Battery charging data detection method and device, computer equipment and storage medium

Abstract

The invention relates to a battery charging data detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring multi-dimensional charging data of a to-be-detected vehicle in a preset time period; according to the multi-dimensional charging data, determining a basic detection index corresponding to each dimension; correcting the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension to obtain a corrected detection index corresponding to each dimension; and generating a battery charging data detection result of the to-be-detected vehicle according to the correction detection index corresponding to each dimension. By evaluating and detecting the multi-dimensional charging data, the detection result of the battery charging data can be accurately determined, and the health state of the battery can be more accurately evaluated through the detection result of the battery charging data.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery charging data detection method, device, computer equipment and storage medium. Background Art

[0002] The battery of a new energy vehicle is one of the core components of an electric vehicle. The performance of the battery is directly related to the performance, safety and range of the vehicle. During the use of a new energy vehicle, the battery management system of the vehicle monitors and controls the status of the vehicle battery to ensure the performance and safety of the battery during use.

[0003] The current traditional technology usually identifies the safe and healthy status of the battery by monitoring parameters such as the battery's internal resistance, charge and discharge indicators, self-discharge efficiency, temperature, and physical deformation. However, the above battery safety and health status detection does not take into account the battery charging data during the user's use of the vehicle. Although the battery charging data will not directly affect the health of the battery in the short term, long-term poor charging behavior has an important impact on the safety and life of the battery. For the detection of battery charging data, the current traditional technology has not proposed an effective solution. Summary of the invention

[0004] Based on this, it is necessary to provide a battery charging data detection method, device, computer equipment and storage medium to address the above technical problems.

[0005] In a first aspect, the present application provides a battery charging data detection method, the method comprising: obtaining multi-dimensional charging data of a vehicle to be detected within a preset time period; determining a basic detection index corresponding to each dimension based on the multi-dimensional charging data; correcting the basic detection index of the corresponding dimension based on an index detection model corresponding to each dimension to obtain a corrected detection index corresponding to each dimension; and generating a battery charging data detection result of the vehicle to be detected based on the corrected detection index corresponding to each dimension.

[0006] In one of the embodiments, the multi-dimensional charging data includes: the number of charging times, the power deficit remaining at the beginning of charging, the power supply remaining at the end of charging, the number of fast charging times, and the number of slow charging times.

[0007] In one of the embodiments, determining the basic detection index corresponding to each dimension based on the multi-dimensional charging data includes: determining a charging number index based on the charging number and a charging number reference value; determining a low-power margin index based on the low-power margin and the low-power margin reference value; determining a feeding margin index based on the feeding margin and the feeding margin reference value; determining a fast charging number index based on the fast charging number and the fast charging number reference value; and determining a slow charging number index based on the slow charging number and the slow charging number reference value.

[0008] In one of the embodiments, the basic detection index of the corresponding dimension is corrected according to the index detection model corresponding to each dimension to obtain the corrected detection index corresponding to each dimension, including: inputting the charging data of the target dimension and the corresponding basic detection index into the pre-trained index detection model of the target dimension to obtain the corrected detection index of the target dimension; the target dimension is any dimension among the multiple dimensions.

[0009] In one embodiment, the charging data of the target dimension and the corresponding basic detection index are input into a pre-trained index detection model of the target dimension to obtain a corrected detection index of the target dimension, including: the pre-trained index detection model of the target dimension determines an index array corresponding to the charging data in a preset range based on the charging data of the target dimension; determines whether the basic detection index needs to be corrected according to the index array and the basic detection index; if correction is required, obtaining the corrected detection index of the target dimension based on the index array.

[0010] In one of the embodiments, generating the battery charging data detection result of the vehicle to be detected according to the correction detection index corresponding to each dimension includes: obtaining the comprehensive weight corresponding to each dimension; determining the comprehensive detection index according to the correction detection index corresponding to each dimension and the comprehensive weight corresponding to each dimension; generating the battery charging data detection result of the vehicle to be detected according to the comprehensive detection index.

[0011] In one of the embodiments, the battery risk level and processing strategy of the vehicle to be inspected are determined based on the comprehensive inspection index and preset evaluation rules.

[0012] In the second aspect, the present application also provides a battery charging data detection device, which includes: an acquisition module for acquiring multi-dimensional charging data of a vehicle to be detected within a preset time period; an index calculation module for determining a basic detection index corresponding to each dimension based on the multi-dimensional charging data; a correction module for correcting the basic detection index of the corresponding dimension according to an index detection model corresponding to each dimension to obtain a corrected detection index corresponding to each dimension; and a result generation module for generating a battery charging data detection result of the vehicle to be detected according to the corrected detection index corresponding to each dimension.

[0013] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any one of the battery charging data detection methods in the first aspect is implemented.

[0014] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program implements any one of the battery charging data detection methods in the first aspect.

[0015] The above-mentioned battery charging data detection method, device, computer equipment and storage medium obtain the multi-dimensional charging data of the vehicle to be detected within a preset time period, and determine the basic detection index corresponding to each dimension based on the multi-dimensional charging data; then correct the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension, and obtain the corrected detection index corresponding to each dimension, and finally generate the battery charging data detection result of the vehicle to be detected according to the corrected detection index corresponding to each dimension. By evaluating and detecting the multi-dimensional charging data, the battery charging data detection result can be accurately determined, and further through the battery charging data detection result, the battery health status can be more accurately evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 An application environment diagram of a battery charging data detection method in one embodiment;

[0017] Figure 2 A schematic diagram of a flow chart of a battery charging data detection method in one embodiment;

[0018] Figure 3 A schematic diagram of a process flow of a basic detection index calculation method in one embodiment;

[0019] Figure 4 It is a schematic diagram of a flow chart of a method for correcting a basic detection index by an index detection model in one embodiment;

[0020] Figure 5 A schematic diagram of a flow chart of a method for calculating a comprehensive detection index in one embodiment;

[0021] Figure 6 is a principle block diagram of a battery charging data detection method in one embodiment;

[0022] Figure 7 It is a structural block diagram of a battery charging data detection device in one embodiment;

[0023] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] At present, the sales volume of new energy vehicles maintains a high growth trend. According to the latest data, from January to June 2024, the sales volume of new energy vehicles in my country reached 4.944 million units, a year-on-year growth rate of 32%. The sustained rapid growth of the new energy vehicle market and the wide acceptance of consumers have driven the penetration rate of the new energy market to continue to rise, indicating that new energy vehicles are gradually becoming the mainstream of the market. As the acceptance of new energy vehicles gradually increases, the attention to the safety and health of new energy batteries is also increasing. High-end models continue to make breakthroughs in battery life and other aspects, battery capacity is rapidly increasing, and the pure electric range generally reaches 550-700 kilometers. In terms of charging and energy replenishment, cutting-edge technologies such as 800V fast charging have also made breakthroughs and have been actually applied in design and production. Therefore, battery safety and health monitoring has been regarded by users as an important criterion for choosing new energy vehicles.

[0026] At present, companies' monitoring of the safety and health of new energy batteries mainly focuses on the monitoring of the current attribute indicators of the battery. For example, by monitoring the internal resistance of the battery, charging and discharging indicators, self-discharge efficiency, temperature, physical deformation and other indicators, the safe and healthy status of the battery can be identified. However, the above-mentioned battery safety and health monitoring lacks a health monitoring and diagnosis mechanism for battery charging-related operation behaviors during the user's use of the vehicle. For example, the frequency of charging, the frequency of using fast charging, the distribution of remaining power during charging, etc. Although these indicators do not directly affect the safety and health of the battery in the short term, they have an important impact on the safety performance and life of the battery in the long run. For example, high-frequency fast charging for one year (charging more than 3 times a day) will cause the battery power to decay faster and reduce the battery life.

[0027] The embodiment of the present application provides a battery charging data detection method, which obtains multi-dimensional charging data of the vehicle to be detected through the Internet of Vehicles, analyzes the battery charging behavior of the user during the use of the vehicle based on the multi-dimensional charging data, and obtains the battery charging data detection result. According to the battery charging data detection result, the risk behavior is promptly prompted and corrected, thereby improving the safety and health of the battery through reasonable battery charging behavior.

[0028] The battery charging data detection method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the vehicle end 102 communicates with the server 104 through a communication network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the multi-dimensional charging data of the vehicle to be detected within a preset time period from the vehicle end 102; based on the multi-dimensional charging data, the basic detection index corresponding to each dimension is determined; according to the index detection model corresponding to each dimension, the basic detection index of the corresponding dimension is corrected to obtain the corrected detection index corresponding to each dimension; according to the corrected detection index corresponding to each dimension, the battery charging data detection result of the vehicle to be detected is generated. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0029] In one embodiment, Figure 2 As shown, a battery charging data detection method is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0030] Step 201, obtaining multi-dimensional charging data of a vehicle to be detected within a preset time period.

[0031] The new energy vehicle transmits the multi-dimensional charging data of the vehicle to the server through the vehicle networking system. The server can also obtain multi-dimensional charging data from the new energy vehicle through the vehicle network system. Among them, the vehicle to be detected is the new energy vehicle corresponding to the multi-dimensional charging data. The multi-dimensional charging data includes: the number of charging times, the power deficit margin at the beginning of charging, the power feeding margin at the end of charging, the number of fast charging times and the number of slow charging times. Among them, the number of charging times is: the number of charging times of the vehicle battery; the power deficit margin is: the remaining power of the battery at the beginning of charging the vehicle; the power feeding margin is: the remaining power of the battery at the end of charging the vehicle; the number of fast charging times is: the number of times the vehicle battery is charged using fast charging; the number of slow charging times is: the number of times the vehicle battery is charged using full charging. The preset time period can be set according to the actual detection requirements. For example, when the battery charging data of the vehicle to be detected within one year needs to be detected, the corresponding preset time period is one year; when the battery charging data of the vehicle to be detected within one month needs to be detected, the corresponding preset time period is one month. This embodiment does not specifically limit the setting of the preset time period, as long as it can meet the actual use requirements.

[0032] Step 202: Determine the basic detection index corresponding to each dimension based on the multi-dimensional charging data.

[0033] When the multi-dimensional charging data includes: the number of charging times, the power deficit at the beginning of charging, the power supply balance at the end of charging, the number of fast charging times, and the number of slow charging times, the basic detection index corresponding to each dimension includes: the charging times index corresponding to the charging times dimension; the power deficit index corresponding to the power deficit balance dimension; the power supply balance index corresponding to the power supply balance dimension; the fast charging times index corresponding to the fast charging times dimension; and the slow charging times index corresponding to the slow charging times dimension. When calculating the basic detection index corresponding to each dimension, different calculation rules are pre-set for charging data of different dimensions. The charging data of each dimension determines the basic detection index of the corresponding dimension through the pre-set calculation rules of the corresponding dimension.

[0034] Step 203, correcting the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension, to obtain the corrected detection index corresponding to each dimension.

[0035] For each dimension of charging data, a corresponding index detection model is pre-trained. For example: for the number of charges, a charging number index detection model is pre-trained; for the power shortage margin, a power shortage margin index detection model is pre-trained; for the feeding margin, a feeding margin index detection model is pre-trained; for the fast charging number, a fast charging number index detection model is pre-trained; for the slow charging number, a slow charging number index detection model is pre-trained. The index detection model of each dimension is used to detect whether the charging data of the corresponding dimension matches the corresponding basic detection index. If not, the basic detection index of the corresponding dimension is corrected to obtain the corrected detection index of the corresponding dimension; if it matches, the basic detection index of the corresponding dimension is directly used as the corrected detection index. For example: the charging number index detection model is used to detect whether the charging number and the charging number index calculated based on the charging number match. If not, the charging number index is corrected to obtain the corrected charging number index; if it matches, the charging number index is directly used as the corrected charging number index. The data processing method of the index detection model of each dimension is the same, only for charging data of different dimensions.

[0036] Step 204 : generating a battery charging data detection result of the vehicle to be detected according to the calibrated detection index corresponding to each dimension.

[0037] After determining the correction detection index corresponding to each dimension, the correction detection index of each dimension is integrated into a comprehensive detection index. The integration into a comprehensive detection index can be a weighted summation method or a direct summation method, which is not specifically limited in this embodiment. The battery charging data detection result of the vehicle to be detected is represented by a comprehensive detection index. Based on the score of the comprehensive detection index, the charging behavior of the vehicle to be detected within a preset time period can be accurately evaluated, thereby more accurately evaluating the battery health status.

[0038] The above-mentioned battery charging data detection method obtains the multi-dimensional charging data of the vehicle to be detected within a preset time period, and determines the basic detection index corresponding to each dimension based on the multi-dimensional charging data; then corrects the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension, and obtains the corrected detection index corresponding to each dimension, and finally generates the battery charging data detection result of the vehicle to be detected based on the corrected detection index corresponding to each dimension. By evaluating and detecting the multi-dimensional charging data, the battery charging data detection result can be accurately determined, and further through the battery charging data detection result, the battery health status can be more accurately evaluated.

[0039] In one embodiment, Figure 3 As shown, a basic detection index calculation method is provided, comprising the following steps:

[0040] Step 301, determining a charging times index according to the charging times and a charging times reference value.

[0041] A charging number reference value is pre-set, and the charging number reference value indicates the number of charging times that does not affect the safety and health of the battery. The charging number reference value can be customized according to the battery type and vehicle type. Specifically, the charging number CN of the vehicle to be tested within one year is obtained, and the charging number reference value CZ is set; if the charging number CN is greater than the charging number reference value CZ, the charging number index C is equal to 0; if the charging number CN is less than or equal to the charging number reference value CZ, the charging number index C=((CZ-CN)÷CZ)×100. For example, assuming that the charging number reference value is 266 times, the charging number of the vehicle to be tested within one year is obtained to be 300 times, and the charging number index is equal to 0 at this time; assuming that the charging number reference value is 266 times, the charging number of the vehicle to be tested within one year is obtained to be 200 times, and the charging number index is equal to ((266-200)÷266)×100=24.8. The fewer the charging times, the higher the charging number index, and the higher the charging number index indicates the healthier the charging behavior.

[0042] Step 302, determining a low-power margin index according to the low-power margin and the low-power margin reference value.

[0043] A power deficit reference value is pre-set, and the power deficit reference value indicates the power deficit that does not affect the safety and health of the battery. The power deficit reference value can be customized according to the battery type and vehicle type. Specifically, the power deficit of the vehicle to be tested at the beginning of each charging within one year is obtained, and the average power deficit HN is calculated. Among them, the power deficit can be expressed as a percentage, for example, the power deficit at the beginning of charging is 20%. Set the power deficit reference value HZ, then the power deficit index H = 100-(HN×HZ). For example, assuming that the power deficit reference value is 100, the power deficit at the beginning of each charging of the vehicle to be tested within one year is obtained, and the average power deficit is calculated to be 20%. At this time, the power deficit index is equal to 100-(20%×100)=80. The smaller the power deficit, the higher the power deficit index, and the higher the power deficit index indicates the healthier the charging behavior.

[0044] Step 303: determine a power margin index according to the power margin and the power margin reference value.

[0045] A feed margin reference value is set in advance, and the feed margin reference value indicates the feed margin that does not affect the safety and health of the battery. The feed margin reference value can be customized according to the battery type and vehicle type. Specifically, the feed margin of the vehicle to be tested at the end of each charging within a year is obtained, and the feed margin mean FN is calculated. Among them, the feed margin can be expressed as a percentage, for example, the feed margin at the end of charging is 95%. Set the feed margin reference value FZ, then the feed margin index F = FN × FZ. For example, assuming that the feed margin reference value is 100, the feed margin of the vehicle to be tested at the end of each charging within a year is obtained, and the feed margin mean is calculated to be 93%. At this time, the feed margin index is equal to 93% × 100 = 93. The larger the feed margin, the higher the feed margin index, and the higher the feed margin index indicates the healthier the charging behavior.

[0046] Step 304, determining a fast charge frequency index according to the fast charge frequency and the fast charge frequency reference value.

[0047] A fast charge number reference value is pre-set, and the fast charge number reference value indicates the number of fast charges that does not affect the safety and health of the battery. The fast charge number reference value can be customized according to the battery type and vehicle type. Specifically, the number of fast charges QN of the vehicle to be tested within one year is obtained, and the fast charge number reference value QZ is set; if the fast charge number QN is greater than the fast charge number reference value QZ, the fast charge number index Q is equal to 0; if the fast charge number QN is less than or equal to the fast charge number reference value QZ, the fast charge number index Q=((QZ-QN)÷QZ)×100. For example, assuming that the fast charge number reference value is 104 times, the number of fast charges of the vehicle to be tested within one year is obtained to be 150 times, and the fast charge number index is equal to 0 at this time; assuming that the fast charge number reference value is 104 times, the number of fast charges of the vehicle to be tested within one year is obtained to be 70 times, and the fast charge number index is equal to ((104-70)÷104)×100=32.7. The fewer the fast charging times, the higher the fast charging index. A higher fast charging index indicates healthier charging behavior.

[0048] Step 305: Determine a slow charge number index according to the slow charge number and the slow charge number reference value.

[0049] The slow charge number reference value is pre-set, and the slow charge number reference value indicates the slow charge number that does not affect the safety and health of the battery. The slow charge number reference value can be customized according to the battery type and vehicle type. Specifically, the number of slow charges NN of the vehicle to be tested within one year is obtained, and the slow charge number reference value NZ is set; if the slow charge number NN is greater than the slow charge number reference value NZ, the slow charge number index N is equal to 100; if the slow charge number NN is less than or equal to the slow charge number reference value NZ, the slow charge number index N=(1-(NZ-NN)÷NZ)×100. For example, assuming that the slow charge number reference value is 52 times, the number of slow charges of the vehicle to be tested within one year is 60 times, and the slow charge number index is equal to 100; assuming that the slow charge number reference value is 52 times, the number of slow charges of the vehicle to be tested within one year is 30 times, and the slow charge number index is equal to (1-(52-30)÷52)×100=57.7. The more slow charging times, the higher the slow charging index. The higher the slow charging index, the healthier the charging behavior.

[0050] Among them, the basic detection index corresponding to the charging times dimension is the charging times index; the basic detection index corresponding to the power shortage margin dimension is the power shortage margin index; the basic detection index corresponding to the power feeding margin dimension is the power feeding margin index; the basic detection index corresponding to the fast charging times dimension is the fast charging times index; the basic detection index corresponding to the slow charging times dimension is the slow charging times index.

[0051] This embodiment uses multi-dimensional charging data to calculate the basic detection index of each dimension respectively. The multi-dimensional basic detection index can more comprehensively reflect the charging data of the vehicle to be tested, more accurately evaluate the user's charging behavior, and based on the multi-dimensional basic detection index, it can more accurately evaluate the battery health status.

[0052] In one of the embodiments, after determining the basic detection index corresponding to each dimension, it is necessary to correct the basic detection index of the corresponding dimension through a pre-trained index detection model corresponding to each dimension to obtain a corrected detection index for each dimension.

[0053] Specifically, for the number of charges, a charging number index detection model is pre-trained; for the low power margin, a low power margin index detection model is pre-trained; for the feeding margin, a feeding margin index detection model is pre-trained; for the number of fast charges, a fast charging number index detection model is pre-trained; for the number of slow charges, a slow charging number index detection model is pre-trained. Input the charging data of the target dimension and the corresponding basic detection index into the pre-trained index detection model of the target dimension to obtain the corrected detection index of the target dimension; the target dimension is any dimension in the multiple dimensions.

[0054] For the number of charging times, a large amount of historical stock data is first obtained, and each historical stock data includes: the number of charging times of the vehicle in a preset time period and the corresponding charging number index. The preset time period is the same as the preset time period of the charging data of the vehicle to be detected in the actual detection. A data set is constructed through a large amount of historical stock data, and a deep learning model is trained through the data set to obtain a pre-trained index detection model corresponding to the number of charging times. Among them, the deep learning model can be a Transformer model, such as BERT, LLaMA, or a self-developed language model. In actual use, the number of charging times and the corresponding charging number index are input into the pre-trained index detection model corresponding to the number of charging times to obtain a corrected charging number index. It can be understood that when the number of charging times does not match the corresponding charging number index, the charging number index is corrected to obtain the corrected charging number index; when the number of charging times matches the corresponding charging number index, the charging number index is directly output, that is, the charging number index is used as the corrected charging number index.

[0055] For the power shortage, a pre-trained index detection model corresponding to the power shortage is obtained, which is the same as the pre-trained index detection model corresponding to the number of charging times obtained above, except for the historical stock data used. For the specific method, please refer to the above limitation, which will not be repeated here. The historical stock data includes: the average power shortage of the vehicle in a preset time period and the corresponding power shortage index. In actual use, the power shortage and the corresponding power shortage index are input into the pre-trained index detection model corresponding to the power shortage to obtain a corrected power shortage index. It can be understood that when the power shortage does not match the corresponding power shortage index, the power shortage index is corrected to obtain a corrected power shortage index; when the power shortage matches the corresponding power shortage index, the power shortage index is directly output, that is, the power shortage index is used as the corrected power shortage index.

[0056] For the power supply margin, a pre-trained index detection model corresponding to the power supply margin is obtained, which is the same as the pre-trained index detection model corresponding to the number of charging times obtained above, except that the historical stock data used is different. For the specific method, please refer to the above limitation, which will not be repeated here. The historical stock data includes: the average power supply margin of the vehicle in a preset time period and the corresponding power supply margin index. In actual use, the power supply margin and the corresponding power supply margin index are input into the pre-trained index detection model corresponding to the power supply margin to obtain the corrected power supply margin index. It can be understood that when the power supply margin does not match the corresponding power supply margin index, the power supply margin index is corrected to obtain the corrected power supply margin index; when the power supply margin matches the corresponding power supply margin index, the power supply margin index is directly output, that is, the power supply margin index is used as the corrected power supply margin index.

[0057] For the number of fast charges, the index detection model corresponding to the pre-trained fast charge number is obtained, which is the same as the index detection model corresponding to the pre-trained charging number obtained above, except for the historical stock data used. Please refer to the above limitations for the specific method, which will not be repeated here. The historical stock data includes: the number of fast charges in the preset time period of the vehicle and the corresponding fast charge number index. In actual use, the number of fast charges and the corresponding fast charge number index are input into the pre-trained fast charge number corresponding to the index detection model to obtain the corrected fast charge number index. It can be understood that when the number of fast charges does not match the corresponding fast charge number index, the fast charge number index is corrected to obtain the corrected fast charge number index; when the number of fast charges matches the corresponding fast charge number index, the fast charge number index is directly output, that is, the fast charge number index is used as the corrected fast charge number index.

[0058] For the number of slow charges, the index detection model corresponding to the pre-trained number of slow charges is obtained, which is the same as the index detection model corresponding to the pre-trained number of charges obtained above, except for the historical stock data used. Please refer to the above limitations for the specific method, which will not be repeated here. The historical stock data includes: the number of slow charges in the preset time period of the vehicle and the corresponding slow charge number index. In actual use, the number of slow charges and the corresponding slow charge number index are input into the pre-trained index detection model corresponding to the number of slow charges to obtain the corrected slow charge number index. It can be understood that when the number of slow charges does not match the corresponding slow charge number index, the slow charge number index is corrected to obtain the corrected slow charge number index; when the slow charge number matches the corresponding slow charge number index, the slow charge number index is directly output, that is, the slow charge number index is used as the corrected slow charge number index.

[0059] In this embodiment, for each dimension, an index detection model corresponding to each dimension is trained respectively, and abnormal data correction is performed on the charging data and the corresponding basic detection index through the index detection model, thereby improving the accuracy of the basic detection index.

[0060] In one embodiment, if Figure 4 As shown, a method for correcting a basic detection index using an index detection model is provided, comprising the following steps:

[0061] The correction method for the charging number index by the index detection model corresponding to the charging number, the correction method for the low-power remainder index by the index detection model corresponding to the feeding remainder, the correction method for the fast charging number index by the index detection model corresponding to the fast charging number, and the correction method for the slow charging number by the index detection model corresponding to the slow charging number are all the same, only the corresponding charging data are different. The following embodiments are illustrated by taking the charging number dimension as an example.

[0062] Step 401 : A pre-trained index detection model of a target dimension determines an index array corresponding to charging data in a preset range based on charging data of the target dimension.

[0063] The pre-trained index detection model of the target dimension is used as an example to illustrate the pre-trained index detection model corresponding to the number of charging times. After the number of charging times and the corresponding charging number index are input into the pre-trained index detection model corresponding to the number of charging times, the index detection model corresponding to the number of charging times will search for the index array of the number of charging times in the preset range corresponding to the currently input number of charging times. For example, the current input number of charging times is 110 times, and the corresponding charging number index is 58.6. Then the index detection model corresponding to the number of charging times will find all the charging number indices corresponding to the charging times of 120-100 times in the historical data to form an index array.

[0064] Step 402: Determine whether the basic detection index needs to be corrected according to the index array and the basic detection index.

[0065] After finding the index array, the arithmetic mean value of all the charging times indexes in the index array is calculated to obtain the arithmetic index average value, and whether the charging times index needs to be corrected is determined based on the arithmetic index average value and the input charging times index. If the absolute value of the difference between the charging times index and the arithmetic index average value is greater than the preset difference threshold, it is determined that the charging times index is abnormal and the charging times index needs to be corrected; if the absolute value of the difference is less than or equal to the preset difference threshold, it is determined that the charging times index is not abnormal and the charging times index does not need to be corrected.

[0066] Step 403: If correction is required, a correction detection index of the target dimension is obtained based on the index array.

[0067] If the charging number index needs to be corrected, the geometric mean of all the charging number indices in the index array is calculated to obtain the geometric index mean, and the geometric index mean is used as the corrected charging number index; if the charging number index does not need to be corrected, the charging number index is directly output, that is, the charging number index is used as the corrected charging number index.

[0068] This embodiment can accurately identify whether the basic detection index needs to be corrected through the index detection model, and when correction is needed, correction is performed through the geometric index average, thereby improving the accuracy of the basic detection index.

[0069] In one embodiment, if Figure 5 As shown, a method for calculating a comprehensive detection index is provided, comprising the following steps:

[0070] Step 501, obtaining the comprehensive weight corresponding to each dimension.

[0071] The comprehensive weight corresponding to each dimension includes: the comprehensive weight of the number of charging times, the comprehensive weight of the power shortage, the comprehensive weight of the power feeding surplus, the comprehensive weight of the number of fast charging times and the comprehensive weight of the number of slow charging times. The sum of the comprehensive weights of the above five dimensions is 1. The comprehensive weight of each dimension is set according to the vehicle type and the battery type. For example, the fast and slow charging behaviors of some vehicle types have a greater impact on the health of the battery, so the comprehensive weight of the number of fast charging times and the comprehensive weight of the number of slow charging times can be set larger; the power shortage surplus of some vehicle types during charging has a greater impact on the health of the battery, so the comprehensive weight of the power shortage surplus can be set larger. The comprehensive weight of each dimension needs to be set according to the actual usage requirements, and this embodiment does not make specific limitations.

[0072] Step 502, determining a comprehensive detection index according to the correction detection index corresponding to each dimension and the comprehensive weight corresponding to each dimension.

[0073] The correction charging times index is A, the comprehensive weight of charging times is a, the correction power shortage index is B, the comprehensive weight of power shortage is k, the correction feeding surplus index is D, the comprehensive weight of feeding surplus is b, the correction fast charging times index is G, the comprehensive weight of fast charging times is u, the correction slow charging times index is I, and the comprehensive weight of slow charging times is m, then the calculation method of the comprehensive detection index E is:

[0074] E=A×a+B×k+D×b+G×u+I×m

[0075] Step 503: Generate a battery charging data detection result of the vehicle to be detected according to the comprehensive detection index.

[0076] The higher the score of the comprehensive detection index, the healthier the battery charging data and the healthier the charging behavior. The comprehensive detection index represents the battery charging data test results of the vehicle to be tested. Based on the score of the comprehensive detection index, the charging behavior of the vehicle to be tested within the preset time period can be accurately evaluated, thereby more accurately evaluating the battery health status.

[0077] In one embodiment, after the comprehensive detection index is determined, the battery risk level and processing strategy of the vehicle to be detected can also be determined according to the comprehensive detection index and the preset evaluation rules. The preset evaluation rules are pre-set, and the preset evaluation rules include multiple comprehensive detection index ranges and the battery risk level and processing strategy corresponding to each range. After the comprehensive detection index is determined, the corresponding comprehensive detection index range is determined according to the comprehensive detection index, and the corresponding battery risk level and processing strategy are found according to the comprehensive detection index range. For example, the comprehensive detection index range is 90-100, the corresponding battery risk level is level 1, and the processing strategy is the battery maintenance strategy; the comprehensive detection index range is 70-89, the corresponding battery risk level is level 2, and the processing strategy is the battery safety warning; the comprehensive detection index range is 60-69, the corresponding battery risk level is level 3, and the processing strategy is the battery diagnosis instruction; the comprehensive detection index range is 40-59, the corresponding battery risk level is level 4, and the processing strategy is the battery maintenance strategy; the comprehensive detection index range is 0-39, the corresponding battery risk level is level 5, and the processing strategy is the battery replacement strategy. The lower the battery risk level, the higher the segment range of the comprehensive detection index, which means the healthier the charging behavior of the vehicle battery. After determining the battery risk level and treatment strategy of the vehicle to be tested, the corresponding comprehensive detection index, battery risk level and treatment strategy will be sent to the after-sales system. The after-sales system will push the comprehensive detection index, battery risk level and treatment strategy to the vehicle to be tested through the Internet of Vehicles, thereby guiding users to adjust their charging behavior and provide battery health. When the battery risk level is greater than level 3, battery maintenance and repair suggestions will also be pushed to the vehicle to be tested, thereby guiding users to go to designated service points for battery maintenance, repair or replacement.

[0078] In a specific embodiment, Figure 6 As shown, a principle block diagram of a battery charging data detection method is provided, which consists of three parts: a battery behavior data calculator, a battery behavior health comprehensive diagnostic device, and a battery behavior health instruction distributor. The battery behavior data calculator obtains the multi-dimensional charging data of the vehicle to be detected from the Internet of Vehicles system, that is, the battery behavior data, and calculates the basic detection index of each dimension through the analysis model. The battery behavior health comprehensive diagnostic device integrates and weights the basic detection index of each dimension and outputs a comprehensive detection index. The battery behavior health instruction distributor divides the comprehensive detection index into segments and grades it, and performs segment-level matching on the comprehensive detection index output by the battery behavior health comprehensive diagnostic device, determines the response processing strategy according to the matching result, and sends the response processing strategy to the after-sales system to complete the battery behavior health diagnosis of the vehicle to be detected.

[0079] For the battery behavior data calculator, this module mainly has two functions. One is to connect with the Internet of Vehicles system to obtain multi-dimensional charging data of the vehicle to be tested, that is, battery behavior data. The second is to build a battery behavior health dimension analysis model through the Transformer pre-training model (such as BERT, LLaMA or self-developed language model) and a unified model framework, which includes: charging number analysis model, power shortage balance distribution analysis model, feeding balance distribution analysis model, fast charging behavior analysis model, slow charging behavior analysis model. Through the above five-dimensional analysis model, the battery behavior data is calculated to determine the basic detection index of each dimension.

[0080] The architecture of the battery behavior health dimension analysis model is described. Through a unified "calculation + discrimination" structure, the analysis model of each dimension is trained and constructed to realize the calculation of basic detection index and accurate and intelligent identification calibration. The architecture mainly includes two parts. One is the Transformer pre-training model, which uses historical stock charging times data, historical stock power shortage balance distribution data, historical stock feeding balance distribution data, historical stock fast charging times data and historical stock slow charging times data for enhanced training to obtain the index detection model of the corresponding dimension. The second is the battery behavior index calculator, which calculates the charging times index, power shortage balance index, feeding balance index, fast charging times index and slow charging times index according to the battery behavior data. When calculating the index of the above five dimensions, the calculator corresponding to each dimension uses a different calculation algorithm, and inputs the calculated basic detection index of each dimension into the index detection model of the corresponding dimension for discrimination calibration, and outputs the final corrected detection index.

[0081] The operating logic of the battery behavior health dimension analysis model:

[0082] In the first step, the analysis model of each dimension presets the benchmark value, among which the benchmark values ​​can be uniformly maintained regularly. The preset benchmark values ​​include: charging times benchmark value CZ, power-off balance benchmark value HZ, power-feeding balance benchmark value FZ, fast charging times benchmark value QZ, and slow charging times benchmark value NZ. Among them, the power-off balance benchmark value HZ and power-feeding balance benchmark value FZ default to 100. For automotive products whose battery power calculation method is not a percentage, the percentage can be obtained by calculating the average battery remaining and the total battery capacity. The charging times benchmark value CZ, the fast charging times benchmark value QZ, and the slow charging times benchmark value NZ can be customized according to the vehicle type and battery type.

[0083] In the second step, the analysis model of each dimension serves as a continuously running evaluation service, regularly receiving battery behavior data input from the Internet of Vehicles system, including: charging times CN, average power reserve HN, average power reserve FN, fast charging times QN, and slow charging times NN.

[0084] In the third step, the analysis model of each dimension uses the preset reference value in the first step and the battery behavior data received in the second step to calculate the charging times index C, the low power index H, the feeding index F, the fast charging times index Q and the slow charging times index N, and outputs them to the index detection model of the corresponding dimension. The specific calculation method is as follows:

[0085] Charging times index C: The charging times CN obtained from the car networking system is input into the charging times analysis model. The analysis model uses the charging times reference value CZ for deviation calculation. The farther the deviation value is, the higher the charging times index C is. The higher the charging times index C is, the healthier the charging behavior is. Among them, the charging times reference value CZ is set according to different models and is a positive integer. The charging times reference value CZ for one year is usually set to 266 times. If CZ < CN, the charging times index C is 0; if CZ ≥ CN, the charging times index C = ((CZ-CN) ÷ CZ) × 100. That is, when the charging times CN is less than or equal to the charging times reference value CZ, the farther from the reference value, the higher the charging times index C is; when the charging times CN is greater than the charging times reference value CZ, the charging times have exceeded the risk threshold, and the charging times index C is 0.

[0086] Low power margin index H: The low power margin mean value HN obtained from the Internet of Vehicles system is input into the low power margin distribution analysis model. The analysis model uses the low power margin reference value HZ for deviation calculation. Low power margin index H = 100-(HN×HZ). That is, the smaller the low power margin, the higher the low power margin index H. The higher the low power margin index H, the healthier the charging behavior.

[0087] Feed margin index F: The feed margin index F is opposite to the power deficit margin index H. When charging is completed, the higher the remaining power, the higher the feed margin index F. The feed margin index F is equal to the percentage of the remaining power after charging is completed. The feed margin mean FN obtained from the Internet of Vehicles system is input into the feed margin distribution analysis model, and the feed margin index F = FN × FZ.

[0088] Fast charging index Q: The fast charging times QN obtained from the car networking system is input into the fast charging behavior analysis model. The analysis model uses the fast charging times reference value QZ for deviation calculation. The farther the deviation value is, the higher the fast charging times index Q is. The higher the fast charging times index Q is, the healthier the charging behavior is. Among them, the fast charging times reference value QZ is set according to different models and is a positive integer. The fast charging times reference value QZ for one year is usually set to 104 times. If QZ < QN, the fast charging times index Q is 0; if QZ ≥ QN, the fast charging times index Q = ((QZ-QN) ÷ QZ) × 100. That is, when the fast charging times QN is less than or equal to the fast charging times reference value QZ, the farther from the reference value, the higher the fast charging times index Q is; when the fast charging times QN is greater than the fast charging times reference value QZ, the fast charging times have exceeded the risk threshold, and the fast charging times index Q is 0.

[0089] Slow charging times index N: The slow charging times NN obtained from the car networking system is input into the slow charging behavior analysis model. The analysis model uses the slow charging times reference value NZ for deviation calculation. The closer the deviation value is, the higher the slow charging times index N is. The higher the slow charging times index N is, the healthier the charging behavior is. Among them, the slow charging times reference value NZ is set according to different models and is a positive integer. The slow charging times reference value NZ for one year is usually set to 52 times. If NZ < NN, the slow charging times index N is 100; if NZ ≥ NN, the slow charging times index N = (1-(NZ-NN) ÷ NZ) × 100. That is, when the slow charging times NN is less than or equal to the slow charging times reference value NZ, the farther from the reference value, the lower the slow charging times index N is; when the slow charging times NN is greater than the slow charging times reference value NZ, the slow charging times are very healthy and the slow charging times index N is 100.

[0090] For the battery behavior health comprehensive diagnostics, this module has two main functions. The first is to maintain and manage the comprehensive weight of each dimension through the behavior index weight configuration function. The comprehensive weight of each dimension is customized according to the vehicle type and battery type. The maximum value is 1 and the minimum value is 0. The sum of the comprehensive weights of all dimensions must be equal to 1. The second is to receive the charging number index C, the power shortage index H, the feeding margin index F, the fast charging number index Q and the slow charging number index N output by the battery behavior data calculator, and integrate and calculate the comprehensive weight of each index to output the battery comprehensive health index E.

[0091] Among them, the comprehensive weight of charging times is a, the comprehensive weight of power deficit is k, the comprehensive weight of power feeding is b, the comprehensive weight of fast charging times is u, and the comprehensive weight of slow charging times is m.

[0092] Battery comprehensive health index E = C × a + H × k + F × b + Q × u + N × m

[0093] For the battery behavior health instruction distributor, this module has two main functions. One is to perform segmentation and grading according to the numerical range of the battery comprehensive health index to form a segmentation grading table. The other is to receive the battery comprehensive health index E output by the battery behavior health comprehensive diagnostic device and match it with the segmentation grading table to determine the risk level of the vehicle to be tested and the corresponding processing strategy, and send the processing instructions to the after-sales system through the long connection instruction channel of the processing strategy distribution module, and save the issued instruction information at the same time to complete the instruction distribution operation.

[0094] The specific classification table is as follows:

[0095]

[0096]

[0097] Specifically, the segmentation and grading table can be divided into corresponding segmentation and grading according to the after-sales service system, or it can be divided into segmentation and grading according to the general service model. The lower the risk level, the higher the segment range of the battery comprehensive health index, which means the charging behavior of the vehicle battery is healthier, and vice versa.

[0098] After obtaining the risk level of the vehicle to be tested and the corresponding processing strategy, call the external system, such as the after-sales system or other communication platform, to issue information instructions and complete a battery behavior health test for the vehicle to be tested. The battery behavior health instruction distributor realizes the automatic issuance of the processing strategy, so as to timely remind users to pay attention to charging behavior and improve battery health.

[0099] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0100] Based on the same inventive concept, the embodiment of the present application also provides a battery charging data detection device for implementing the battery charging data detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more battery charging data detection device embodiments provided below can refer to the limitations of the battery charging data detection method above, and will not be repeated here.

[0101] In one embodiment, Figure 7 As shown, a battery charging data detection device is provided, comprising: an acquisition module 100, an index calculation module 200, a correction module 300 and a result generation module 400, wherein:

[0102] The acquisition module 100 is used to acquire multi-dimensional charging data of the vehicle to be detected within a preset time period;

[0103] An index calculation module 200, configured to determine a basic detection index corresponding to each dimension according to the multi-dimensional charging data;

[0104] A correction module 300 is used to correct the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension, so as to obtain a corrected detection index corresponding to each dimension;

[0105] The result generating module 400 is used to generate the battery charging data detection result of the vehicle to be detected according to the correction detection index corresponding to each dimension.

[0106] The multi-dimensional charging data includes: the number of charging times, the power deficit remaining at the beginning of charging, the power supply remaining at the end of charging, the number of fast charging times, and the number of slow charging times.

[0107] The index calculation module 200 is also used to determine the charging number index according to the charging number and the charging number reference value; determine the power shortage margin index according to the power shortage margin and the power shortage margin reference value; determine the feeding margin index according to the feeding margin and the feeding margin reference value; determine the fast charging number index according to the fast charging number and the fast charging number reference value; determine the slow charging number index according to the slow charging number and the slow charging number reference value.

[0108] The correction module 300 is also used to input the charging data of the target dimension and the corresponding basic detection index into a pre-trained index detection model of the target dimension to obtain a correction detection index of the target dimension; the target dimension is any dimension in the multiple dimensions.

[0109] The correction module 300 is also used for the pre-trained index detection model of the target dimension to determine the index array corresponding to the charging data in a preset range based on the charging data of the target dimension; determine whether the basic detection index needs to be corrected according to the index array and the basic detection index; if correction is required, obtain the corrected detection index of the target dimension based on the index array.

[0110] The result generation module 400 is also used to obtain the comprehensive weight corresponding to each dimension; determine the comprehensive detection index according to the correction detection index corresponding to each dimension and the comprehensive weight corresponding to each dimension; and generate the battery charging data detection result of the vehicle to be detected according to the comprehensive detection index.

[0111] The result generation module 400 is also used to determine the battery risk level and processing strategy of the vehicle to be tested according to the comprehensive detection index and preset evaluation rules.

[0112] Each module in the above-mentioned battery charging data detection device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0113] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data used or generated when running a battery charging data detection method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a battery charging data detection method is implemented.

[0114] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program. When the processor executes the computer program, any one of the battery charging data detection methods in the above embodiments is implemented.

[0116] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the battery charging data detection methods in the above embodiments is implemented.

[0117] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, any one of the battery charging data detection methods in the above embodiments is implemented.

[0118] It should be noted that the charging data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0120] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A battery charging data detection method, characterized in that: The method comprises: Obtain multi-dimensional charging data of the vehicle to be tested within a preset time period; Determine a basic detection index corresponding to each dimension according to the multi-dimensional charging data; Correcting the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension to obtain a corrected detection index corresponding to each dimension; The battery charging data detection result of the vehicle to be detected is generated according to the corrected detection index corresponding to each dimension.

2. The method according to claim 1, characterized in that: The multi-dimensional charging data includes: the number of charging times, the power deficit remaining at the beginning of charging, the power supply remaining at the end of charging, the number of fast charging times, and the number of slow charging times.

3. The method according to claim 2, characterized in that Determining the basic detection index corresponding to each dimension according to the multi-dimensional charging data includes: Determining a charging frequency index according to the charging frequency and the charging frequency reference value; Determining a power shortage margin index according to the power shortage margin and the power shortage margin reference value; Determining a power feeding margin index according to the power feeding margin and the power feeding margin reference value; Determining a fast charge frequency index according to the fast charge frequency and the fast charge frequency benchmark value; A slow charging number index is determined according to the slow charging number and the slow charging number reference value.

4. The method according to claim 1, characterized in that: The step of correcting the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension to obtain the corrected detection index corresponding to each dimension includes: The charging data of the target dimension and the corresponding basic detection index are input into the pre-trained index detection model of the target dimension to obtain the corrected detection index of the target dimension; the target dimension is any dimension among multiple dimensions.

5. The method according to claim 4, characterized in that The step of inputting the charging data of the target dimension and the corresponding basic detection index into the pre-trained index detection model of the target dimension to obtain the corrected detection index of the target dimension includes: The pre-trained index detection model of the target dimension determines an index array corresponding to the charging data in a preset range based on the charging data of the target dimension; Determining whether the basic detection index needs to be corrected according to the index array and the basic detection index; If correction is required, a correction detection index of the target dimension is obtained based on the index array.

6. The method according to claim 1, characterized in that Generating the battery charging data detection result of the vehicle to be detected according to the correction detection index corresponding to each dimension includes: Get the comprehensive weight corresponding to each dimension; Determine a comprehensive detection index according to the correction detection index corresponding to each dimension and the comprehensive weight corresponding to each dimension; A battery charging data detection result of the vehicle to be detected is generated according to the comprehensive detection index.

7. The method according to claim 6, characterized in that The method further comprises: According to the comprehensive detection index and preset evaluation rules, the battery risk level and processing strategy of the vehicle to be detected are determined.

8. A battery charging data detection device, characterized in that: The device comprises: An acquisition module is used to acquire multi-dimensional charging data of the vehicle to be detected within a preset time period; An index calculation module, used to determine a basic detection index corresponding to each dimension according to the multi-dimensional charging data; A correction module, used to correct the basic detection index of the corresponding dimension according to the index detection model corresponding to each dimension, so as to obtain a corrected detection index corresponding to each dimension; The result generating module is used to generate the battery charging data detection result of the vehicle to be detected according to the correction detection index corresponding to each dimension.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images