Bank marketing business data analysis method and device

Abstract

The invention discloses a bank marketing business data analysis method and device, which can be used in the field of bank business management, and the method comprises the steps: extracting rule data matched with bank marketing business data from a cache pool to determine the matching degree, if the matching degree does not reach a preset standard, creating new rule data to analyze the bank marketing business data, and if the matching degree does not reach the preset standard, creating a database; determining the matching degree between the new rule data and the bank marketing business data according to the analysis result; obtaining the satisfaction degree of the user to the new rule data, and determining the weight of the new rule data according to the satisfaction degree; adjusting the matching degree between the new rule data and the bank marketing business data according to the weight of the new rule data; if the cache pool is full, screening rule data to be eliminated according to the matching degree of the rule data in the cache pool and historical bank marketing business data and the recent use moment; and deleting the rule data to be eliminated from the cache pool, and storing new rule data into the cache pool. The operation analysis efficiency can be effectively improved, and the working cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of banking business management, and in particular to a banking marketing business data analysis method and device. Background Art

[0002] This section is intended to provide a background or context for embodiments of the present invention. No description herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] At present, the bank's marketing business system already supports customer data analysis, marketing activity analysis, etc. In daily system use, operators combine activity-related conditions and extract and analyze relevant data. In daily marketing activities, a large number of indicators need to be extracted. After each rule data is extracted, the extracted rule data needs to be deleted and then recombined. If you want to re-view the recently queried rule data, you need to generate the rule data repeatedly. If the conditions are simple, there is no need for many complex operations. With the refinement of operational activities, marketing analysis work is more detailed, involving more and more combined conditions. Repeated combinations are time-consuming and labor-intensive, increasing marketing labor costs and reducing operational efficiency. Summary of the invention

[0004] The embodiment of the present invention provides a banking marketing business data analysis method for improving operational analysis efficiency and reducing work costs. The method includes:

[0005] receiving bank marketing business data, extracting rule data matching the bank marketing business data from a cache pool, and determining a matching degree between the extracted rule data and the bank marketing business data;

[0006] If the matching degree does not meet the preset standard, create new rule data for the bank's marketing business data;

[0007] Use new rule data to analyze bank marketing business data and obtain analysis results;

[0008] Determine the matching degree between the new rule data and the bank's marketing business data based on the analysis results;

[0009] Obtain user satisfaction with new rule data, and determine the weight of the new rule data based on the satisfaction;

[0010] Adjust the matching degree between the new rule data and the bank's marketing business data according to the weight of the new rule data;

[0011] If the cache pool is full, filter the rule data to be eliminated based on the matching degree between the rule data in the cache pool and the historical bank marketing business data, and the most recent usage time;

[0012] Delete the rule data to be eliminated from the cache pool and store the new rule data into the cache pool.

[0013] The embodiment of the present invention further provides a banking marketing business data analysis device for improving operational analysis efficiency and reducing work costs. The device includes:

[0014] A matching module, used for receiving bank marketing business data, extracting rule data matching the bank marketing business data from a cache pool, and determining a matching degree between the extracted rule data and the bank marketing business data;

[0015] A rule creation module is used to create new rule data for the bank's marketing business data if the matching degree does not meet the preset standard;

[0016] An analysis module is used to analyze the bank's marketing business data using the new rule data to obtain analysis results; and to determine the matching degree between the new rule data and the bank's marketing business data according to the analysis results;

[0017] A matching degree adjustment module is used to obtain user satisfaction with the new rule data, determine the weight of the new rule data according to the satisfaction, and adjust the matching degree between the new rule data and the bank's marketing business data according to the weight of the new rule data;

[0018] The cache pool management module is used to screen the rule data to be eliminated according to the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent use time if the cache pool is full; delete the rule data to be eliminated from the cache pool and store the new rule data into the cache pool.

[0019] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned bank marketing business data analysis method when executing the computer program.

[0020] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned bank marketing business data analysis method is implemented.

[0021] An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned bank marketing business data analysis method is implemented.

[0022] In the embodiment of the present invention, bank marketing business data is received, rule data matching the bank marketing business data is extracted from the cache pool, and the matching degree between the extracted rule data and the bank marketing business data is determined; if the matching degree does not reach the preset standard, new rule data is created for the bank marketing business data; the bank marketing business data is analyzed using the new rule data to obtain the analysis result; the matching degree between the new rule data and the bank marketing business data is determined according to the analysis result; the user's satisfaction with the new rule data is obtained, and the weight of the new rule data is determined according to the satisfaction; the matching degree between the new rule data and the bank marketing business data is adjusted according to the weight of the new rule data; if the cache pool is full, the rule data to be eliminated is screened according to the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent use time; the rule data to be eliminated is deleted from the cache pool, and the new rule data is stored in the cache pool. In this way, by establishing a cache pool to store historical rule data, matching the adapted rule data from the cache pool, adjusting the analysis standard weight with reference to the user satisfaction, determining the matching degree of each rule data, eliminating low-value rule data, effectively improving the efficiency of operation analysis, and reducing work costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0024] Figure 1 A flow chart of a banking marketing business data analysis method provided in an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of determining the matching degree between new rule data and bank marketing business data provided in an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of screening rule data to be eliminated provided in an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of a bank marketing business data analysis device provided in an embodiment of the present invention;

[0028] Figure 5 It is a structural block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0030] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0031] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps is not limited and can be appropriately adjusted as needed.

[0032] The embodiment of the present invention provides a banking marketing business data analysis method, such as Figure 1 As shown, including:

[0033] Step 101: receiving bank marketing business data, extracting rule data matching the bank marketing business data from a cache pool, and determining a matching degree between the extracted rule data and the bank marketing business data;

[0034] Step 102: If the matching degree does not reach the preset standard, create new rule data for the bank marketing business data;

[0035] Step 103: Analyze the bank marketing business data using the new rule data to obtain analysis results;

[0036] Step 104: Determine the matching degree between the new rule data and the bank marketing business data according to the analysis result;

[0037] Step 105: Obtain the user's satisfaction with the new rule data, and determine the weight of the new rule data according to the satisfaction;

[0038] Step 106: adjusting the matching degree between the new rule data and the bank marketing business data according to the weight of the new rule data;

[0039] Step 107: If the buffer pool is full, filter the rule data to be eliminated according to the matching degree between the rule data in the buffer pool and the historical bank marketing business data and the most recent usage time;

[0040] Step 108: Delete the rule data to be eliminated from the cache pool, and store the new rule data into the cache pool.

[0041] The bank marketing business data analysis method proposed in the embodiment of the present invention records relevant marketing rule data according to the customer analysis and operation data analysis conditions used by the operation personnel on a daily basis, creates a marketing rule data cache pool for the operation personnel, and provides a method for extracting and eliminating marketing rule data for the operation personnel. At the same time, a weighted scoring method is provided for the customer to weight the marketing rule data. When the marketing rule data record reaches the upper limit, it is eliminated according to the weighted data and the customer's most recent marketing rule data record, and the marketing rule data that can be eliminated is predicted. In combination with the usage, the relevant marketing rule data is eliminated. In this way, the time cost of customer selection is reduced, the efficiency of marketing activity analysis is improved, and the overall operation efficiency is improved.

[0042] In specific implementation, weighted operations are provided to customers, where weighted operations are mainly implemented through questionnaires. After customers have used the product, the degree of their preference for the marketing rule data is obtained through questionnaires. Scores are calculated based on the answers given by customers, and the scores are converted into corresponding weight values.

[0043] Figure 2 This is a schematic diagram of determining the matching degree between new rule data and bank marketing business data provided in an embodiment of the present invention, such as Figure 2 As shown, in the embodiment of the present invention, the matching degree between the new rule data and the bank marketing business data is determined according to the analysis result, including:

[0044] Step 201: performing multiple matches between the new rule data and the bank marketing business data from multiple dimensions to obtain matching degrees in different dimensions;

[0045] Step 202: Weight the matching degrees of different dimensions, and determine the weighted result as the matching degree between the new rule data and the bank marketing business data.

[0046] In one embodiment, the new rule data is matched with the bank marketing business data multiple times from multiple dimensions to obtain the matching degrees in different dimensions, including:

[0047] The new rule data is matched multiple times with the bank's marketing business data from the dimensions of analysis time point, customer attributes, activity nature, activity cost rules, and the operating personnel's affiliated institutions to obtain matching degrees in different dimensions.

[0048] During the specific implementation, the rule data of the marketing business data is set, and the matching degree is calculated between the marketing rule data operated by the operation personnel and the records in the marketing rule data pool from the dimensions of analysis time point, customer attributes, nature of activities, activity cost rules, and the operation personnel's affiliation organization. If three or more of them are similar or have been used and selected as very applicable in the questionnaire, 5 points are set; if two of them are similar or the marketing rule data are collected, 4 points are set; if only one of them is similar or the marketing rule data has been used, 3 points are set; if the similarity of each item is medium but the marketing rule data has been shared, 2 points are set; if the marketing rule data has been viewed, 1 point is set; if the similarity is low, 0 points are set; if there is no similarity or the evaluation is inappropriate, -5 points are set. The scores range from -5 to +5 points, and the evaluation data of the operation personnel in the marketing rule data cache pool are stored.

[0049] Figure 3 FIG. 1 is a schematic diagram of filtering rule data to be eliminated provided in an embodiment of the present invention, such as Figure 3 As shown, in the embodiment of the present invention, according to the matching degree between the rule data in the cache pool and the historical bank marketing business data, and the most recent use time, the rule data to be eliminated is screened, including:

[0050] Step 301: Determine the usage value of the rule data in the cache pool according to the matching degree between the rule data in the cache pool and the historical bank marketing business data, and the most recent usage time;

[0051] Step 302: Sort the rule data in the cache pool according to the usage value, and determine the rule data with the lowest usage value in the cache pool as the rule data to be eliminated.

[0052] In one embodiment, the usage value of each rule data is determined as follows:

[0053] The lower the matching degree, the lower the usage value of the rule data; and the earlier the most recent usage time, the lower the usage value of the rule data.

[0054] In one embodiment, it further includes:

[0055] If the matching degree between the rule data extracted from the cache pool and the bank's marketing business data reaches a preset standard, the bank's marketing business data is analyzed based on the extracted rule data.

[0056] In the specific implementation, first determine whether the marketing rule data in the cache pool is full. If not, there is no need to eliminate it. If it is full, use a logistic regression model to build a marketing rule data scoring model based on the matching scores of each marketing rule data. Use the elimination and retention of marketing rule data as events in the model, and predict the probability of each marketing rule data being eliminated through the historical data of the marketing rule data. For marketing analysis habits that are predicted to need to be eliminated, determine the marketing rule data that needs to be eliminated based on the most recent usage time and delete it from the cache pool.

[0057] For example, when user A creates relevant marketing analysis conditions, he calculates the marketing data with the highest similarity in the cache pool in real time based on the business data content. The calculation method uses different dimensions W1, W2, W3... (including analysis time point, customer attributes, activity nature, activity cost rules, and operator affiliation) to calculate the matching degree of each dimension using the Pearson correlation coefficient, calculates the average vector using the COS algorithm, and lists them in order for operators to choose.

[0058] If the matching degree does not meet the preset standard, new rule data is created for the bank's marketing business data. After the marketing activity analysis habit enters the pool, the marketing analysis habit elimination module is called to determine whether the cache pool is full. The logistic regression model is used to build an elimination model for marketing analysis habits. This model can be used to obtain a 0-1 data result. If the value exceeds 0.8, it is considered that the data can be eliminated. If the prediction result can be eliminated, combined with the matching degree data, if the matching degree data is low, it will be eliminated from the pool.

[0059] Then, we mainly use three methods: questionnaire, prediction value weighting, and ranking order weighting. Among them, the questionnaire method is to obtain the customer's preference for the marketing analysis habit through the form of a questionnaire after the customer has used it. The score is calculated based on the customer's answer and converted into the corresponding weight value according to the score value. If the questionnaire evaluation is high or low, 0 points, 5 points, and 10 points are given respectively, and the subsequent scoring module is given for comprehensive scoring; while the prediction value weighting does not require the customer to answer the questionnaire. Through the content of the marketing analysis habit, the similarity with the customer's marketing analysis habit history is calculated. The more similar, the higher the weight, and vice versa; and the ranking order weighting is to sort the prediction results, perform weighted calculation according to the ranking, reverse the ranking, and use the ranking as the weight. After the operation is completed, the scoring module is called to score the marketing analysis habit. After the scoring is completed, a new round of marketing analysis will begin.

[0060] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0061] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0062] The present invention also provides a bank marketing business data analysis device, as described in the following embodiments. Since the principle of solving the problem by the device is similar to that of the bank marketing business data analysis method, the implementation of the device can refer to the implementation of the bank marketing business data analysis method, and the repeated parts will not be repeated.

[0063] Figure 4 Schematic diagram of a bank marketing business data analysis device provided in an embodiment of the present invention, Figure 4 As shown, the device comprises:

[0064] The matching module 401 is used to receive the bank marketing business data, extract the rule data matching the bank marketing business data from the cache pool, and determine the matching degree between the extracted rule data and the bank marketing business data;

[0065] A rule creation module 402 is used to create new rule data for the bank marketing business data if the matching degree does not meet the preset standard;

[0066] The analysis module 403 is used to analyze the bank marketing business data using the new rule data to obtain the analysis result; and determine the matching degree between the new rule data and the bank marketing business data according to the analysis result;

[0067] The matching degree adjustment module 404 is used to obtain the user's satisfaction with the new rule data, determine the weight of the new rule data according to the satisfaction, and adjust the matching degree between the new rule data and the bank's marketing business data according to the weight of the new rule data;

[0068] The cache pool management module 405 is used to filter the rule data to be eliminated according to the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent use time if the cache pool is full; delete the rule data to be eliminated from the cache pool and store the new rule data into the cache pool.

[0069] In one embodiment, the analysis module 403 is specifically used for:

[0070] Perform multiple matches between new rule data and bank marketing business data from multiple dimensions to obtain matching degrees in different dimensions;

[0071] The matching degrees of different dimensions are weighted, and the weighted results are determined as the matching degree between the new rule data and the bank's marketing business data.

[0072] In one embodiment, the analysis module 403 is specifically used for:

[0073] The new rule data is matched multiple times with the bank's marketing business data from the dimensions of analysis time point, customer attributes, activity nature, activity cost rules, and the operating personnel's affiliated institutions to obtain matching degrees in different dimensions.

[0074] In one embodiment, the buffer pool management module 405 is specifically used for:

[0075] Determine the usage value of the rule data in the cache pool based on the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent usage time;

[0076] The rule data in the cache pool are sorted according to their usage value, and the rule data with the lowest usage value in the cache pool are determined as the rule data to be eliminated.

[0077] In one embodiment, the buffer pool management module 405 is specifically used for:

[0078] The usage value of each rule data is determined as follows:

[0079] The lower the matching degree, the lower the usage value of the rule data; and the earlier the most recent usage time, the lower the usage value of the rule data.

[0080] In one embodiment, the matching module 401 is further configured to:

[0081] If the matching degree between the rule data extracted from the cache pool and the bank's marketing business data reaches a preset standard, the bank's marketing business data is analyzed based on the extracted rule data.

[0082] Based on the above invention concept, Figure 5 As shown, the present invention also proposes a computer device 500, including a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520, wherein the processor 520 implements the aforementioned banking marketing business data analysis method when executing the computer program 530.

[0083] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned bank marketing business data analysis method is implemented.

[0084] An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned bank marketing business data analysis method is implemented.

[0085] In summary, in the embodiment of the present invention, bank marketing business data is received, rule data matching the bank marketing business data is extracted from the cache pool, and the matching degree between the extracted rule data and the bank marketing business data is determined; if the matching degree does not reach the preset standard, new rule data is created for the bank marketing business data; the bank marketing business data is analyzed using the new rule data to obtain the analysis result; the matching degree between the new rule data and the bank marketing business data is determined according to the analysis result; the user's satisfaction with the new rule data is obtained, and the weight of the new rule data is determined according to the satisfaction; the matching degree between the new rule data and the bank marketing business data is adjusted according to the weight of the new rule data; if the cache pool is full, the rule data to be eliminated is screened according to the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent use time; the rule data to be eliminated is deleted from the cache pool, and the new rule data is stored in the cache pool. In this way, by establishing a cache pool to store historical rule data, matching the adapted rule data from the cache pool, adjusting the analysis standard weight with reference to the user satisfaction, determining the matching degree of each rule data, eliminating low-value rule data, effectively improving the efficiency of operation analysis, and reducing work costs.

[0086] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 processes in the flowchart and / or block diagram. 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.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A banking marketing business data analysis method, characterized in that: include: receiving bank marketing business data, extracting rule data matching the bank marketing business data from a cache pool, and determining a matching degree between the extracted rule data and the bank marketing business data; If the matching degree does not meet the preset standard, create new rule data for the bank's marketing business data; Use new rule data to analyze bank marketing business data and obtain analysis results; Determine the matching degree between the new rule data and the bank's marketing business data based on the analysis results; Obtain user satisfaction with new rule data, and determine the weight of the new rule data based on the satisfaction; Adjust the matching degree between the new rule data and the bank's marketing business data according to the weight of the new rule data; If the cache pool is full, filter the rule data to be eliminated based on the matching degree between the rule data in the cache pool and the historical bank marketing business data, and the most recent usage time; Delete the rule data to be eliminated from the cache pool and store the new rule data into the cache pool.

2. The method according to claim 1, characterized in that Determine the matching degree between the new rule data and the bank's marketing business data based on the analysis results, including: Perform multiple matches between new rule data and bank marketing business data from multiple dimensions to obtain matching degrees in different dimensions; The matching degrees of different dimensions are weighted, and the weighted results are determined as the matching degree between the new rule data and the bank's marketing business data.

3. The method according to claim 2, characterized in that The new rule data is matched with the bank's marketing business data multiple times from multiple dimensions to obtain the matching degree of different dimensions, including: The new rule data is matched multiple times with the bank's marketing business data from the dimensions of analysis time point, customer attributes, activity nature, activity cost rules, and the operating personnel's affiliated institutions to obtain matching degrees in different dimensions.

4. The method according to claim 1, characterized in that According to the matching degree between the rule data in the cache pool and the historical bank marketing business data, and the most recent usage time, filter the rule data to be eliminated, including: Determine the usage value of the rule data in the cache pool based on the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent usage time; The rule data in the cache pool are sorted according to their usage value, and the rule data with the lowest usage value in the cache pool are determined as the rule data to be eliminated.

5. The method according to claim 4, characterized in that The usage value of each rule data is determined as follows: The lower the matching degree, the lower the usage value of the rule data; and the earlier the most recent usage time, the lower the usage value of the rule data.

6. The method according to claim 1, characterized in that Also includes: If the matching degree between the rule data extracted from the cache pool and the bank's marketing business data reaches a preset standard, the bank's marketing business data is analyzed based on the extracted rule data.

7. A banking marketing business data analysis device, characterized in that: include: A matching module, used for receiving bank marketing business data, extracting rule data matching the bank marketing business data from a cache pool, and determining a matching degree between the extracted rule data and the bank marketing business data; A rule creation module is used to create new rule data for the bank's marketing business data if the matching degree does not meet the preset standard; An analysis module is used to analyze the bank's marketing business data using the new rule data to obtain analysis results; and to determine the matching degree between the new rule data and the bank's marketing business data according to the analysis results; A matching degree adjustment module is used to obtain user satisfaction with the new rule data, determine the weight of the new rule data according to the satisfaction, and adjust the matching degree between the new rule data and the bank's marketing business data according to the weight of the new rule data; The cache pool management module is used to screen the rule data to be eliminated according to the matching degree between the rule data in the cache pool and the historical bank marketing business data and the most recent use time if the cache pool is full; delete the rule data to be eliminated from the cache pool and store the new rule data into the cache pool.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images