Method and system for analyzing the flow of customer information groups

Abstract

The present application provides a method for analyzing the flow of customer information groups and a system for analyzing the flow of customer information groups. The method includes: determining the flow data of customer information groups based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group. By applying the technical solution of the present application, it is possible to classify the target customer based on the first customer identification information at the first moment, and reclassify the second customer identification information of the same target customer at the second moment. In this way, since the classification criteria are the same, but the classification information is different (or the classification information can also be the same), the target customer can be accurately classified into the corresponding customer information group at different moments, and then the changes of various types of customer information groups at different periods can be accurately determined.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and more specifically, to a method and device for analyzing the flow of customer information groups, a computer-readable storage medium, and a system for analyzing the flow of customer information groups. Background Art

[0002] With the continuous advancement of technology and the maturing market, the differences between banking products and services are becoming increasingly narrow. The production-centric, sales-oriented management philosophy is gradually being replaced by a new, customer-centric, service-oriented mindset. In recent years, the electronic payment market has entered a mature stage after experiencing rapid growth. The banking industry's electronic payment market is becoming saturated, and internal growth potential is shrinking. Therefore, it is necessary to shift from focusing on card binding scale and simply accumulating benefits to managing payment customer information groups, using data-driven, refined operations to further tap into business development potential.

[0003] In the area of ​​customer behavior analysis at large state-owned commercial banks, research has found that if the structure and changing trends of these banks' customer information groups can be visually and effectively observed after segmenting them based on indicators such as transaction behavior, age, asset status, and consumption, this will not only be of positive significance in guiding state-owned banks in conducting internal business analysis and formulating targeted business strategies, but will also provide guidance for indirectly analyzing the growth, activity, cyclicality, and potential downside risks of the national macroeconomic economy through data from these large banks. However, due to the extremely wide range of customer information groups and types covered by these banks, resulting in a huge number of customers and accounts, complex and changing customer transaction behavior variables, and a wide range of asset categories, faced with such a massive amount of data, it is usually only possible to determine the distribution of the number of customer information groups within a bank, but it is impossible to determine the changes in the bank's various customer information groups over time. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, computer-readable storage medium and customer information group flow analysis system to at least solve the problem in the existing technology that it is impossible to determine the changes in various types of customer information groups of a bank in different periods of time.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for analyzing the flow of customer information groups is provided, including: obtaining multiple first customer identification information, wherein the first customer identification information is the customer identification information of the target customer collected at the first moment, and the customer identification information includes at least one of the following: customer identification, card number, transaction record; obtaining a first preset condition, wherein the first preset condition is a condition for classifying multiple target customers according to at least one of the customer identification information; classifying multiple first customer identification information according to the first preset condition to obtain multiple first customer information groups, wherein each of the first customer information groups includes at least one target customer, and the first customer identification information of the target customers of the same first customer information group is the same and / or is in the same classification interval, and the classification interval is classified according to the value range of the customer identification information. The method comprises the following steps: obtaining a plurality of second customer identification information, wherein the second customer identification information is the customer identification information of the target customer collected at a second moment, and the second moment is later than the first moment; classifying the plurality of second customer identification information according to the first preset condition to obtain a plurality of second customer information groups, wherein each of the second customer information groups includes at least one target customer, and the second customer identification information of the target customers of the same second customer information group is the same and / or is located in the same classification interval; determining customer group flow data according to the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the customer group flow data is at least used to characterize the customer flow situation of the target customer flowing between the plurality of the first customer information groups to form the plurality of the second customer information groups.

[0006] Optionally, the first customer group flow data includes the first outflow customer number, the first inflow customer number and the first net flow number, the first customer group flow data is the data of the target customer flowing in the customer information group across the same layer, and the customer group flow data is determined based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, including: determining first transfer information based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the first transfer information is the change of the customer information group to which the target customer belongs from the first moment to the second moment; constructing a first matrix based on the first transfer information, wherein the The elements of the first row of the first matrix are the second customer information group, the elements of the first column of the first matrix are the first customer information group, and the elements of the Nth row and Nth column of the first matrix are the first transfer information, where N≥2; based on the elements in the first matrix, the number of the first outflow customers flowing out of each first customer information group to multiple second customer information groups is calculated respectively; based on the elements in the first matrix, the number of the first inflow customers flowing into each first customer information group from multiple second customer information groups is calculated respectively; the difference between the first outflow customer number and the first inflow customer number is calculated to obtain the first net flow number, where the first net flow number is the change in the number of the target customers of the first customer information group.

[0007] Optionally, after determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes: acquiring multiple third customer identification information, wherein the third customer identification information is the customer identification information of the target customer collected at a third time, and the third time is later than the second time; classifying the third customer identification information in the multiple second customer information groups according to the first preset condition to obtain multiple updated second customer information groups, wherein each updated second customer information group includes at least one target customer, and the third customer identification information of the target customers in the same updated second customer information group is the same and / or falls within the same classification interval; determining second customer group flow data based on the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group, wherein the second customer group flow data is used to characterize the flow of the target customer between the second customer information groups of the same level and type, and the second customer group flow data includes a second outflow customer quantity, a second inflow customer quantity, and a second net flow quantity.

[0008] Optionally, determining the second customer group flow data based on the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group includes: determining second transfer information based on the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group, wherein the second transfer information is a change in the customer information group to which the target customer belongs from the second moment to the third moment; constructing a second matrix based on the second transfer information, wherein the first M elements of the first row of the second matrix are the second customer information group, and the elements of the first column of the second matrix are the updated second customer information group. The M-th element of the first row of the second matrix is ​​the first customer information group, and the element of the N-th row and N-th column of the second matrix is ​​the second transfer information, where N≥2, M>N; based on the elements in the second matrix, the number of the second outflow customers flowing out of each second customer information group to the multiple updated second customer information groups is calculated respectively; based on the elements in the second matrix, the number of the second inflow customers flowing into each second customer information group from the multiple updated second customer information groups is calculated respectively; the difference between the second outflow customer number and the second inflow customer number is calculated to obtain the second net flow number, where the second net flow number is the number of the target customers of the updated second customer information group.

[0009] Optionally, after determining customer flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes: obtaining a second preset condition, wherein the second preset condition is a condition for classifying the target customers in multiple second customer information groups based on at least one of the customer identification information; classifying the second customer information groups in multiple second customer information groups according to the second preset condition to obtain multiple third customer information groups, wherein the number of the third customer information groups is less than or equal to the number of the second customer information groups, each of the third customer information groups includes at least one target customer, and the second customer identification information of the target customers in the same third customer information group is the same and / or is located in the same classification interval; determining third customer group flow information based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, wherein the third customer group flow information is used to characterize the customer flow of the target customers between multiple second customer information groups to form multiple third customer information groups.

[0010] Optionally, based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, determining the flow information of the third customer group includes: determining third transfer information based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, wherein the third transfer information is the change of the target customer moving from the second customer information group to the third customer information group; constructing a third matrix based on the third transfer information, wherein the elements of the first row of the third matrix are the third customer information group, the elements of the first column of the third matrix are the second customer information group, and the elements of the Nth row and Nth column of the third matrix are the third transfer information, where N≥2; and calculating the number of the target customers of the second customer information group included in each of the third customer information groups based on the elements in the third matrix.

[0011] Optionally, after determining the customer flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes: generating a Sankey diagram according to the customer flow data and displaying it in a display interface, wherein the first customer information group is used as a node in the first column of the Sankey diagram, the second customer information group is used as a node in the second column of the Sankey diagram, and the customer flow data is used as the flow between the first column and the second column of the Sankey diagram.

[0012] According to another aspect of the present application, a device for analyzing the flow of customer information groups is provided, comprising: a first acquisition unit, configured to acquire multiple first customer identification information, wherein the first customer identification information is customer identification information of a target customer collected at a first moment, and the customer identification information includes at least one of the following: customer identification, card number, and transaction record; a second acquisition unit, configured to acquire a first preset condition, wherein the first preset condition is a condition for classifying multiple target customers according to at least one of the customer identification information; a first classification unit, configured to classify multiple first customer identification information according to the first preset condition to obtain multiple first customer information groups, wherein each of the first customer information groups includes at least one target customer, and the first customer identification information of the target customers of the same first customer information group is the same and / or is located in the same classification interval, and the classification interval is obtained by dividing according to the value range of the customer identification information. a third acquisition unit for acquiring a plurality of second customer identification information, wherein the second customer identification information is the customer identification information of the target customer collected at a second moment, and the second moment is later than the first moment; a second classification unit for classifying the plurality of second customer identification information according to the first preset condition to obtain a plurality of second customer information groups, wherein each of the second customer information groups includes at least one target customer, and the second customer identification information of the target customers of the same second customer information group is the same and / or is located in the same classification interval; a first determination unit for determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the customer group flow data is at least used to characterize the customer flow situation of the target customer flowing between the plurality of the first customer information groups to form the plurality of the second customer information groups.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the customer information group flow analysis methods.

[0014] According to another aspect of the present application, a system for analyzing the flow of customer information groups is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the analysis methods of the flow of customer information groups.

[0015] By applying the technical solution of the present application, it is possible to classify the target customers based on their first customer identification information at the first moment, and to classify the same target customers again based on their second customer identification information at the second moment. In this way, since the classification criteria are the same, but the classification information is different (or the classification information may be the same), the target customers can be accurately classified into corresponding customer information groups at different moments, and thus the changes in various types of customer information groups at different periods can be accurately determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for analyzing the flow of customer information groups provided in an embodiment of the present application is shown;

[0018] Figure 2 A schematic diagram showing a flow chart of a method for analyzing the flow of customer information groups provided according to an embodiment of the present application is shown;

[0019] Figure 3 A flow chart showing the analysis and display of customer information group flows;

[0020] Figure 4 Shown based on Figure 3 A schematic diagram of the structure of a virtual device of the scheme;

[0021] Figure 5 shows a schematic diagram of the structure of a data table;

[0022] Figure 6 A schematic diagram of the process of generating a Sankey diagram is shown;

[0023] Figure 7 A schematic diagram of a Sankey diagram generated by this solution is shown;

[0024] Figure 8 The figure shows a structural block diagram of a device for analyzing the flow of customer information groups provided according to an embodiment of the present application.

[0025] The above drawings include the following reference numerals:

[0026] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in 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 this application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein. In addition, the terms "including" and "having" and any of their variations 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.

[0030] In some solutions, customer information group flow analysis has the following main problems and shortcomings:

[0031] 1. In the case of massive amounts of data, it is impossible to query the flow of multi-layer customer information groups in real time. Customer information group flow data can only be processed in batches at the end of each day, which has poor timeliness.

[0032] 2. The method for displaying the flow of customer information groups generally only compares the customer information group structure distribution diagrams between the base period and the target period to show the changes in the customer information group. However, it lacks an effective way to display the detailed sources and destinations of the accounts in the customer information group.

[0033] 3. There is a lack of effective means to visually display the changes in the flow of customer information groups between multiple time period nodes, which makes it impossible for analysts to make efficient judgments on the long-term trends of the flow of customer information groups.

[0034] As introduced in the background technology, the existing technology is unable to determine the changes in various types of customer information groups of a bank at different times. In order to solve the above problems, the embodiments of the present application provide a method, device, computer-readable storage medium and customer information group flow analysis system.

[0035] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0036] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for analyzing the flow of customer information groups according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 102 (the processor 102 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. 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 mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0037] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the device information display method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. 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 examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0038] In this embodiment, a method for analyzing the flow of customer information groups running on a mobile terminal, a computer terminal or a similar computing device 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.

[0039] Figure 2 This is a flow chart of a method for analyzing the flow of customer information groups according to an embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0040] Step S201: Acquire multiple first customer identification information, wherein the first customer identification information is customer identification information of a target customer collected at a first moment, and the customer identification information includes at least one of the following: customer identification, card number, and transaction record;

[0041] Specifically, the target customer's customer identification information can be collected. The customer identification information can also include at least one of the following: background, products held, transaction behavior, transaction frequency, etc. In this way, by collecting the original customer identification information, the customer identification information can be subsequently counted and filtered to mark the customer and form a customer tag.

[0042] Specifically, the first customer identification information may include a formed customer tag, which may contain a comprehensive description of one or more customer identification information, accurately reflect the relevant characteristics of the customer's transaction behavior, and may also integrate customer information groups according to certain specific conditions, so that there is no need to repeat the data preparation process later.

[0043] Step S202, obtaining a first preset condition, wherein the first preset condition is a condition for classifying the plurality of target customers according to at least one of the customer identification information;

[0044] Specifically, one type of customer identification information can be used to classify target customers, or a combination of multiple types of customer identification information can be used to classify target customers. In this way, different preset conditions can be set through different combinations to comprehensively determine the differences between target customers in terms of value, risk, background, behavior, etc., and different customer information groups can be established subsequently.

[0045] Optionally, if there are 10 target customers, the transaction amount in the customer identification information can be used as the first preset condition, or a combination of region and transaction amount can be used as the first preset condition, for example, the region is region A and the transaction amount is above RMB 50,000.

[0046] Step S203: Classifying the plurality of first customer identification information according to the first preset condition to obtain a plurality of first customer information groups, wherein each of the first customer information groups includes at least one target customer, and the first customer identification information of the target customers in the same first customer information group is the same and / or falls within the same classification interval, where the classification interval is obtained by dividing the plurality of first customer identification information according to the value range of the customer identification information.

[0047] Specifically, after obtaining the first preset condition, the multiple first customer identification information obtained in advance can be classified, so that multiple first customer information groups can be obtained. For example, the transaction amount is greater than 50,000 yuan as customer information group A (customer information group, referred to as customer group), and the transaction amount is less than or equal to 50,000 yuan as customer information group B. Among them, the transaction amount of the target customers in customer information group A is greater than 50,000 yuan, and the transaction amount of the target customers in customer information group B is less than or equal to 50,000 yuan. For another example, the region is region A as customer information group A, and the region is region B as customer information group B. Alternatively, the first customer identification information can be combined to group the region A with a transaction amount of more than 50,000 yuan as customer information group A, and the region B with a transaction amount of more than 50,000 yuan as customer information group B.

[0048] Step S204, obtaining a plurality of second customer identification information, wherein the second customer identification information is the customer identification information of the target customer collected at a second moment, the second moment being later than the first moment;

[0049] Specifically, after obtaining the first customer information group, a certain first customer information group may be selected as a focus customer information group layer, so that the flow of customer information groups in the same layer or across layers can be analyzed.

[0050] In addition, the target customers in the first customer information group and the target customers in the second customer information group have not changed, but the customer identification information has changed. For example, the transaction amount of target customer A at the first moment is 10,000 yuan, and target customer A is classified into the first customer information group (first customer information group, referred to as the first customer group). At the second moment, the transaction amount of target customer A is 50,000 yuan, and target customer A is classified into the second customer information group (second customer information group, referred to as the second customer group). In this way, the second customer identification information must be obtained again at the second moment, and the same target customer can be classified multiple times subsequently.

[0051] You can also select a base period (the first moment), an intermediate period (the second moment), and a target period (a moment later than the second moment). For example, "January 2021 - May 2021 - August 2021" indicates changes in the focus customer information group layer from January to May 2021, and from May to August 2021. You can select one or more intermediate periods.

[0052] Step S205: Classifying the plurality of second customer identification information according to the first preset condition to obtain a plurality of second customer information groups, wherein each second customer information group includes at least one target customer, and the second customer identification information of the target customers in the same second customer information group is the same and / or falls within the same classification interval;

[0053] Specifically, after obtaining the first preset condition, the target customers were classified using the first preset condition to obtain the first customer information group. The target customers can be classified again, and the second customer identification information of the target customers obtained at the second moment can be classified. In this way, the customer identification information of the target customers can be classified at different times. For example, the target customer belongs to the first customer information group during the first classification, and the target customer belongs to the second customer information group after the second classification. In this way, the customer identification information can be classified at different times, and the customer flow situation can be determined subsequently.

[0054] Step S206, determining customer flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the customer flow data is at least used to characterize the customer flow situation of the target customer flowing between multiple first customer information groups to form multiple second customer information groups.

[0055] Specifically, the flow of target customers can be determined based on the customer identification information (first customer identification information and second customer identification information) of the same target customer at different times, so that changes in the customer information group to which the target customer belongs can be determined.

[0056] Specifically, the process of grouping customer information groups is actually based on a combination of one or several attributes such as the customer's assets, transaction behavior, age, transaction preferences, etc. After grouping, customers in different groups are specifically identified by their own customer identification information, that is, the first customer identification information and the second customer identification information can both correspond to a combination of one or several attributes such as assets, transaction behavior, age, transaction preferences, etc., and the first customer identification information and the second customer identification information can be the same in different time periods.

[0057] Through this embodiment, the target customer can be classified based on the first customer identification information at the first moment, and the second customer identification information of the same target customer at the second moment can be re-classified. In this way, since the classification criteria are the same, but the classification information is different (or the classification information can also be the same), the target customers can be accurately classified into corresponding customer information groups at different moments, and then the changes in various customer information groups at different periods can be accurately determined.

[0058] Specifically, after obtaining the customer group flow data, the customer group flow data can also be visualized. The analysis and display process of the customer information group flow is as follows: Figure 3 As shown, the following steps are included:

[0059] (1) Target customer identification information collection and label processing: Collect target customers within the bank and collect and organize data such as target customers' background, product holdings, and transaction behavior. By counting and screening the original data (target customer identification information), the target customers are marked to form customer labels (the first customer identification information). The customer label contains a comprehensive description of one or more related original data and can relatively accurately reflect the characteristics of the target customer's transaction behavior. At the same time, customer groups can be arbitrarily integrated according to specific conditions without repeating the data preparation process;

[0060] (2) Customer group classification process: Through different combinations and judgments of target customer labels, comprehensively examine the differences of target customers in terms of value, risk, background, behavior, etc., and establish different customer group classifications;

[0061] (3) Customer group selection process: select a customer group as the focus customer group, and conduct customer group flow display work within and across layers;

[0062] (4) Set the observation time point process: select the base period, intermediate time point and target time point. For example, January 2021 to May 2021 to August 2021 means to check the changes of the focus customer group layer from January to May 2021 and the changes of the focus customer group layer from May to August 2021. There can be one or more intermediate time points;

[0063] (5) Display of the flow of key customer groups: The flow of other major customer groups on the same level, the mutual flow between the same major categories on the same level, and the belonging of this level to the previous level. The flow of customer groups is displayed in the form of a Sankey diagram. Based on the original Sankey diagram, it has been optimized to more intuitively display the multi-dimensional changes in customer group flow.

[0064] according to Figure 3 The program description can also build a display device for the flow of customer information groups, such as Figure 4 As shown, the device includes:

[0065] (1) Data collection module: Synchronizes the target customer data within the bank and cleans and processes the data, collecting and organizing the target customer's background, product holdings, transaction behavior, etc. By counting and screening the original data, the target customer is marked to form a customer label;

[0066] (2) Customer group classification module: By combining and judging different customer labels, the system comprehensively examines the differences in target customers in terms of value, risk, background, behavior, etc., and establishes different customer group classifications. The system separately labels the target customers and the customer groups to which the target customers belong, optimizes the data storage type (any existing feasible optimization algorithm can be used), and facilitates flexible query by the upper-level module;

[0067] (3) Customer flow display module: Based on the selected focus customer group, comparison time, and comparison customer group information, the focus customer group and inflow / outflow situation are displayed using the Sankey diagram.

[0068] There are many ways to determine customer flow information. This solution uses a matrix-building method to determine customer group flow data, so as to analyze each first customer information group in turn. In the specific implementation process, the first customer group flow data includes the first outflow customer number, the first inflow customer number and the first net flow number. The above-mentioned first customer group flow data is the data of the flow of the above-mentioned target customers in the customer information group across categories at the same level. According to the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, the customer group flow data is determined. It can be achieved by the following steps: According to the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, the first transfer information is determined, wherein the above-mentioned first transfer information is the flow of the above-mentioned target customers from the above-mentioned first moment to the above-mentioned second moment. changes in the customer information groups belonging to it; constructing a first matrix based on the above-mentioned first transfer information, wherein the elements of the first row of the above-mentioned first matrix are the above-mentioned second customer information groups, the elements of the first column of the above-mentioned first matrix are the above-mentioned first customer information groups, and the elements of the Nth row and Nth column of the above-mentioned first matrix are the above-mentioned first transfer information, wherein N≥2; calculating the number of the first outflow customers flowing out of each of the above-mentioned first customer information groups to the multiple second customer information groups based on the elements in the above-mentioned first matrix; calculating the number of the first inflow customers flowing into each of the above-mentioned first customer information groups from the multiple second customer information groups based on the elements in the above-mentioned first matrix; calculating the difference between the first outflow customer number and the first inflow customer number to obtain the above-mentioned first net flow number, wherein the above-mentioned first net flow number is the change in the number of the above-mentioned target customers of the above-mentioned first customer information group.

[0069] In this solution, the transfer status of a target customer in a first customer information group (i.e., the first transfer information) can be determined in sequence first. Specifically, the transfer status of the target customer can be determined based on customer identification information. For example, it can be determined based on the target customer's ID number. At the first moment, it is determined that the target customer belongs to the first customer information group based on the target customer's ID number. At the second moment, it is determined that the target customer belongs to the second customer information group based on the target customer's ID number. Then, by constructing a matrix, the flow status of customers between multiple first customer information groups and multiple second customer information groups can be determined respectively. Among them, the customer flow status generally includes data on inflow, outflow and net flow. Through this embodiment, the flow status of customers between different categories can be determined more accurately.

[0070] Specifically, we can first build a customer information group layer P for customer information group flow analysis (taking two categories of customer information groups A and B as an example). Assume that category A has x different customer information groups {C A1 ,C A2 ,C A3 ,...C Ax}, Class B has y different customer information groups {C B1 ,C B2 ,C B3 ,...C By}, calculate the first moment T0 and the second moment T m The flow of customer information groups between them. Category A and Category B are different customer information groups across categories at the same level. The first moment is T0 and the second moment is T m The first matrix between the Class A customer information group and the Class B customer information group is as follows:

[0071]

[0072] <F AxBy ,F ByAx > represents the first transfer information. The calculation method for the flow of customer information groups between the same layer and different categories is as follows: at the first moment T0 and at the second moment T m1 During this period, a customer information group C of category A in layer P A1 The number of first outflow customers flowing to the B-layer customer information group is The number of first inflow customers is The customer information group C A1 The first net flow quantity is The first customer flow data of other first customer information groups are calculated in the same way, which will not be elaborated here.

[0073] In the case where the customer flow direction between the same layer and across categories has been determined, if the customer flow direction between the same layer and the same category is to be determined, the customer identification information can be obtained again after a certain period of time. The customer identification information obtained at this time is the customer identification information in the second customer information group. Some customer identification information may be updated, resulting in the second customer information group also being updated. At this time, the customer flow direction between the same layer and the same category can be determined. In the specific implementation process, after determining the customer group flow data based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, the above-mentioned method further includes the following steps: obtaining multiple third customer identification information, wherein the above-mentioned third customer identification information is the above-mentioned customer identification information of the above-mentioned target customer collected at a third moment, and the above-mentioned third moment is later than the above-mentioned The second moment; classify the above-mentioned third customer identification information in the multiple above-mentioned second customer information groups according to the above-mentioned first preset condition to obtain multiple updated second customer information groups, wherein each of the above-mentioned updated second customer information groups includes at least one above-mentioned target customer, and the above-mentioned third customer identification information of the above-mentioned target customers of the same above-mentioned updated second customer information group is the same and / or is located in the same above-mentioned classification interval; determine the second customer group flow data based on the above-mentioned second customer identification information in the above-mentioned second customer information group and the above-mentioned third customer identification information in the above-mentioned updated second customer information group, wherein the above-mentioned second customer group flow data is used to characterize the flow of the above-mentioned target customers between the above-mentioned second customer information groups of the same level and the same type, and the above-mentioned second customer group flow data includes the second outflow customer number, the second inflow customer number and the second net flow number.

[0074] In this solution, after obtaining the second customer information group, customer identification information can be obtained again at the third moment. The customer identification information obtained at this time all belongs to the same general category, but some customer identification information is updated, resulting in some target customers being classified into different second customer information groups, that is, the second customer information group is updated, while the number of second customer information groups does not change. Based on the updated second customer information group, the flow of customers of the same category can be accurately determined.

[0075] In order to further ensure that the flow of customer information groups between the same level and the same category can be accurately determined, the present application determines the second customer group flow data based on the above-mentioned second customer identification information in the above-mentioned second customer information group and the above-mentioned third customer identification information in the above-mentioned updated second customer information group, which can be achieved through the following steps: determining the second transfer information based on the above-mentioned second customer identification information in the above-mentioned second customer information group and the above-mentioned third customer identification information in the above-mentioned updated second customer information group, wherein the above-mentioned second transfer information is the change of the customer information group to which the above-mentioned target customer belongs from the above-mentioned second moment to the above-mentioned third moment; constructing a second matrix based on the above-mentioned second transfer information, wherein the first M elements of the first row of the above-mentioned second matrix are the above-mentioned second customer information group, and the above-mentioned second matrix The elements of the first column are the updated second customer information group, the Mth element of the first row of the second matrix is ​​the first customer information group, and the elements of the Nth row and Nth column of the second matrix are the second transfer information, wherein N≥2, M>N; according to the elements in the second matrix, respectively calculate the number of the second outflow customers flowing out of each of the second customer information groups to the multiple updated second customer information groups; according to the elements in the second matrix, respectively calculate the number of the second inflow customers flowing into each of the second customer information groups from the multiple updated second customer information groups; calculate the difference between the second outflow customer number and the second inflow customer number to obtain the second net flow number, wherein the second net flow number is the number of the target customers of the updated second customer information group.

[0076] In this solution, the flow of customer information groups between the same level and the same category can be determined based on the second customer identification information at the second moment and the third customer identification information at the third moment. At this time, the number of second customer information groups has not changed. It is just that due to changes in time, the customer identification information of the target customer has changed, and the second customer information group in which the target customer is located will be different. Therefore, the matrix construction method can be chosen to further accurately determine the flow of customer information groups between the same level and the same category.

[0077] Specifically, the second time T can be calculated m At the third moment T F It should be noted that the flow of customer information groups calculated at this time is the change of customer information groups between multiple second customer information groups. Different from the change of customer information groups across categories at the same level above, this section introduces the change of customer information groups between the same level and the same category. The second matrix constructed is:

[0078]

[0079] <F ByBy> represents the second transfer information. The calculation method for the flow of customer information groups between the same level and the same category is as follows: m At the third moment T F During this period, a customer information group C of category B in layer P B1 The number of second outflow customers flowing to the same-layer customer information group is The second number of inbound customers is The customer information group C B1 The second net flow amount is The second customer flow data of other second customer information groups are calculated in the same way, which will not be elaborated here.

[0080] In the case where the customer flow between the same level and the same category or across categories at the same level has been determined, if it is to be determined that the customer flow is at the upper level of a certain customer information group level, that is, to classify the customer information group again at a higher level or a larger range, the customer information group can still be classified again according to different conditions. In the specific implementation process, after determining the customer group flow data based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, the above-mentioned method further includes the following steps: obtaining a second preset condition, wherein the above-mentioned second preset condition is a condition for classifying the above-mentioned target customers in the multiple above-mentioned second customer information groups according to at least one of the above-mentioned customer identification information; classifying the multiple above-mentioned target customers according to the above-mentioned second preset condition. The above-mentioned second customer information groups in the above-mentioned second customer information group are classified to obtain multiple third customer information groups, wherein the number of the above-mentioned third customer information groups is less than or equal to the number of the above-mentioned second customer information groups, each of the above-mentioned third customer information groups includes at least one above-mentioned target customer, and the above-mentioned second customer identification information of the above-mentioned target customers in the same above-mentioned third customer information group is the same and / or is located in the same above-mentioned classification interval; based on the above-mentioned second customer identification information in the above-mentioned second customer information group and the above-mentioned second customer identification information in the above-mentioned third customer information group, the third customer group flow information is determined, and the above-mentioned third customer group flow information is used to characterize the customer flow situation of the above-mentioned target customers flowing between the multiple above-mentioned second customer information groups to form the multiple above-mentioned third customer information groups.

[0081] In this solution, after obtaining the second customer information group, the second preset condition can be used to reclassify the second customer information group. This is to reclassify the second customer information group, and it is a higher-level classification. For example, there are 10 second customer information groups in total, which need to be classified again. The third customer information group obtained after the final classification can be 8, 6, or even 2 (not limited to these, it can also be others). This is to determine the upper-level category of the target customers in the second customer information group, and then more accurately determine the classification of the target customers in the upper-level category.

[0082] Specifically, after the above classification, 5 second customer information groups were obtained, namely A, B, C, D, and E. They were previously divided according to transaction amount. For example, the transaction amount of group A is 5000-10000, the transaction amount of group B is 10001-20000, the transaction amount of group C is 20001-30000, the transaction amount of group D is 30001-40000, and the transaction amount of group E is 40001-50000. In order to classify the target customers again and determine the VIP, VVIP, and VVVIP among the customers, the transaction amount can still be used to divide them. For example, the transaction amount of 1000-20000 is classified as VIP, the transaction amount of 20001-40000 is classified as VVIP, and the transaction amount of 40001-60000 is classified as VVVIP.

[0083] In order to further efficiently reclassify the second customer information group, the present application determines the flow information of the third customer group based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, which can be achieved through the following steps: determining third transfer information based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, wherein the third transfer information is the change of the target customer from the second customer information group to the third customer information group; constructing a third matrix based on the third transfer information, wherein the elements of the first row of the third matrix are the third customer information group, the elements of the first column of the third matrix are the second customer information group, and the elements of the Nth row and Nth column of the third matrix are the third transfer information, N≥2; calculating the number of the target customers of the second customer information group included in each of the third customer information groups based on the elements in the third matrix.

[0084] In this solution, the classification of a certain customer information group level toward the upper layer can be determined based on the second customer identification information of the second customer information group and the second customer identification information of the third customer information group. At this time, the second customer information group may not have been updated yet, or the second customer information group may have been updated. The method of this embodiment can be used to perform upper-level classification on the second customer information group. Therefore, the method of constructing a matrix can be selected to further efficiently perform upper-level reclassification on the second customer information group.

[0085] Specifically, the customer information group layer constructed in the aforementioned part is the P layer. Now a new customer information group layer O layer is constructed. The O layer has z different customer information groups {C o1 ,C o2 ,C o3 ,...C oz}, the second moment T can be calculated m The flow of customer information groups can also be calculated at the second moment T m At the third moment T F It should be noted that the flow of customer information groups calculated at this time is the change of customer information groups between multiple second customer information groups and the third customer information group. It is different from the change of customer information groups across categories at the same level and the change of customer information groups of the same level. This section introduces the change of customer information groups between different levels. For example, at the third moment T F When the third matrix is ​​constructed by using the Class B customer information group and classifying it according to the previous layer, it is:

[0086]

[0087] S ByOz The third transfer information is represented by the following calculation method for the customer information group flow of the upper classification (i.e., the upper classification of the second customer information group): F When it belongs to a customer information group classification S at layer O O1 The number of P-layer B-type customer information groups is The third customer flow data of other third customer information groups are calculated in the same way, which will not be elaborated here.

[0088] The algorithm provided by this solution supports real-time flow query of customer information groups of hundreds of millions of customers. Business personnel can select any time point and any comparison range to query data, and the system supports response within seconds.

[0089] Specifically, to more accurately determine customer identification information and use different customer identification information to determine customer flow, making it easier to use data when generating a Sankey diagram later, you can use a wide table to store customer information. In a specific implementation, this solution uses a data source table, a basic wide table, and a wide table to store data. The following describes the functions of each data table:

[0090] (1) Data source table: Data directly maintained by external systems or business personnel is collectively referred to as the data source table. Only data cleaning operations are performed on the data without any data processing, statistics, or calculations. The structure is basically consistent with the original system, and it is mainly responsible for basic data synchronization and storage. The purpose is to simplify the subsequent data processing work. Figure 5 As shown, the data source table includes customer name, customer account, customer tag, customer institution, customer storage bank type (UnionPay merchant or NetsUnion merchant), customer contracted bank type (UnionPay contract or NetsUnion contract), customer transaction bank type (UnionPay transaction or NetsUnion transaction), and customer order bank type (UnionPay order or NetsUnion order).

[0091] (2) Basic wide table: lightly processes the data source table, mainly performing data classification and data mapping operations. The basic wide table decouples the wide table and the data source table, and the wide table data processing is oriented to the basic wide table, avoiding the impact of the original system changes on the upper wide table. The basic wide table is a logical table and does not store specific data. Figure 5 As shown, the basic broad table includes customer name, customer account, customer organization, merchant, contract signing method, and transaction type.

[0092] (2) Conduct statistical processing on basic customer information, and conduct statistical analysis on the user's daily transaction behavior, contract signing status and other information. Mark the customer according to the label rules set by the business. Store the marked data according to different provinces. Figure 5 As shown, the wide table includes customer name, customer account, customer institution, contract signing method, transaction type, daily transaction statistics table, monthly transaction statistics table, customer analysis wide table, and customer tag table.

[0093] Current visualization technologies for analyzing customer information groups typically use pie charts, histograms, discount charts, and other methods to display the distribution of the number of bank customer information groups and analysis of dimensions such as changes over time periods. Such visualization solutions can only independently display changes in different customer information groups themselves, but lack accurate and intuitive display methods for analyzing account flows between different customer information groups (or the flow of other information within customer information groups). In particular, existing visualization solutions cannot meet the requirements for account transfers between a large number of customer information groups. Therefore, to address the problem of poor visualization, in some embodiments, after determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes the following steps: generating a Sankey diagram based on the customer group flow data and displaying it on a display interface, wherein the first customer information group is used as a node in the first column of the Sankey diagram, the second customer information group is used as a node in the second column of the Sankey diagram, and the customer group flow data is used as the flow between the first and second columns of the Sankey diagram.

[0094] In this solution, since we can determine the inflow of customer information from other major categories on the same layer, the mutual flow between the same major categories on the same layer, and the ownership of this layer in the previous layer, we can use the Sankey diagram to display the flow of customer information groups. This is based on the original Sankey diagram and has been optimized to more intuitively display the multi-dimensional changes in the flow of customer information groups.

[0095] Specifically, this solution uses the visualization method of Sankey diagram to intuitively display the changes in the flow of customer information groups between different types of customer information groups at the same level, and between the same type of customer information groups at the same level, as well as the affiliation of the customer information groups at this level to the customer information groups at the previous level. It intuitively displays the changes in the flow of customer information groups between multiple time period nodes, making it easier for analysts to make efficient judgments on the long-term trends in the flow of customer information groups.

[0096] In a specific solution, the generation process of the multi-layer customer information group flow to the Sankey diagram is as follows Figure 6 As shown, the following steps are included:

[0097] (1) Customer wide table loading: Load and collect the source tables in the internal database of the device. Such source tables contain source data of all customer transaction attributes, customer attributes, asset attributes, etc. Then, through data processing and screening, a series of technical wide tables such as customers, accounts, institutions, and transactions are formed. Finally, by combining the basic tables, a customer information group wide table with grouping attributes such as initial customers, assets, age, consumption behavior, and consumption areas is constructed according to the grouping rules and conditions required by the customer information group;

[0098] (2) Classification and processing of customer information groups: Based on the customer broad table, combined with the customer information group classification rules set by business personnel, different combinations and judgments of customer identification information, and comprehensive consideration of differences in customer value, risk, background, behavior, etc., different customer information group classifications are established to classify customers and form independent customer information groups. The specific process is as follows:

[0099] a) Business personnel can formulate different customer information group classification rule parameters for customers based on their geographical location.

[0100] b) Automatically perform customer wide table data calculations and mark customers layer by layer based on customer wide table data and customer information group classification rules.

[0101] c) Perform a series of permutations, combinations, and processing operations on customer tags to group customers with similar characteristics into the same customer information group;

[0102] (3) Customer information group flow calculation, which is the calculation method of the customer group flow data mentioned above in this application;

[0103] (4) Display of customer information group flow: Based on the above customer information group nodes, transfer matrix and related calculation methods, a visualization example is generated through the Sankey diagram. It can quickly generate the flow of customer information groups between different categories at the same level, the flow of customer information groups between the same level and the same level, and the classification of customer information groups at this level in the upper level, so as to meet the requirements of customer information group flow and structural change analysis in multiple dimensions. The width of the river between customer information groups in the Sankey diagram can represent the outflow / inflow of customer information groups (the two flow directions of the Sankey diagram can be switched with one click).

[0104] Specifically, the generated Sankey diagram is as follows Figure 7 As shown, the nodes in the first column are the first customer information group (the original customer group), the nodes in the second column are the second customer information group (the first customer group), the nodes in the third column are the updated second customer information group (the second customer group), and the nodes in the fourth column are the third customer information group (the third customer group). The traffic between the first and second columns is the flow data of the first customer group, the traffic between the second and third columns is the flow data of the second customer group, and the traffic between the third and fourth columns is the flow information of the third customer group.

[0105] The embodiments of the present application also provide an analysis device for the flow of customer information groups. It should be noted that the analysis device for the flow of customer information groups in the embodiments of the present application can be used to execute the analysis method for the flow of customer information groups provided in the embodiments of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation methods, and the details that have been described will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0106] The following introduces the device for analyzing the flow of customer information groups provided in an embodiment of the present application.

[0107] Figure 8 This is a structural block diagram of a device for analyzing the flow of customer information groups according to an embodiment of the present application. Figure 8 As shown, the device includes:

[0108] A first acquiring unit 10 is configured to acquire a plurality of first customer identification information, wherein the first customer identification information is customer identification information of a target customer collected at a first moment, and the customer identification information includes at least one of the following: customer identification, card number, and transaction record;

[0109] A second acquiring unit 20 is configured to acquire a first preset condition, wherein the first preset condition is a condition for classifying the plurality of target customers according to at least one of the customer identification information;

[0110] a first classification unit 30 configured to classify the plurality of first customer identification information according to the first preset condition to obtain a plurality of first customer information groups, wherein each of the first customer information groups includes at least one target customer, and the first customer identification information of the target customers in the same first customer information group is the same and / or falls within the same classification interval, where the classification interval is obtained by dividing the plurality of first customer identification information according to the value range of the customer identification information;

[0111] A third acquiring unit 40 is configured to acquire a plurality of second customer identification information, wherein the second customer identification information is the customer identification information of the target customer collected at a second moment, the second moment being later than the first moment;

[0112] a second classification unit 50 configured to classify the plurality of second customer identification information according to the first preset condition to obtain a plurality of second customer information groups, wherein each second customer information group includes at least one target customer, and the second customer identification information of the target customers in the same second customer information group is the same and / or falls within the same classification interval;

[0113] The first determination unit 60 is used to determine customer flow data based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, wherein the above-mentioned customer flow data is at least used to characterize the customer flow situation of the above-mentioned target customers flowing between multiple above-mentioned first customer information groups to form multiple above-mentioned second customer information groups.

[0114] Through this embodiment, the target customer can be classified based on the first customer identification information at the first moment, and the second customer identification information of the same target customer at the second moment can be re-classified. In this way, since the classification criteria are the same, but the classification information is different (or the classification information can also be the same), the target customers can be accurately classified into corresponding customer information groups at different moments, and then the changes in various customer information groups at different periods can be accurately determined.

[0115] There are many ways to determine customer flow information. In this solution, a matrix construction method is used to determine customer group flow data, so as to analyze each first customer information group in turn. In the specific implementation process, the first customer group flow data includes the first outflow customer number, the first inflow customer number and the first net flow number. The above-mentioned first customer group flow data is the data of the flow of the above-mentioned target customer in the customer information group across categories at the same level. The first determination unit includes a first determination module, a first construction module, a first calculation module, a second calculation module and a third calculation module. The first determination module is used to determine the first transfer information based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, wherein the above-mentioned first transfer information is the change of the customer information group to which the above-mentioned target customer belongs from the above-mentioned first moment to the above-mentioned second moment; the first construction module is used to determine the first transfer information based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group. The first transfer information is used to construct a first matrix, wherein the elements of the first row of the first matrix are the second customer information groups, the elements of the first column of the first matrix are the first customer information groups, and the elements of the Nth row and Nth column of the first matrix are the first transfer information, wherein N≥2; a first calculation module is used to calculate the first number of outflow customers flowing out of each of the first customer information groups to the multiple second customer information groups according to the elements in the first matrix; a second calculation module is used to calculate the first number of inflow customers flowing into each of the first customer information groups from the multiple second customer information groups according to the elements in the first matrix; a third calculation module is used to calculate the difference between the first number of outflow customers and the first number of inflow customers to obtain the first net flow number, wherein the first net flow number is the change in the number of the target customers of the first customer information group.

[0116] In this solution, the transfer status of a target customer in a first customer information group (i.e., the first transfer information) can be determined in sequence first. Specifically, the transfer status of the target customer can be determined based on customer identification information. For example, it can be determined based on the target customer's ID number. At the first moment, it is determined that the target customer belongs to the first customer information group based on the target customer's ID number. At the second moment, it is determined that the target customer belongs to the second customer information group based on the target customer's ID number. Then, by constructing a matrix, the flow status of customers between multiple first customer information groups and multiple second customer information groups can be determined respectively. Among them, the customer flow status generally includes data on inflow, outflow and net flow. Through this embodiment, the flow status of customers between different categories can be determined more accurately.

[0117] In the case where the customer flow direction between the same layer and across categories has been determined, if the customer flow direction between the same layer and the same category needs to be determined, the customer identification information can be obtained again after a certain period of time. The customer identification information obtained at this time is all the customer identification information in the second customer information group. Some customer identification information may be updated, resulting in the second customer information group also being updated. At this time, the customer flow direction between the same layer and the same category can be determined. In the specific implementation process, the above-mentioned device also includes a fourth acquisition unit, a third classification unit and a second determination unit. The fourth acquisition unit is used to obtain multiple third customer identification information after determining the customer group flow data based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group. Among them, the above-mentioned third customer identification information is the above-mentioned customer identification information of the above-mentioned target customer collected at the third moment. later than the above-mentioned second moment; the third classification unit is used to classify the above-mentioned third customer identification information in the multiple above-mentioned second customer information groups according to the above-mentioned first preset condition, and obtain multiple updated second customer information groups, wherein each of the above-mentioned updated second customer information groups includes at least one above-mentioned target customer, and the above-mentioned third customer identification information of the above-mentioned target customers of the same above-mentioned updated second customer information group is the same and / or is located in the same above-mentioned classification interval; the second determination unit is used to determine the second customer group flow data based on the above-mentioned second customer identification information in the above-mentioned second customer information group and the above-mentioned third customer identification information in the above-mentioned updated second customer information group, wherein the above-mentioned second customer group flow data is used to characterize the flow of the above-mentioned target customers between the above-mentioned second customer information groups of the same level and the same type, and the above-mentioned second customer group flow data includes the second outflow customer number, the second inflow customer number and the second net flow number.

[0118] In this solution, after obtaining the second customer information group, customer identification information can be obtained again at the third moment. The customer identification information obtained at this time all belongs to the same general category, but some customer identification information is updated, resulting in some target customers being classified into different second customer information groups, that is, the second customer information group is updated, while the number of second customer information groups does not change. Based on the updated second customer information group, the flow of customers of the same category can be accurately determined.

[0119] In order to further ensure that the flow of customer information groups between the same level and the same category can be accurately determined, the second determination unit of the present application includes a second determination module, a second construction module, a fourth calculation module, a fifth calculation module and a sixth calculation module. The second determination module is used to determine the second transfer information based on the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group, wherein the second transfer information is the change in the customer information group to which the target customer belongs from the second moment to the third moment; the second construction module is used to construct a second matrix based on the second transfer information, wherein the first M elements of the first row of the second matrix are the second customer information group, and the elements of the first column of the second matrix are the updated second customer information group. , the M-th element of the first row of the above-mentioned second matrix is ​​the above-mentioned first customer information group, and the element of the N-th row and N-th column of the above-mentioned second matrix is ​​the above-mentioned second transfer information, wherein N≥2, M>N; the fourth calculation module is used to calculate the second outflow customer quantity of each above-mentioned second customer information group to the multiple above-mentioned updated second customer information groups according to the elements in the above-mentioned second matrix; the fifth calculation module is used to calculate the second inflow customer quantity of each above-mentioned second customer information group from the multiple above-mentioned updated second customer information groups according to the elements in the above-mentioned second matrix; the sixth calculation module is used to calculate the difference between the second outflow customer quantity and the second inflow customer quantity to obtain the above-mentioned second net flow quantity, wherein the above-mentioned second net flow quantity is the number of the above-mentioned target customers of the above-mentioned updated second customer information group.

[0120] In this solution, the flow of customer information groups between the same level and the same category can be determined based on the second customer identification information at the second moment and the third customer identification information at the third moment. At this time, the number of second customer information groups has not changed. It is just that due to changes in time, the customer identification information of the target customer has changed, and the second customer information group in which the target customer is located will be different. Therefore, the matrix construction method can be chosen to further accurately determine the flow of customer information groups between the same level and the same category.

[0121] In the case where the customer flow between the same level and the same type or across categories at the same level has been determined, if it is to be determined that the customer flow is at the upper level of a certain customer information group level, that is, the customer information group is to be classified again at a higher or larger range, the customer information group can still be classified again according to different conditions. In the specific implementation process, the above-mentioned device also includes a fifth acquisition unit, a fourth classification unit and a third determination unit. The fifth acquisition unit is used to obtain the second preset condition after determining the customer group flow data based on the above-mentioned first customer identification information in the above-mentioned first customer information group and the above-mentioned second customer identification information in the above-mentioned second customer information group, wherein the above-mentioned second preset condition is a condition for classifying the above-mentioned target customers in the multiple above-mentioned second customer information groups according to at least one of the above-mentioned customer identification information; the fourth classification unit is used to obtain the second preset condition according to The above-mentioned second preset condition classifies the above-mentioned second customer information groups in the multiple above-mentioned second customer information groups to obtain multiple third customer information groups, wherein the number of the above-mentioned third customer information groups is less than or equal to the number of the above-mentioned second customer information groups, each of the above-mentioned third customer information groups includes at least one above-mentioned target customer, and the above-mentioned second customer identification information of the above-mentioned target customers of the same above-mentioned third customer information group is the same and / or is located in the same above-mentioned classification interval; the third determination unit is used to determine the third customer group flow information based on the above-mentioned second customer identification information in the above-mentioned second customer information group and the above-mentioned second customer identification information in the above-mentioned third customer information group, and the above-mentioned third customer group flow information is used to characterize the customer flow situation of the above-mentioned target customers flowing between the multiple above-mentioned second customer information groups to form the multiple above-mentioned third customer information groups.

[0122] In this solution, after obtaining the second customer information group, the second preset condition can be used to reclassify the second customer information group. This is to reclassify the second customer information group, and it is a higher-level classification. For example, there are 10 second customer information groups in total, which need to be classified again. The third customer information group obtained after the final classification can be 8, 6, or even 2 (not limited to these, it can also be others). This is to determine the upper-level category of the target customers in the second customer information group, and then more accurately determine the classification of the target customers in the upper-level category.

[0123] In order to further efficiently reclassify the second customer information group, the third determination unit of the present application includes a third determination module, a third construction module and a seventh calculation module. The third determination module is used to determine the third transfer information based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, wherein the third transfer information is the change of the target customer from the second customer information group to the third customer information group; the third construction module is used to construct a third matrix based on the third transfer information, wherein the elements of the first row of the third matrix are the third customer information group, the elements of the first column of the third matrix are the second customer information group, and the elements of the Nth row and Nth column of the third matrix are the third transfer information, N≥2; the seventh calculation module is used to calculate the number of the target customers of the second customer information group included in each of the third customer information groups based on the elements in the third matrix.

[0124] In this solution, the classification of a certain customer information group level toward the upper layer can be determined based on the second customer identification information of the second customer information group and the second customer identification information of the third customer information group. At this time, the second customer information group may not have been updated yet, or the second customer information group may have been updated. The method of this embodiment can be used to perform upper-level classification on the second customer information group. Therefore, the method of constructing a matrix can be selected to further efficiently perform upper-level reclassification on the second customer information group.

[0125] Current visualization technologies for analyzing customer information groups typically use pie charts, histograms, discount charts, and other methods to display the distribution of the number of bank customer information groups and analyze changes over time. These visualization solutions can only independently display changes in different customer information groups themselves, but lack accurate and intuitive display methods for analyzing account flows between different customer information groups (or the flow of other information within customer information groups). In particular, existing visualization solutions cannot meet the requirements for account transfers between a large number of customer information groups. Therefore, to address the problem of poor visualization, in some embodiments, the apparatus further includes a display generation unit configured to, after determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, generate a Sankey diagram based on the customer group flow data and display it on a display interface. The first customer information group is represented as a node in the first column of the Sankey diagram, the second customer information group is represented as a node in the second column of the Sankey diagram, and the customer group flow data is represented as the flow between the first and second columns of the Sankey diagram.

[0126] In this solution, since we can determine the inflow of customer information from other major categories on the same layer, the mutual flow between the same major categories on the same layer, and the ownership of this layer in the previous layer, we can use the Sankey diagram to display the flow of customer information groups. This is based on the original Sankey diagram and has been optimized to more intuitively display the multi-dimensional changes in the flow of customer information groups.

[0127] The device for analyzing the flow of customer information groups includes a processor and a memory. The first acquisition unit, second acquisition unit, first classification unit, third acquisition unit, second classification unit, and first determination unit are all stored as program units in the memory. The processor executes the program units stored in the memory to implement the corresponding functions. The modules are all located in the same processor; alternatively, the modules can be located in different processors in any combination.

[0128] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and by adjusting kernel parameters, the problem of the existing technology that cannot determine the changes in the bank's various customer information groups over time can be solved.

[0129] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0130] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for analyzing the flow of customer information groups.

[0131] The present application also provides a customer information group flow analysis system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the above-mentioned customer information group flow analysis methods.

[0132] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the method for analyzing the flow of customer information groups when running.

[0133] An embodiment of the present invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, a method for analyzing the flow of customer information groups is implemented.

[0134] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0135] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initiating the steps of an analysis method having at least a flow of customer information groups.

[0136] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0137] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0138] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1The function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0141] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0142] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0143] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0144] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0145] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0146] 1) The method for analyzing the flow of customer information groups of the present application can classify the target customer based on the first customer identification information of the target customer at the first moment, and re-classify the second customer identification information of the same target customer at the second moment. In this way, since the classification criteria are the same, but the classification information is different (or the classification information can also be the same), the target customers can be accurately classified into corresponding customer information groups at different moments, and then the changes in various customer information groups at different periods can be accurately determined.

[0147] 2) The customer information group flow analysis device of the present application can classify the target customer based on the first customer identification information of the target customer at the first moment, and re-classify the second customer identification information of the same target customer at the second moment. In this way, since the classification standard is the same, but the classification information is different (or the classification information can also be the same), the target customers can be accurately classified into the corresponding customer information groups at different times, and then the changes in various customer information groups at different periods can be accurately determined.

[0148] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for analyzing the flow of customer information groups, characterized in that: include: Acquire multiple first customer identification information, wherein the first customer identification information is customer identification information of a target customer collected at a first moment, and the customer identification information includes at least one of the following: customer identification, card number, and transaction record; Acquire a first preset condition, wherein the first preset condition is a condition for classifying the plurality of target customers according to at least one type of customer identification information; Classifying the plurality of first customer identification information according to the first preset condition to obtain a plurality of first customer information groups, wherein each of the first customer information groups includes at least one target customer, and the first customer identification information of the target customers in the same first customer information group is the same and / or falls within the same classification interval, where the classification interval is obtained by dividing according to a value range of the customer identification information; Acquire multiple pieces of second customer identification information, wherein the second customer identification information is the customer identification information of the target customer collected at a second moment, and the second moment is later than the first moment; classifying the plurality of second customer identification information according to the first preset condition to obtain a plurality of second customer information groups, wherein each second customer information group includes at least one target customer, and the second customer identification information of the target customers in the same second customer information group is the same and / or falls within the same classification interval; Determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the customer group flow data is used to at least characterize customer flow conditions of the target customer flowing between the plurality of first customer information groups to form the plurality of second customer information groups; The first customer group flow data includes the first outflow customer number, the first inflow customer number and the first net flow number. The first customer group flow data is the data of the target customer flowing in the customer information group across the same layer and categories. The customer group flow data is determined based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, including: determining the first transfer information based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the first transfer information is the change of the customer information group to which the target customer belongs from the first moment to the second moment; constructing a first matrix based on the first transfer information, wherein the first matrix is ​​the first transfer information. The elements of the first row of a matrix are the second customer information group, the elements of the first column of the first matrix are the first customer information group, and the elements of the Nth row and Nth column of the first matrix are the first transfer information, where N≥2; based on the elements in the first matrix, the number of the first outflow customers flowing out of each first customer information group to multiple second customer information groups is calculated respectively; based on the elements in the first matrix, the number of the first inflow customers flowing into each first customer information group from multiple second customer information groups is calculated respectively; the difference between the first outflow customer number and the first inflow customer number is calculated to obtain the first net flow number, where the first net flow number is the change in the number of the target customers of the first customer information group.

2. The method according to claim 1, characterized in that After determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes: Acquire multiple third customer identification information, wherein the third customer identification information is the customer identification information of the target customer collected at a third moment, and the third moment is later than the second moment; classifying the third customer identification information in a plurality of the second customer information groups according to the first preset condition to obtain a plurality of updated second customer information groups, wherein each of the updated second customer information groups includes at least one target customer, and the third customer identification information of the target customers in the same updated second customer information group is the same and / or falls within the same classification interval; Based on the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group, the second customer group flow data is determined, wherein the second customer group flow data is used to characterize the flow of the target customers between the second customer information groups of the same level and type, and the second customer group flow data includes the second outflow customer number, the second inflow customer number and the second net flow number.

3. The method according to claim 2, characterized in that Determining second customer group flow data according to the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group includes: Determining second transfer information based on the second customer identification information in the second customer information group and the third customer identification information in the updated second customer information group, wherein the second transfer information is a change in the customer information group to which the target customer belongs from the second moment to the third moment; Constructing a second matrix based on the second transfer information, wherein the first M elements of the first row of the second matrix are the second customer information group, the elements of the first column of the second matrix are the updated second customer information group, the Mth element of the first row of the second matrix is ​​the first customer information group, and the element of the Nth row and Nth column of the second matrix is ​​the second transfer information, where N≥2 and M>N; Calculating the number of the second outflow customers from each second customer information group to the plurality of updated second customer information groups according to the elements in the second matrix; calculating, based on the elements in the second matrix, the number of second incoming customers for each second customer information group from the plurality of updated second customer information groups; The difference between the second outflow customer quantity and the second inflow customer quantity is calculated to obtain the second net flow quantity, wherein the second net flow quantity is the quantity of the target customers for updating the second customer information group.

4. The method according to claim 1, wherein After determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes: Acquire a second preset condition, wherein the second preset condition is a condition for classifying the target customers in the plurality of second customer information groups according to at least one type of customer identification information; classifying the second customer information groups among the plurality of second customer information groups according to the second preset condition to obtain a plurality of third customer information groups, wherein the number of the third customer information groups is less than or equal to the number of the second customer information groups, each of the third customer information groups includes at least one target customer, and the second customer identification information of the target customers in the same third customer information group is the same and / or falls within the same classification interval; Based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, the third customer group flow information is determined, and the third customer group flow information is used to characterize the customer flow of the target customer between multiple second customer information groups to form multiple third customer information groups.

5. The method according to claim 4, characterized in that Determining the flow information of the third customer group according to the second customer identification information in the second customer information group and the second customer identification information in the third customer information group includes: determining third transfer information based on the second customer identification information in the second customer information group and the second customer identification information in the third customer information group, wherein the third transfer information is a change in the target customer from the second customer information group to the third customer information group; constructing a third matrix based on the third transfer information, wherein elements of a first row of the third matrix are the third customer information group, elements of a first column of the third matrix are the second customer information group, and elements of an Nth row and an Nth column of the third matrix are the third transfer information, where N≥2; The number of the target customers of the second customer information group included in each of the third customer information groups is calculated according to the elements in the third matrix.

6. The method according to claim 1, characterized in that After determining customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, the method further includes: A Sankey diagram is generated according to the customer flow data and displayed in a display interface, wherein the first customer information group is used as a node in the first column of the Sankey diagram, the second customer information group is used as a node in the second column of the Sankey diagram, and the customer flow data is used as the flow between the first column and the second column of the Sankey diagram.

7. A device for analyzing the flow of customer information groups, characterized in that: include: A first acquiring unit is configured to acquire a plurality of first customer identification information, wherein the first customer identification information is customer identification information of a target customer collected at a first moment, and the customer identification information includes at least one of the following: customer identification, card number, and transaction record; A second acquiring unit is configured to acquire a first preset condition, wherein the first preset condition is a condition for classifying the plurality of target customers according to at least one type of customer identification information; a first classification unit, configured to classify the plurality of first customer identification information according to the first preset condition to obtain a plurality of first customer information groups, wherein each of the first customer information groups includes at least one target customer, and the first customer identification information of the target customers in the same first customer information group is the same and / or falls within the same classification interval, where the classification interval is obtained by dividing the plurality of first customer identification information according to a value range of the customer identification information; a third acquiring unit, configured to acquire a plurality of second customer identification information, wherein the second customer identification information is the customer identification information of the target customer collected at a second moment, the second moment being later than the first moment; a second classification unit, configured to classify the plurality of second customer identification information according to the first preset condition to obtain a plurality of second customer information groups, wherein each second customer information group includes at least one target customer, and the second customer identification information of the target customers in the same second customer information group is the same and / or falls within the same classification interval; a first determining unit configured to determine customer group flow data based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the customer group flow data is used to at least characterize customer flow conditions of the target customer flowing between the plurality of first customer information groups to form the plurality of second customer information groups; The first customer group flow data includes the first outflow customer number, the first inflow customer number and the first net flow number. The first customer group flow data is the data of the target customer flowing in the customer information group across the same layer. The first determination unit includes a first determination module, a first construction module, a first calculation module, a second calculation module and a third calculation module. The first determination module is used to determine the first transfer information based on the first customer identification information in the first customer information group and the second customer identification information in the second customer information group, wherein the first transfer information is the change of the customer information group to which the target customer belongs from the first moment to the second moment; the first construction module is used to construct a first matrix based on the first transfer information, wherein the elements of the first row of the first matrix are the The second customer information group, the elements of the first column of the first matrix are the first customer information group, and the elements of the Nth row and Nth column of the first matrix are the first transfer information, wherein N≥2; the first calculation module is used to calculate the first outflow customer quantity flowing out of each first customer information group to multiple second customer information groups according to the elements in the first matrix; the second calculation module is used to calculate the first inflow customer quantity flowing into each first customer information group from multiple second customer information groups according to the elements in the first matrix; the third calculation module is used to calculate the difference between the first outflow customer quantity and the first inflow customer quantity to obtain the first net flow quantity, wherein the first net flow quantity is the change in the quantity of the target customers of the first customer information group.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for analyzing the flow of customer information groups as claimed in any one of claims 1 to 6.

9. A customer information group flow analysis system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for analyzing the flow of customer information groups according to any one of claims 1 to 6.

Images