Business abnormity evaluation method and device of battery changing operator, and electronic equipment

Abstract

The invention discloses a service abnormity evaluation method and device for a battery changing operator and electronic equipment, and relates to the field of artificial intelligence and big data, and the method comprises the steps: inputting user data into an abnormal user feature recognition model and an abnormal user preference entropy recognition model, and calculating an abnormal user evaluation score based on a result outputted by the models; calculating a user development level score based on the preprocessed user data; calculating an operation level score and a service level score of the battery replacement operator based on the preprocessed business operation data; and based on the abnormal user evaluation score, the user development level score, the operation level score, the service level score and the corresponding weight values, calculating a comprehensive evaluation score of the power conversion operator, and based on the comprehensive evaluation score, identifying the power conversion operator with abnormal business. According to the method and the device, the technical problem of relatively low accuracy of an evaluation result in a mode of carrying out business abnormity evaluation on a battery replacement supplier through a manual offline visiting mode in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and big data or other related technical fields, and in particular to a business anomaly assessment method for a battery swap operator, a device thereof, and electronic equipment. Background Art

[0002] With the rapid development of mobile internet and the popularization of green travel concepts, battery swapping services for electric bicycles and electric vehicles, as a convenient and efficient way to replenish energy, have gradually become an important support for short-distance urban delivery and personal travel. Major battery swapping suppliers have sprung up like mushrooms after a rain, committed to building a nationwide battery swapping network. In the process of business expansion, battery swapping suppliers, as the supply side, have introduced diversified battery swapping promotion channels, namely battery swapping operators, to build a battery swapping service network architecture that connects battery swapping suppliers, battery swapping operators, and users to accelerate the growth of the user base and strengthen the layout of the service network. However, as the scale of the channel continues to expand, the complexity and challenges of managing battery swapping operators have become increasingly prominent.

[0003] In order to maximize the interests of battery swap suppliers, battery swap suppliers need to conduct real-time monitoring and identify business anomalies of their subordinate battery swap operators. In related technologies, when monitoring battery swap suppliers, manual offline visits are often used to identify whether the battery swap supplier has business anomalies, and battery swap suppliers with business anomalies are dealt with in a timely manner. This manual offline visit method has the problem of low evaluation efficiency, and the method based on manual subjective evaluation will also lead to low accuracy of evaluation results.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present invention provide a business anomaly assessment method for battery swap operators, a device thereof, and an electronic device, so as to at least solve the technical problem in the related art of conducting business anomaly assessments on battery swap suppliers through manual offline visits, resulting in low accuracy of assessment results.

[0006] According to one aspect of an embodiment of the present invention, a method for evaluating business anomalies of a battery swap operator is provided, comprising: collecting user data and business operation data of the battery swap operator, and preprocessing the user data and the business operation data, wherein the battery swap operator is used to promote battery swap services; inputting the preprocessed user data into an abnormal user feature recognition model to output a first abnormal user recognition result, and inputting the preprocessed user data into an abnormal user preference entropy recognition model to output a second abnormal user recognition result, and calculating an abnormal user evaluation score based on the first abnormal user recognition result and the second abnormal user recognition result; calculating a user development level score based on the preprocessed user data; calculating an operation level score and a service level score of the battery swap operator based on the preprocessed business operation data; calculating a comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and identifying battery swap operators with business anomalies based on the comprehensive evaluation score.

[0007] Furthermore, the preprocessed user data is input into an abnormal user feature recognition model, and the step of outputting a first abnormal user recognition result includes: inputting the preprocessed user data into an abnormal user feature recognition model, and extracting user features corresponding to each user through the abnormal user feature recognition model; matching the user features with the abnormal user features through the abnormal user feature recognition model, and determining that the user is an abnormal user when the user features corresponding to the user hit any abnormal user feature, wherein the abnormal user features include: abnormal features of the number of battery swaps, profit features of purchasing battery swap packages, and abnormal features of new user invitations; generating a first abnormal user list for the identified abnormal users through the abnormal user feature recognition model, and outputting the first abnormal user list as the first abnormal user recognition result.

[0008] Furthermore, the preprocessed user data is input into the abnormal user preference entropy identification model, and the step of outputting the second abnormal user identification result includes: extracting the user's battery replacement timestamp in the user data through the abnormal user preference entropy identification model, and calculating the time interval between two adjacent battery replacements of the user based on the user's battery replacement timestamp to obtain a battery replacement time interval sequence, and calculating the battery replacement time interval preference entropy of each user based on the battery replacement time interval sequence; extracting the user consumption data in the user data through the abnormal user preference entropy identification model, and calculating the consumption distribution data of each user based on the user consumption data, and calculating the battery replacement price preference entropy of each user based on the consumption distribution data, wherein the consumption distribution data represents the price of the battery replacement package purchased by the user. The frequency distribution falls within each price range; the user evaluation data in the user data is extracted through the abnormal user preference entropy identification model, and the evaluation distribution data of each user is calculated based on the user evaluation data, and the battery swap evaluation preference entropy of each user is calculated based on the evaluation distribution data, wherein the evaluation distribution data represents the frequency distribution of the evaluation scores posted by users after using the battery swap service in each score range; the preference entropy score of each user is calculated based on the battery swap time interval preference entropy, the battery swap price preference entropy and the battery swap evaluation preference entropy and the corresponding weight values, abnormal users are identified based on the preference entropy scores, and a second abnormal user list is generated according to the identified abnormal users, and the second abnormal user list is output as the second abnormal user identification result.

[0009] Furthermore, the step of calculating an abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result includes: performing an intersection calculation on the first abnormal user list in the first abnormal user identification result and the second abnormal user list in the second abnormal user identification result to obtain an abnormal user list; counting the number of abnormal users in the abnormal user list and the total number of battery swap users in the user data of the battery swap operator; calculating the ratio of the number of abnormal users to the total number of battery swap users to obtain an abnormal user evaluation score.

[0010] Furthermore, the step of calculating the user development level score based on the pre-processed user data includes: counting the total number of subordinate users of the battery swap operator during the evaluation period based on the pre-processed user data; counting the proportion of new users of the battery swap operator during the evaluation period based on the pre-processed user data, wherein the proportion of new users represents the proportion of users who purchase battery swap services for the first time during the evaluation period to the total number of subordinate users; counting the proportion of old users of the battery swap operator during the evaluation period based on the pre-processed user data, wherein the proportion of old users represents the proportion of users who purchase battery swap services not for the first time during the evaluation period to the total number of subordinate users. The proportion of the total number of subordinate users; the proportion of off-grid users of the battery swap operator within the evaluation period based on the pre-processed user data, wherein the off-grid user proportion represents the proportion of users who did not purchase the battery swap service in the current evaluation period but purchased the battery swap service in the previous evaluation period adjacent to the current evaluation period to the total number of subordinate users; the total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users are normalized, and the user development level score is calculated based on the normalized total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users and the corresponding weight values.

[0011] Furthermore, the step of calculating the operating level score of the battery swap operator based on the pre-processed business operation data includes: extracting the revenue, cost and fixed expenditure of the battery swap operator during the evaluation period from the pre-processed business operation data; calculating the operating profit margin of the battery swap operator during the evaluation period based on the revenue, cost and fixed expenditure to obtain the operating level score.

[0012] Furthermore, the step of calculating the service level score of the battery swap operator based on the pre-processed business operation data includes: calculating the average response time and response timeliness of the battery swap operator based on the pre-processed business operation data, and calculating the service response score based on the average response time and response timeliness; calculating the correct answer ratio of consultations of the battery swap operator based on the pre-processed business operation data, and obtaining the service accuracy score based on the correct answer ratio of consultations, wherein the correct answer ratio of consultations indicates the proportion of consultations with correct results returned by the battery swap operator when processing user consultations to the total number of consultations; calculating the average value of the service attitude scores of user feedback based on the pre-processed business operation data to obtain the service attitude score of the battery swap operator; calculating the service level score of the battery swap operator based on the service response score, service accuracy score and service attitude score.

[0013] According to another aspect of an embodiment of the present invention, a business anomaly assessment device for a battery swap operator is also provided, including: a collection unit for collecting user data and business operation data of the battery swap operator, and preprocessing the user data and the business operation data, wherein the battery swap operator is used to promote battery swap services; an output unit for inputting the preprocessed user data into an abnormal user feature recognition model, outputting a first abnormal user recognition result, and inputting the preprocessed user data into an abnormal user preference entropy recognition model, outputting a second abnormal user recognition result, and calculating an abnormal user evaluation score based on the first abnormal user recognition result and the second abnormal user recognition result; a first calculation unit for calculating a user development level score based on the preprocessed user data; a second calculation unit for calculating the operation level score and service level score of the battery swap operator based on the preprocessed business operation data; an evaluation unit for calculating a comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and identifying battery swap operators with business anomalies based on the comprehensive evaluation score.

[0014] Furthermore, the output unit includes: a first extraction module, used to input the preprocessed user data into an abnormal user feature recognition model, and extract user features corresponding to each user through the abnormal user feature recognition model; a first matching module, used to match the user features and the abnormal user features through the abnormal user feature recognition model, and determine that the user is an abnormal user when the user features corresponding to the user hit any abnormal user features, wherein the abnormal user features include: abnormal features of the number of battery swaps, profit features of purchasing battery swap packages, and abnormal features of new user invitations; a first output module, used to generate a first abnormal user list for the identified abnormal users through the abnormal user feature recognition model, and output the first abnormal user list as the first abnormal user identification result.

[0015] Furthermore, the output unit also includes: a first calculation module, which is used to extract the user battery replacement timestamp in the user data through the abnormal user preference entropy recognition model, and calculate the time interval between two adjacent battery replacements of the user based on the user battery replacement timestamp to obtain a battery replacement time interval sequence, and calculate the battery replacement time interval preference entropy of each user based on the battery replacement time interval sequence; a second calculation module, which is used to extract the user consumption data in the user data through the abnormal user preference entropy recognition model, and calculate the consumption distribution data of each user based on the user consumption data, and calculate the battery replacement price preference entropy of each user based on the consumption distribution data, wherein the consumption distribution data represents the frequency distribution of the battery replacement package prices purchased by the user falling within various price ranges; a third calculation module A module is used to extract user evaluation data from the user data through the abnormal user preference entropy identification model, and calculate the evaluation distribution data of each user based on the user evaluation data, and calculate the battery replacement evaluation preference entropy of each user based on the evaluation distribution data, wherein the evaluation distribution data represents the frequency distribution of the evaluation scores posted by users after using the battery replacement service in each score interval; a second output module is used to calculate the preference entropy score of each user based on the battery replacement time interval preference entropy, the battery replacement price preference entropy and the battery replacement evaluation preference entropy and the corresponding weight values, identify abnormal users based on the preference entropy scores, and generate a second abnormal user list according to the identified abnormal users, and output the second abnormal user list as the second abnormal user identification result.

[0016] Furthermore, the output unit also includes: a fourth calculation module, used to perform intersection calculation on the first abnormal user list in the first abnormal user identification result and the second abnormal user list in the second abnormal user identification result to obtain an abnormal user list; a first statistical module, used to count the number of abnormal users in the abnormal user list and the total number of battery swap users in the user data of the battery swap operator; a fifth calculation module, used to calculate the ratio of the number of abnormal users to the total number of battery swap users to obtain an abnormal user evaluation score.

[0017] Furthermore, the first calculation unit includes: a first statistical module for counting the total number of subordinate users of the battery swap operator within the evaluation period based on the preprocessed user data; a second statistical module for counting the proportion of new users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of new users represents the proportion of users who purchase battery swap services for the first time within the evaluation period to the total number of subordinate users; a third statistical module for counting the proportion of old users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of old users represents the proportion of users who purchase battery swap services not for the first time within the evaluation period to the total number of subordinate users the proportion of the number of off-grid users of the battery swap operator within the evaluation period based on the pre-processed user data, wherein the off-grid user proportion represents the proportion of users who have not purchased the battery swap service in the current evaluation period but have purchased the battery swap service in the previous evaluation period adjacent to the current evaluation period to the total number of subordinate users; the first processing module is used to normalize the total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users, and calculate the user development level score according to the normalized total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users and the corresponding weight values.

[0018] Furthermore, the second calculation unit includes: a second extraction module, used to extract the revenue, cost and fixed expenditure of the battery swap operator during the evaluation period from the pre-processed business operation data; a sixth calculation module, used to calculate the operating profit margin of the battery swap operator during the evaluation period based on the revenue, cost and fixed expenditure to obtain the operating level score.

[0019] Furthermore, the second calculation unit also includes: a seventh calculation module, which is used to calculate the average response time and response timeliness of the battery swap operator based on the pre-processed business operation data, and calculate the service response score based on the average response time and response timeliness; an eighth calculation module, which is used to calculate the correct answer ratio of the battery swap operator's consultations based on the pre-processed business operation data, and obtain the service accuracy score based on the correct answer ratio of consultations, wherein the correct answer ratio of consultations indicates the proportion of consultations with correct results returned by the battery swap operator when processing user consultations to the total number of consultations; a ninth calculation module, which is used to calculate the average service attitude score of user feedback based on the pre-processed business operation data, and obtain the service attitude score of the battery swap operator; a tenth calculation module, which is used to calculate the service level score of the battery swap operator based on the service response score, service accuracy score and service attitude score.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned business anomaly assessment methods for battery swap operators.

[0021] According to another aspect of an embodiment of the present invention, an electronic device is also provided, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned business anomaly assessment methods for battery swap operators.

[0022] In the present application, the following steps are taken: collecting user data and business operation data of the battery swap operator, and preprocessing the user data and business operation data, wherein the battery swap operator is used to promote the battery swap service, and inputting the preprocessed user data into the abnormal user feature recognition model, outputting the first abnormal user identification result, and inputting the preprocessed user data into the abnormal user preference entropy recognition model, outputting the second abnormal user identification result, calculating the abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result, and then calculating the user development level score based on the preprocessed user data, calculating the operation level score and service level score of the battery swap operator based on the preprocessed business operation data, and finally calculating the comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and identifying the battery swap operator with business abnormalities based on the comprehensive evaluation score.

[0023] In this application, by collecting user data and business operation data of the battery swap supplier, and analyzing the abnormal situations of the supplier's subordinate users based on the abnormal user feature recognition model and the abnormal user preference entropy recognition model, and by calculating the user development level score, the battery swap operator's operation level score and the service level score, the battery swap operator's subordinate user development situation, operation level and service level are analyzed. Artificial intelligence analysis and big data analysis technology are used to comprehensively score the battery swap supplier from multiple dimensions such as subordinate user abnormal situations, subordinate user development situation, operation level and service level, and identify the battery swap supplier with business abnormalities, thereby improving the evaluation efficiency. At the same time, based on multi-dimensional data evaluation, the accuracy of the evaluation results is improved. This solves the technical problem of low accuracy of the evaluation results in the related technology of evaluating the business abnormality of the battery swap supplier through manual offline visits. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a service anomaly assessment method for a battery swap operator is shown;

[0026] Figure 2 is a flowchart of an optional service anomaly assessment method for a battery swap operator according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of an optional service anomaly assessment process for a battery swap operator according to an embodiment of the present invention;

[0028] Figure 4 is a schematic diagram of an optional service anomaly assessment device for a battery swap operator according to an embodiment of the present invention;

[0029] Figure 5 This is a hardware structure block diagram of an electronic device (or mobile device) that optionally executes a service anomaly assessment method for a battery swap operator according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the business anomaly assessment method and device for battery swap operators in this application can be used in the field of artificial intelligence, i.e., big data, when evaluating and identifying battery swap operators with business anomalies. It can also be used in any field except the field of blockchain technology. When evaluating and identifying battery swap operators with business anomalies, this application does not limit the application field of the business anomaly assessment method and device for battery swap operators.

[0033] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation portals for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0034] The following embodiments of the present invention can be applied to the business anomaly assessment systems / applications / devices of various battery swap operators. The present invention conducts comprehensive testing and anomaly assessment of battery swap suppliers from four dimensions: user development and maintenance level, abnormal user assessment and identification, operating cost accounting, and service quality assessment. This comprehensive and objective approach can effectively identify battery swap suppliers with business anomalies, improve the accuracy of the identification results, and effectively reduce losses caused by business anomalies of battery swap suppliers.

[0035] The present invention will be described in detail below with reference to various embodiments.

[0036] Example 1

[0037] According to an embodiment of the present invention, an embodiment of a business anomaly assessment method for a battery swap operator is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for evaluating the abnormality of a battery swapping operator's business is shown. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0039] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0040] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the business anomaly assessment method for battery swap operators in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned business anomaly assessment method for battery swap operators. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0041] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0042] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0043] Under the above operating environment, this application provides Figure 2 The business anomaly assessment method for battery swap operators shown in the figure is implemented by the business anomaly assessment system of the battery swap operator.

[0044] Figure 2 is a flow chart of an optional service anomaly assessment method for a battery swap operator according to an embodiment of the present invention. Figure 2 As shown, the method includes the following steps:

[0045] Step S201: Collect user data and business operation data of the battery swap operator, and pre-process the user data and business operation data.

[0046] In the above step S201, the battery swap operator refers to an enterprise or individual that provides battery swap services. The battery swap operator cooperates with the battery swap supplier, uses the supplier's battery resources and battery swap network, is responsible for market promotion, develops new users, maintains old users, and handles user problems and complaints, etc., and works with the supplier to enhance the market influence and user satisfaction of the battery swap business. User data is obtained based on users of the battery swap operator's services, and may include users' battery swap behavior records, battery swap package ordering information, complaint records, satisfaction evaluation information, etc. These data can reflect key information such as users' usage preferences, usage behavior patterns, and satisfaction with battery swap services. Business operation data may include promotional activity data, cost accounting information, revenue, service quality indicators (such as complaint rate, response time), etc. of the battery swap operator. These data can be used to assist in analyzing the operator's economic benefits, operational efficiency, and customer service quality.

[0047] In an embodiment of the present invention, an automated data collection tool can be used to capture user data and business operation data from systems such as the battery swap service system of a battery swap supplier or the battery swap service system of a battery swap operator on a regular or real-time basis to ensure the timeliness and integrity of the data.

[0048] It should be noted that data preprocessing mainly includes: data integration, data cleaning, data feature extraction and vector encoding, etc.

[0049] In step S202, the preprocessed user data is input into an abnormal user feature recognition model to output a first abnormal user recognition result, and the preprocessed user data is input into an abnormal user preference entropy recognition model to output a second abnormal user recognition result, and an abnormal user evaluation score is calculated based on the first abnormal user recognition result and the second abnormal user recognition result.

[0050] In the above step S202, abnormal users of the battery swap supplier are identified through the abnormal user feature identification model and the abnormal user preference entropy identification model. The abnormal user feature identification model can identify specific user features, thereby realizing accurate identification of abnormal users. The abnormal user preference entropy identification model uses information entropy theory to analyze user behavior patterns, and can identify user behaviors that actually deviate from the normal distribution, thereby realizing fuzzy identification of abnormal users. By taking the intersection of the identification results output by the two models, the list of abnormal users and the number of abnormal users under the battery swap supplier can be determined, thereby calculating the abnormal user evaluation score of the battery swap supplier. The identification of abnormal users can reflect whether the battery swap supplier has committed fraud when promoting battery swap services, such as defrauding the battery swap supplier of commissions by falsely attracting a large number of users.

[0051] Furthermore, the preprocessed user data is input into the abnormal user feature recognition model, and the step of outputting the first abnormal user identification result includes: inputting the preprocessed user data into the abnormal user feature recognition model, and extracting the user features corresponding to each user through the abnormal user feature recognition model; matching the user features and the abnormal user features through the abnormal user feature recognition model, and determining that the user is an abnormal user when the user features corresponding to the user hit any abnormal user feature, wherein the abnormal user features include: abnormal features of the number of battery swaps, profit features of purchasing battery swap packages, and abnormal features of new user invitations; generating a first abnormal user list for the identified abnormal users through the abnormal user feature recognition model, and outputting the first abnormal user list as the first abnormal user identification result.

[0052] Specifically, the abnormal user feature recognition model is an algorithm model established based on clear business rules and user behavior features, which is used to identify users with obvious abnormal behavior features, such as silent users, abnormal profit-seeking users (formerly known as "wool-shearing users"), and abnormal new user invitation users. This model uses preset rules and thresholds, such as no battery swapping records within the package period, users participating in the rebate activity after purchasing the package and then refunding but retaining the preferential benefits, etc., to accurately screen out potential abnormal users and form the first abnormal user recognition result. First, the preprocessed user data is input into the abnormal user feature recognition model. The model analyzes data such as the number of battery swapping times, package purchase behavior, and new user invitation behavior of each user, and extracts corresponding user features, such as: the number of battery swapping times within the validity period of the battery swapping package, the subsequent behavior features of users after purchasing the battery swapping package, and the behavior features of old users inviting new users. Then, the extracted user features are matched with the preset abnormal user features. If the user features match any one of the abnormal user features, the user is determined to be an abnormal user, thus accurately identifying users with abnormal behavior patterns.

[0053] It should be noted that the specific abnormal user features include: abnormal battery swapping times feature, profit-making feature of purchasing the battery swapping package, and abnormal new user invitation feature. The abnormal battery swapping times feature reflects that after the user purchases the battery swapping package, the battery swapping service is not used within the package validity period. The profit-making feature of purchasing the battery swapping package reflects that the user refunds after purchasing the battery swapping package through the rebate activity but uses the preferential activities related to the purchased package. The abnormal new user invitation feature reflects that existing users pull a large number of new users in a short period and there are abnormal device logins for the new users. Based on the preset abnormal user features, the above-mentioned features with abnormal behavior can be recognized. If the number of abnormal users under the battery swapping supplier is relatively large, it can reflect from one aspect that there may be business abnormalities for this battery swapping supplier.

[0054] Furthermore, the pre-processed user data is input into the abnormal user preference entropy recognition model, and the step of outputting the second abnormal user identification result includes: extracting the user's battery replacement timestamp in the user data through the abnormal user preference entropy recognition model, and calculating the time interval between two adjacent battery replacements of the user based on the user's battery replacement timestamp to obtain a battery replacement time interval sequence, and calculating the battery replacement time interval preference entropy of each user based on the battery replacement time interval sequence; extracting the user consumption data in the user data through the abnormal user preference entropy recognition model, and calculating the consumption distribution data of each user based on the user consumption data, and calculating the battery replacement price preference entropy of each user based on the consumption distribution data, wherein the consumption distribution data represents the price of the battery replacement package purchased by the user. The frequency distribution of the evaluation scores in each price range is obtained by grid analysis; the user evaluation data in the user data is extracted through the abnormal user preference entropy identification model, and the evaluation distribution data of each user is calculated based on the user evaluation data, and the battery swap evaluation preference entropy of each user is calculated based on the evaluation distribution data, wherein the evaluation distribution data represents the frequency distribution of the evaluation scores posted by users after using the battery swap service in each score range; the preference entropy score of each user is calculated based on the battery swap time interval preference entropy, the battery swap price preference entropy and the battery swap evaluation preference entropy and the corresponding weight values, abnormal users are identified based on the preference entropy score, and a second abnormal user list is generated according to the identified abnormal users, and the second abnormal user list is output as the second abnormal user identification result.

[0055] Specifically, the Abnormal User Preference Entropy Identification Model uses information entropy theory to analyze user behavior patterns, identifying users whose behavior appears normal but actually deviates from the normal distribution. The Abnormal User Preference Entropy Identification Model identifies abnormal users based on their preferences for battery swap intervals, battery swap prices, and battery swap service.

[0056] First, the abnormal user preference entropy identification model extracts the timestamps of all user battery swaps from the preprocessed user data, including the time of power collection and return for each battery swap. Based on the timestamp data, the time interval between two consecutive battery swaps for each user is calculated to generate a battery swap time interval sequence. Using the information entropy calculation method, the frequency of each user's battery swap time interval falling within each battery swap time interval interval is analyzed, thereby calculating each user's battery swap time interval preference entropy, reflecting the uncertainty of the user's battery swap time regularity. For example: based on business characteristics, the battery swap time interval is divided into 0-4 hours, 4-8 hours, 8-12 hours, 12-16 hours, 16-24 hours, and more than 24 hours; and the number of times each user's battery swap time interval falls within each of the above intervals is counted to obtain the frequency distribution of the user's battery swap time interval.

[0057] The battery replacement time interval preference entropy can be expressed as: H = ∑p i log(p i ), where p iIt represents the frequency of each user's battery replacement time interval falling in each battery replacement time interval interval. For example, the probability of a user in each time interval interval is p1=0.5, p2=0.3, and p3=0.2, respectively. Then its entropy value is H=-0.5(log(0.5)-0.3(log(0.3)-0.2(log(0.2)).

[0058] The abnormal user preference entropy identification model further extracts each user's consumption data from the user data, including the purchase and consumption records of the battery swap package. Then, based on the user consumption data, the frequency distribution of the price of each user's battery swap package purchase falling within each price range is calculated to obtain the user's consumption distribution data, from which the battery swap price preference entropy of each user can be calculated. The calculation formula for the battery swap price preference entropy is expressed as: H = ∑q i log(q i ), where q i It indicates the probability that the price of the battery swap package purchased by the user falls within each price range.

[0059] Finally, the abnormal user preference entropy identification model extracts feedback about the user's evaluation of the battery swap service from the user data, including the rating records after each service. Analyze the frequency distribution of each user's ratings in each evaluation score range (such as 1 to 5 points). Based on the information entropy calculation principle, the evaluation distribution data is used as input to calculate the battery swap evaluation preference entropy of each user to reflect the regularity and consistency of the user's evaluation behavior. The calculation formula for the battery swap evaluation preference entropy is expressed as: H = ∑w i log(w i ), where w i It indicates the probability that the user's evaluation score for the battery swap service falls within each evaluation score range.

[0060] After calculating each user's battery swap time interval preference entropy, battery swap price preference entropy, and battery swap evaluation preference entropy, the mean μ and standard deviation σ of the three are calculated. Then, the value of each preference entropy is standardized through the formula and converted into a standard value. Then, the preference entropy is integrated based on the standard value and weight value of each preference entropy to calculate the preference entropy score of each user. The preference entropy score is compared with the preset preference entropy threshold. If the user's preference entropy score exceeds the preset preference entropy threshold, the user is marked as an abnormal user, and the second abnormal user identification list is obtained based on the abnormal user preference entropy identification model and output.

[0061] By extracting multi-level information such as time intervals, consumption distribution, and evaluation distribution from user data, and using the preference entropy recognition model to conduct in-depth behavioral analysis, abnormal users of battery swap suppliers can be accurately identified, avoiding misjudgments caused by single rule detection and improving the comprehensiveness and accuracy of abnormal user identification.

[0062] Furthermore, the step of calculating the abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result includes: performing an intersection calculation on the first abnormal user list in the first abnormal user identification result and the second abnormal user list in the second abnormal user identification result to obtain an abnormal user list; counting the number of abnormal users in the abnormal user list and the total number of battery swap users in the user data of the battery swap operator; calculating the ratio of the number of abnormal users to the total number of battery swap users to obtain an abnormal user evaluation score.

[0063] Specifically, after obtaining the first abnormal user identification result and the second abnormal user identification result, the intersection of the first abnormal user list in the first abnormal user identification result and the second abnormal user list in the second abnormal user identification result is obtained to find users that appear in both the first abnormal user list and the second abnormal user list. These users have obvious abnormal behavior characteristics and exhibit irregular behavior patterns, and are therefore considered to be high-probability abnormal users. The result of the intersection operation forms the final abnormal user list, which contains abnormal user records that have been cross-validated by the dual model. The number of users in the generated abnormal user list is counted to obtain the number of abnormal users. At the same time, the total number of all battery swap users in the user data of the battery swap operator is counted, that is, the battery swap user base. The number of abnormal users is compared with the total number of battery swap users, and the ratio between the two is calculated, that is, the abnormal user ratio, based on which the abnormal user evaluation score can be obtained.

[0064] The purpose of the intersection calculation is to compare the results of the two abnormal user identification models and find users that are marked by both models to enhance the accuracy and credibility of abnormal user identification. This will improve the accuracy of the subsequent abnormality identification results for battery swap suppliers.

[0065] Step S203: Calculate the user development level score based on the pre-processed user data.

[0066] In the above step S203, based on the pre-processed development data, the user development level score corresponding to the battery swap operator can also be calculated by analyzing the number of users, the proportion of new users, the proportion of old users and the user churn rate. The user development level score reflects the ability of the battery swap operator to develop new customers and maintain old customers. If the user development level is lower than the threshold, it indicates that the battery swap operator may have business abnormalities.

[0067] Furthermore, the step of calculating the user development level score based on the preprocessed user data includes: counting the total number of subordinate users of the battery swap operator within the evaluation period based on the preprocessed user data; counting the proportion of new users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of new users represents the proportion of the number of users who purchase the battery swap service for the first time within the evaluation period to the total number of subordinate users; counting the proportion of old users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of old users represents the proportion of the number of users who purchase the battery swap service not for the first time within the evaluation period to the total number of subordinate users; counting the proportion of off-grid users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of off-grid users represents the proportion of users who did not purchase the battery swap service in the current evaluation period but purchased the battery swap service in the previous evaluation period adjacent to the current evaluation period to the total number of subordinate users; normalizing the total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users, and calculating the user development level score based on the normalized total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users and the corresponding weight values.

[0068] Specifically, the user development level score is calculated based on multi-dimensional information such as the total number of subordinate users, the proportion of new users, the proportion of old users, and the proportion of off-grid users. First, from the pre-processed user data, all user records within the evaluation period are screened out to obtain the total number of subordinate users of the battery swap operator within the evaluation period. The total number of subordinate users is a key indicator for evaluating the scale of the operator's user base, which directly reflects the operator's influence in the market and user coverage. Then, the number of new users who purchased the battery swap service for the first time during the evaluation period is counted, and the proportion of new users is calculated based on the number of new users and the total number of subordinate users. The proportion of new users reflects the operator's user acquisition ability within a specific period and is an important indicator for measuring its market expansion and user attractiveness. Secondly, the number of old users who did not purchase the battery swap service for the first time during the evaluation period is calculated, and then the proportion of old users is calculated based on the number of old users and the total number of subordinate users. The proportion of old users reflects user loyalty and the operator's user retention ability, and is one of the key indicators of operational health. It is also necessary to count the number of churned users during the evaluation period. Churned users are users who did not purchase battery swap services during the current evaluation period but purchased battery swap services in the previous evaluation period, so as to calculate the proportion of off-grid users during the evaluation period. The proportion of off-grid users is a key indicator for evaluating user churn and reflects the operator's performance in user retention.

[0069] Finally, through normalization, the total number of subordinate users, the proportion of new users, the proportion of old users, and the proportion of off-grid users are adjusted to the same level, eliminating the impact of differences in the numerical ranges of different indicators and ensuring fairness and accuracy when calculating the user development level score. Corresponding weights are set for the total number of subordinate users, the proportion of new users, the proportion of old users, and the proportion of off-grid users after normalization. Finally, the user development level score of the battery swap operator is calculated based on the total number of subordinate users, the proportion of new users, the proportion of old users, and the proportion of off-grid users and their corresponding weights.

[0070] Specifically, the total number of subordinate users is normalized: U min is the minimum value of the total number of subordinate users, U max is the maximum value of the total number of subordinate users, U is the total number of subordinate users before normalization, and U n is the total number of subordinate users after normalization.

[0071] Normalization of new user ratio: NUP min is the minimum value of the new user ratio, NUP max is the maximum value of the new user ratio, NUP is the new user ratio before normalization, NUP n is the normalized proportion of new users.

[0072] Normalization of the proportion of old users: OUP min is the minimum value of the proportion of old users, OUP max is the maximum ratio of old users, OUP is the ratio of old users before normalization, OUP n is the normalized proportion of old users.

[0073] Normalization of the proportion of off-grid users: DUP min is the minimum value of the proportion of off-grid users, DUP max is the maximum value of the proportion of off-grid users, DUP is the proportion of off-grid users before normalization, and DUP n is the normalized proportion of users who have left the network.

[0074] Step S204: Calculate the operation level score and service level score of the battery swap operator based on the pre-processed business operation data.

[0075] In the above step S204, the operation level and service quality of the battery swap operator are maliciously evaluated based on the processed business operation data, so as to obtain the operation level score and service level score of the battery swap operator, which covers the quantitative analysis of the operator's profitability and comprehensively evaluates its customer service performance.

[0076] Furthermore, the step of calculating the operating level score of the battery swap operator based on the preprocessed business operation data includes: extracting the revenue, cost and fixed expenditure of the battery swap operator during the evaluation period from the preprocessed business operation data; calculating the operating profit margin of the battery swap operator during the evaluation period based on the revenue, cost and fixed expenditure to obtain the operating level score.

[0077] Specifically, when calculating the battery swap operator's operational level score, the revenue, cost, and fixed expenses of the battery swap operator during the evaluation period are extracted from the pre-processed business operation data. Fixed expenses may include taxes, equipment maintenance costs, etc. The profit data can be calculated by the difference between the revenue and cost. Then, based on the ratio of the difference between the profit data and fixed expenses to the revenue, the operating profit margin of the battery swap service provider during the evaluation period is calculated and used as the operational level score.

[0078] Furthermore, the step of calculating the service level score of the battery swap operator based on the preprocessed business operation data includes: calculating the average response time and response timeliness of the battery swap operator based on the preprocessed business operation data, and calculating the service response score based on the average response time and response timeliness; calculating the correct answer ratio of the battery swap operator's consultations based on the preprocessed business operation data, and obtaining the service accuracy score based on the correct answer ratio of consultations, wherein the correct answer ratio of consultations indicates the proportion of consultations with correct results returned by the battery swap operator when processing user consultations to the total number of consultations; calculating the average service attitude score of user feedback based on the preprocessed business operation data to obtain the service attitude score of the battery swap operator; calculating the service level score of the battery swap operator based on the service response score, service accuracy score and service attitude score.

[0079] Specifically, the service level score consists of three parts: service response score, service accuracy score and service attitude score. First, the user consultation time, first response time and response status data are extracted from the pre-processed business operation data. The average response time of the battery swap operator from the time the user initiates the consultation to the first reply is calculated. At the same time, the proportion of consultations that are responded to within the specified time (for example, within 1 hour) to the total number of consultations is calculated to obtain the response timeliness rate. The service response score is calculated based on the average response time and the response timeliness rate. Secondly, the operator's feedback results on user consultations and the user's confirmation of the feedback results are obtained from the pre-processed business operation data. When the operator handles user consultations, the proportion of consultations that are confirmed as correct results to the total number of consultations is counted to obtain the proportion of correct answers to consultations, and thus the service accuracy score is obtained. Finally, from the pre-processed business operation data, the user's feedback score on the operator's service attitude is collected, and the average of the service attitude scores of all user feedback is calculated to obtain the service attitude score of the battery swap operator. Based on the importance of the service response score, service accuracy score, and service attitude score, reasonable weights are set for each (for example, a weight of 30% for response speed, a weight of 30% for service accuracy, and a weight of 40% for service attitude). Using a weighted average calculation method, the service response score, service accuracy score, and service attitude score are comprehensively calculated according to the set weights to derive the service level score of the battery swap operator. The service level score comprehensively considers the three key dimensions of the operator's service response speed, service accuracy, and service attitude, forming a comprehensive evaluation of the battery swap operator's service level.

[0080] Step S205: Calculate the comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score, service level score and their corresponding weight values, and identify the battery swap operator with business abnormalities based on the comprehensive evaluation score.

[0081] In the above step S205, the comprehensive evaluation score of the battery swap operator is calculated by weighted average calculation based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and the score values ​​of the battery swap operator under multiple dimensions are comprehensively considered to obtain a comprehensive evaluation result. Based on a pre-set business abnormality score threshold (such as less than 60 points is considered as business abnormality), the comprehensive evaluation score of the battery swap operator is compared with the threshold. For operators with scores lower than the threshold, they will be identified as battery swap operators with business abnormalities, and cooperation with battery swap operators with business abnormalities can be terminated.

[0082] Through the above steps, the user data and business operation data of the battery swap operator are collected, and the user data and business operation data are preprocessed, wherein the battery swap operator is used to promote the battery swap service, and the preprocessed user data is input into the abnormal user feature recognition model to output the first abnormal user recognition result, and the preprocessed user data is input into the abnormal user preference entropy recognition model to output the second abnormal user recognition result, and the abnormal user evaluation score is calculated based on the first abnormal user recognition result and the second abnormal user recognition result, and then the user development level score is calculated based on the preprocessed user data, and the operation level score and service level score of the battery swap operator are calculated based on the preprocessed business operation data, and finally the comprehensive evaluation score of the battery swap operator is calculated based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and the battery swap operator with business abnormalities is identified based on the comprehensive evaluation score.

[0083] In this embodiment, user data and business operation data of the battery swap supplier are collected, and the abnormal situations of the supplier's subordinate users are analyzed based on the abnormal user feature recognition model and the abnormal user preference entropy recognition model. The development situation, operation level and service level of the subordinate users of the battery swap operator are analyzed by calculating the user development level score, the operation level score and the service level score of the battery swap operator. Artificial intelligence analysis and big data analysis technology are used to comprehensively score the battery swap supplier from multiple dimensions such as the abnormal situation of subordinate users, the development situation of subordinate users, the operation level and the service level, and identify the battery swap supplier with business abnormalities, thereby improving the evaluation efficiency. At the same time, based on the multi-dimensional data evaluation, the accuracy of the evaluation results is improved. This solves the technical problem of low accuracy of the evaluation results in the related technology of evaluating the business abnormality of the battery swap supplier through manual offline visits.

[0084] The following describes in detail another optional specific implementation.

[0085] The embodiment of the present invention proposes a multi-dimensional big data-based abnormality assessment method for battery swap operators from four dimensions: user development and maintenance level, abnormal user assessment and identification, operating cost accounting, and service quality assessment. It can comprehensively and objectively identify battery swap operators with business abnormalities. Figure 3 FIG. 1 is a schematic diagram of an optional business abnormality assessment process for a battery swap operator according to an embodiment of the present invention. Figure 3As shown, first, the user data and business operation data of each battery swap operator are obtained from the database. Based on the user data, the abnormal user feature recognition model and the abnormal user preference entropy recognition model are used to output the abnormal user evaluation results respectively, and the intersection of the two outputs is used to determine the abnormal user, thereby calculating the abnormal user evaluation score of the battery swap operator. Based on the user data, the business user development level of the battery swap operator can also be analyzed, thereby calculating the user development level score.

[0086] Furthermore, based on the business operation data of battery swap operators, operating costs and service quality can be analyzed to calculate the operation level score and service level score of the battery swap operators. Finally, a comprehensive evaluation score is calculated based on the abnormal user evaluation score, user development level score, operation level score and service level score to calculate the comprehensive evaluation score of each battery swap operator. Based on the comprehensive evaluation score, battery swap operators with business anomalies can be identified, thereby reducing the losses caused by abnormal battery swap operators.

[0087] The following describes it in detail with reference to another embodiment.

[0088] Example 2

[0089] The business anomaly assessment device for a battery swap operator provided in this embodiment includes multiple implementation units, each implementation unit corresponds to each implementation step in the above-mentioned embodiment 1. Its specific implementation method and beneficial effects can refer to the above-mentioned method embodiment and will not be repeated here.

[0090] Figure 4 is a schematic diagram of an optional service anomaly assessment device for a battery swap operator according to an embodiment of the present invention, such as Figure 4 As shown, the business anomaly assessment device of the battery swap operator may include: a collection unit 41, an output unit 42, a first calculation unit 43, a second calculation unit 44, and an assessment unit 45, wherein:

[0091] The collection unit 41 is used to collect user data and business operation data of the battery swap operator and pre-process the user data and business operation data, wherein the battery swap operator is used to promote the battery swap service;

[0092] An output unit 42 is configured to input the preprocessed user data into an abnormal user feature recognition model to output a first abnormal user recognition result, input the preprocessed user data into an abnormal user preference entropy recognition model to output a second abnormal user recognition result, and calculate an abnormal user evaluation score based on the first abnormal user recognition result and the second abnormal user recognition result;

[0093] A first calculation unit 43 is used to calculate the user development level score based on the pre-processed user data;

[0094] The second calculation unit 44 is used to calculate the operation level score and service level score of the battery swap operator based on the pre-processed business operation data;

[0095] The evaluation unit 45 is used to calculate the comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and identify the battery swap operator with business abnormalities based on the comprehensive evaluation score.

[0096] The above-mentioned business anomaly assessment device for battery swap operators collects user data and business operation data of the battery swap operators through the collection unit 41, and pre-processes the user data and business operation data, wherein the battery swap operators are used to promote battery swap services; the pre-processed user data is input into the abnormal user feature recognition model through the output unit 42, and a first abnormal user recognition result is output, and the pre-processed user data is input into the abnormal user preference entropy recognition model, and a second abnormal user recognition result is output, and an abnormal user evaluation score is calculated based on the first abnormal user recognition result and the second abnormal user recognition result; the user development level score is calculated based on the pre-processed user data through the first calculation unit 43; the operation level score and service level score of the battery swap operator are calculated based on the pre-processed business operation data through the second calculation unit 44; the comprehensive evaluation score of the battery swap operator is calculated based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values ​​through the evaluation unit 45, and the battery swap operator with business anomalies is identified based on the comprehensive evaluation score.

[0097] In this embodiment, user data and business operation data of the battery swap supplier are collected, and the abnormal situations of the supplier's subordinate users are analyzed based on the abnormal user feature recognition model and the abnormal user preference entropy recognition model. The development situation, operation level and service level of the subordinate users of the battery swap operator are analyzed by calculating the user development level score, the operation level score and the service level score of the battery swap operator. Artificial intelligence analysis and big data analysis technology are used to comprehensively score the battery swap supplier from multiple dimensions such as the abnormal situation of subordinate users, the development situation of subordinate users, the operation level and the service level, and identify the battery swap supplier with business abnormalities, thereby improving the evaluation efficiency. At the same time, based on the multi-dimensional data evaluation, the accuracy of the evaluation results is improved. This solves the technical problem of low accuracy of the evaluation results in the related technology of evaluating the business abnormality of the battery swap supplier through manual offline visits.

[0098] Furthermore, the output unit includes: a first extraction module, used to input the preprocessed user data into the abnormal user feature recognition model, and extract the user features corresponding to each user through the abnormal user feature recognition model; a first matching module, used to match the user features and abnormal user features through the abnormal user feature recognition model, and determine that the user is an abnormal user when the user features corresponding to the user hit any abnormal user features, wherein the abnormal user features include: abnormal features of the number of battery swaps, profit features of purchasing battery swap packages, and abnormal features of new user invitations; a first output module, used to generate a first abnormal user list for the identified abnormal users through the abnormal user feature recognition model, and output the first abnormal user list as the first abnormal user identification result.

[0099] Furthermore, the output unit also includes: a first calculation module, which is used to extract the user's battery replacement timestamp from the user data through the abnormal user preference entropy recognition model, and calculate the time interval between two adjacent battery replacements of the user based on the user's battery replacement timestamp to obtain a battery replacement time interval sequence, and calculate the battery replacement time interval preference entropy of each user based on the battery replacement time interval sequence; a second calculation module, which is used to extract the user consumption data from the user data through the abnormal user preference entropy recognition model, and calculate the consumption distribution data of each user based on the user consumption data, and calculate the battery replacement price preference entropy of each user based on the consumption distribution data, wherein the consumption distribution data represents the frequency distribution of the battery replacement package prices purchased by the user falling within various price ranges; a third calculation module A calculation module is used to extract user evaluation data from user data through an abnormal user preference entropy identification model, and calculate the evaluation distribution data of each user based on the user evaluation data, and calculate the battery swap evaluation preference entropy of each user based on the evaluation distribution data, wherein the evaluation distribution data represents the frequency distribution of the evaluation scores posted by users after using the battery swap service in each score range; a second output module is used to calculate the preference entropy score of each user based on the battery swap time interval preference entropy, the battery swap price preference entropy and the battery swap evaluation preference entropy and the corresponding weight values, identify abnormal users based on the preference entropy scores, and generate a second abnormal user list based on the identified abnormal users, and output the second abnormal user list as the second abnormal user identification result.

[0100] Furthermore, the output unit also includes: a fourth calculation module, used to perform intersection calculation on the first abnormal user list in the first abnormal user identification result and the second abnormal user list in the second abnormal user identification result to obtain an abnormal user list; a first statistical module, used to count the number of abnormal users in the abnormal user list and the total number of battery swap users in the user data of the battery swap operator; a fifth calculation module, used to calculate the ratio of the number of abnormal users to the total number of battery swap users to obtain an abnormal user evaluation score.

[0101] Furthermore, the first calculation unit includes: a first statistical module for counting the total number of subordinate users of the battery swap operator within the evaluation period based on the preprocessed user data; a second statistical module for counting the proportion of new users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of new users represents the proportion of users who purchase the battery swap service for the first time within the evaluation period to the total number of subordinate users; a third statistical module for counting the proportion of old users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of old users represents the proportion of users who purchase the battery swap service not for the first time within the evaluation period to the total number of subordinate users. The fourth statistical module is used to count the proportion of off-grid users of the battery swap operator within the evaluation period based on the pre-processed user data, wherein the proportion of off-grid users represents the proportion of users who have not purchased the battery swap service in the current evaluation period but have purchased the battery swap service in the previous evaluation period adjacent to the current evaluation period to the total number of subordinate users; the first processing module is used to normalize the total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users, and calculate the user development level score based on the normalized total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users and the corresponding weight values.

[0102] Furthermore, the second calculation unit includes: a second extraction module, used to extract the revenue, cost and fixed expenditure of the battery swap operator during the evaluation period from the preprocessed business operation data; a sixth calculation module, used to calculate the operating profit margin of the battery swap operator during the evaluation period based on the revenue, cost and fixed expenditure to obtain an operating level score.

[0103] Furthermore, the second calculation unit also includes: a seventh calculation module, which is used to calculate the average response time and response timeliness of the battery swap operator based on the preprocessed business operation data, and calculate the service response score based on the average response time and response timeliness; an eighth calculation module, which is used to calculate the correct answer ratio of the battery swap operator's consultations based on the preprocessed business operation data, and obtain the service accuracy score based on the correct answer ratio of consultations, wherein the correct answer ratio of consultations indicates the proportion of consultations with correct results returned by the battery swap operator when processing user consultations to the total number of consultations; a ninth calculation module, which is used to calculate the average service attitude score of user feedback based on the preprocessed business operation data, and obtain the service attitude score of the battery swap operator; a tenth calculation module, which is used to calculate the service level score of the battery swap operator based on the service response score, service accuracy score and service attitude score.

[0104] It should be noted that the acquisition unit 41, output unit 42, first calculation unit 43, second calculation unit 44, and evaluation unit 45 correspond to steps S201 to S205 in the first embodiment. The examples and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the contents disclosed in the first embodiment. It should be noted that the above modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules or units can also be part of the device and can be run in the computer terminal 10 provided in the first embodiment.

[0105] The present invention is described below in conjunction with another optional embodiment.

[0106] Example 3

[0107] An embodiment of the present invention may further provide an electronic device, Figure 5 This is a hardware structure block diagram of an electronic device (or mobile device) that optionally executes a service anomaly assessment method for a battery swap operator according to an embodiment of the present invention, such as Figure 5 As shown, the electronic device may include: one or more ( Figure 5 Only one is shown) processor 502, memory 504, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0108] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0109] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: collect user data and business operation data of the battery swap operator, and preprocess the user data and business operation data, wherein the battery swap operator is used to promote the battery swap service; input the preprocessed user data into the abnormal user feature recognition model, output the first abnormal user identification result, and input the preprocessed user data into the abnormal user preference entropy recognition model, output the second abnormal user identification result, and calculate the abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result; calculate the user development level score based on the preprocessed user data; calculate the operation level score and service level score of the battery swap operator based on the preprocessed business operation data; calculate the comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and identify the battery swap operator with business abnormalities based on the comprehensive evaluation score.

[0110] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: input the preprocessed user data into the abnormal user feature recognition model, and the step of outputting the first abnormal user identification result includes: inputting the preprocessed user data into the abnormal user feature recognition model, and extracting the user features corresponding to each user through the abnormal user feature recognition model; matching the user features and abnormal user features through the abnormal user feature recognition model, and determining that the user is an abnormal user when the user features corresponding to the user hit any abnormal user features, wherein the abnormal user features include: abnormal features of the number of battery swaps, profit features of purchasing battery swap packages, and abnormal features of new user invitations; generating a first abnormal user list for the identified abnormal users through the abnormal user feature recognition model, and outputting the first abnormal user list as the first abnormal user identification result.

[0111] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: input the preprocessed user data into the abnormal user preference entropy recognition model, and the step of outputting the second abnormal user identification result includes: extracting the user's battery replacement timestamp in the user data through the abnormal user preference entropy recognition model, and calculating the time interval between two adjacent battery replacements of the user based on the user's battery replacement timestamp to obtain a battery replacement time interval sequence, and calculating the battery replacement time interval preference entropy of each user based on the battery replacement time interval sequence; extracting the user consumption data in the user data through the abnormal user preference entropy recognition model, and calculating the consumption distribution data of each user based on the user consumption data, and calculating the battery replacement price preference entropy of each user based on the consumption distribution data, wherein the consumption distribution data is the consumption distribution data of each user. The distribution data represents the frequency distribution of the prices of the battery swap packages purchased by users falling within various price ranges; the user evaluation data in the user data is extracted through the abnormal user preference entropy identification model, and the evaluation distribution data of each user is calculated based on the user evaluation data, and the battery swap evaluation preference entropy of each user is calculated based on the evaluation distribution data, wherein the evaluation distribution data represents the frequency distribution of the evaluation scores posted by users after using the battery swap service in various score ranges; the preference entropy score of each user is calculated based on the battery swap time interval preference entropy, the battery swap price preference entropy and the battery swap evaluation preference entropy and the corresponding weight values, abnormal users are identified based on the preference entropy scores, and a second abnormal user list is generated according to the identified abnormal users, and the second abnormal user list is output as the second abnormal user identification result.

[0112] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: the step of calculating the abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result includes: performing intersection calculation on the first abnormal user list in the first abnormal user identification result and the second abnormal user list in the second abnormal user identification result to obtain the abnormal user list; counting the number of abnormal users in the abnormal user list and the total number of battery swap users in the user data of the battery swap operator; calculating the ratio of the number of abnormal users to the total number of battery swap users to obtain the abnormal user evaluation score.

[0113] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: the step of calculating the user development level score based on the preprocessed user data includes: counting the total number of subordinate users of the battery swap operator within the evaluation period based on the preprocessed user data; counting the proportion of new users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of new users represents the proportion of users who purchase battery swap services for the first time within the evaluation period to the total number of subordinate users; counting the proportion of old users of the battery swap operator within the evaluation period based on the preprocessed user data, wherein the proportion of old users represents the proportion of old users within the evaluation period The proportion of users who did not purchase the battery swap service for the first time during the period to the total number of subordinate users; the proportion of off-grid users of the battery swap operator during the evaluation period based on the pre-processed user data, where the off-grid user proportion represents the proportion of users who did not purchase the battery swap service in the current evaluation period but purchased the battery swap service in the previous evaluation period adjacent to the current evaluation period to the total number of subordinate users; the total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users are normalized, and the user development level score is calculated based on the normalized total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of off-grid users and the corresponding weight values.

[0114] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: The steps of calculating the operating level score of the battery swap operator based on the preprocessed business operation data include: extracting the revenue, cost and fixed expenditure of the battery swap operator during the evaluation period from the preprocessed business operation data; calculating the operating profit margin of the battery swap operator during the evaluation period based on the revenue, cost and fixed expenditure to obtain the operating level score.

[0115] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: the step of calculating the service level score of the battery swap operator based on the preprocessed business operation data includes: calculating the average response time and response timeliness of the battery swap operator based on the preprocessed business operation data, and calculating the service response score based on the average response time and response timeliness; calculating the correct answer ratio of the battery swap operator's consultations based on the preprocessed business operation data, and obtaining the service accuracy score based on the correct answer ratio of consultations, wherein the correct answer ratio of consultations indicates the proportion of consultations with correct results returned by the battery swap operator when processing user consultations to the total number of consultations; calculating the average service attitude score of user feedback based on the preprocessed business operation data to obtain the service attitude score of the battery swap operator; calculating the service level score of the battery swap operator based on the service response score, service accuracy score and service attitude score.

[0116] By adopting the embodiment of the present invention, a business anomaly assessment method for a battery swap operator is provided. The user data and business operation data of the battery swap supplier are collected, and the abnormal conditions of the supplier's subordinate users are analyzed based on the abnormal user feature recognition model and the abnormal user preference entropy recognition model. The development status, operation level and service level of the subordinate users of the battery swap operator are analyzed by calculating the user development level score, the operation level score and the service level score of the battery swap operator. Artificial intelligence analysis and big data analysis technology are used to comprehensively score the battery swap supplier from multiple dimensions such as the abnormal conditions of subordinate users, the development status of subordinate users, the operation level and the service level, and identify the battery swap supplier with business anomalies, thereby improving the evaluation efficiency. At the same time, based on the multi-dimensional data evaluation, the accuracy of the evaluation results is improved. This solves the technical problem in the related art of the method of conducting business anomaly assessment of battery swap suppliers through manual offline visits, and the low accuracy of the evaluation results.

[0117] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a terminal device such as a smart phone, a tablet computer, a PDA, a mobile Internet device (MID), or a PAD. Figure 5 It does not limit the structure of the above electronic device. For example, the electronic device may also include Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 5 Different configurations shown.

[0118] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0119] The present invention is described below in conjunction with another optional embodiment.

[0120] Example 4

[0121] The embodiment of the present invention further provides a computer-readable storage medium. Optionally, in the embodiment of the present invention, the computer-readable storage medium can be used to store the program code executed by the service anomaly assessment method for battery swap operators provided in the first embodiment.

[0122] Optionally, in an embodiment of the present invention, the above-mentioned storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0123] An embodiment of the present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of a business anomaly assessment method for a battery swap operator: collecting user data and business operation data of the battery swap operator, and preprocessing the user data and business operation data, wherein the battery swap operator is used to promote the battery swap service; inputting the preprocessed user data into an abnormal user feature recognition model, outputting a first abnormal user identification result, and inputting the preprocessed user data into an abnormal user preference entropy recognition model, outputting a second abnormal user identification result, and calculating an abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result; calculating a user development level score based on the preprocessed user data; calculating an operation level score and a service level score of the battery swap operator based on the preprocessed business operation data; calculating a comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score, service level score and their corresponding weight values, and identifying the battery swap operator with business anomalies based on the comprehensive evaluation score.

[0124] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0125] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0127] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0128] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0129] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0130] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for evaluating business anomalies of a battery swap operator, characterized in that: include: Collecting user data and business operation data of the battery swap operator and pre-processing the user data and business operation data, wherein the battery swap operator is used to promote the battery swap service; Inputting the preprocessed user data into an abnormal user feature recognition model to output a first abnormal user recognition result, and inputting the preprocessed user data into an abnormal user preference entropy recognition model to output a second abnormal user recognition result, and calculating an abnormal user evaluation score based on the first abnormal user recognition result and the second abnormal user recognition result; Calculating a user development level score based on the pre-processed user data; Calculate the operation level score and service level score of the battery swap operator based on the pre-processed business operation data; The comprehensive evaluation score of the battery swap operator is calculated based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and the battery swap operator with business abnormalities is identified based on the comprehensive evaluation score.

2. The method according to claim 1, characterized in that The step of inputting the pre-processed user data into an abnormal user feature recognition model and outputting a first abnormal user recognition result comprises: Inputting the pre-processed user data into an abnormal user feature recognition model, and extracting user features corresponding to each user through the abnormal user feature recognition model; The user characteristics and the abnormal user characteristics are matched by the abnormal user characteristic recognition model. If the user characteristics corresponding to the user hit any abnormal user characteristics, the user is determined to be an abnormal user, wherein the abnormal user characteristics include: abnormal characteristics of the number of battery swaps, profit characteristics of purchasing battery swap packages, and abnormal characteristics of new user invitations; A first abnormal user list is generated for the identified abnormal users using the abnormal user feature identification model, and the first abnormal user list is output as a first abnormal user identification result.

3. The method according to claim 1, characterized in that The step of inputting the pre-processed user data into an abnormal user preference entropy identification model and outputting a second abnormal user identification result comprises: The abnormal user preference entropy identification model is used to extract the user battery replacement timestamp in the user data, and the time interval between two adjacent battery replacements of the user is calculated based on the user battery replacement timestamp to obtain a battery replacement time interval sequence, and the battery replacement time interval preference entropy of each user is calculated based on the battery replacement time interval sequence; The abnormal user preference entropy identification model is used to extract user consumption data from the user data, and the consumption distribution data of each user is calculated based on the user consumption data, and the battery swap price preference entropy of each user is calculated based on the consumption distribution data, wherein the consumption distribution data represents the frequency distribution of the battery swap package prices purchased by the user falling within various price ranges; The user evaluation data in the user data is extracted by the abnormal user preference entropy identification model, and the evaluation distribution data of each user is calculated based on the user evaluation data, and the battery swap evaluation preference entropy of each user is calculated based on the evaluation distribution data, wherein the evaluation distribution data represents the frequency distribution of the evaluation scores published by users after using the battery swap service in each score interval; Based on the battery swap time interval preference entropy, the battery swap price preference entropy, the battery swap evaluation preference entropy and the corresponding weight values, the preference entropy score of each user is calculated, abnormal users are identified based on the preference entropy scores, and a second abnormal user list is generated based on the identified abnormal users, and the second abnormal user list is output as the second abnormal user identification result.

4. The method according to claim 1, wherein The step of calculating an abnormal user evaluation score based on the first abnormal user identification result and the second abnormal user identification result includes: performing an intersection calculation on a first abnormal user list in the first abnormal user identification result and a second abnormal user list in the second abnormal user identification result to obtain an abnormal user list; Counting the number of abnormal users in the abnormal user list and the total number of battery swap users in the user data of the battery swap operator; Calculate the ratio of the number of abnormal users to the total number of battery swap users to obtain the abnormal user evaluation score.

5. The method according to claim 1, wherein The step of calculating the user development level score based on the pre-processed user data includes: Counting the total number of users under the battery swap operator within the evaluation period based on the pre-processed user data; Based on the pre-processed user data, the proportion of new users of the battery swap operator during the evaluation period is counted, wherein the proportion of new users represents the proportion of users who purchase the battery swap service for the first time during the evaluation period to the total number of subordinate users; Based on the pre-processed user data, the proportion of old users of the battery swap operator during the evaluation period is counted, wherein the proportion of old users represents the proportion of users who are not purchasing the battery swap service for the first time during the evaluation period to the total number of subordinate users; The proportion of off-grid users of the battery swap operator within the evaluation period is calculated based on the pre-processed user data, wherein the off-grid user proportion represents the proportion of users who did not purchase the battery swap service in the current evaluation period but purchased the battery swap service in the previous evaluation period adjacent to the current evaluation period to the total number of subordinate users; The total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of offline users are normalized, and the user development level score is calculated based on the normalized total number of subordinate users, the proportion of new users, the proportion of old users and the proportion of offline users and the corresponding weight values.

6. The method according to claim 1, characterized in that The step of calculating the operation level score of the battery swap operator based on the pre-processed business operation data includes: Extracting the revenue, cost and fixed expenditure of the battery swap operator during the evaluation period from the pre-processed business operation data; The operating profit margin of the battery swap operator during the evaluation period is calculated based on the revenue, the cost and the fixed expenditure to obtain the operating level score.

7. The method according to claim 1, characterized in that The step of calculating the service level score of the battery swap operator based on the pre-processed business operation data includes: Calculate the average response time and response timeliness of the battery swap operator based on the pre-processed business operation data, and calculate the service response score based on the average response time and response timeliness; Calculate the correct answer ratio of the battery swap operator's inquiries based on the pre-processed business operation data, and obtain a service accuracy score based on the correct answer ratio, wherein the correct answer ratio represents the proportion of inquiries with correct results returned by the battery swap operator when handling user inquiries to the total number of inquiries; Calculate the average of the service attitude scores of user feedback based on the pre-processed business operation data to obtain the service attitude score of the battery swap operator; The service level score of the battery swap operator is calculated based on the service response score, the service accuracy score and the service attitude score.

8. A business anomaly assessment device for a battery swap operator, characterized in that: include: a collection unit, configured to collect user data and business operation data of a battery swap operator and pre-process the user data and business operation data, wherein the battery swap operator is used to promote battery swap services; an output unit, configured to input the preprocessed user data into an abnormal user feature recognition model to output a first abnormal user recognition result, input the preprocessed user data into an abnormal user preference entropy recognition model to output a second abnormal user recognition result, and calculate an abnormal user evaluation score based on the first abnormal user recognition result and the second abnormal user recognition result; a first calculation unit, configured to calculate a user development level score based on the preprocessed user data; A second calculation unit is used to calculate the operation level score and service level score of the battery swap operator based on the pre-processed business operation data; An evaluation unit is used to calculate the comprehensive evaluation score of the battery swap operator based on the abnormal user evaluation score, user development level score, operation level score and service level score and their corresponding weight values, and identify the battery swap operator with business abnormalities based on the comprehensive evaluation score.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the business anomaly assessment method for battery swap operators according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the business anomaly assessment method for battery swap operators as described in any one of claims 1 to 7.

Images