator data at least includes: station - end operation indicators, vehicle - end operation indicators, and user - end operation indicators.

[0010] In the embodiment of the present application, through a preset time interval, continuously obtain the operation indicator data in the operation indicator database of each battery swapping station, and combine the centralized release of data collection instructions, it can quickly and accurately obtain the operation indicator data at different time intervals in the operation indicator database by using the access connection, which is convenient for subsequent processing of the operation data. At the same time, based on the access and release of data collection instructions, it can also effectively reduce the problem of data loss during data collection and ensure that the extracted operation indicator data is more comprehensive.

[0011] In a feasible implementation manner, before performing unified conversion processing on the operation index data in a relevant standardized data format to obtain unified index data, the method further includes: identifying index type data in the operation index data to obtain multi-dimensional index types; where the multi-dimensional index types at least include: the number of battery swapping times, the battery swapping efficiency, and the battery swapping income; according to each index type in the multi-dimensional index types, performing unified set processing on the dimension types where the battery swapping stations are distributed to obtain a dimension type set; where the dimension types at least include: a super-large city set area, a large city set area, a small city set area, and a regional site set area; based on the dimension type set, determining dimension values corresponding to each of the dimension types; where the dimension values are the names of battery swapping stations in a single area in the city set area and the regional site set area; extracting the data correlation relationships among the multi-dimensional index types, the dimension type set, and the dimension values; based on the data correlation relationships, performing component configuration on the multi-dimensional index types, the dimension type set, and the dimension values to obtain a unified configuration component.

[0012] Through the identification and division of the operation index data in the embodiments of the present application, according to different data characteristics, the operation index data can be divided into multi-dimensional index types, a dimension type set, and dimension values, and combined with the correlation relationships between the classified data above, a unified configuration component for data identification and configuration is generated, which is used to quickly divide the data characteristics of the operation index data at subsequent time nodes, thereby completing the preprocessing of the operation index data, ensuring the format calibration work before the unified conversion of the data format, and facilitating the reduction of data error problems in the standardized data format.

[0013] In a feasible implementation manner, performing unified conversion processing on the operation index data in a relevant standardized data format to obtain unified index data specifically includes: extracting index values in the operation index data that are associated with the dimension type set; where the index values include: the number value of the battery swapping times, the battery swapping efficiency value, and the battery swapping income value; through the unified configuration component, performing data division on the operation index data to generate an index configuration table; where the index configuration table includes: the multi-dimensional index types, the dimension type set, the dimension values, and the index values; according to a preset standard data format, performing unified numerical conversion on the index values in the index configuration table to obtain standardized index values; and updating the standardized index values to the index configuration table; based on the content text in the updated index configuration table, determining the unified index data.

[0014] In the implementation of this application, the generated unified configuration component is used to partition the current operation index data and perform content matching processing, and then based on the standard data format, the numerical values of the index values in different formats in the index configuration table are uniformly processed. This can accurately associate and correspond various multi-dimensional index types, dimension type sets, dimension values, and standardized indexes in the unified index data. Through tabular data configuration processing, it can greatly avoid configuration omissions during the data standardization conversion of operation index data and enhance the data conversion efficiency.

[0015] In a feasible implementation manner, according to the set of historical abnormal index values, the unified index data is compared and judged for abnormal indexes to determine the range of abnormal values in the unified index data. Specifically, it includes: obtaining, through the swap station management platform, the set of historical index values of the swap station within a preset time period; where the set of historical index values is the set of historical index values within a historical continuous time period; dividing the numerical ranges of several historical index values in the set of historical index values to obtain interval historical index values; where the numerical ranges include: the upper quartile range, the median range, and the lower quartile range; based on the interval historical index values, determining the upper edge abnormal value and the lower edge abnormal value of the set of historical index values; comparing and judging the current index value in the unified index data with the upper edge abnormal value and the lower edge abnormal value respectively; if the current index value is greater than the upper edge abnormal value, then determining the current index value as the abnormally large value in the unified index data; if the current index value is less than the lower edge abnormal value, then determining the current index value as the abnormally small value in the unified index data; based on the abnormally large value and the abnormally small value, determining the range of abnormal values.

[0016] This application can compare and judge the current abnormal index value with the upper edge abnormal value and the lower edge abnormal value by using the set of historical abnormal index values and combining the division processing of data ranges, that is, screening and judging the data threshold for the current abnormal index value, so as to more accurately obtain the range of abnormal values in the unified index data, that is, the actual abnormal index values of each index value at the current time node, which is beneficial to accurately detecting abnormal situations of various operation index data in the swap station.

[0017] In a feasible implementation manner, based on the interval historical abnormal index values, determining the upper edge abnormal value and the lower edge abnormal value of the set of historical abnormal index values, specifically including: obtaining the upper edge abnormal value A according to A = Q3 + 1.5 * (|Q3 - Q1|); where Q3 is the numerical value corresponding to the upper quartile range; Q1 is the numerical value corresponding to the lower quartile range; obtaining the lower edge abnormal value B according to B = Q1 - 1.5 * (|Q3 - Q1|).

[0018] In a feasible implementation manner, according to the outlier range, perform an outlier judgment on the current operation index data to obtain the current outlier index data and the corresponding continuous days of the outlier index, which specifically includes: obtaining the current time node corresponding to the current operation index data; if the index value in the current operation index data is not within the outlier range, determining the current operation index data as the current outlier index data; based on the current outlier index data, querying whether there is continuously outlier index data within the historical consecutive days; wherein, the historical consecutive days are the consecutive historical days pushed forward based on the current time node; if there is continuously outlier index data within the historical consecutive days, defining the current time node as the duration base point and determining the historical consecutive days as the continuous days of the outlier index.

[0019] The embodiments of the present application can detect outliers in the current operation index data in real time, helping to timely discover and respond to potential problems. By identifying and excluding outlier data, the overall quality of the data set can be improved, ensuring the accuracy of subsequent analysis and decision-making. It can clearly indicate which index data is abnormal, helping to quickly locate the source of the problem and facilitating the adoption of targeted measures. The system can track the continuous days of the outlier index data, helping to understand the severity and duration of the abnormal situation and providing important information for problem-solving. Providing the continuous days of the outlier index data helps management make more informed decisions, such as adjusting operation strategies or resource allocation. By analyzing the continuous days of the outlier index data, operation risks can be evaluated and major problems that may occur can be warned in advance. Understanding the continuous days of the outlier data can help optimize the monitoring strategy, adjust the monitoring frequency and focus, and improve the monitoring efficiency. By quickly identifying the outlier index data, the time from the occurrence of the outlier to taking action can be shortened, reducing potential losses. Using historical data to identify outliers can better understand the patterns and behaviors of the outlier data and improve the accuracy of outlier detection.

[0020] In a feasible implementation manner, if the continuous days of the outlier index are greater than the first preset threshold, perform a range adjustment on the outlier range to obtain an optimized outlier range, which specifically includes: if the continuous days of the outlier index are greater than the first preset threshold, perform an edge value adjustment process on the outlier maximum value and the outlier minimum value in the outlier range to obtain the optimized outlier range, and perform a range adjustment on the historical consecutive time in the historical index value set to obtain an optimized historical index value set; according to the optimized historical index value set and the optimized outlier range, re-perform an outlier index judgment on the current operation index data to complete the outlier detection of the operation index of the battery swapping station.

[0021] In an embodiment of the present application, after training a model with the identified outlier range and combining it with a deep learning network model, an outlier index recognition model is determined. Then, using the outlier index recognition model, it is possible to optimize the parameter recognition of the outlier index values in the unified index data, which is beneficial for identifying outliers in a large range of operation index value data, enabling outlier detection for the operation index value data in each swapping station, further improving the automated detection of outlier indices, and ensuring comprehensive outlier detection for all operation index data.

[0022] In a second aspect, an embodiment of the present application further provides an operation index outlier detection device based on a swapping station. The device includes: an acquisition module for acquiring operation index data in a swapping station index library based on a preset time interval; a conversion module for performing unified conversion processing on the operation index data in a relevant standardized data format to obtain unified index data; a comparison module for comparing and judging the unified index data for outlier indices according to a historical index value set to determine the outlier range in the unified index data; a judgment module for performing outlier judgment on the current operation index data according to the outlier range to obtain the current outlier index data and the corresponding continuous days of the outlier index; an adjustment module for, if the continuous days of the outlier index are greater than a first preset threshold, adjusting the outlier range to obtain an optimized outlier range.

[0023] In a third aspect, an embodiment of the present application further provides an electronic device, including: an operation index outlier detection device based on a swapping station, the device including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, so that the at least one processor can execute the above-mentioned operation index outlier detection method based on a swapping station.

[0024] In a fourth aspect, an embodiment of the present application further provides a non-volatile computer storage medium, the storage medium being a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each program including instructions, and when the instructions are executed by a terminal, the terminal executes the above-mentioned operation index outlier detection method based on a swapping station.

[0025] The present application provides an operation index outlier detection method, device, and medium based on a swapping station. Compared with the prior art, the embodiments of the present application have the following beneficial technical effects:

[0026] In the embodiment of the present application, after converting the operation index data obtained from the battery swapping station into a unified data format and combining it with the historical abnormal index value set, the current abnormal index value is compared and judged. It can accurately identify the abnormal index values of each index type in the unified index data, then obtain the abnormal index values at the current time node, and perform model training on them, so as to obtain the abnormal detection result data at all time nodes. It reduces the phenomenon of uneven operation indexes of the battery swapping station, realizes unified data detection, can accurately identify the real abnormal values in various operation indexes, reduces the lag error problem of index abnormal values, and optimizes the abnormal detection method of operation indexes in the battery swapping station. Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0028] Figure 1 It is a flowchart of an operation index abnormal detection method based on a battery swapping station provided by an embodiment of the present application;

[0029] Figure 2 It is a schematic structural diagram of an electronic device for operation index abnormal detection based on a battery swapping station provided by an embodiment of the present application. Detailed Embodiments

[0030] In order to enable those skilled in the art to better understand the technical solutions in the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0031] The embodiment of the present application provides an operation index abnormal detection method based on a battery swapping station, as Figure 1 shown, the operation index abnormal detection method based on a battery swapping station specifically includes steps S101 - S104:

[0032] S101. Obtain the operation index data in the battery swapping station index library based on a preset time interval.

[0033] Specifically, first, through the data request instruction set of the battery swapping station management platform, access and publish data collection instructions to the battery swapping stations within a preset area, and obtain the access links to the battery swapping station index libraries in each battery swapping station. Among them, the battery swapping station index library contains various battery swapping data collected during the daily use of the battery swapping station.

[0034] Furthermore, according to the access links, obtain the operation index data in the battery swapping station index library at different time intervals. Among them, the operation index data at least includes: station-side operation indexes, vehicle-side operation indexes, and user-side operation indexes.

[0035] As a feasible implementation method, by preset time intervals, continuously obtain the operation index data in the battery swapping station index libraries of each battery swapping station, and combined with the centralized release of data collection instructions, it is possible to use the access connection to quickly and accurately obtain the operation index data in the battery swapping station index library at different time intervals, which is convenient for subsequent processing of the operation data. At the same time, based on the access and release of data collection instructions, it can also effectively reduce the problem of data loss during data collection and ensure that the extracted operation index data is more comprehensive.

[0036] S102. Perform unified conversion processing on the operation index data in the relevant standardized data format to obtain unified index data.

[0037] Specifically, identify the index type data in the operation index data to obtain multi-dimensional index types. Among them, the multi-dimensional index types at least include: the number of battery swaps, the battery swap efficiency, and the battery swap income.

[0038] Furthermore, according to each index type in the multi-dimensional index types, perform unified aggregation processing on the dimension types where the battery swapping stations are distributed to obtain a dimension type set. Among them, the dimension types at least include: super-large city aggregation areas, large city aggregation areas, small city aggregation areas, and regional site aggregation areas.

[0039] Furthermore, based on the dimension type set, determine the dimension values corresponding to each dimension type. Among them, the dimension values are the names of the battery swapping stations in a single area within the city aggregation area and the regional site aggregation area.

[0040] Furthermore, extract the data correlation relationships among the multi-dimensional index types, the dimension type set, and the dimension values. Then, based on the data correlation relationships, perform component configuration on the multi-dimensional index types, the dimension type set, and the dimension values to obtain a unified configuration component.

[0041] As a feasible implementation method, after identifying and classifying the operation index data, the operation index data can be divided into multi-dimensional index types, dimension type sets, and dimension values according to different data characteristics. And by combining the correlation relationships between the classified data above, a unified configuration component for data identification and configuration is generated, which is used to quickly classify the data characteristics of the operation index data in subsequent time nodes, thereby completing the preprocessing of the operation index data, ensuring the format calibration work before the unified conversion of the data format, and facilitating the reduction of data error problems in the standardized data format.

[0042] Furthermore, continue to extract the index values associated with the dimension type set in the operation index data. Among them, the index values include: the number of battery swapping times value, the battery swapping efficiency value, and the battery swapping income value.

[0043] Furthermore, through the unified configuration component, the operation index data is divided to generate an index configuration table. Among them, the index configuration table includes: multi-dimensional index types, dimension type sets, dimension values, and index values.

[0044] Furthermore, according to the preset standard data format, the index values in the index configuration table are uniformly numerically converted to obtain standardized index values. And the standardized index values are updated to the index configuration table. Then, based on the content text in the updated index configuration table, unified index data is determined.

[0045] As a feasible implementation method, using the generated unified configuration component, the current operation index data is divided and content-matched, and then based on the standard data format, the numerical values of the index values in different formats in the index configuration table are uniformly processed, which can accurately associate and correspond each multi-dimensional index type, dimension type set, dimension value, and standardized index in the unified index data. And through tabular data configuration processing, it can greatly avoid configuration omissions during the data standardization conversion of the operation index data and enhance the data conversion efficiency.

[0046] S103. According to the historical index value set, compare and judge the unified index data for abnormal indexes to determine the range of abnormal values in the unified index data.

[0047] Specifically, it is also necessary to first obtain the historical index value set of the battery swapping station within the preset time period through the battery swapping station management platform. Among them, the historical index value set is the historical index value set within the historical continuous time.

[0048] Furthermore, divide the numerical ranges of several historical abnormal index values in the historical abnormal index value set to obtain interval historical abnormal index values. Among them, the numerical ranges include: the upper quartile range, the median range, and the lower quartile range.

[0049] Further, based on the historical anomaly index values in the interval, the upper-edge anomaly value and the lower-edge anomaly value of the historical anomaly index value set are determined: Optionally, the upper-edge anomaly value A can be obtained according to A = Q3 + 1.5 * (|Q3 - Q1|). Where Q3 is the value corresponding to the upper quartile interval. Q1 is the value corresponding to the lower quartile interval. The lower-edge anomaly value B is obtained according to B = Q1 - 1.5 * (|Q3 - Q1|).

[0050] As a feasible implementation, based on the historical anomaly index values under each interval, the data with relatively large noise can be well preliminarily screened, and then according to the upper-edge anomaly value and the lower-edge anomaly value, the current anomaly index value in the unified index data can be further screened in the subsequent process, so as to ensure that the currently screened anomaly index is an accurate data volume.

[0051] Further, the current anomaly index value in the unified index data is respectively compared and judged with the upper-edge anomaly value and the lower-edge anomaly value:

[0052] If the current anomaly index value is greater than the upper-edge anomaly value, the current anomaly index value is determined as the abnormally large value in the unified index data. If the current anomaly index value is less than the lower-edge anomaly value, the current anomaly index value is determined as the abnormally small value in the unified index data. Finally, the anomaly value range includes: the abnormally large value and the abnormally small value.

[0053] As a feasible implementation, by using the historical anomaly index value set and combining the division processing of the data interval, the current anomaly index value can be compared and judged with the upper-edge anomaly value and the lower-edge anomaly value, that is, the current anomaly index value is used for the screening and judgment of the data threshold, so as to more accurately obtain the anomaly value range in the unified index data, that is, the actual anomaly index value of each index value at the current time node, which is beneficial to accurately detecting the abnormal conditions of various operation index data in the battery swapping station.

[0054] In one implementation, the anomaly value range and its corresponding time node also need to be stored in a preset dedicated anomaly value table. The preset dedicated anomaly value table is used to record the actual anomaly index value of each multi-dimensional index type in the unified index data under each time node.

[0055] As a feasible implementation, by storing the anomaly value range and its corresponding time node in the preset dedicated anomaly value table, the anomaly value range can be fixedly stored, preventing data omission and data incompleteness, which is beneficial to providing excellent data reference for the subsequent anomaly detection result data.

[0056] S104. Based on the outlier range, perform an outlier judgment on the current operation index data to obtain the current outlier index data and the corresponding continuous days of the outlier index.

[0057] Specifically, first obtain the current time node corresponding to the current operation index data. If the index value in the current operation index data is not within the outlier range, determine the current operation index data as the current outlier index data.

[0058] Furthermore, based on the current outlier index data, query whether there is continuously outlier index data within the historical consecutive days. Here, the historical consecutive days are the consecutive historical days pushed forward based on the current time node. If there is continuously outlier index data within the historical consecutive days, define the current time node as the duration base point and determine the historical consecutive days as the continuous days of the outlier index.

[0059] As a feasible implementation method, after comparing the index values in the identified current operation index data with the outlier range, it is possible to screen out which current operation index data are the current outlier index data, thereby determining the current outlier index data as the end time node of the abnormal time node, and then performing a time-forward screening to query whether there is outlier index data in the previous consecutive historical days. If there is outlier index data in all of them, then determine these historical consecutive days as the continuous days of the outlier index.

[0060] S105. If the continuous days of the outlier index are greater than the first preset threshold, adjust the range of the outlier range to obtain an optimized outlier range.

[0061] Specifically, if the continuous days of the outlier index are greater than the first preset threshold, perform edge value adjustment processing on the outlier maximum value and the outlier minimum value in the outlier range to obtain an optimized outlier range, and adjust the range of the historical continuous time in the historical index value set to obtain an optimized historical index value set.

[0062] Furthermore, based on the optimized historical index value set and the optimized outlier range, re-perform an outlier index judgment on the current operation index data to complete the outlier detection of the operation index of the battery swapping station.

[0063] In one embodiment, during the actual operation of the battery swapping station, when there are abnormal indicators continuously within a certain period of time, it indicates that the previous abnormal value range may no longer be applicable, and it is necessary to re-adjust the abnormal value range to reduce the continuous impact on subsequent data and avoid situations such as data misjudgment. That is, perform edge value adjustment processing on the abnormal large value and abnormal small value in the abnormal value range to obtain an optimized abnormal value range, and then correspondingly adjust the historical continuous time in the historical indicator value set to obtain an optimized historical indicator value set, which is to re-adjust the historical indicator value set to try to avoid the influence of abnormal indicators on subsequent battery swapping indicators and other indicators within a certain period of time. Then, re-use the optimized historical indicator value set and the optimized abnormal value range to judge abnormal indicators for subsequent operation indicator data to complete the abnormal detection of the operation indicators of the battery swapping station.

[0064] In addition, an embodiment of the present application also provides an electronic device for abnormal detection of operation indicators based on a battery swapping station, as Figure 2 shown. The electronic device 200 for abnormal detection of operation indicators based on a battery swapping station specifically includes:

[0065] At least one processor 201. And, a memory 202 communicatively connected to the at least one processor 201. Wherein, the memory 202 stores instructions that can be executed by the at least one processor 201, so that when the at least one processor 201 executes the instructions, the abnormal detection method of operation indicators based on a battery swapping station in any of the above embodiments is implemented.

[0066] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the abnormal detection method of operation indicators based on a battery swapping station in any of the above embodiments is implemented.

[0067] Meanwhile, an embodiment of the present application also provides an abnormal detection device for operation indicators based on a battery swapping station. The device includes:

[0068] An acquisition module, configured to acquire operation indicator data in a battery swapping station indicator library based on a preset time interval.

[0069] A conversion module, configured to perform unified conversion processing on the operation indicator data in a unified standardized data format to obtain unified indicator data.

[0070] A comparison module, configured to compare and judge the unified indicator data for abnormal indicators according to the historical indicator value set, and determine the abnormal value range in the unified indicator data.

[0071] A judgment module, configured to perform abnormal judgment on the current operation indicator data according to the abnormal value range to obtain the current abnormal indicator data and the corresponding number of consecutive days of abnormal indicators.

[0072] An adjustment module, configured to perform range adjustment on the abnormal value range to obtain an optimized abnormal value range if the number of consecutive days of the abnormal index is greater than a first preset threshold.

[0073] In the embodiments of the present application, after converting the operation index data obtained from the battery swapping station into a unified data format and combining it with the historical abnormal index value set, the current abnormal index value is compared and judged. The abnormal index values of each index type in the unified index data can be accurately identified, and then the abnormal index values at the current time node are obtained and used for model training, so as to obtain the abnormal detection result data at all time nodes. This reduces the phenomenon of uneven operation indexes of the battery swapping station, realizes unified data detection, can accurately identify the true abnormal values in various operation indexes comprehensively, reduces the problem of lag error of the index abnormal values, and optimizes the abnormal detection method for the operation indexes in the battery swapping station.

[0074] The embodiments in the present application are all described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device and the medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0075] The device and the medium provided in the embodiments of the present application correspond one by one to the method. Therefore, the device and the medium also have beneficial technical effects similar to those of the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and the medium are not described herein again.

[0076] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0078] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0080] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0081] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0082] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0083] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0084] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An abnormal detection method for operation indicators based on a battery swapping station, characterized in that, The method includes: Obtaining operation index data in the swap station index library based on a preset time interval; Performing unified conversion processing on the operation index data in a relevant standardized data format to obtain unified index data; Comparing and judging the unified index data for abnormal indexes according to the historical index value set, and determining the range of abnormal values in the unified index data; Performing abnormal judgment on the current operation index data according to the range of abnormal values to obtain the current abnormal index data and the corresponding continuous days of abnormal indexes; If the continuous days of the abnormal index are greater than a first preset threshold, adjusting the range of the abnormal value range to obtain an optimized abnormal value range.

2. The operation index anomaly detection method based on a battery swapping station according to claim 1, wherein Obtaining operation index data in the swap station index library based on a preset time interval specifically includes: Issuing data collection instructions to access swap stations in a preset area through the data request instruction set of the swap station management platform to obtain access links to the swap station index libraries in each swap station; wherein, the swap station index library contains various swap data collected during the daily use of the swap station; Obtaining operation index data at different time intervals in the swap station index library according to the access link; wherein, the operation index data at least includes: station - end operation indexes, vehicle - end operation indexes, and user - end operation indexes.

3. The operation index abnormal detection method based on a battery swapping station according to claim 1, characterized in that Before performing unified conversion processing on the operation index data in a relevant standardized data format to obtain unified index data, the method further includes: Identifying the index type data in the operation index data to obtain multi - dimensional index types; wherein, the multi - dimensional index types at least include: number of swap times, swap efficiency, and swap income; Performing unified set processing on the dimension types where the swap stations are distributed according to each index type in the multi - dimensional index types to obtain a dimension type set; wherein, the dimension types at least include: super - large city set area, large city set area, small city set area, and regional site set area; Determining dimension values corresponding to each dimension type based on the dimension type set; wherein, the dimension value is the name of the swap station in a single area of the city set area and the regional site set area; Extracting the data correlation relationships among the multi - dimensional index types, the dimension type set, and the dimension values; Performing component configuration on the multi - dimensional index types, the dimension type set, and the dimension values based on the data correlation relationships to obtain a unified configuration component.

4. The operation index anomaly detection method based on a battery swapping station according to claim 3, characterized in that, Performing unified conversion processing on the operation index data in a relevant standardized data format to obtain unified index data specifically includes: Extracting the index values in the operation index data associated with the dimension type set; wherein, the index values include: number value of swap times, swap efficiency value, and swap income value; Dividing the operation index data through the unified configuration component to generate an index configuration table; wherein, the index configuration table includes: the multi - dimensional index types, the dimension type set, the dimension values, and the index values; According to the preset standard data format, perform unified numerical conversion on the index values in the index configuration table to obtain standardized index values; and update the standardized index values to the index configuration table; Based on the content text in the updated index configuration table, determine the unified index data.

5. The operation index abnormal detection method based on a battery swapping station according to claim 1, wherein, According to the set of historical abnormal index values, perform comparison and judgment on the unified index data regarding abnormal indexes to determine the range of abnormal values in the unified index data, specifically including: Through the swap station management platform, obtain the set of historical index values of the swap station within a preset time period; wherein, the set of historical index values is the set of historical index values within a continuous historical time; Divide several historical index values in the set of historical index values into numerical intervals to obtain interval historical index values; wherein, the numerical intervals include: upper quartile interval, median interval, and lower quartile interval; Based on the interval historical index values, determine the upper boundary abnormal value and the lower boundary abnormal value of the set of historical index values; Compare and judge the current index value in the unified index data with the upper boundary abnormal value and the lower boundary abnormal value respectively; If the current index value is greater than the upper boundary abnormal value, determine the current index value as the abnormally large value in the unified index data; If the current index value is less than the lower boundary abnormal value, determine the current index value as the abnormally small value in the unified index data; Based on the abnormally large value and the abnormally small value, determine the range of abnormal values.

6. The operation index anomaly detection method based on a battery swapping station according to claim 5, characterized in that, Based on the interval historical index values, determine the upper boundary abnormal value and the lower boundary abnormal value of the set of historical index values, specifically including: According to A = Q3 + 1.5 * (|Q3 - Q1|), obtain the upper boundary abnormal value A; where Q3 is the value corresponding to the upper quartile interval; Q1 is the value corresponding to the lower quartile interval; According to B = Q1 - 1.5 * (|Q3 - Q1|), obtain the lower boundary abnormal value B.

7. A method for detecting abnormal operation indicators based on a battery swapping station according to claim 1, characterized in that, According to the range of abnormal values, perform abnormal judgment on the current operation index data to obtain the current abnormal index data and the corresponding continuous days of abnormal indexes, specifically including: Obtain the current time node corresponding to the current operation index data; If the index value in the current operation index data is not within the range of abnormal values, determine the current operation index data as the current abnormal index data; Based on the current abnormal index data, query whether there is continuous abnormal index data within the historical continuous days; wherein, the historical continuous days are the consecutive historical days pushed forward based on the current time node; If there is continuous abnormal index data within the historical continuous days, define the current time node as the continuous time base point and determine the historical continuous days as the continuous days of abnormal indexes.

8. The operation index anomaly detection method based on a battery swapping station according to claim 1, wherein, If the continuous days of abnormal indexes are greater than the first preset threshold, perform range adjustment on the range of abnormal values to obtain an optimized range of abnormal values, specifically including: If the number of consecutive days of the abnormal indicator is greater than the first preset threshold, the abnormally large value and the abnormally small value in the abnormal value range are adjusted as edge values to obtain the optimized abnormal value range, and the historical continuous time in the historical indicator value set is adjusted in range to obtain the optimized historical indicator value set; Based on the optimized historical indicator value set and the optimized abnormal value range, the current operation indicator data is rejudged for abnormal indicators to complete the abnormal detection of the operation indicators of the battery swapping station.

9. An abnormal operation index detection device based on a battery swapping station, characterized in that, The device includes: An acquisition module, configured to acquire operation indicator data in a battery swapping station indicator library based on a preset time interval; A conversion module, configured to perform unified conversion processing on the operation indicator data in a unified standard data format to obtain unified indicator data; A comparison module, configured to compare and judge the unified indicator data for abnormal indicators according to a historical indicator value set, and determine an abnormal value range in the unified indicator data; A judgment module, configured to perform an abnormality judgment on the current operation indicator data according to the abnormal value range to obtain current abnormal indicator data and the corresponding number of consecutive days of the abnormal indicator; An adjustment module, configured to adjust the range of the abnormal value range to obtain an optimized abnormal value range if the number of consecutive days of the abnormal indicator is greater than the first preset threshold.

10. An electronic device, characterized in that, Including: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, so that the at least one processor can execute a method for abnormal detection of operation indicators based on a battery swapping station according to any one of claims 1-8.

11. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each program includes instructions, and when the instructions are executed by a terminal, the terminal executes a method for abnormal detection of operation indicators based on a battery swapping station according to any one of claims 1-8.

Images