Evaluation method and device of equipment working condition behavior, equipment and medium

Abstract

The invention discloses an equipment working condition behavior evaluation method and device, equipment and a medium, and the method comprises the steps: extracting a first feature value of a key feature item corresponding to each working condition behavior through employing battery related data of target equipment under at least one working condition behavior, the first feature value of the key feature item corresponding to the working condition behavior represents the parameter feature of the battery of the target equipment under the working condition behavior; reference feature values corresponding to the key feature items are obtained, and the reference feature values are obtained by analyzing second feature values of the key feature items corresponding to multiple pieces of reference equipment with different battery health degrees; and comparing the first feature value of each key feature item with the corresponding reference feature value to determine whether the working condition behavior corresponding to each key feature item affects the battery health degree of the target equipment or not. According to the scheme, whether the working condition behavior of the target equipment affects the battery health degree can be qualitatively evaluated.

Description

Technical Field

[0001] The present application relates to the field of batteries, and particularly to a method, device, equipment and medium for evaluating the operating condition behavior of a device. Background Art

[0002] The battery health is the ratio of the current capacity of the battery to its original designed capacity, which is an indicator to measure the battery performance and capacity status, usually expressed in percentage. The battery health has an important impact on the battery's endurance time and charging speed, and is very important for improving the user experience. However, in the prior art, it is impossible to qualitatively analyze whether the specific operating condition behavior of the device will affect the battery health. Summary of the Invention

[0003] The present application provides at least a method, device, equipment and medium for evaluating the operating condition behavior of a device, which can qualitatively evaluate whether the operating condition behavior of the target device affects the battery health.

[0004] The present application provides a method for evaluating the operating condition behavior of a device, including: based on the battery-related data of the target device under at least one operating condition behavior, extracting the first characteristic value of each key characteristic item corresponding to each operating condition behavior, where the first characteristic value of the key characteristic item corresponding to the operating condition behavior characterizes the parameter characteristics of the battery of the target device under the operating condition behavior; and obtaining the reference characteristic value corresponding to each key characteristic item, where the reference characteristic value is obtained by analyzing the second characteristic values of the key characteristic items corresponding to multiple reference devices with different battery health levels; respectively comparing the first characteristic value of each key characteristic item with the corresponding reference characteristic value to determine whether the operating condition behavior corresponding to each key characteristic item affects the battery health of the target device.

[0005] In the above solution, by analyzing the characteristic values of the reference devices with different battery health levels, it is clear under what circumstances the characteristic values will affect the battery health, and the reference characteristic value indicating whether it affects the battery health can be obtained, which is used to compare with the first characteristic value of the target vehicle, so as to qualitatively evaluate whether the operating condition behavior of the target device affects the battery health.

[0006] In some embodiments, the battery-related data under operating conditions includes the battery time-series data of several battery parameters respectively under operating conditions; the battery time-series data of battery parameters includes the parameter values of battery parameters at multiple historical moments when the operating conditions occur; based on the battery-related data of the target device under at least one operating condition respectively, the first feature value of the key feature item corresponding to each operating condition is extracted, including: for each operating condition, dividing the several battery time-series data into at least one group of time-series data groups corresponding to the operating condition, and each group of time-series data groups includes the battery time-series data of at least one battery parameter; for each group of time-series data corresponding to the operating condition, performing at least one statistic on the time-series data group under the operating condition to obtain the first feature value of at least one key feature item corresponding to the operating condition.

[0007] In the above solution, at least one statistical method is adopted to extract key features from the data, which can be used to achieve qualitative judgment.

[0008] In some embodiments, the first feature value of the key feature item includes at least one of the following: the time characterization feature value and the parameter value characterization feature value corresponding to the time-series data group. The time characterization feature value is obtained by performing time statistics on the battery time-series data in the time-series data group, and the parameter value characterization feature value is obtained by performing statistics on the parameter values included in the battery time-series data in the time-series data group.

[0009] In the above solution, two means of feature extraction are provided, namely, directly performing statistics on the parameter values of the time-series data and performing time statistics on the time-series data, which can flexibly extract key features to reflect the operating conditions of the device.

[0010] In some embodiments, before extracting the first feature value of the key feature item corresponding to each operating condition based on the battery-related data of the target device under at least one operating condition respectively, it further includes: obtaining the original battery data collected from the battery of the target device, and the original battery data includes multiple parameter values of several battery parameters corresponding to different historical moments in the first historical period; based on the operating conditions of the target device in the first historical period, dividing the original battery data to obtain the battery-related data under each operating condition, where the battery-related data under the operating condition includes the parameter values of each battery parameter at multiple historical moments when the operating condition occurs.

[0011] In the above solution, the original data is divided into battery-related data corresponding to each operating condition, and then each operating condition can be analyzed separately to achieve qualitative evaluation of different operating conditions.

[0012] In some embodiments, before obtaining the first eigenvalue of each key feature item corresponding to each operating condition behavior based on battery-related data of the target device under at least one operating condition behavior, the method further includes: constructing a battery feature item set, where the battery feature item set includes a plurality of battery feature items; analyzing the relationship between each battery feature item in the battery feature item set and the battery health; and selecting, based on the relationship, the battery feature items related to the battery health from the battery feature item set as the key feature items.

[0013] In the above solution, a battery feature item set is constructed in advance, the feature items in the set are screened, and the feature items that affect the battery health are selected to participate in the subsequent qualitative evaluation, which can avoid making invalid evaluations on the feature items that do not affect the battery health and improve the efficiency.

[0014] In some embodiments, obtaining the reference eigenvalue corresponding to each key feature item includes: obtaining the second eigenvalue of each key feature item corresponding to a plurality of reference devices with different battery health levels; clustering the second eigenvalues of each key feature item corresponding to the plurality of reference devices based on the battery health level to obtain a first feature cluster and a second feature cluster, where the first feature cluster includes the second eigenvalues of each key feature item corresponding to the first reference device, and the second feature cluster includes the second eigenvalues of each key feature item corresponding to the second reference device, the first reference device is each reference device belonging to the first battery health level, and the second reference device is each reference device belonging to the second battery health level; for each key feature item, counting the second eigenvalues of each key feature item corresponding to the first reference devices in the first feature cluster to obtain a first statistical value, and counting the second eigenvalues of each key feature item corresponding to the second reference devices in the second feature cluster to obtain a second statistical value; and obtaining the reference eigenvalue corresponding to the key feature item based on the first statistical value and the second statistical value.

[0015] In the above solution, the reference devices are clustered according to the battery health level to distinguish the reference devices with high health level and the reference devices with low health level. On this basis, the differences in the eigenvalues of the reference devices with high and low health levels can be analyzed, so as to obtain the reference eigenvalues for qualitative evaluation.

[0016] In some embodiments, the first statistical value is the cluster center of the second eigenvalues of the key feature item corresponding to the first reference devices in the first feature cluster, and the second statistical value is the cluster center of the second eigenvalues of the key feature item corresponding to the second reference devices in the second feature cluster.

[0017] In the above solution, using the cluster center as the representative of the cluster can accurately represent the eigenvalue situations of the two clusters with high and low health levels, and thus can obtain accurate reference eigenvalues.

[0018] In some embodiments, obtaining a reference feature value corresponding to a key feature item based on a first statistical value and a second statistical value includes: calculating a distance between the first statistical value and the second statistical value as the reference feature value corresponding to the key feature item.

[0019] In the above solution, the distance between the two can represent the performance difference of devices with high and low health levels in terms of key feature items, and thus can be used to distinguish whether the operating conditions of the target device affect the health level.

[0020] In some embodiments, comparing the first feature value of each key feature item with the corresponding reference feature value respectively to determine whether the operating conditions corresponding to each key feature item affect the battery health of the target device includes: in response to the first feature value of the key feature item and the corresponding reference feature value satisfying a first magnitude relationship, determining that the operating conditions corresponding to the key feature item affect the battery health of the target device; in response to the first feature value of the key feature item and the corresponding reference feature value satisfying a second magnitude relationship, determining that the operating conditions corresponding to the key feature item do not affect the battery health of the target device.

[0021] In the above solution, based on the set reference feature value, by judging the magnitude relationship between the first feature value and the reference feature value, a qualitative evaluation of the operating conditions of the target device is realized.

[0022] In some embodiments, the first feature value of a key feature item is determined by the parameter value of the battery parameter corresponding to the key feature item in a second historical time period; after comparing the first feature value of each key feature item with the corresponding reference feature value respectively to determine whether the operating conditions corresponding to each key feature item affect the battery health of the target device, it further includes: in response to determining that the operating conditions corresponding to the key feature item affect the battery health of the target device, analyzing the change of the eigenvalue of the associated time series feature of the key feature item in terms of time series to determine the degree of influence of the operating conditions corresponding to the key feature item on the battery health, where the associated time series feature of the key feature item includes third feature values corresponding to the associated feature items in different time units, the associated feature items are key feature items or other feature items, different time units are within the second historical time period, and the third feature value of the time unit is determined based on the parameter value of the battery parameter corresponding to the associated feature item within the time unit.

[0023] In the above solution, the operating conditions correspond to associated time series features, and analyzing the change of the eigenvalue of the associated time series features can reflect the change of the influence of the corresponding operating conditions on the battery health.

[0024] In some embodiments, the first eigenvalue of a key feature item is obtained by statistically calculating the parameter values of the battery parameters corresponding to the key feature item within a second historical time period; the third eigenvalue of a time unit is obtained by statistically calculating the parameter values of the battery parameters corresponding to the associated feature item within the time unit; the associated timing feature of the key feature item includes the third eigenvalues of the key feature item corresponding to different time units; analyzing the change of the eigenvalue in the timing of the associated timing feature of the key feature item to determine the degree of influence of the operating condition behavior corresponding to the key feature item on the battery health, including: clustering the associated timing feature of the key feature item to determine the frequency change of the operating condition behavior corresponding to the key feature item in the target time period relative to other time periods within the second historical time period; based on the frequency change, determining whether the influence of the operating condition behavior corresponding to the key feature item on the battery health increases or decreases within the target time period.

[0025] In the above solution, by clustering the associated timing feature, the change of the eigenvalue in the timing can be determined, and further, the change of the influence on the battery health in different time periods can be judged.

[0026] In some embodiments, after respectively comparing the first eigenvalue of each key feature item with the corresponding reference eigenvalue to determine whether the operating condition behavior corresponding to each key feature item affects the battery health of the target device, it further includes: providing the user with the evaluation result of the influence of the operating condition behavior corresponding to the key feature item on the battery health; providing the user with the feature data corresponding to the key feature item.

[0027] In the above solution, the evaluation result of the influence and the corresponding feature data can be prompted to the user, so as to facilitate the user to understand the influence of the operating condition behavior on the battery health.

[0028] In some embodiments, the operating condition behavior includes at least one of charging, discharging, and standing still; the battery-related data under the operating condition behavior includes at least one parameter value of several battery parameters respectively when the operating condition behavior occurs, and the several battery parameters include at least one of current, voltage, state of charge, and temperature; the target device is a vehicle.

[0029] The present application provides an evaluation device for the operating conditions and behaviors of a device, including an extraction module, a reference acquisition module, and a comparison module. The extraction module is configured to extract, based on battery-related data of a target device under at least one operating condition and behavior, first feature values of key feature items corresponding to each operating condition and behavior, where the first feature value of the key feature item corresponding to the operating condition and behavior characterizes the parameter features of the battery of the target device under the operating condition and behavior; and, the reference acquisition module is configured to acquire reference feature values corresponding to each key feature item, and the reference feature values are obtained by analyzing second feature values of the key feature items corresponding to a plurality of reference devices with different battery health degrees; the comparison module is configured to compare the first feature value of each key feature item with the corresponding reference feature value respectively to determine whether the operating condition and behavior corresponding to each key feature item affect the battery health degree of the target device.

[0030] The present application provides a computer-readable storage medium, on which program instructions are stored, and when the program instructions are executed by a processor, the above method is implemented.

[0031] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings herein are incorporated into the specification and constitute a part of this specification. These drawings show embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0033] Figure 1 It is a schematic flowchart of a method for evaluating the operating conditions and behaviors of a device provided by some embodiments of the present application; Figure 2 It is a schematic framework diagram of an evaluation device for the operating conditions and behaviors of a device provided by some embodiments of the present application; Figure 3 It is a schematic framework diagram of an electronic device provided by some embodiments of the present application; Figure 4 It is a schematic framework diagram of a computer-readable storage medium provided by some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] The following describes the solutions of the embodiments of the present application in detail with reference to the drawings of the specification.

[0035] In the following description, specific details such as specific subsystem structures, interfaces, and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the present application.

[0036] In this text, the term "and / or" is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, in this text, the character " / " generally indicates that the associated objects before and after are in an "or" relationship. Furthermore, "multiple" in this text means two or more than two. Additionally, the term "at least one" in this text means any one of multiple or any combination of at least two of multiple. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0037] The battery health is the ratio of the current capacity of the battery to its original designed capacity, which is an indicator for measuring the battery performance and capacity status, usually expressed in percentage. The battery health has an important impact on the battery's endurance time and charging speed, and is very important for improving the user experience. It is impossible to qualitatively analyze whether the specific equipment working condition behavior will affect the battery health in the prior art.

[0038] The researchers of this application found that the characterizations of the same characteristic item of devices with different battery healths are different. By analyzing the characteristic items of devices with different healths, it is possible to clarify under what circumstances the characteristic item will affect the battery health, and obtain the threshold value representing the key characteristic item that affects the battery health, which is used to compare with the first characteristic value of the target vehicle, so as to be able to qualitatively evaluate whether the working condition behavior of the target device affects the battery health.

[0039] The evaluation method of the device working condition behavior disclosed in the embodiments of this application can be applied to any device equipped with a battery. For example, the device can be a new energy vehicle, etc. Among them, the type of the battery provided on the device is not limited herein. Exemplarily, it can be a lithium-ion battery, etc.

[0040] Refer to Figure 1 , Figure 1 which is a schematic flow chart of the evaluation method of the device working condition behavior provided by some embodiments of this application. Specifically, the method includes: Step S110: Based on the battery-related data of the target device under at least one working condition behavior respectively, extract the first characteristic value of the key characteristic item corresponding to each working condition behavior.

[0041] Among them, the target device can be any device equipped with a battery. The working condition behavior can represent the working state of the battery provided on the target device.

[0042] In some embodiments, the working condition behavior can include at least one of charging, discharging, and standing still.

[0043] In a specific application scenario, the operating conditions include charging, discharging, and standing still. Further, charging, discharging, and standing still, as operating conditions, can be further divided into multiple sub-operating conditions. Exemplarily, specific sub-operating conditions can be further divided based on charging, discharging, and standing still. For example, charging can be divided into fast charging and normal charging. An operating condition can also be divided from different perspectives to obtain the division results from each perspective. For example, charging can be divided into fast charging and normal charging according to the charging current, and charging can be divided into low-temperature charging and high-temperature charging according to the charging temperature.

[0044] In some embodiments, the battery-related data can include several battery parameters. Among them, the aforementioned battery parameters can include at least one of current, voltage, state of charge, and temperature.

[0045] It can be understood that the battery parameters can be directly collected from the battery. For example, current, voltage, and temperature. Or, the battery parameters can also be indirectly collected, that is, calculated from the directly collected data. For example, the state of charge (SOC, State of Charge).

[0046] In a specific application scenario, the battery set on the target device works continuously for a period of time. During the operation of the battery, its battery parameters can be continuously obtained to get multiple parameter values of the battery parameters. For example, the current, voltage, and temperature at different times are collected during its operation. Further, the state of charge corresponding to each moment is obtained.

[0047] The battery parameters can be associated with the operating conditions. The battery-related data under a certain operating condition can include several battery parameters when this operating condition occurs. For example, the battery-related data of charging can include charging current, charging voltage, charging temperature, and state of charge during charging.

[0048] Each operating condition can correspond to its own key feature items. An operating condition can correspond to several key feature items. For example, charging key feature items, discharging key feature items, standing still key feature items. The key feature items of each operating condition can be determined in advance. The feature values corresponding to each key feature item of the target device can be extracted using the battery-related data of the target device to represent the parameter characteristics of the battery of the target device under each operating condition. Specifically, each operating condition is processed separately. Using the battery-related data of the target device under a certain operating condition, the first feature value of the key feature item corresponding to this operating condition can be extracted, and this first feature value can characterize the parameter characteristics of the battery of the target device when it is in this operating condition.

[0049] In a specific application scenario, taking the charging condition as an example for illustration, the first characteristic values of each charging key characteristic item corresponding to charging are extracted by using the battery-related data of the target device during charging.

[0050] Step S120: Obtain the reference characteristic values corresponding to each key characteristic item.

[0051] Among them, each key characteristic item corresponds to its reference characteristic value, and the reference characteristic value is obtained by analyzing the second characteristic values of the key characteristic items corresponding to multiple reference devices. Among them, the battery health degrees of the multiple reference devices are different. The battery characteristics set on the reference device are the same as or similar to the battery characteristics set on the target device, so that the analysis of the characteristic values of the reference device can be applied to the target device.

[0052] The key characteristic item is a characteristic item that has an association with the battery health degree. Further analyzing the performance of the reference devices with different health degrees on the key characteristic item, that is, the second characteristic value, can clarify under what circumstances the characteristic value of the key characteristic item will affect the battery health degree, and obtain the reference characteristic value of the corresponding key characteristic item. The reference characteristic value can be used to represent the critical value that affects the battery health degree for this key characteristic item.

[0053] Step S130: Compare the first characteristic value of each key characteristic item with the corresponding reference characteristic value respectively to determine whether the working condition behavior corresponding to each key characteristic item affects the battery health degree of the target device.

[0054] For each key characteristic item, by comparing the first characteristic value of the target device with the corresponding reference characteristic value, it can be determined whether the working condition behavior corresponding to this key characteristic item affects the battery health degree of the target device.

[0055] It should be noted that after obtaining the first characteristic value and the corresponding reference characteristic value, the magnitudes of the two can be compared to determine whether the corresponding working condition behavior affects the battery health degree of the target device.

[0056] In some embodiments, in response to the first characteristic value of the key characteristic item and the corresponding reference characteristic value satisfying the first magnitude relationship, it is determined that the working condition behavior corresponding to the key characteristic item affects the battery health degree of the target device. In response to the second characteristic value of the key characteristic item and the corresponding reference characteristic value satisfying the second magnitude relationship, it is determined that the working condition behavior corresponding to the key characteristic item does not affect the battery health degree of the target device.

[0057] The possible magnitude relationships between the first characteristic value and the corresponding reference characteristic value are divided into a first magnitude relationship and a second magnitude relationship. The former corresponds to the working condition behavior affecting the battery health degree of the target device, and the latter corresponds to the working condition behavior not affecting the battery health degree of the target device.

[0058] In a specific application scenario, the first magnitude relationship indicates that the first eigenvalue is greater than or equal to the corresponding reference eigenvalue, while the second magnitude relationship indicates that the first eigenvalue is less than the corresponding reference eigenvalue.

[0059] It should be noted that the first magnitude relationship corresponding to each key feature item is predetermined. The first magnitude relationships corresponding to different key feature items may be different. For example, for feature A, when the first eigenvalue is greater than the corresponding reference eigenvalue, the corresponding operating condition behavior affects the battery health of the target device, while when the first eigenvalue is less than or equal to the corresponding reference eigenvalue, the corresponding operating condition behavior does not affect the battery health of the target device. For feature B, when the first eigenvalue is less than or equal to the corresponding reference eigenvalue, the corresponding operating condition behavior affects the battery health of the target device, while when the first eigenvalue is greater than the corresponding reference eigenvalue, the corresponding operating condition behavior does not affect the battery health of the target device.

[0060] It can be understood that before extracting the first eigenvalue, the key feature items corresponding to each operating condition behavior can be predetermined. There are numerous battery-related feature items, and the feature items that affect the battery health can be selected from them as key feature items.

[0061] In some embodiments, a battery feature item set is constructed, which includes multiple battery feature items. The relationship between each battery feature item in the set and the battery health is analyzed, and based on the foregoing relationship, the battery feature items related to the battery health are selected from the set as key feature items.

[0062] It should be noted that the battery feature item set can be constructed around the operating condition behavior. Exemplarily, the battery feature items corresponding to each operating condition behavior are constructed respectively to form the battery feature item set.

[0063] It can be understood that the method provided by the embodiments of the present application can be executed by the target processing device. Among them, the steps of constructing the battery feature item set, selecting the key feature items, and determining the reference eigenvalue can be executed by other processing devices, and the other processing devices provide data such as key feature items and reference eigenvalues to the target processing device.

[0064] In some application scenarios, DOE (Design of Experiments) comparative analysis experiments can be set up or battery EIS (Electrochemical Impedance Spectroscopy) data can be collected and analyzed to determine whether the battery feature items will affect the battery health. Among them, the battery EIS data can include polarization internal resistance and polarization capacitance.

[0065] In some application scenarios, the key feature items corresponding to charging may include the fast charging ratio and the ambient temperature. The key feature items corresponding to static state may include the minimum static temperature.

[0066] It should be noted that the feature values corresponding to the key feature items can be obtained by a certain feature extraction method from the battery-related data of the actual device under this operating condition behavior. For example, the corresponding first feature value is obtained from the battery-related data of a certain operating condition behavior of the target device, and the corresponding second feature value is obtained from the battery-related data of a certain operating condition behavior of the reference device as described above.

[0067] The feature extraction method corresponding to this key feature item can also be determined in advance. The feature extraction method may include a time range and a data processing method. The time range can be used to limit which time range of battery-related data is used to extract the feature value. The data processing method can be used to limit which battery-related data in the aforementioned time range is processed by what method to obtain the feature value. Further, the data processing method may include which one or several battery parameters in the battery-related data are used for processing, and may also include the processing means for the aforementioned one or several battery parameters. For example, selecting the maximum value, calculating the average value, judging whether it is greater than a threshold, etc.

[0068] In some application scenarios, taking the fast charging ratio as an example, it can be determined that the time range corresponding to this key feature item is the entire life cycle, or one year before the current moment. That is, the battery-related data within the entire life cycle of the device, or the battery-related data within one year before the current moment, is used for feature extraction. The charging current within the aforementioned time range can be selected, and it is judged whether this charging is a fast charge according to the magnitude of the charging current once. The ratio of the number of fast charges to the total number of charges is calculated to obtain the feature value corresponding to the fast charging ratio.

[0069] In some application scenarios, the charging current within the aforementioned time range can be selected, and it is judged whether it is a fast charge according to the magnitude of the charging current. The ratio of the fast charging duration to the total charging duration is statistically calculated to obtain the feature value corresponding to the fast charging ratio.

[0070] In some application scenarios, taking the minimum static temperature as an example, it can be determined that the time range corresponding to this key feature item is the entire life cycle, and the battery-related data within the entire life cycle of the device is used for feature extraction. The static temperature within the aforementioned time range can be selected, the minimum static temperature is selected during one static process, and the average value of all the minimum static temperatures within the aforementioned time range is statistically calculated as the feature value corresponding to the minimum static temperature.

[0071] Further, the key feature items corresponding to the operating condition behavior can be further divided into key feature items corresponding to sub-operating condition behaviors. For example, the fast charging ratio can be associated with fast charging. In the case of such an association, it can be further determined whether the sub-operating condition behavior affects the battery health.

[0072] In some embodiments, before extracting the first eigenvalue from the battery-related data, the method further includes: obtaining the original battery data collected from the battery of the target device; dividing the original battery data based on the operating condition behavior of the target device in the first historical time period to obtain the battery-related data under each operating condition behavior.

[0073] The original battery data includes multiple parameter values of several battery parameters corresponding to different historical moments in the first historical time period.

[0074] Pre-judge the operating condition behavior of the target device in the first historical time period. Exemplarily, the operating condition behavior of the target device can be judged by using the current of the battery. Specifically, when there is no current or almost no current, it can be considered to be in the static state. When the battery current is positive, it can be considered to be in the discharging state. When the current is negative, it can be considered to be in the charging state.

[0075] After the operating condition behavior at different historical moments can be determined, the original battery data can be divided according to the operating condition behavior to obtain the battery-related data under each operating condition behavior. The battery-related data under a certain operating condition behavior includes the parameter values of each battery parameter at multiple historical moments when this operating condition behavior occurs.

[0076] It should be noted that during the operation of the device, the operating condition behavior can switch. For example, the first historical time period can be divided into four parts. The operating condition behavior of the first part is charging, the operating condition behavior of the second part is static, the operating condition behavior of the third part is discharging, and the operating condition behavior of the fourth part is charging. The battery parameter values at the historical moments in the first part and the battery parameter values at the historical moments in the fourth part are divided into the battery-related data corresponding to charging. The battery parameter values at the historical moments in the second part are divided into the battery-related data corresponding to static. The battery parameter values at the historical moments in the third part are divided into the battery-related data corresponding to discharging.

[0077] The parameter values of a battery parameter at multiple historical moments when a certain operating condition behavior occurs can jointly form the battery time-series data of this battery parameter under this operating condition behavior. The battery-related data under a certain operating condition behavior includes the battery time-series data of all battery parameters under this operating condition behavior.

[0078] In some embodiments, based on the battery-related data of the target device under at least one operating condition behavior, the first feature values of the key feature items corresponding to each operating condition behavior are extracted, including: for each operating condition behavior, several battery time-series data are divided into at least one set of time-series data groups corresponding to the operating condition behavior, and each set of time-series data groups includes battery time-series data of at least one battery parameter; for each set of time-series data groups corresponding to the operating condition behavior, at least one statistic is performed on the time-series data groups under the operating condition behavior to obtain the first feature values of at least one key feature item corresponding to the operating condition behavior.

[0079] It can be understood that the battery-related data under a certain operating condition behavior includes the battery time-series data of each battery parameter under the operating condition behavior. The battery time-series data of the foregoing battery parameters can be used to form at least one set of time-series data groups, and a set of time-series data groups can include battery time-series data of one or more battery parameters.

[0080] In a specific application scenario, the battery time-series data of each battery parameter can separately form a set of time-series data groups. The battery time-series data of two or more battery parameters can also jointly form the same set of time-series data groups.

[0081] Among them, a certain operating condition behavior can correspond to several sets of time-series data groups. After the sets of time-series data groups are selected, at least one statistic can be performed on the sets of time-series data groups to obtain the first feature values of at least one key feature item corresponding to the operating condition behavior. Exemplarily, if the set of time-series data groups contains battery time-series data of multiple battery parameters, the battery time-series data of multiple battery parameters can be processed first, and the foregoing statistic can be performed on the processed time-series data.

[0082] The first feature value can be characterized from at least one of the time dimension and the parameter value dimension. In some embodiments, the first feature values of the key feature items include at least one of the following: the time characterization feature value and the parameter value characterization feature value corresponding to the set of time-series data groups. Among them, the time characterization feature value is obtained by performing a time statistic on the battery time-series data in the set of time-series data groups, and the parameter value characterization feature value is obtained by performing a statistic on the parameter values included in the battery time-series data in the set of time-series data groups.

[0083] In some application scenarios, the parameter value characterization feature value can include the minimum standing temperature.

[0084] In some application scenarios, the parameter value characterization feature value includes the statistical parameter values of the battery parameters corresponding to the set of time-series data groups in at least one time dimension. Exemplarily, the parameter value characterization feature value includes the minimum standing temperature within one month, the minimum standing temperature within one quarter, etc.

[0085] In some application scenarios, the time representation feature value includes at least one of the duration of the operating condition behavior and the proportion of the operating condition behavior. Exemplarily, the time representation feature value may include the fast charging proportion, which can be obtained based on the ratio of the fast charging time to the total charging duration, or obtained by counting the number of fast charging times within a period of time.

[0086] In some embodiments, obtaining the reference feature value corresponding to each key feature item may include: obtaining the second feature value corresponding to each key feature item of multiple reference devices respectively. Based on the battery health, cluster the second feature values of each key feature item corresponding to the multiple reference devices to obtain a first feature cluster and a second feature cluster. For each key feature item, count the second feature values of each first reference device corresponding to the key feature item in the first feature cluster to obtain a first statistical value, and count the second feature values of each second reference device corresponding to the key feature item in the second feature cluster to obtain a second statistical value. Based on the first statistical value and the second statistical value, obtain the reference feature value corresponding to the key feature item.

[0087] Among them, the battery health of the multiple reference devices is different. For each reference device, its battery health and a piece of feature value data can be obtained. The feature value data includes the second feature value corresponding to each key feature item of the reference device. When clustering, the basis for clustering is the battery health of the reference device. Take a piece of feature value data corresponding to a reference device as a single object for clustering, and cluster all objects.

[0088] In some implementation scenarios, a clustering method that can calculate the cluster center, such as K-means, can be used.

[0089] Before clustering, the number of clusters can be determined in advance. Specifically, it is determined in advance that all objects need to be divided into two clusters, that is, the battery health of the reference devices is divided into two levels. The first feature cluster corresponds to the first battery health level, and the second feature cluster corresponds to the second battery health level. One of the first battery health level and the second battery health level represents high battery health, and the other represents low battery health.

[0090] The first feature cluster includes the feature value data of the first reference devices, that is, includes the second feature values corresponding to each key feature item of the first reference devices. The second feature cluster includes the feature value data of the second reference devices, that is, includes the second feature values corresponding to each key feature item of the second reference devices. The first reference devices are the reference devices belonging to the first battery health level, and the second reference devices are the reference devices belonging to the second battery health level.

[0091] After the clustering of the feature value data is completed, the reference feature value is calculated for each key feature item respectively.

[0092] In some application scenarios, the battery health of 100 reference devices and the second feature values corresponding to each key feature item are obtained respectively. According to the battery health, the feature value data of these 100 reference devices are divided into two clusters, obtaining the first feature cluster and the second feature cluster. The first feature cluster contains the feature value data of 77 first reference devices, and the second feature cluster contains the feature value data of 33 second reference devices. Each key feature item is processed separately. The second feature values corresponding to key feature item A of 77 first reference devices are statistically analyzed to obtain the first statistical value of key feature item A. The second feature values corresponding to key feature item A of 33 second reference devices are statistically analyzed to obtain the second statistical value of key feature item A. Using the first statistical value and the second statistical value of key feature item A, the reference feature value of key feature item A is obtained.

[0093] In some embodiments, the first statistical value and the second statistical value can be obtained by calculating the cluster center.

[0094] In some implementation scenarios, the first statistical value is the cluster center of the second feature values corresponding to the key feature item in the first feature cluster. The second statistical value is the cluster center of the second feature values corresponding to the key feature item in the second feature cluster.

[0095] In some embodiments, the reference feature value can be obtained in the following way: Calculate the distance between the first statistical value and the second statistical value corresponding to the key feature item, and use it as the reference feature value corresponding to the key feature item.

[0096] In some implementation scenarios, the Euclidean distance between the first statistical value and the second statistical value corresponding to the key feature item can be calculated, and the Euclidean distance is used as the reference feature value corresponding to the key feature item.

[0097] In some application scenarios, the first statistical value and the second statistical value are respectively denoted as x1 and x2. The Euclidean distance is denoted as d, and the Euclidean distance can be obtained by the following formula:

[0098] In some implementation scenarios, the Mahalanobis distance between the first statistical value and the second statistical value corresponding to the key feature item can be calculated, and the Mahalanobis distance is used as the reference feature value corresponding to the key feature item.

[0099] In some application scenarios, for a key feature item, the cluster center of the second feature values in the first feature cluster is denoted as P, and the cluster center of the second feature values in the second feature cluster is denoted as Q. The Mahalanobis distance D M (P, Q) can be obtained by the following formula:

[0100] Wherein, S represents the covariance of the data set. In the embodiments of the present application, it may be the covariance of the second eigenvalue corresponding to all reference devices for this key feature item.

[0101] It should be noted that when using the reference eigenvalue to determine whether the corresponding operating condition behavior affects the battery health of the target device, in addition to the reference eigenvalue, it is also necessary to determine the first magnitude relationship and the second magnitude relationship corresponding to this key feature item.

[0102] In some application scenarios, the reference eigenvalue of the key feature item A is 60%. It is also necessary to determine that when the first eigenvalue is greater than or equal to 60%, it can be determined that the operating condition behavior affects the battery health of the target device. When the first eigenvalue is less than 60%, it can be determined that the operating condition behavior does not affect the battery health of the target device.

[0103] In some embodiments, the first magnitude relationship and the second magnitude relationship can be determined based on the magnitude relationship between at least two of the statistical values of the high battery health clusters, the statistical values of the low battery health clusters, and the reference eigenvalue.

[0104] Exemplarily, if the statistical value of the high battery health cluster is greater than the statistical value of the low battery health cluster, it means that the eigenvalue corresponding to high battery health is higher, and the eigenvalue corresponding to low battery health is lower. Then the first magnitude relationship includes that the first eigenvalue is less than the reference eigenvalue, and the second magnitude relationship includes that the first eigenvalue is greater than the reference eigenvalue.

[0105] If the statistical value of the high battery health cluster is less than the statistical value of the low battery health cluster, it means that the eigenvalue corresponding to high battery health is lower, and the eigenvalue corresponding to low battery health is higher. Then the first magnitude relationship includes that the first eigenvalue is greater than the reference eigenvalue, and the second magnitude relationship includes that the first eigenvalue is less than the reference eigenvalue.

[0106] If the statistical value of the low battery health cluster is greater than the reference eigenvalue, and / or, the statistical value of the high battery health cluster is less than the reference eigenvalue, it means that the eigenvalue corresponding to low battery health is higher, and the eigenvalue corresponding to high battery health is lower. Then the first magnitude relationship includes that the first eigenvalue is greater than the reference eigenvalue, and the second magnitude relationship includes that the first eigenvalue is less than the reference eigenvalue.

[0107] It should be noted that the original battery data includes multiple parameter values at different historical moments within the first historical time period. When extracting the first eigenvalue, a second historical time period can be selected from within the range of the first historical time period, and the extraction is based on the parameter values within the second historical time period. The second historical time period can be equal to or less than the first historical time period. The second historical time periods corresponding to different key feature items can be different.

[0108] In some embodiments, when it is determined that the operating condition behavior corresponding to the key feature item affects the battery health of the target device, the change of the eigenvalue of the associated time-series feature of the key feature item in time can also be analyzed to determine the degree of influence of the operating condition behavior corresponding to the key feature item on the battery health. Among them, the associated time-series feature includes the third eigenvalue corresponding to the associated feature item for different time units, and the associated feature item can be the key feature item itself or other feature items.

[0109] In some implementation scenarios, the associated feature item of the fast charging ratio can be the fast charging ratio or other feature items related to fast charging.

[0110] By analyzing the change of the eigenvalue of the associated time-series feature in time, the change of the operating condition behavior corresponding to the key feature item in time can be determined. The change of the operating condition behavior is related to the degree of influence on the battery health, and thus the change of the degree of influence of the operating condition behavior on the battery health can be determined.

[0111] Among them, the second historical time period can be divided into multiple time units, and the associated time-series feature includes the third eigenvalue corresponding to the associated feature item for different time units. For each time unit, the third eigenvalue of the time unit can be determined by using the parameter value of the battery parameter corresponding to the associated feature item within the time unit. Among them, the battery parameter corresponding to the associated feature item is the battery parameter used to obtain the feature item.

[0112] Among them, the length of the time unit can be determined as needed. For example, it can be a moment, a day, a month, a year, etc.

[0113] It should be noted that the parameter values at different historical moments within the second historical time period are time series data themselves, which can be directly used as time-series features, or at least one-dimensionality reduction processing can be performed on the aforementioned parameter values to obtain time-series features with different granularities. The lengths of the time units corresponding to different granularities are different. The sequence features to be used can be selected as needed.

[0114] In some implementation scenarios, the change of the eigenvalue of the associated time-series feature in time can be analyzed by clustering all the third eigenvalues included in the associated time-series feature.

[0115] Among them, the first eigenvalue of the key feature item is obtained by statistically calculating the parameter values of the battery parameter corresponding to the key feature item within the second historical time period. And the third eigenvalue of a time unit is obtained by statistically calculating the parameter values of the battery parameter corresponding to the associated feature item within the time unit.

[0116] In some embodiments, the associated timing features of the key feature items include third feature values corresponding to different time units for the key feature items; analyzing the change of the feature values of the associated timing features of the key feature items in terms of time sequence to determine the influence degree of the operating conditions corresponding to the key feature items on the battery health includes: clustering the associated timing features of the key feature items to determine the frequency change of the operating conditions corresponding to the key feature items in the target time period relative to other time periods within the second historical time period; based on the frequency change, determining whether the influence of the operating conditions corresponding to the key feature items on the battery health increases or decreases within the target time period.

[0117] In some implementation scenarios, the key feature items can reflect the frequency of the operating conditions. For example, the fast charge ratio can reflect the frequency of the fast charge behavior.

[0118] Among them, clustering the associated timing features of the key feature items can determine whether there are changes in the associated timing features in the time dimension, which can also indicate whether there are changes in the operating conditions corresponding to the key feature items in the time dimension. Further, the change time of the operating conditions corresponding to the key feature items can be obtained, and whether there are changes in the recent period (for example, within the recent three months) can be determined.

[0119] In some implementation scenarios, when clustering the associated timing features of the key feature items, if multiple clusters can be obtained, it indicates that there are corresponding operating conditions that change in the time dimension. Each cluster can correspond to a time period, and the time periods corresponding to each cluster can be used as the target time periods respectively, and compared with other time periods to compare the change of the feature values of the target time periods relative to other time periods, so as to determine the change of the influence degree of the corresponding operating conditions on the battery health.

[0120] In some application scenarios, taking the fast charge ratio as an example, the corresponding associated timing feature can be the fast charge ratio of each month within the second historical time period. Clustering the fast charge ratio of each month within the second historical time period to obtain the change of the feature values. Furthermore, it can be analyzed whether there are changes in the fast charge behavior in the time dimension within the second historical time period.

[0121] In some application scenarios, when clustering the associated timing features of a single vehicle, a clustering method that can distinguish timing features, such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise), can be used to determine whether there are clusters and outliers in the timing distribution of this feature for this vehicle, so as to judge the recent behavior changes of this vehicle.

[0122] In some implementation scenarios, the target device can be a vehicle equipped with a battery.

[0123] In some embodiments, the method may further include: providing the user with a judgment result of the influence of the operating condition behavior corresponding to the key feature item on the battery health.

[0124] In some embodiments, the method may further include: providing the user with the feature data corresponding to the key feature item. Wherein, the feature data may be obtained by time-weighting the feature values of the key feature item. Exemplarily, the second historical time period is divided into two time periods, the feature values of the key feature item corresponding to the two time periods are obtained, and the duration of the time period is used as the weight to perform weighted summation on the feature values corresponding to the time period to obtain the feature data for display.

[0125] Wherein, a certain time threshold may be set to divide the two time periods. Exemplarily, the time threshold may be set to a certain duration from the current moment to divide the recent data and the long-term data.

[0126] In a specific application scenario, the original battery data reported by the vehicle-mounted BMS (battery management system) can be obtained from the cloud database, the data is cleaned of outliers and invalid values, and then the data of the charging, discharging, and static behavior segments is divided.

[0127] In a specific application scenario, the key feature item is the fast charge ratio, and the division threshold y is obtained through cluster analysis. If the fast charge ratio of a vehicle is higher than y, it is considered that the fast charge behavior of the vehicle affects the battery health.

[0128] In a specific application scenario, the key feature item is the fast charge ratio. Identify whether there is an obvious clustering of the associated time series features of the fast charge ratio. If there is a clustering, it means that there is a change in the fast charge behavior in the time dimension. Further, it can be judged whether the fast charge ratio of the vehicle has increased or decreased recently. If the fast charge ratio of the vehicle was 4% in the previous 8 months and 90% in the recent 4 months, it can be found that the fast charge behavior of the vehicle has become more frequent in the recent four months, and the impact on the battery health has been further expanded.

[0129] In a specific application scenario, if the fast charge ratio of the vehicle was 90% in the previous 8 months and 4% in the recent 4 months, the weighted fast charge ratio of the vehicle is obtained according to time weighting as 0.9 * 8 / 12 + 0.4 * 4 / 12 = 73.3%. The above data can be provided for the user to view to facilitate the user's understanding of the vehicle situation.

[0130] Refer to Figure 2 , Figure 2 is a schematic framework diagram of the evaluation device for the operating condition behavior of the device provided in some embodiments of the present application.

[0131] The evaluation device 20 for the operating condition behavior of the device includes an extraction module 21, a reference acquisition module 22, and a comparison module 23. The extraction module 21 is configured to extract, based on the battery-related data of the target device under at least one operating condition behavior, the first feature values of the key feature items corresponding to each operating condition behavior, where the first feature value of the key feature item corresponding to the operating condition behavior characterizes the parameter feature of the battery of the target device under the operating condition behavior; and, the reference acquisition module 22 is configured to acquire the reference feature values corresponding to each key feature item, and the reference feature values are obtained by analyzing the second feature values of the key feature items corresponding to multiple reference devices with different battery health degrees; the comparison module 23 is configured to compare the first feature value of each key feature item with the corresponding reference feature value respectively to determine whether the operating condition behavior corresponding to each key feature item affects the battery health degree of the target device.

[0132] Refer to Figure 3 , Figure 3 It is a schematic framework diagram of an electronic device provided by some embodiments of the present application.

[0133] The electronic device 30 includes a memory 31 and a processor 32. The processor 32 is configured to execute the program instructions stored in the memory 31 to implement the evaluation method for the operating condition behavior of any of the above devices. In a specific implementation scenario, the electronic device 30 may include, but is not limited to: a computer device, an electrical device, a microcomputer, a desktop computer, a server. In addition, the electronic device 30 may also include mobile devices such as a laptop computer and a tablet computer, which are not limited herein.

[0134] Specifically, the processor 32 is configured to control itself and the memory 31 to implement the evaluation method for the operating condition behavior of any of the above devices. The processor 32 may also be referred to as a CPU (Central Processing Unit). The processor 32 may be an integrated circuit chip with signal processing capabilities. The processor 32 may also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field-Programmable Gate Array, FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Additionally, the processor 32 may be implemented jointly by integrated circuit chips.

[0135] Refer to Figure 4 , Figure 4 It is a schematic framework diagram of a computer-readable storage medium provided by some embodiments of the present application.

[0136] The computer-readable storage medium 40 stores program instructions 41 that can be run by a processor. When the program instructions 41 are executed by the processor, they are used to implement the evaluation method for any of the above device operating conditions and behaviors.

[0137] The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments. Their similarities or resemblances can be referred to each other. For the sake of brevity, they will not be elaborated herein.

[0138] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation manners described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, units or components can be combined or integrated into another subsystem, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0139] In addition, in each embodiment of the present application, the various functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. If the integrated units are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

Claims

1. A method for evaluating equipment operating behavior, characterized in that: The method comprises: Based on the battery-related data of the target device under at least one operating condition, extracting the first characteristic value of the key characteristic item corresponding to each operating condition, wherein the first characteristic value of the key characteristic item corresponding to the operating condition represents the parameter characteristics of the battery of the target device under the operating condition; and Obtaining a reference characteristic value corresponding to each of the key characteristic items, where the reference characteristic value is obtained by analyzing second characteristic values ​​of the key characteristic item corresponding to a plurality of reference devices with different battery health conditions; The first characteristic value of each of the key characteristic items is compared with the corresponding reference characteristic value to determine whether the operating behavior corresponding to each of the key characteristic items affects the battery health of the target device.

2. The method according to claim 1, characterized in that The battery-related data under the operating condition behavior includes battery time series data of several battery parameters under the operating condition behavior; the battery time series data of the battery parameters includes parameter values ​​of the battery parameters at multiple historical moments when the operating condition behavior occurs; The extracting, based on the battery-related data of the target device under at least one operating condition, first characteristic values ​​of key characteristic items corresponding to each operating condition behavior respectively include: For each of the operating conditions, the battery time series data of the plurality of battery parameters are divided into at least one group of time series data groups corresponding to the operating condition, each group of the time series data group including the battery time series data of at least one of the battery parameters; For each of the time series data groups corresponding to the operating behavior, at least one statistic is performed on the time series data group under the operating behavior to obtain a first characteristic value of at least one key characteristic item corresponding to the operating behavior.

3. The method according to claim 2, characterized in that The first characteristic value of the key characteristic item includes at least one of the following: a time characterization characteristic value and a parameter value characterization characteristic value corresponding to the timing data group, wherein the time characterization characteristic value is obtained by performing time statistics on the battery timing data in the timing data group, and the parameter value characterization characteristic value is obtained by performing statistics on the parameter values ​​contained in the battery timing data in the timing data group.

4. The method according to claim 1, characterized in that: Before extracting the first characteristic value of the key characteristic item corresponding to each operating condition based on the battery-related data of the target device under at least one operating condition, the method further includes: Acquire raw battery data collected from a battery of the target device, the raw battery data including multiple parameter values ​​of multiple battery parameters corresponding to different historical moments within a first historical time period; Based on the operating behavior of the target device in the first historical time period, the original battery data is divided to obtain battery-related data under each operating behavior, wherein the battery-related data under the operating behavior includes parameter values ​​of each battery parameter at multiple historical moments when the operating behavior occurs; And / or, before extracting the first characteristic value of the key characteristic item corresponding to each operating condition based on the battery-related data of the target device under at least one operating condition, the method further includes: Constructing a battery feature item set, wherein the battery feature item set includes a plurality of battery feature items; Analyzing the relationship between each battery characteristic item in the battery characteristic item set and the battery health; The battery feature item related to the battery health is selected from the battery feature item set based on the relationship as the key feature item.

5. The method according to claim 1, characterized in that The obtaining of reference feature values ​​corresponding to the key feature items includes: Obtaining second characteristic values ​​of the key characteristic items corresponding to a plurality of reference devices with different battery health conditions; Based on the battery health, the second feature values ​​of each of the key feature items corresponding to the multiple reference devices are clustered to obtain a first feature cluster and a second feature cluster, wherein the first feature cluster includes the second feature values ​​of each of the key feature items corresponding to the first reference device, the second feature cluster includes the second feature values ​​of each of the key feature items corresponding to the second reference device, the first reference device is each of the reference devices belonging to the first battery health level, and the second reference device is each of the reference devices belonging to the second battery health level; For each of the key feature items, counting the second feature value of each of the first reference devices in the first feature cluster corresponding to the key feature item to obtain a first statistical value, and counting the second feature value of each of the second reference devices in the second feature cluster corresponding to the key feature item to obtain a second statistical value; The reference feature value corresponding to the key feature item is obtained based on the first statistical value and the second statistical value.

6. The method according to claim 5, characterized in that The first statistical value is the cluster center of the second eigenvalue of the key feature item in the first feature cluster, and the second statistical value is the cluster center of the second eigenvalue of the key feature item in the second feature cluster; And / or, obtaining the reference feature value corresponding to the key feature item based on the first statistical value and the second statistical value includes: A distance between the first statistical value and the second statistical value is calculated as the reference feature value corresponding to the key feature item.

7. The method according to claim 1, characterized in that The comparing the first characteristic value of each of the key characteristic items with the corresponding reference characteristic value to determine whether the operating behavior corresponding to each of the key characteristic items affects the battery health of the target device includes: In response to the first characteristic value of the key characteristic item and the corresponding reference characteristic value satisfying a first magnitude relationship, determining that the operating condition behavior corresponding to the key characteristic item affects the battery health of the target device; In response to the first characteristic value of the key characteristic item and the corresponding reference characteristic value satisfying a second magnitude relationship, it is determined that the operating condition behavior corresponding to the key characteristic item does not affect the battery health of the target device.

8. The method according to claim 1, characterized in that The first characteristic value of the key characteristic item is determined by the parameter value of the battery parameter corresponding to the key characteristic item in the second historical time period; After respectively comparing the first characteristic value of each of the key characteristic items with the corresponding reference characteristic value to determine whether the operating behavior corresponding to each of the key characteristic items affects the battery health of the target device, the method further includes: In response to determining that the operating condition behavior corresponding to the key feature item affects the battery health of the target device, the characteristic value change of the associated timing feature of the key feature item in the timing is analyzed to determine the degree of influence of the operating condition behavior corresponding to the key feature item on the battery health, wherein the associated timing feature of the key feature item includes third characteristic values ​​of the associated characteristic items corresponding to different time units, the associated characteristic items are the key feature items or other characteristic items, the different time units are located in the second historical time period, and the third characteristic value of the time unit is determined based on the parameter value of the battery parameter corresponding to the associated characteristic item in the time unit.

9. The method according to claim 8, characterized in that The first characteristic value of the key characteristic item is obtained by statistically analyzing the parameter value of the battery parameter corresponding to the key characteristic item in the second historical time period; the third characteristic value of the time unit is obtained by statistically analyzing the parameter value of the battery parameter corresponding to the associated characteristic item in the time unit; And / or, analyzing the change of characteristic values ​​of the associated time series characteristics of the key characteristic items in the time series to determine the influence of the operating behavior corresponding to the key characteristic items on the battery health includes: Clustering the associated time series features of the key feature items to determine the frequency change of the operating behavior corresponding to the key feature items in the target time period within the second historical time period relative to other time periods; Based on the frequency change, it is determined whether the influence of the operating condition behavior corresponding to the key characteristic item on the battery health during the target time period increases or decreases.

10. The method according to claim 1, characterized in that After respectively comparing the first characteristic value of each of the key characteristic items with the corresponding reference characteristic value to determine whether the operating behavior corresponding to each of the key characteristic items affects the battery health of the target device, the method further includes: Providing the user with an assessment result of the impact of the operating behavior corresponding to the key feature item on the battery health; and / or, The feature data corresponding to the key feature item is provided to the user.

11. The method according to claim 1, characterized in that: The operating behavior includes at least one of charging, discharging and standing; And / or, the battery-related data under the operating behavior includes at least one parameter value of a plurality of battery parameters under the operating behavior when the operating behavior occurs, the plurality of battery parameters including at least one of current, voltage, state of charge, and temperature; And / or, the target device is a vehicle.

12. An evaluation device for equipment operating behavior, characterized in that: include: An extraction module, configured to extract first characteristic values ​​of key characteristic items corresponding to each operating condition based on battery-related data of the target device under at least one operating condition, wherein the first characteristic values ​​of the key characteristic items corresponding to the operating condition represent parameter characteristics of the battery of the target device under the operating condition; and A reference acquisition module, used to acquire a reference characteristic value corresponding to each of the key characteristic items, wherein the reference characteristic value is obtained by analyzing the second characteristic values ​​of the key characteristic items corresponding to a plurality of reference devices with different battery healths; The comparison module is used to compare the first characteristic value of each key characteristic item with the corresponding reference characteristic value to determine whether the operating behavior corresponding to each key characteristic item affects the battery health of the target device.

13. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores program instructions, and the program instructions are used to execute the method according to any one of claims 1 to 11 when executed by the processor.

14. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images