Method and device for constructing charging behavior portrait, electronic equipment and storage medium

Abstract

The application relates to the technical field of vehicles, in particular to a charging behavior portrait construction method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring historical charging data of a vehicle; identifying a plurality of charging features representing user charging behaviors in the historical charging data; and generating a charging behavior portrait of the user according to the distribution of the plurality of charging features. Thus, the problems that the charging indicators in the related art cannot accurately describe the historical charging behaviors of the user are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, electronic device, and storage medium for constructing a charging behavior profile. Background Technology

[0002] The quality of charging behavior can even directly affect the lifespan of the power battery. Currently, a popular way to describe user characteristics is through user profiling. By drawing on this approach, we can construct user charging profiles to describe the user's charging behavior.

[0003] Current technologies primarily use charging metrics to construct profiles of user charging behavior, but these cannot accurately describe the historical charging records of a battery pack. Therefore, studying the charging behavior of electric vehicle users is of great significance. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for constructing a charging behavior profile, in order to solve the problem that charging indicators cannot accurately describe a user's historical charging behavior in related technologies.

[0005] The first aspect of this application provides a method for constructing a charging behavior profile, comprising the following steps: acquiring historical charging data of a vehicle; identifying multiple charging features in the historical charging data that characterize user charging behavior; and generating a user charging behavior profile based on the distribution of the multiple charging features.

[0006] Optionally, in one embodiment of this application, generating the user's charging behavior profile based on the distribution of the plurality of charging features includes: identifying charging features belonging to the same charging segment among the plurality of charging features; clustering the target charging features of each charging segment to obtain a clustering result, and determining the charging behavior label of the corresponding charging segment based on the clustering result, wherein the charging behavior label is used to identify the category of the charging behavior corresponding to the charging segment; and generating the user's charging behavior profile based on all charging segments carrying the charging behavior label.

[0007] Optionally, in one embodiment of this application, the step of clustering the target charging features of each charging segment to obtain a clustering result includes: identifying the cluster center of the target charging features of each charging segment; calculating the distance between each charging feature and the cluster center; and taking the category of the charging behavior corresponding to the charging feature with the smallest distance as the clustering result.

[0008] Optionally, in one embodiment of this application, the charging behavior label includes a first label and a second label, wherein the charging segments represented by the first label and the second label correspond to different categories of charging behavior.

[0009] Optionally, in one embodiment of this application, generating the user's charging behavior profile based on all charging segments carrying the charging behavior tag includes: identifying a first number of charging segments carrying the first tag and a second number of charging segments carrying the second tag; calculating the actual proportion of the charging segments carrying the first tag based on the first number and the second number; if the actual proportion is greater than a proportion threshold, generating a third tag for the charging behavior corresponding to the historical charging data in the charging behavior profile; otherwise, generating a fourth tag for the charging behavior corresponding to the historical charging data in the charging behavior profile, wherein the third tag and the fourth tag correspond to different categories of charging behavior.

[0010] Optionally, in one embodiment of this application, before clustering all charging features of each charging segment to obtain the clustering result, the method further includes: reducing the dimensionality of the charging features; and using the dimensionality-reduced charging features as the target charging features.

[0011] Optionally, in one embodiment of this application, before identifying multiple charging features in the historical charging data that characterize user charging behavior, the method further includes: performing data preprocessing on the historical charging data.

[0012] A second aspect of this application provides an apparatus for constructing a charging behavior profile, comprising: an acquisition module for acquiring historical charging data of a vehicle; an identification module for identifying multiple charging features in the historical charging data that characterize user charging behavior; and a generation module for generating a charging behavior profile of the user based on the distribution of the multiple charging features.

[0013] Optionally, in one embodiment of this application, the generation module is further configured to: identify charging features belonging to the same charging segment among the plurality of charging features; cluster the target charging features of each charging segment to obtain a clustering result, and determine the charging behavior label of the corresponding charging segment based on the clustering result, wherein the charging behavior label is used to identify the category of the charging behavior corresponding to the charging segment; and generate the user's charging behavior profile based on all charging segments carrying the charging behavior label.

[0014] Optionally, in one embodiment of this application, the generation module is further configured to identify the cluster center of the target charging feature of each charging segment; calculate the distance between each charging feature and the cluster center, and take the category of the charging behavior corresponding to the charging feature with the smallest distance as the clustering result.

[0015] Optionally, in one embodiment of this application, the charging behavior label includes a first label and a second label, wherein the charging segments represented by the first label and the second label correspond to different categories of charging behavior.

[0016] Optionally, in one embodiment of this application, the generation module is further configured to identify a first number of charging segments carrying the first tag and a second number of charging segments carrying the second tag; calculate the actual proportion of the charging segments carrying the first tag based on the first number and the second number; if the actual proportion is greater than a proportion threshold, generate a third tag for the charging behavior corresponding to the historical charging data in the charging behavior profile; otherwise, generate a fourth tag for the charging behavior corresponding to the historical charging data in the charging behavior profile, wherein the third tag and the fourth tag correspond to different categories of charging behavior.

[0017] Optionally, in one embodiment of this application, the charging behavior profile construction device further includes: a dimensionality reduction module, used to reduce the dimensionality of the charging features before clustering all charging features of each charging segment to obtain the clustering result; and to use the dimensionality-reduced charging features as the target charging features.

[0018] Optionally, in one embodiment of this application, the charging behavior profile construction apparatus further includes: a processing module, used to preprocess the historical charging data before identifying multiple charging features in the historical charging data that characterize user charging behavior.

[0019] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the charging behavior profile construction method as described in the above embodiments.

[0020] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to perform the method for constructing a charging behavior profile as described in the above embodiments.

[0021] Therefore, this application has at least the following beneficial effects:

[0022] This application's embodiments can identify multiple charging features characterizing user charging behavior in historical vehicle charging data, and generate a highly accurate charging behavior profile based on the distribution and clustering analysis of these features. This solves the problem in related technologies where charging indicators cannot accurately describe a user's historical charging behavior.

[0023] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0025] Figure 1 This is a flowchart of a method for constructing a charging behavior profile according to an embodiment of this application;

[0026] Figure 2 This is an example diagram illustrating the construction of a charging behavior profile according to an embodiment of this application;

[0027] Figure 3 This is an example diagram of an apparatus for constructing a charging behavior profile according to an embodiment of this application;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0030] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for constructing a charging behavior profile according to embodiments of this application. Addressing the problems mentioned in the background section, this application provides a method for constructing a charging behavior profile. This method identifies multiple charging features characterizing user charging behavior in historical vehicle charging data and generates a highly accurate charging behavior profile based on the distribution and clustering analysis of these multiple charging features. This solves the problem in related technologies where charging indicators cannot accurately describe a user's historical charging behavior.

[0031] Specifically, Figure 1 This is a flowchart illustrating a method for constructing a charging behavior profile provided in an embodiment of this application.

[0032] like Figure 1 As shown, the method for constructing this charging behavior profile includes the following steps:

[0033] In step S101, the vehicle's historical charging data is acquired.

[0034] Historical charging data includes the initial SOC at the start of battery pack charging, the final SOC at the end of battery pack charging, the average battery pack temperature, the battery pack charging temperature difference, the average charging current, the average charging time, and the battery pack health status.

[0035] It is understood that the vehicle in this application embodiment can be a vehicle with charging function, such as a new energy vehicle. New energy vehicles upload historical charging data that conforms to industry, enterprise or national standards to the vehicle manufacturer's data platform. This application embodiment takes historical charging data that conforms to national standards as an example. If it is necessary to build a user's charging behavior profile, historical charging data that conforms to national standards can be obtained from the vehicle manufacturer's data platform.

[0036] In step S102, multiple charging features characterizing user charging behavior are identified in historical charging data.

[0037] It is understood that the embodiments of this application can filter multiple charging characteristics of a single vehicle charge, including start SOC, end SOC, average battery pack temperature, battery pack charging temperature difference, average charging current, and average charging time. These charging characteristics are calculated using a computer programming language, such as the pandas dependency package in Python, and the calculated charging characteristics representing user charging behavior are saved for later use.

[0038] In one embodiment of this application, before identifying multiple charging features in historical charging data that characterize user charging behavior, the method further includes: data preprocessing of the historical charging data.

[0039] This application embodiment addresses the need to clean dirty data appearing in historical vehicle charging data. Dirty data includes duplicate data in the database, values ​​outside the normal range of field values, and outliers. For duplicate data and values ​​outside the normal range, this application embodiment can use direct deletion. For outlier charging data, this application embodiment can identify outliers using quantiles and box plots, and delete the entire row of identified outlier fields. Regarding the field definitions in the database, this application embodiment requires preprocessing of all historical vehicle charging data. This mainly includes offset removal and unit conversion. Offset removal mainly refers to correcting the field value offset set in the field definitions, and unit conversion mainly refers to the difference in field value due to different unit settings.

[0040] In step S103, a user's charging behavior profile is generated based on the distribution of multiple charging features.

[0041] In one embodiment of this application, generating a user's charging behavior profile based on the distribution of multiple charging features includes: identifying charging features belonging to the same charging segment among the multiple charging features; clustering the target charging features of each charging segment to obtain a clustering result, and determining the charging behavior label of the corresponding charging segment based on the clustering result, wherein the charging behavior label is used to identify the category of the charging behavior corresponding to the charging segment; and generating a user's charging behavior profile based on all charging segments carrying charging behavior labels.

[0042] In this embodiment of the application, each charging segment can be calculated to obtain a row of charging features, wherein the charging segment filtering rule can be:

[0043] a. The vehicle is in a parking charging state.

[0044] b. The SOC value is at the rising edge.

[0045] c. The vehicle's mileage remains unchanged.

[0046] d. The vehicle speed remains at 0.

[0047] Use the method described above to filter out all charging segments of the vehicle and save them.

[0048] Understandably, due to the high dimensionality of charging features, direct clustering analysis would lead to significant biases in distance calculations during the clustering process. Therefore, this embodiment requires dimensionality reduction of the charging features, using the dimensionality-reduced features as target charging features for clustering analysis. In practice, this embodiment can use Principal Component Analysis (PCA) for dimensionality reduction. Each principal component obtained through PCA is a linear combination of the original features. Principal components are selected based on their number and cumulative variance explained. This embodiment can select principal components with a cumulative variance explained greater than 80% as target charging features for clustering analysis.

[0049] Furthermore, embodiments of this application can use the principal components obtained in the above steps to perform KMEANS dynamic clustering analysis. When calculating the number of each category with different numbers of categories, the sum of squared errors formula can be used: Calculate the sum of squared errors, where, This represents the observed value (true value). This represents the predicted value (model prediction); and by selecting the points where the sum of squared errors abruptly changes, the number of corresponding categories is the final number of clusters selected. After determining the number of clusters, the KMEANS method from the sklearn library in Python is used to perform cluster analysis on the selected principal components to obtain the final clustering results. For example, the clustering results can cluster the charging features into 5 categories, numbered 1-5, where 1 can represent whether there is high SOC, 2 can represent whether there is shallow charging and discharging, 3 can represent whether there is a small temperature difference, etc.

[0050] Furthermore, clustering is performed on the target charging features of each charging segment to obtain clustering results, including: identifying the cluster center of the target charging features of each charging segment; calculating the distance between each charging feature and the cluster center, and taking the category of charging behavior corresponding to the charging feature with the smallest distance as the clustering result.

[0051] Understandably, after obtaining the final clustering results, the cluster centers for each category can be obtained. Based on the values ​​of the cluster centers, and combined with battery mechanisms and common sense, it is determined whether the charging behavior of that category is labeled as a primary or secondary tag. For example, for lithium-ion batteries in the high SOC segment, shallow charging and discharging, low charging current, small charging temperature difference, moderate charging temperature, moderate charging time without overcharging, and good battery life indicate that the charging behavior is labeled as a primary tag. Conversely, if the charging behavior is labeled as a secondary tag and the battery life is poor, then the charging behavior is labeled as a secondary tag. The primary and secondary tags represent different categories of charging behaviors corresponding to different charging segments.

[0052] Furthermore, for a single electric vehicle, embodiments of this application can calculate all feature numbers used in cluster analysis. For each charging segment, the distance between the feature number of that segment and the cluster center of the cluster category is calculated, and the category with the smallest distance is taken as the final charging category for that charging segment.

[0053] In one embodiment of this application, a user's charging behavior profile is generated based on all charging segments carrying charging behavior tags, including: identifying a first number of charging segments carrying a first tag and a second number of charging segments carrying a second tag; calculating the actual proportion of charging segments carrying the first tag based on the first and second numbers; if the actual proportion is greater than a proportion threshold, generating a third tag for the charging behavior corresponding to historical charging data in the charging behavior profile; otherwise, generating a fourth tag for the charging behavior corresponding to historical charging data in the charging behavior profile, wherein the third tag and the fourth tag correspond to different categories of charging behavior.

[0054] The percentage threshold can be set according to the actual situation in this application embodiment, and is not specifically limited.

[0055] This application embodiment can determine the quality of charging behavior corresponding to historical charging data based on the number of first and second tags. Building upon the above embodiment, when the proportion of charging behaviors carrying the first tag is greater than a preset percentage threshold, this application embodiment can add a third tag to the charging profile, indicating that the charging behavior corresponding to the historical charging data is good. When the proportion of charging behaviors carrying the second tag is less than a preset percentage threshold, this application embodiment can add a fourth tag to the charging profile, indicating that the charging behavior corresponding to the historical charging data is poor. Therefore, by calculating the percentage, the quality of historical vehicle charging behavior can be quantified, enabling more accurate generation of charging behavior profile information.

[0056] The following is combined Figure 2 The construction of the charging behavior profile in the embodiments of this application is described in detail, including the following steps:

[0057] 1. Obtain online data on new energy vehicles and filter vehicle charging segments.

[0058] 2. Calculate the single-charge characteristics of new energy vehicles, including start and end SOC, current, charging temperature, charging time, etc.

[0059] 3. Use principal component analysis to calculate principal components and reduce the dimensionality of the features.

[0060] 4. Use KMEANS to perform cluster analysis on principal components.

[0061] 5. Analyze the data characteristics of each category to obtain the cluster centers of each category.

[0062] 6. Analyze the proportion of all historical charging data of the vehicle in each charging type to obtain the final charging profile result.

[0063] The charging behavior profile construction method proposed in this application can identify multiple charging features characterizing user charging behavior in the vehicle's historical charging data, and generate a highly accurate charging behavior profile based on the distribution and clustering analysis of these multiple charging features. This solves the problem in related technologies where charging indicators cannot accurately describe a user's historical charging behavior.

[0064] Next, with reference to the accompanying drawings, an apparatus for constructing a charging behavior profile according to an embodiment of this application is described.

[0065] Figure 3 This is a block diagram of a charging behavior profile construction device according to an embodiment of this application.

[0066] like Figure 3 As shown, the charging behavior profile building device 10 includes: an acquisition module 100, an identification module 200, and a generation module 300.

[0067] The acquisition module 100 is used to acquire historical charging data of the vehicle; the identification module 200 is used to identify multiple charging features in the historical charging data that characterize the user's charging behavior; and the generation module 300 is used to generate a user's charging behavior profile based on the distribution of the multiple charging features.

[0068] In one embodiment of this application, the generation module 300 is further configured to: identify charging features belonging to the same charging segment among multiple charging features; cluster the target charging features of each charging segment to obtain a clustering result, and determine the charging behavior label of the corresponding charging segment based on the clustering result, wherein the charging behavior label is used to identify the category of the charging behavior corresponding to the charging segment; and generate a user's charging behavior profile based on all charging segments carrying charging behavior labels.

[0069] In one embodiment of this application, the generation module 300 is further configured to identify the cluster center of the target charging feature for each charging segment; calculate the distance between each charging feature and the cluster center, and take the category of the charging behavior corresponding to the charging feature with the smallest distance as the clustering result.

[0070] In one embodiment of this application, the charging behavior label includes a first label and a second label, wherein the charging segments represented by the first label and the second label correspond to different categories of charging behavior.

[0071] In one embodiment of this application, the generation module 300 is further configured to identify a first number of charging segments carrying a first tag and a second number of charging segments carrying a second tag; calculate the actual proportion of charging segments carrying the first tag based on the first number and the second number; if the actual proportion is greater than the proportion threshold, generate a third tag for the charging behavior corresponding to the historical charging data in the charging behavior profile; otherwise, generate a fourth tag for the charging behavior corresponding to the historical charging data in the charging behavior profile, wherein the third tag and the fourth tag correspond to different categories of charging behavior.

[0072] In one embodiment of this application, the charging behavior profile construction device 10 further includes a dimensionality reduction module.

[0073] The dimension reduction module is used to reduce the dimension of the charging features before clustering all charging features of each charging segment to obtain the clustering results; the dimension-reduced charging features are used as the target charging features.

[0074] In one embodiment of this application, the charging behavior profile building device 10 further includes a processing module.

[0075] The processing module is used to preprocess historical charging data before identifying multiple charging features that characterize user charging behavior in historical charging data.

[0076] It should be noted that the explanation of the above-described method for constructing a charging behavior profile also applies to the apparatus for constructing a charging behavior profile in this embodiment, and will not be repeated here.

[0077] The charging behavior profile construction apparatus proposed in this application can identify multiple charging features characterizing user charging behavior in historical vehicle charging data, and generate a highly accurate charging behavior profile based on the distribution and clustering analysis of these multiple charging features. This solves the problem in related technologies where charging indicators cannot accurately describe a user's historical charging behavior.

[0078] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0079] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0080] When the processor 402 executes the program, it implements the method for constructing a charging behavior profile provided in the above embodiments.

[0081] Furthermore, electronic devices also include:

[0082] Communication interface 403 is used for communication between memory 401 and processor 402.

[0083] The memory 401 is used to store computer programs that can run on the processor 402.

[0084] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0085] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0086] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0087] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0088] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for constructing a charging behavior profile.

[0089] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0090] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0091] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0092] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0093] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A method for constructing a charging behavior profile, characterized in that, Includes the following steps: Obtain historical charging data for the vehicle; Identify multiple charging features that characterize user charging behavior in the historical charging data; Identify charging features belonging to the same charging segment among the multiple charging features; Clustering is performed on the target charging features of each charging segment to obtain clustering results, and charging behavior labels for the corresponding charging segments are determined based on the clustering results. The charging behavior labels are used to identify the category of the charging behavior corresponding to the charging segment. A charging behavior profile of the user is generated based on all charging segments carrying the charging behavior labels. The charging behavior labels include a first label and a second label, and the first label and the second label represent different categories of the charging behavior corresponding to the charging segments. The step of generating a user's charging behavior profile based on all charging segments carrying the charging behavior tag includes: identifying a first number of charging segments carrying the first tag and a second number of charging segments carrying the second tag; calculating the actual proportion of the charging segments carrying the first tag based on the first number and the second number; if the actual proportion is greater than a proportion threshold, generating a third tag for the charging behavior corresponding to the historical charging data in the charging behavior profile; otherwise, generating a fourth tag for the charging behavior corresponding to the historical charging data in the charging behavior profile, wherein the third tag and the fourth tag correspond to different categories of charging behavior.

2. The method for constructing a charging behavior profile according to claim 1, characterized in that, The clustering of the target charging features for each charging segment to obtain the clustering results includes: Identify the cluster centers of the target charging features for each charging segment; Calculate the distance between each charging feature and the cluster center, and take the category of the charging behavior corresponding to the charging feature with the smallest distance as the clustering result.

3. The method for constructing a charging behavior profile according to claim 1, characterized in that, Before clustering all charging features for each charging segment to obtain the clustering results, the following steps are also included: The charging characteristics are reduced in dimensionality; The dimensionality-reduced charging features are used as the target charging features.

4. The method for constructing a charging behavior profile according to claim 1, characterized in that, Before identifying multiple charging features characterizing user charging behavior in the historical charging data, the method further includes: The historical charging data is preprocessed.

5. A device for constructing a charging behavior profile, characterized in that, include: The acquisition module is used to acquire the vehicle's historical charging data; The identification module is used to identify multiple charging features that characterize user charging behavior in the historical charging data; A generation module is used to identify charging features belonging to the same charging segment among the multiple charging features; Clustering is performed on the target charging features of each charging segment to obtain clustering results, and charging behavior labels for the corresponding charging segments are determined based on the clustering results. The charging behavior labels are used to identify the category of the charging behavior corresponding to the charging segment. A charging behavior profile of the user is generated based on all charging segments carrying the charging behavior labels. The charging behavior labels include a first label and a second label, and the first label and the second label represent different categories of the charging behavior corresponding to the charging segments. The generation module is further configured to: identify a first number of charging segments carrying the first tag and a second number of charging segments carrying the second tag; calculate the actual proportion of the charging segments carrying the first tag based on the first number and the second number; if the actual proportion is greater than a proportion threshold, generate a third tag for the charging behavior corresponding to the historical charging data in the charging behavior profile; otherwise, generate a fourth tag for the charging behavior corresponding to the historical charging data in the charging behavior profile, wherein the third tag and the fourth tag correspond to different categories of charging behavior.

6. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method for constructing a charging behavior profile as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for constructing a charging behavior profile as described in any one of claims 1-4.

Images