Customer transaction monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides a customer transaction monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the transaction analysis of the business of a to-be-monitored customer based on the obtained business data of the to-be-monitored customer, determining transaction data, carrying out the trend analysis of the transaction data, and obtaining transaction trend data representing the transaction trend, and based on the corresponding relationship between each transaction early warning level and each transaction trend, determining a target transaction early warning level, and performing transaction processing on the to-be-monitored client according to a transaction processing mode corresponding to the target transaction early warning level. By adopting the technical scheme of the embodiment, the transaction trend of the to-be-monitored customer can be determined through transaction analysis and transaction trend analysis on the business data of the to-be-monitored customer, transaction monitoring on the customer is realized, and the user experience is improved. And transaction processing is carried out on the to-be-monitored client in time according to the transaction processing mode corresponding to the transaction early warning level to which the transaction trend belongs, so that the client loss can be reduced, and the client retention rate is improved.

Description

Technical Field

[0001] This application relates to the field of customer monitoring technology, and in particular to a method, device, electronic device, and storage medium for monitoring customer anomalies. Background Technology

[0002] PB clients refer to high-net-worth clients, while SME clients are small and medium-sized enterprises that settle transactions at the end of each month. PB and SME clients constitute the largest and most promising customer base for logistics companies, forming an indispensable part of their overall revenue structure. Any unusual activity or changes in PB or SME client activity can lead to customer churn and financial losses. Therefore, effectively monitoring customer activity, reducing churn, and improving customer retention are critical technical challenges that need to be addressed in this field. Summary of the Invention

[0003] Based on the above requirements, this application proposes a customer anomaly monitoring method, device, electronic device and storage medium, which can realize the monitoring of customer anomalies, reduce customer churn and improve customer retention rate.

[0004] To achieve the above objectives, this application proposes the following technical solution:

[0005] According to a first aspect of the embodiments of this application, a customer movement monitoring method is provided, comprising:

[0006] Based on the acquired business data of the customers to be monitored, anomaly analysis is performed on the business of the customers to be monitored to determine the abnormal data;

[0007] Perform trend analysis on the abnormal data to obtain abnormal trend data that characterizes the abnormal trend;

[0008] Based on the correspondence between each anomaly warning level and each anomaly trend, the target anomaly warning level is determined, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data;

[0009] The abnormality handling method corresponding to the target abnormality warning level shall be used to handle the abnormality of the monitored customer.

[0010] Optionally, based on the acquired business data of the customer to be monitored, anomaly analysis is performed on the business of the customer to be monitored to determine the anomaly data, including:

[0011] Based on the acquired business data of the customers to be monitored, year-on-year and / or month-on-month analysis is performed on the business of the customers to be monitored to obtain year-on-year and / or month-on-month abnormal data.

[0012] Optionally, based on the acquired business data of the customer to be monitored, a year-on-year analysis of the customer's business is performed to obtain year-on-year anomaly data, including:

[0013] From the acquired business data of the customers to be monitored, query the revenue data of the current first preset time range and the revenue data of the previous year's first preset time range, and calculate the average daily revenue data corresponding to the current first preset time range and the average daily revenue data corresponding to the previous year's first preset time range.

[0014] The comparison between the current average daily revenue data for the first preset time range and the average daily revenue data for the first preset time range of the previous year is used as the year-on-year change data.

[0015] Optionally, based on the acquired business data of the customer to be monitored, a month-on-month analysis is performed on the business of the customer to be monitored to obtain month-on-month anomaly data, including:

[0016] From the acquired business data of the customers to be monitored, query the revenue data within the current second preset time range and the revenue data within the preset time range before the current second preset time range, and calculate the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset time range before the current second preset time range.

[0017] The ratio between the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range, as well as the average daily revenue data corresponding to the current second preset time range, are both used as month-on-month change data.

[0018] Optionally, the business data includes: business data corresponding to at least one product type;

[0019] The abnormal trend data includes at least one of the following: year-on-year abnormal trend data corresponding to product type, year-on-year abnormal trend data corresponding to all business data, month-on-month abnormal trend data corresponding to product type, and month-on-month abnormal trend data corresponding to all business data.

[0020] Optionally, the monitored customer may be processed according to the anomaly handling method corresponding to the target anomaly warning level, including:

[0021] If the target anomaly warning level is the first warning level, then a warning message is sent to the anomaly handler corresponding to the customer to be monitored;

[0022] If the target anomaly warning level is the second warning level, then a warning message and a customer follow-up task are sent to the anomaly handler corresponding to the customer to be monitored.

[0023] The risk level of the first warning level is lower than that of the second warning level; the warning message is used to notify the anomaly handler that the monitored customer has an anomaly, so that the anomaly handler can pay attention to the anomaly of the monitored customer; the customer follow-up task refers to the task of following up on and reporting the anomaly of the monitored customer.

[0024] Optionally, anomaly analysis is performed on the business operations of the customer to be monitored to identify anomaly data, and trend analysis is performed on the anomaly data to obtain anomaly trend data characterizing the anomaly trend, including:

[0025] Using a pre-built anomaly analysis algorithm, anomaly analysis is performed on the business of the customer to be monitored to determine anomaly data, and trend analysis is performed on the anomaly data to obtain anomaly trend data that characterizes the anomaly trend.

[0026] The anomaly analysis algorithm is an algorithm encapsulated using Java Agent technology.

[0027] According to a second aspect of the embodiments of this application, a customer movement monitoring device is provided, comprising:

[0028] The anomaly analysis module is used to perform anomaly analysis on the business of the customer to be monitored based on the acquired business data of the customer to be monitored, and to determine the anomaly data;

[0029] The trend analysis module is used to perform trend analysis on the abnormal data to obtain abnormal trend data that characterizes the abnormal trend.

[0030] Anomaly warning module is used to determine the target anomaly warning level based on the correspondence between each anomaly warning level and each anomaly trend, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data;

[0031] The anomaly processing module is used to process the anomalies of the monitored customer according to the anomaly processing method corresponding to the target anomaly warning level.

[0032] According to a third aspect of the embodiments of this application, an electronic device is provided, including: a memory and a processor;

[0033] The memory is connected to the processor and is used to store programs;

[0034] The processor is used to implement the above-described customer anomaly monitoring method by running the program in the memory.

[0035] According to a fourth aspect of the embodiments of this application, a storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-described customer anomaly monitoring method.

[0036] The customer anomaly monitoring method proposed in this application analyzes the anomaly data of the customer to be monitored based on the acquired business data, identifies the anomaly data, performs trend analysis on the anomaly data to obtain anomaly trend data representing the anomaly trend, determines the target anomaly warning level based on the correspondence between each anomaly warning level and each anomaly trend, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data, and processes the anomaly of the customer to be monitored according to the anomaly processing method corresponding to the target anomaly warning level. By adopting the technical solution of this embodiment, the anomaly trend of the customer to be monitored can be determined through anomaly analysis and anomaly trend analysis of the business data of the customer to be monitored, realizing customer anomaly monitoring, and promptly processing the customer to be monitored according to the anomaly processing method corresponding to the anomaly warning level to which the anomaly trend belongs, thereby reducing customer churn and improving customer retention rate. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0038] Figure 1 A flowchart illustrating a customer movement monitoring method provided in this application embodiment;

[0039] Figure 2 A schematic diagram of the processing flow for year-on-year business analysis provided in this application embodiment;

[0040] Figure 3 A schematic diagram of the processing flow for business month-on-month analysis provided in this application embodiment;

[0041] Figure 4 A schematic diagram of a customer anomaly monitoring device provided in this application embodiment;

[0042] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0043] The technical solution of this application is applicable to customer movement monitoring scenarios, specifically for monitoring customer movement in logistics companies. By employing the technical solution of this application, customer movement can be monitored, thereby reducing customer churn and increasing customer retention.

[0044] PB clients refer to high-net-worth individuals, while SME clients are small and medium-sized enterprises that settle transactions at the end of each month. PB and SME clients constitute the largest and most promising customer base for logistics companies, forming an indispensable part of their overall revenue structure. Logistics companies typically have account manager and sales teams to maintain relationships with PB and SME clients, including overseeing the sales process, after-sales service, and service quality.

[0045] When clients such as PB and SME exhibit unusual activity, these changes can directly impact the cooperation between the two companies, potentially leading to public relations issues and disputes, ultimately resulting in customer churn and financial losses. To minimize customer loss and financial losses for logistics companies, it is necessary to monitor the activity of clients such as PB and SME, detect unusual behavior early, and allow the logistics company's customer maintenance staff to intervene promptly to retain clients, thereby improving customer satisfaction and trust, and stabilizing the cooperative relationship.

[0046] Therefore, how to monitor customer activity, reduce customer churn, and improve customer retention is a technical problem that urgently needs to be solved by those skilled in the art.

[0047] Based on this, this application proposes a customer movement monitoring method. This technical solution can realize the monitoring of customer movement, thereby solving the problem of high customer churn and low customer retention rate caused by customer movement in the prior art.

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] Exemplary methods

[0050] See Figure 1 As shown in the figure, this application proposes a method for monitoring customer movement. The method includes:

[0051] S101. Based on the acquired business data of the customer to be monitored, perform anomaly analysis on the business of the customer to be monitored and determine the anomaly data.

[0052] This embodiment identifies customers requiring anomaly monitoring as the monitored customers and extracts their business data. Specifically, initial business data for the monitored customers is first extracted from the logistics company's multi-terminal systems, including CRM, parcel delivery, and sales systems. Then, the initial business data extracted from these systems is integrated and cleaned to obtain the final business data for the monitored customers. This business data includes revenue data, among other things.

[0053] After obtaining the business data of the customer to be monitored, this embodiment needs to perform anomaly analysis on the customer's business to determine the anomaly data. The customer to be monitored may be involved in multiple businesses; therefore, the obtained business data includes data from multiple businesses. When performing anomaly analysis on the customer's business, anomaly analysis can be performed on all types of businesses to determine the anomaly data for each type of business. Specifically, the business includes businesses corresponding to all product types and at least one of all businesses. The number of product types is at least one, and all businesses refer to all businesses involved in the customer to be monitored. The obtained business data includes business data corresponding to at least one product type. Product types include at least one of express products, standard express products, e-commerce products, and air freight products. That is, the business includes express product business, standard express product business, e-commerce product business, air freight product business, and at least one of all businesses. Therefore, the business data includes at least one of the business data corresponding to express product business, standard express product business, e-commerce product business, and air freight product business. For example, when the business of the customer to be monitored includes express product business, standard express product business, e-commerce product business, air cargo product business, and all business, the first step is to extract the business data corresponding to the express product business, standard express product business, e-commerce product business, and air cargo product business from the customer's business data. Then, perform anomaly analysis on the express product business data to obtain the anomaly data for the customer's express product business; perform anomaly analysis on the standard express product business data to obtain the anomaly data for the customer's standard express product business; perform anomaly analysis on the e-commerce product business data to obtain the anomaly data for the customer's e-commerce product business; perform anomaly analysis on the air cargo product business data to obtain the anomaly data for the customer's air cargo business; and perform anomaly analysis on all business data (i.e., all business data of the customer to be monitored) to obtain the anomaly data for all business of the customer to be monitored.

[0054] Furthermore, in this embodiment, the anomaly analysis of the monitored customer's business includes year-on-year analysis and / or month-on-month analysis of the monitored customer's business, thereby obtaining year-on-year and / or month-on-month anomaly data for the monitored customer. Year-on-year analysis refers to comparing business data in the current period with business data in the same historical period, such as comparing business data in the most recent time period with business data in the same time period of the previous year. Preferably, the comparative analysis is based on average daily revenue data calculated from the business data, specifically discounted average daily revenue. Month-on-month analysis refers to analyzing the ratio between business data in the current period and business data in the adjacent previous period, as well as analyzing average daily revenue data calculated based on business data in the current period (such as discounted average daily revenue). Preferably, the ratio analysis is based on average daily revenue data calculated from the business data (such as discounted average daily revenue).

[0055] Specifically, in this embodiment, if the business of the customer to be monitored includes multiple categories, it is necessary to perform year-on-year and / or month-on-month analysis on the business data corresponding to each business of the customer to be monitored, thereby obtaining the year-on-year and / or month-on-month fluctuation data for each business of the customer to be monitored. For example, if the business of the customer to be monitored includes express product business, standard express product business, e-commerce product business, air cargo product business, and all businesses, and year-on-year and month-on-month analysis is performed on each business, the final business fluctuation data of the customer to be monitored will include: year-on-year fluctuation data corresponding to all businesses, year-on-year fluctuation data corresponding to express product business, year-on-year fluctuation data corresponding to standard express product business, year-on-year fluctuation data corresponding to e-commerce product business, year-on-year fluctuation data corresponding to air cargo product business, month-on-month fluctuation data corresponding to all businesses, month-on-month fluctuation data corresponding to express product business, month-on-month fluctuation data corresponding to standard express product business, month-on-month fluctuation data corresponding to e-commerce product business, and month-on-month fluctuation data corresponding to air cargo product business.

[0056] S102. Perform trend analysis on the abnormal data to obtain abnormal trend data that characterizes the abnormal trend.

[0057] After identifying the abnormal data of the customer to be monitored, this embodiment requires performing trend analysis on the abnormal data according to pre-set abnormal trend standards to determine the abnormal trend data of the customer to be monitored. This abnormal trend data represents the abnormal trend reflected in the abnormal data of the customer to be monitored. The pre-set abnormal trend standards include year-on-year abnormal trend standards and month-on-month abnormal trend standards. Trend analysis based on year-on-year abnormal data determines the year-on-year abnormal trend data, specifically including three cases: year-on-year deterioration, year-on-year improvement, and year-on-year flatness. Trend analysis based on month-on-month abnormal data determines the month-on-month abnormal trend data, specifically including three cases: negative abnormality, positive abnormality, and stable business. The abnormal trend data of the customer to be monitored includes at least one of the following: year-on-year abnormal trend data for all product types, year-on-year abnormal trend data for all businesses, month-on-month abnormal trend data for all product types, and month-on-month abnormal trend data for all businesses. That is, the abnormal trend data of the customers to be monitored includes at least one of the following: year-on-year abnormal trend data of express product business, year-on-year abnormal trend data of standard express product business, year-on-year abnormal trend data of e-commerce product business, year-on-year abnormal trend data of air cargo product business, year-on-year abnormal trend data of all businesses, month-on-month abnormal trend data of express product business, month-on-month abnormal trend data of standard express product business, month-on-month abnormal trend data of e-commerce product business, month-on-month abnormal trend data of air cargo product business, and month-on-month abnormal trend data of all businesses.

[0058] For example, if the business of the customer to be monitored includes express product business, standard express product business, e-commerce product business, air cargo product business, and all business, and if year-on-year and month-on-month analyses are performed for each business, the final abnormal trend data of the customer to be monitored will include: year-on-year abnormal trend data for all business, year-on-year abnormal trend data for express product business, year-on-year abnormal trend data for standard express product business, year-on-year abnormal trend data for e-commerce product business, year-on-year abnormal trend data for air cargo product business, month-on-month abnormal trend data for all business, month-on-month abnormal trend data for express product business, month-on-month abnormal trend data for standard express product business, month-on-month abnormal trend data for e-commerce product business, and month-on-month abnormal trend data for air cargo product business.

[0059] Specifically, if the comparison between the current period's discounted average daily revenue and the historical average daily revenue in the year-on-year anomaly data indicates that the current period's discounted average daily revenue is less than the historical average daily revenue, then the year-on-year anomaly trend data indicates a downward trend; if the comparison between the current period's discounted average daily revenue and the historical average daily revenue in the year-on-year anomaly data indicates that the current period's discounted average daily revenue is greater than the historical average daily revenue, then the year-on-year anomaly trend data indicates a positive trend; if the comparison between the current period's discounted average daily revenue and the historical average daily revenue in the year-on-year anomaly data indicates that the current period's discounted average daily revenue is equal to the historical average daily revenue, then the year-on-year anomaly trend data indicates a flat trend.

[0060] If the ratio of the discounted average daily income of the current period to the discounted average daily income of the adjacent previous period, after subtracting one, is less than a first preset ratio (preferably set to -30%), and the discounted average daily income of the current period is greater than a preset average daily income (preferably set to 10,000), then the month-on-month change trend data indicates a negative change; if the ratio of the discounted average daily income of the current period to the discounted average daily income of the adjacent previous period, after subtracting one, is greater than or equal to a second preset ratio (preferably set to 10,000), then the month-on-month change trend data indicates a negative change. If the average daily revenue after discount in the current period is greater than the preset average daily revenue (preferably set to 10,000), then the month-on-month anomaly trend data indicates a positive anomaly; if the ratio between the average daily revenue after discount in the current period and the average daily revenue after discount in the adjacent previous period, minus one, is greater than or equal to the first preset ratio and less than the second preset ratio, or if the average daily revenue after discount in the current period is less than or equal to the preset average daily revenue (preferably set to 10,000), then the month-on-month anomaly trend data indicates stable business.

[0061] S103. Based on the correspondence between each anomaly warning level and each anomaly trend, determine the target anomaly warning level.

[0062] After determining the abnormal trend data of the customer to be monitored through the above steps, it is necessary to determine the target abnormal trend warning level for the customer based on the abnormal trend data and the correspondence between each abnormal trend warning level. The target abnormal trend warning level is the abnormal trend warning level corresponding to the abnormal trend represented by the abnormal trend data. Specifically, in this embodiment, a rule for determining the abnormal trend warning level is pre-set. This rule stores the correspondence between each abnormal trend warning level and each abnormal trend. Based on this rule, the abnormal trend warning level to which the abnormal trend data of the customer to be monitored belongs is determined.

[0063] In one specific embodiment, the target anomaly warning level is determined based on the correspondence between each anomaly warning level and each anomaly trend. The specific steps are as follows:

[0064] Given the following customer anomaly trend data to be monitored: year-on-year anomaly trend data for all businesses, year-on-year anomaly trend data for express products, year-on-year anomaly trend data for standard express products, year-on-year anomaly trend data for e-commerce products, year-on-year anomaly trend data for air cargo products, month-on-month anomaly trend data for all businesses, month-on-month anomaly trend data for express products, month-on-month anomaly trend data for standard express products, month-on-month anomaly trend data for e-commerce products, and month-on-month anomaly trend data for air cargo products, if the year-on-year anomaly trend data for e-commerce products indicates a year-on-year change, and the year-on-year anomaly trend data for air cargo products... If any three or more of the following conditions are met: year-on-year anomaly trend data for product business indicates a year-on-year decline; month-on-month anomaly trend data for all business indicates a negative change; and month-on-month anomaly trend data for express product business indicates a negative change, and the year-on-year anomaly trend data for all business does not indicate a year-on-year decline; the year-on-year anomaly trend data for express product business does not indicate a year-on-year decline; the year-on-year anomaly trend data for standard express product business does not indicate a year-on-year decline; the month-on-month anomaly trend data for standard express product business does not indicate a negative change; and the month-on-month anomaly trend data for e-commerce product business does not indicate a negative change, then the target anomaly warning level for the customer to be monitored is determined to be a Level 1 warning. If any three or more of the following conditions are met: year-on-year trend of abnormal fluctuations in e-commerce product business, year-on-year trend of abnormal fluctuations in air cargo product business, month-on-month trend of abnormal fluctuations in all business, or month-on-month trend of abnormal fluctuations in express product business; or if any one of the following conditions is met: year-on-year trend of abnormal fluctuations in all business, year-on-year trend of abnormal fluctuations in express product business, year-on-year trend of abnormal fluctuations in standard express product business, month-on-month trend of abnormal fluctuations in standard express product business, or month-on-month trend of abnormal fluctuations in e-commerce product business, then the target abnormal fluctuation warning level for the customer to be monitored is determined to be a Level II warning. If any two or more of the following conditions are met: year-on-year anomaly trend data for all business segments indicates a negative year-on-year change; year-on-year anomaly trend data for express products indicates a negative year-on-year change; year-on-year anomaly trend data for standard express products indicates a negative year-on-year change; month-on-month anomaly trend data for standard express products indicates a negative month-on-month change; and month-on-month anomaly trend data for e-commerce products indicates a negative month-on-month change, then the target anomaly warning level for the customer to be monitored is determined to be a Level 3 warning. Among these, Level 1 and Level 2 warnings are both the first warning level, and Level 3 warnings are the second warning level.

[0065] S104. Handle the abnormality of the monitored customer according to the abnormality handling method corresponding to the target abnormality warning level.

[0066] This embodiment sets different anomaly handling methods for different anomaly warning levels. After determining the target anomaly warning level for the customer to be monitored, the anomaly handling is performed according to the anomaly handling method corresponding to that target anomaly warning level. Specifically, this embodiment can set two anomaly warning levels, namely, a first warning level and a second warning level. The risk level of the first warning level is lower than that of the second warning level. That is, if the target anomaly warning level for the customer to be monitored is the first warning level, then the customer to be monitored is a low-risk customer, and the possibility of churn is small. If the target anomaly warning level for the customer to be monitored is the second warning level, then the customer to be monitored is a high-risk customer, and the possibility of churn is large. If the target anomaly warning level for the customer to be monitored is determined to be the first warning level, then a warning message is sent to the anomaly handling person corresponding to the customer to be monitored. This warning message is used to notify the anomaly handling person corresponding to the customer to be monitored that the customer has anomalies, so that the anomaly handling person can pay attention to the anomaly situation of the customer to be monitored. The anomaly handling person corresponding to the customer to be monitored is the account manager or salesperson who maintains customer relations for the customer to be monitored. If the target anomaly alert level for the customer to be monitored is determined to be the second alert level, then an alert message and a customer follow-up task are sent to the anomaly handler corresponding to the customer to be monitored. The customer follow-up task is the task of following up on and reporting the anomalies of the customer to be monitored. The anomaly follow-up for the customer to be monitored can be done by visiting the customer in person or contacting the customer by phone to understand the specific situation and reasons for the customer's anomaly. After following up on the anomalies of the customer to be monitored, the specific situation learned after the anomaly follow-up needs to be fed back in the customer follow-up task.

[0067] As described above, the customer anomaly monitoring method proposed in this application, based on the acquired business data of the customer to be monitored, performs anomaly analysis on the customer's business to determine anomaly data, performs trend analysis on the anomaly data to obtain anomaly trend data representing the anomaly trend, determines the target anomaly warning level based on the correspondence between each anomaly warning level and each anomaly trend, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data, and processes the anomaly of the customer to be monitored according to the anomaly processing method corresponding to the target anomaly warning level. By adopting the technical solution of this embodiment, the anomaly trend of the customer to be monitored can be determined through anomaly analysis and anomaly trend analysis of the business data of the customer to be monitored, realizing customer anomaly monitoring, and promptly processing the customer to be monitored according to the anomaly processing method corresponding to the anomaly warning level to which the anomaly trend belongs, thereby reducing customer churn and improving customer retention rate.

[0068] As an optional implementation, another embodiment of this application discloses a method for performing anomaly analysis on the business of the customer to be monitored, identifying anomaly data, performing trend analysis on the anomaly data, and obtaining anomaly trend data representing the anomaly trend. Specifically, a pre-built anomaly analysis algorithm is used to perform anomaly analysis on the business of the customer to be monitored, identify anomaly data, perform trend analysis on the anomaly data, and obtain anomaly trend data representing the anomaly trend. The pre-built anomaly analysis algorithm is encapsulated using Java Agent technology, thereby enabling non-code-intrusive application of the anomaly analysis algorithm to other systems. Specifically, Java Agent technology and configuration technology are used to encapsulate the anomaly analysis algorithm, providing a general SDK approach. The Java Agent JAR is directly imported, and the corresponding interface interception point and push interface of the system to which it is applied are configured, thus enabling non-code-intrusive application of the encapsulated anomaly analysis algorithm to that system. The anomaly analysis algorithm can be a model; that is, the model is encapsulated using Java Agent technology.

[0069] As an optional implementation, see [link to implementation details]. Figure 2 As shown, another embodiment of this application discloses a method for performing year-on-year analysis of the business data of the customer to be monitored based on the acquired business data of the customer to be monitored, to obtain year-on-year anomaly data, specifically including the following steps:

[0070] S201. From the acquired business data of the customers to be monitored, query the revenue data of the current first preset time range and the revenue data of the previous year's first preset time range, and calculate the average daily revenue data corresponding to the current first preset time range and the average daily revenue data corresponding to the previous year's first preset time range.

[0071] This embodiment retrieves revenue data within the current first preset time range and revenue data within the previous year's first preset time range from the acquired business data of the customer to be monitored. Preferably, the revenue data in this embodiment uses discounted revenue. The current first preset time range refers to the current period, and the previous year's first preset time range refers to the same period of the previous year. The current first preset time range is preferably the most recent two consecutive weeks. Correspondingly, the previous year's first preset time range is the period in the previous year where the dates of the most recent two consecutive weeks are the same. For example, if the current first preset time range, i.e., the most recent two consecutive weeks, is May 10th to May 24th, then the previous year's first preset time range would be May 10th to May 24th of the previous year.

[0072] Then, based on the revenue data within the current first preset time range and the number of days included in the first preset time range, the average daily revenue data corresponding to the current first preset time range is calculated. Where the revenue data is discounted revenue, the average daily revenue data is the average discounted daily revenue, calculated by dividing the total discounted revenue of all businesses within the current first preset time range by the number of days included in the first preset time range. Similarly, based on the discounted revenue and the number of days included in the first preset time range of the previous year, the average discounted daily revenue corresponding to the first preset time range of the previous year is calculated, calculated by dividing the total discounted revenue of all businesses within the first preset time range of the previous year by the number of days included in the first preset time range.

[0073] When the customer to be monitored involves multiple businesses, it is necessary to query the discounted revenue of the current business within the first preset time range and the discounted revenue of the previous year within the first preset time range for each business based on the business data corresponding to each business of the customer to be monitored, and calculate the discounted average daily revenue of the current business within the first preset time range and the discounted average daily revenue of the previous year within the first preset time range for each business.

[0074] S202. The comparison result between the current average daily revenue data corresponding to the first preset time range and the average daily revenue data corresponding to the first preset time range of the previous year is used as the year-on-year change data.

[0075] This embodiment calculates the average daily income data corresponding to the current first preset time range and the average daily income data corresponding to the first preset time range of the previous year, compares the average daily income data corresponding to the current first preset time range and the average daily income data corresponding to the first preset time range of the previous year, and uses the comparison result as the year-on-year change data.

[0076] In this embodiment, revenue data preferably uses discounted revenue, and average daily revenue data preferably uses discounted average daily revenue. If the year-on-year change data of the customer to be monitored is that the discounted average daily revenue of the current first preset time range is less than the discounted average daily revenue of the previous year's first preset time range, then the year-on-year change trend data of the customer to be monitored is determined to be a year-on-year decline. If the year-on-year change data of the customer to be monitored is that the discounted average daily revenue of the current first preset time range is greater than the discounted average daily revenue of the previous year's first preset time range, then the year-on-year change trend data of the customer to be monitored is determined to be a year-on-year improvement. If the year-on-year change data of the customer to be monitored is that the discounted average daily revenue of the current first preset time range is equal to the discounted average daily revenue of the previous year's first preset time range, then the year-on-year change trend data of the customer to be monitored is determined to be a year-on-year flat trend.

[0077] When the monitored customer involves multiple businesses, the comparison between the current average daily revenue after discount for the first preset time range and the average daily revenue after discount for the first preset time range of the previous year is used as the year-on-year change data for each business of the monitored customer.

[0078] As an optional implementation, see [link to implementation details]. Figure 3 As shown, another embodiment of this application discloses a method for performing month-on-month analysis on the business data of the customer to be monitored, based on the acquired business data of the customer to be monitored, to obtain month-on-month anomaly data, specifically including the following steps:

[0079] S301. From the acquired business data of the customer to be monitored, query the revenue data within the current second preset time range and the revenue data within the preset duration before the current second preset time range, and calculate the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range.

[0080] This embodiment retrieves revenue data within the current second preset time range and revenue data within a preset time period preceding the current second preset time range from the acquired business data of the customer to be monitored. Preferably, the revenue data in this embodiment uses discounted revenue, the current second preset time range is the current period, and the preset time period preceding the current second preset time range is the previous period adjacent to the current period. The current second preset time range is preferably the most recent week, and correspondingly, the preset time period preceding the current second preset time range is preferably the three months preceding the current second preset time range.

[0081] Then, based on the revenue data within the current second preset time range and the number of days included in the second preset time range, the average daily revenue corresponding to the current second preset time range is calculated. This is calculated by dividing the total discounted revenue of all businesses within the current second preset time range by the number of days included in the second preset time range. Similarly, based on the discounted revenue of businesses within a preset duration preceding the current second preset time range and the number of days included in that preset duration, the average daily discounted revenue corresponding to the preset duration preceding the current second preset time range is calculated. This is calculated by dividing the total discounted revenue of all businesses within the preset duration preceding the current second preset time range by the number of days included in that preset duration.

[0082] When the customer to be monitored involves multiple businesses, it is necessary to query the discounted revenue of each business within the current second preset time range and the discounted revenue of each business within the preset time range before the current second preset time range based on the business data corresponding to each business of the customer to be monitored, and calculate the discounted average daily revenue of each business within the current second preset time range and the discounted average daily revenue of each business within the preset time range before the current second preset time range.

[0083] S302. The ratio between the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range, as well as the average daily revenue data corresponding to the current second preset time range, are all taken as month-on-month change data.

[0084] This embodiment calculates the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range. Then, it calculates the ratio between the discounted average daily revenue of the current second preset time range and the discounted average daily revenue of the current second preset time range and the discounted average daily revenue of the current second preset time range and the discounted average daily revenue of the current second preset time range. This ratio and the discounted average daily revenue of the current second preset time range are both used as the month-on-month anomaly data of the customer to be monitored.

[0085] In this embodiment, revenue data preferably uses discounted revenue, and average daily revenue data preferably uses discounted daily average revenue. If the month-on-month change data of the customer to be monitored meets the condition that the ratio between the discounted daily average revenue corresponding to the current second preset time range and the discounted daily average revenue corresponding to the preset time range before the current second preset time range minus one is less than the first preset ratio (preferably set to -30%), and the discounted daily average revenue corresponding to the current second preset time range is greater than the preset daily average revenue (preferably set to 10,000), then the month-on-month change trend data of the customer to be monitored indicates a negative change; if the month-on-month change data of the customer to be monitored meets the condition that the ratio between the discounted daily average revenue corresponding to the current second preset time range and the discounted daily average revenue corresponding to the preset time range before the current second preset time range minus one is greater than or equal to the second preset ratio, then the month-on-month change trend data of the customer to be monitored indicates a negative change. If the ratio (preferably set to 15%) and the average daily revenue after discounts for the current second preset time range are greater than the preset average daily revenue (preferably set to 10,000), then the month-on-month anomaly trend data of the customer to be monitored is determined to indicate a positive anomaly. If the month-on-month anomaly data of the customer to be monitored is greater than or equal to the first preset ratio and less than the second preset ratio after the ratio between the average daily revenue after discounts for the current second preset time range and the average daily revenue after discounts for the preset duration before the current second preset time range minus one, or if the average daily revenue after discounts for the current second preset time range is less than or equal to the preset average daily revenue (preferably set to 10,000), then the month-on-month anomaly trend data of the customer to be monitored is determined to indicate stable business.

[0086] When the monitored customer involves multiple businesses, the ratio between the average daily revenue after discount for the current second preset time range corresponding to each business and the average daily revenue after discount for the business corresponding to the preset duration before the current second preset time range, as well as the average daily revenue after discount for the current second preset time range corresponding to each business, are used as the month-on-month business anomaly data for each business of the monitored customer.

[0087] Exemplary device

[0088] Accordingly, this application also provides a customer movement monitoring device, see [link to relevant documentation]. Figure 4 As shown, the device includes:

[0089] The anomaly analysis module 100 is used to perform anomaly analysis on the business data of the customer to be monitored based on the acquired business data of the customer to be monitored, and to determine the anomaly data;

[0090] Trend analysis module 110 is used to perform trend analysis on abnormal data to obtain abnormal trend data that characterizes the abnormal trend;

[0091] Anomaly warning module 120 is used to determine the target anomaly warning level based on the correspondence between each anomaly warning level and each anomaly trend, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data;

[0092] The anomaly processing module 130 is used to process anomalies of monitored customers according to the anomaly processing method corresponding to the target anomaly warning level.

[0093] As can be seen from the above description, the customer anomaly monitoring device proposed in this application embodiment can determine the anomaly trend of the customer to be monitored by analyzing the anomaly and anomaly trend of the business data of the customer to be monitored, realize the monitoring of customer anomalies, and promptly handle the anomalies of the monitored customer according to the anomaly handling method corresponding to the anomaly warning level to which the anomaly trend belongs, thereby reducing customer churn and improving customer retention rate.

[0094] As an optional implementation, another embodiment of this application discloses an anomaly analysis module 100, which is specifically used to perform year-on-year and / or month-on-month analysis on the business data of the customer to be monitored based on the acquired business data of the customer to be monitored, so as to obtain year-on-year anomaly data and / or month-on-month anomaly data.

[0095] As an optional implementation, another embodiment of this application discloses an anomaly analysis module 100, which includes a calculation unit and a determination unit;

[0096] The calculation unit is used to query the revenue data within the current first preset time range and the revenue data within the previous year's first preset time range from the acquired business data of the customers to be monitored, and to calculate the average daily revenue data corresponding to the current first preset time range and the average daily revenue data corresponding to the previous year's first preset time range.

[0097] The determination unit is used to compare the average daily revenue data corresponding to the current first preset time range with the average daily revenue data corresponding to the first preset time range of the previous year, and use the result as the year-on-year change data.

[0098] As an optional implementation, another embodiment of this application discloses that the calculation unit is further configured to query the revenue data within the current second preset time range and the revenue data within the preset duration before the current second preset time range from the acquired business data of the customer to be monitored, and calculate the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range.

[0099] The determining unit is also used to take the ratio between the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range, as well as the average daily revenue data corresponding to the current second preset time range, as month-on-month change data.

[0100] As an optional implementation, another embodiment of this application discloses that the business data includes: business data corresponding to at least one product type;

[0101] The abnormal trend data includes at least one of the following: year-on-year abnormal trend data corresponding to product type, year-on-year abnormal trend data corresponding to all business data, month-on-month abnormal trend data corresponding to product type, and month-on-month abnormal trend data corresponding to all business data.

[0102] As an optional implementation, another embodiment of this application discloses an anomaly processing module 130, specifically used for:

[0103] If the target anomaly warning level is the first warning level, then a warning message will be sent to the person in charge of handling the anomaly for the customer to be monitored.

[0104] If the target anomaly warning level is the second warning level, then send a warning message and a customer follow-up task to the anomaly handler corresponding to the customer to be monitored.

[0105] The risk level of the first warning level is lower than that of the second warning level; the warning message is used to notify the anomaly handler that there is an anomaly in the customer to be monitored, so that the anomaly handler can pay attention to the anomaly of the customer to be monitored; the customer follow-up task means the task of following up and reporting the anomaly of the customer to be monitored.

[0106] As an optional implementation, another embodiment of this application discloses an anomaly analysis module 100 and a trend analysis module 110, specifically used for:

[0107] Using a pre-built anomaly analysis algorithm, anomaly analysis is performed on the business of the customer to be monitored to identify anomaly data, and trend analysis is performed on the anomaly data to obtain anomaly trend data that represents the anomaly trend.

[0108] The anomaly analysis algorithm is an algorithm encapsulated using Java Agent technology.

[0109] The customer movement monitoring device provided in this embodiment belongs to the same concept as the customer movement monitoring method provided in the above embodiments of this application. It can execute the customer movement monitoring method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the customer movement monitoring method. Technical details not described in detail in this embodiment can be found in the specific processing content of the customer movement monitoring method provided in the above embodiments of this application, and will not be repeated here.

[0110] Exemplary electronic devices

[0111] Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 5 As shown, the device includes:

[0112] Memory 200 and processor 210;

[0113] The memory 200 is connected to the processor 210 and is used to store programs;

[0114] The processor 210 is used to implement the customer anomaly monitoring method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0115] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0116] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them:

[0117] A bus can include a pathway for transmitting information between various components of a computer system.

[0118] The processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0119] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.

[0120] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0121] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0122] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0123] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0124] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement any of the steps of the customer anomaly monitoring method provided in the above embodiments of this application.

[0125] Exemplary computer program products and storage media

[0126] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the customer anomaly monitoring methods according to various embodiments of this application described in the "Exemplary Methods" section of this specification.

[0127] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0128] Furthermore, embodiments of this application may also be storage media storing a computer program thereon, the computer program being executed by a processor of the steps in the customer anomaly monitoring methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0129] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0130] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0131] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0132] The modules and sub-modules in the various embodiments of the present application's devices and terminals can be merged, divided, and deleted according to actual needs.

[0133] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0134] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.

[0135] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.

[0136] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0137] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0138] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0139] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring customer movement, characterized in that, include: Based on the acquired business data of the customers to be monitored, anomaly analysis is performed on the business of the customers to be monitored to determine the abnormal data; Perform trend analysis on the abnormal data to obtain abnormal trend data that characterizes the abnormal trend; Based on the correspondence between each anomaly warning level and each anomaly trend, the target anomaly warning level is determined, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data; The abnormality handling method corresponding to the target abnormality warning level shall be used to handle the abnormality of the monitored customer.

2. The method according to claim 1, characterized in that, Based on the acquired business data of the customers to be monitored, anomaly analysis is performed on the business of the customers to be monitored to determine the abnormal data, including: Based on the acquired business data of the customers to be monitored, year-on-year and / or month-on-month analysis is performed on the business of the customers to be monitored to obtain year-on-year and / or month-on-month abnormal data.

3. The method according to claim 2, characterized in that, Based on the acquired business data of the customers to be monitored, a year-on-year analysis of the business of the customers to be monitored is performed to obtain year-on-year anomaly data, including: From the acquired business data of the customers to be monitored, query the revenue data of the current first preset time range and the revenue data of the previous year's first preset time range, and calculate the average daily revenue data corresponding to the current first preset time range and the average daily revenue data corresponding to the previous year's first preset time range. The comparison between the current average daily revenue data for the first preset time range and the average daily revenue data for the first preset time range of the previous year is used as the year-on-year change data.

4. The method according to claim 2, characterized in that, Based on the acquired business data of the customers to be monitored, a month-on-month analysis is performed on the business of the customers to be monitored to obtain month-on-month anomaly data, including: From the acquired business data of the customers to be monitored, query the revenue data within the current second preset time range and the revenue data within the preset time range before the current second preset time range, and calculate the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset time range before the current second preset time range. The ratio between the average daily revenue data corresponding to the current second preset time range and the average daily revenue data corresponding to the preset duration before the current second preset time range, as well as the average daily revenue data corresponding to the current second preset time range, are both used as month-on-month change data.

5. The method according to any one of claims 1-4, characterized in that, The business data includes: business data corresponding to at least one product type; The abnormal trend data includes at least one of the following: year-on-year abnormal trend data corresponding to product type, year-on-year abnormal trend data corresponding to all business data, month-on-month abnormal trend data corresponding to product type, and month-on-month abnormal trend data corresponding to all business data.

6. The method according to claim 1, characterized in that, The monitored customer is processed according to the anomaly handling method corresponding to the target anomaly warning level, including: If the target anomaly warning level is the first warning level, then a warning message is sent to the anomaly handler corresponding to the customer to be monitored; If the target anomaly warning level is the second warning level, then a warning message and a customer follow-up task are sent to the anomaly handler corresponding to the customer to be monitored. The risk level of the first warning level is lower than that of the second warning level; the warning message is used to notify the anomaly handler that the monitored customer has an anomaly, so that the anomaly handler can pay attention to the anomaly of the monitored customer; the customer follow-up task refers to the task of following up on and reporting the anomaly of the monitored customer.

7. The method according to claim 1, characterized in that, Anomaly analysis is performed on the business operations of the customer to be monitored to identify anomaly data. Trend analysis is then performed on the anomaly data to obtain anomaly trend data characterizing the anomaly trend, including: Using a pre-built anomaly analysis algorithm, anomaly analysis is performed on the business of the customer to be monitored to determine anomaly data, and trend analysis is performed on the anomaly data to obtain anomaly trend data that characterizes the anomaly trend. The anomaly analysis algorithm is an algorithm encapsulated using Java Agent technology.

8. A customer anomaly monitoring device, characterized in that, include: The anomaly analysis module is used to perform anomaly analysis on the business of the customer to be monitored based on the acquired business data of the customer to be monitored, and to determine the anomaly data; The trend analysis module is used to perform trend analysis on the abnormal data to obtain abnormal trend data that characterizes the abnormal trend. Anomaly warning module is used to determine the target anomaly warning level based on the correspondence between each anomaly warning level and each anomaly trend, wherein the target anomaly warning level is the anomaly warning level corresponding to the anomaly trend represented by the anomaly trend data; The anomaly processing module is used to process the anomalies of the monitored customer according to the anomaly processing method corresponding to the target anomaly warning level.

9. An electronic device, characterized in that, include: Memory and processor; The memory is connected to the processor and is used to store programs; The processor is configured to implement the customer anomaly monitoring method as described in any one of claims 1 to 7 by running a program in the memory.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the customer anomaly monitoring method as described in any one of claims 1 to 7.

Images