Intelligent merchant data analysis method and system

Abstract

The invention provides an intelligent merchant data analysis method and system, and belongs to the technical field of data analysis, and the method specifically comprises the steps: according to the historical transaction data amount in different dates and the deviation condition of the user portrait of a transaction user and the reference user portrait of a merchant, calculating the data of the merchant; determining transaction data change dates in the dates to obtain historical transaction data volumes of different transaction data change dates, and determining that the user portrait change risk of the merchant does not meet the requirement by combining the distribution data of the transaction data change dates and the deviation condition of the user portrait and the reference user portrait. The analysis and processing model of the transaction data of the commercial tenant on the current date is determined according to the transaction data volume of different types of user portraits on the current date and the distribution deviation condition of the reference user portraits, and the difficulty of data analysis and processing is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and particularly relates to an intelligent merchant data analysis method and system. Background Art

[0002] During the operation of merchants, a large amount of transaction data will be generated. In the past, the transaction data of merchants often has not been effectively analyzed, so that it is impossible to provide effective data support for the operation of merchants.

[0003] In order to analyze and process the transaction data of merchants, in the invention patent application CN202210169639.7 "Merchant Data Resource Analysis Method Based on a Digital Intelligence System", by collecting user consumption data, interaction data, and behavior trajectories and organizing them, useful resource data can be obtained, and these resource data are analyzed and stored, so as to realize the evaluation and prediction of the development of rapid marketing, brand business expansion, and promotion of merchants. However, the following technical problems exist in the above technical solutions: When analyzing and processing merchant data, due to the difference in the transaction data volume of merchant data and the limitation of server resources at the same time, it often fails to meet the analysis and processing requirements of different merchants by using a fixed analysis and processing model for transaction data. Therefore, how to generate a differentiated analysis and processing strategy according to the transaction data volume of merchant data has become an urgent technical problem to be solved.

[0004] In view of the above technical problems, specifically, the present application provides an intelligent merchant data analysis method and system. Summary of the Invention

[0005] To achieve the object of the present invention, the present invention adopts the following technical solutions: In a first aspect, the present application provides an intelligent merchant data analysis method, which specifically includes: S1 Use the historical transaction data volume of the merchant on different dates to determine whether the merchant needs to perform data analysis and processing using a preset time period. If so, go to step S4; if not, go to the next step; S2 Based on the historical transaction data of the merchant, determine the user portraits of the transaction users of the merchant on different dates, and determine the date of change of the transaction data in the date according to the deviation between the historical transaction data volume, the user portraits of the transaction users, and the benchmark user portrait of the merchant on different dates; S3 Obtain the historical transaction data volume of different dates of change of transaction data, and combine the distribution data of the dates of change of transaction data and the deviation between the user portrait and the benchmark user portrait. When it is determined that the risk of change of the user portrait of the merchant does not meet the requirements, go to the next step; S4 determines the analysis and processing model of the merchant's transaction data for the current date based on the transaction data volume of different types of user portraits in the current date and the distribution deviation from the benchmark user portrait.

[0006] The beneficial effects of the present invention are as follows: Based on the historical transaction data volume of different transaction data change dates, the distribution data of the transaction data change dates, and the deviation between the user portrait and the benchmark user portrait, it is determined whether the user portrait change risk of the merchant meets the requirements, realizing the screening of merchants with large changes in transaction data, and also laying a foundation for the analysis and processing model of the transaction data of merchants differentiated according to the changes in transaction data. This not only ensures the reliability of data analysis for merchants with large changes in transaction data but also reduces the processing difficulty of data analysis for merchants.

[0007] Based on the transaction data volume of different types of user portraits in the current date and the distribution deviation from the benchmark user portrait, the analysis and processing model of the merchant's transaction data for the current date is determined. This not only considers the impact of the transaction data on the merchant's data processing results due to the distribution deviation in the current date but also takes into account the differences in the impact of the transaction data volume of the user portrait on the merchant's data processing results. It realizes the determination of the analysis and processing model of the merchant's transaction data from multiple perspectives, ensuring the accuracy of the data analysis results while reducing the processing difficulty of data analysis.

[0008] A further technical solution is that the historical transaction data volume includes the number of transaction users on different dates and the data volume of associated transaction data of different transaction data.

[0009] A further technical solution is that determining whether the merchant needs to perform data analysis and processing using a preset time period specifically includes: Based on the historical transaction data volume of the merchant on different dates, determine the dates with a historical transaction data volume greater than the preset transaction data volume and use them as valid transaction dates; According to the proportion of the number of valid transaction dates in different divided time periods, determine the proportion of the number of valid dates in different divided time periods; Determine whether the merchant needs to perform data analysis and processing using a preset time period through the average value of the proportion of the number of valid dates in different divided time periods.

[0010] A further technical solution is that when the average value of the proportion of the number of valid dates in different divided time periods is greater than the preset threshold of the proportion of valid dates, it is determined that the merchant needs to perform data analysis and processing using a preset time period.

[0011] A further technical solution lies in that the preset time period is based on days for analyzing and processing the transaction data of the merchant.

[0012] A further technical solution lies in that the analysis and processing results of the transaction data of the current date include the baseline user portrait of the merchant, the matching user portraits of different types of goods, and the sales popularity of different types of goods in different types of user portraits.

[0013] In a second aspect, the present application provides an intelligent merchant data analysis system, which adopts the above-mentioned intelligent merchant data analysis method, and specifically includes: A data change date analysis module, a change risk assessment module, and an analysis model determination module; The data change date analysis module is responsible for determining the change date of the transaction data in the date; The change risk assessment module is responsible for determining whether the user portrait change risk of the merchant meets the requirements; The analysis model determination module is responsible for determining the analysis and processing model of the transaction data of the merchant on the current date.

[0014] Other features and advantages will be described in the following specification. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0015] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious.

[0017] Figure 1 is a flowchart of an intelligent merchant data analysis method; Figure 2 is a flowchart for determining whether the merchant needs to use a preset time period for data analysis and processing; Figure 3 is a flowchart of a method for determining the change date of the transaction data in the date; Figure 4 is a flowchart for determining that the user portrait change risk of the merchant does not meet the requirements; Figure 5 is a flowchart of a method for determining the analysis and processing model of the transaction data of the merchant on the current date; Figure 6 is a framework diagram of an intelligent merchant data analysis system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] To enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the scope of protection of this specification.

[0019] The purpose of the present invention is to determine the analysis and processing model of merchants differentiated according to the distribution deviation between different types of user portraits on the current date and the benchmark user portrait of the merchant, and on the basis of reducing the difficulty of data analysis, ensure the accuracy and timeliness of the data analysis and processing results of the merchant.

[0020] The date with the historical transaction data volume greater than the preset transaction data volume is used as the effective transaction date. According to the proportion of the number of effective transaction dates in different divided time periods, the proportion of the number of effective dates in different divided time periods is determined. When the average value of the proportion of the number of effective dates in different divided time periods is greater than the preset effective date proportion threshold, it is determined that the merchant needs to perform data analysis and processing using the preset time period.

[0021] The number of trading users in the date is determined by the historical transaction data volume in the date, and the deviated trading users among the trading users are determined by using the deviation between the user portraits of the trading users in the date and the benchmark user portrait of the merchant in different dimensions. The transaction data change date is the date when the number of trading users is greater than the preset user number and the number of deviated trading users is greater than the preset number of deviated trading users.

[0022] The number of trading users on different transaction data change dates is determined by the historical transaction data volume on different transaction data change dates. According to the distribution data of the transaction data change dates, the proportion of the number of transaction data change dates in different unit time periods is determined. Based on the ratio of the number of deviated trading users to the number of trading users on different transaction data change dates, the change weight coefficient of different transaction data change dates is determined. The change risk coefficient of different unit time periods is determined by the product of the proportion of the number of transaction data change dates in different unit time periods and the change weight coefficient of different transaction data change dates. The change time period in the unit time period is determined by using the change risk coefficient. When the number of change time periods is greater than the preset number of change time periods, it is determined that the change risk of the user portrait of the merchant does not meet the requirements.

[0023] Based on the deviation between the distribution proportion of different types of user portraits on the current date and the distribution proportion of the merchant in different types of user portraits, determine the types of user portraits with a deviation in the distribution proportion on the current date. When the number of trading users of the type of user portrait with a deviation in the distribution proportion on the current date is greater than the preset deviation trading user number, then use the preset analysis model to analyze and process the trading data of the merchant. When the number of trading users of the type of user portrait with a deviation in the distribution proportion on the current date is not greater than the preset deviation trading user number, then use the second preset analysis model to analyze and process the trading data of the merchant.

[0024] Embodiment 1 As Figure 1 shown, the present application provides an intelligent merchant data analysis method, which specifically includes: S1 Use the historical transaction data volume of the merchant on different dates to determine whether the merchant needs to perform data analysis processing using a preset time period. If so, go to step S4; if not, go to the next step; S2 Based on the historical transaction data of the merchant, determine the user portraits of the trading users of the merchant on different dates. According to the historical transaction data volume, the user portraits of the trading users, and the deviation from the benchmark user portrait of the merchant on different dates, determine the date of the change in the trading data in the date; S3 Obtain the historical transaction data volume of different trading data change dates, and combine the distribution data of the trading data change dates and the deviation between the user portrait and the benchmark user portrait. When it is determined that the user portrait change risk of the merchant does not meet the requirements, go to the next step; S4 Based on the trading data volume of different types of user portraits on the current date and the distribution deviation from the benchmark user portrait, determine the analysis processing model of the trading data of the merchant on the current date.

[0025] Furthermore, the historical transaction data volume includes the number of trading users on different dates and the data volume of associated transaction data of different transaction data.

[0026] Specifically, as Figure 2 shown, determining whether the merchant needs to perform data analysis processing using a preset time period specifically includes: Based on the historical transaction data volume of the merchant on different dates, determine the dates with a historical transaction data volume greater than the preset transaction data volume, and use them as valid transaction dates; According to the proportion of the number of valid transaction dates in different divided time periods, determine the proportion of the number of valid dates in different divided time periods; Determine whether the merchant needs to perform data analysis processing using a preset time period based on the average value of the proportion of the number of valid dates in different divided time periods.

[0027] It should be noted that when the average value of the proportion of the number of valid dates in different divided time periods is greater than the preset valid date proportion threshold, it is determined that the merchant needs to perform data analysis processing using a preset time period.

[0028] It can be understood that the preset time period is based on days for analyzing and processing the transaction data of the merchant.

[0029] Optionally, determining whether the merchant needs to perform data analysis processing using a preset time period specifically includes: Based on the historical transaction data volume of the merchant on different dates, determine the dates with a historical transaction data volume greater than the preset transaction data volume and use them as valid transaction dates; According to the proportion of the number of valid transaction dates in different divided time periods, determine the proportion of the number of valid dates in different divided time periods; Through the proportion of the number of valid dates in different divided time periods, determine the valid divided time periods in the divided time periods, and use the number of the valid divided time periods to determine whether the merchant needs to perform data analysis processing using a preset time period.

[0030] Furthermore, when the number of the valid divided time periods is greater than the preset number of valid time periods, it is determined that the merchant needs to perform data analysis processing using a preset time period.

[0031] It should be noted that the valid divided time period is a divided time period in which the proportion of the number of valid dates meets the requirements.

[0032] Furthermore, the user portrait of the transaction user includes the risk of churn, loyalty, shopping preferences, and payment channels.

[0033] It can be understood that the reference user portrait is constructed based on the user portrait with the largest number of transaction users corresponding to the analysis result of the historical transaction data of the merchant.

[0034] Specifically, as Figure 3 shown, the method for determining the transaction data change date in the date is: Determine the number of transaction users in the date based on the historical transaction data volume in the date; Based on the deviation between the user profile of the trading users on the said date and the benchmark user profile of the merchant, determine the deviation of the user profile of the trading users on the said date from the benchmark user profile of the merchant in different dimensions, and use the deviation in different dimensions to determine the deviated trading users among the trading users; Based on the number of trading users and the number of deviated trading users on the said date, determine whether the said date is a trading data change date.

[0035] Furthermore, the deviated trading users are those trading users for whom the number of dimensions with non - compliant deviation situations is greater than the preset number of dimensions.

[0036] It can be understood that the trading data change date is the date when the number of trading users is greater than the preset number of users and the number of deviated trading users is greater than the preset number of deviated trading users.

[0037] Optionally, determining that the user profile change risk of the merchant does not meet the requirements specifically includes: Determine the number of trading users on different trading data change dates based on the historical trading data volume of different trading data change dates; Determine the number of trading data change dates based on the distribution data of trading data change dates, and use the deviation between the user profiles and the benchmark user profiles on different trading data change dates to determine the number of deviated trading users on different trading data change dates; Based on the ratio of the number of deviated trading users to the number of trading users on different trading data change dates, determine the change weight coefficient for different trading data change dates, and determine whether the user profile change risk of the merchant meets the requirements by summing up the change weight coefficients for different trading data change dates.

[0038] Furthermore, when the sum of the change weight coefficients for different trading data change dates is greater than the preset weight coefficient threshold, it is determined that the user profile change risk of the merchant does not meet the requirements.

[0039] Specifically, when the user profile change risk of the merchant meets the requirements, use the preset update period and the preset analysis model to analyze and process the trading data of the merchant.

[0040] It should be noted that as Figure 4 shown, determining that the user profile change risk of the merchant does not meet the requirements specifically includes: Determine the number of trading users on different trading data change dates based on the historical trading data volume of different trading data change dates; Determine the proportion of the number of transaction data change dates in different unit time periods according to the distribution data of the transaction data change dates, and determine the change weight coefficient of different transaction data change dates based on the ratio of the number of deviated transaction users on different transaction data change dates to the number of the transaction users; Determine the change risk coefficient of different unit time periods through the product of the proportion of the number of transaction data change dates in different unit time periods and the change weight coefficient of different transaction data change dates, use the change risk coefficient to determine the change time period in the unit time period, and determine whether the change risk of the user portrait of the merchant meets the requirements according to the number of the change time periods.

[0041] Further, when the number of the change time periods is greater than the preset number of change time periods, it is determined that the change risk of the user portrait of the merchant does not meet the requirements.

[0042] Optionally, determining that the change risk of the user portrait of the merchant does not meet the requirements specifically includes: S31 Determine the number of transaction users on different transaction data change dates based on the historical transaction data volume of different transaction data change dates, and determine the data change coefficient of different transaction data change dates based on the ratio of the number of deviated transaction users on different transaction data change dates to the number of the transaction users and the number of the transaction users; S32 Determine the proportion of the number of transaction data change dates in different unit time periods according to the distribution data of the transaction data change dates, and determine the change risk coefficient of different unit time periods in combination with the data change coefficient of different transaction data change dates; S33 Determine the user portrait change coefficient of the merchant based on the change risk coefficient of different unit time periods, and use the user portrait change coefficient to determine whether the change risk of the user portrait of the merchant meets the requirements.

[0043] It can be understood that when the user portrait change coefficient of the merchant is not within the preset portrait change coefficient interval, it is determined that the change risk of the user portrait of the merchant does not meet the requirements.

[0044] Optionally, the above step S31 includes the following content: S311 Obtain the number of the transaction data change dates. When the number of the transaction data change dates does not meet the requirements, it is determined that the change risk of the user portrait of the merchant does not meet the requirements. When the number of the transaction data change dates meets the requirements, go to step S312; S312 determines the number of trading users on different transaction data change dates based on the historical transaction data volume of different transaction data change dates, and determines the data change coefficient of different transaction data change dates based on the ratio of the number of deviated trading users on different transaction data change dates to the number of the trading users and the number of the trading users; S313 When the sum of the data change coefficients of different transaction data change dates does not meet the requirements, it is determined that the user portrait change risk of the merchant does not meet the requirements. When the sum of the data change coefficients of different transaction data change dates meets the requirements, go to step S314; S314 When there is a transaction data change date with a data change coefficient greater than the preset change coefficient threshold, go to step S315. When there is no transaction data change date with a data change coefficient greater than the preset change coefficient threshold, go to step S32; S315 When the number of transaction data change dates with a data change coefficient greater than the preset change coefficient threshold does not meet the requirements, it is determined that the user portrait change risk of the merchant does not meet the requirements. When the number of transaction data change dates with a data change coefficient greater than the preset change coefficient threshold meets the requirements, go to step S32.

[0045] Optionally, the above step S32 includes the following content: S321 determines the proportion of the number of transaction data change dates in different unit time periods according to the distribution data of the transaction data change dates. When there is a unit time period with the proportion of the number of transaction data change dates greater than the preset proportion, go to step S322. When there is no unit time period with the proportion of the number of transaction data change dates greater than the preset proportion, go to step S323; S322 When the number of unit time periods with the proportion of the number of transaction data change dates greater than the preset proportion does not meet the requirements, it is determined that the user portrait change risk of the merchant does not meet the requirements. When the number of unit time periods with the proportion of the number of transaction data change dates greater than the preset proportion meets the requirements, go to step S323; S323 determines the proportion of the number of transaction data change dates in different unit time periods according to the distribution data of the transaction data change dates, and combines the data change coefficients of different transaction data change dates to determine the change risk coefficients of different unit time periods. When the average value of the change risk coefficients of different unit time periods does not meet the requirements, it is determined that the user portrait change risk of the merchant does not meet the requirements. When the average value of the change risk coefficients of different unit time periods meets the requirements, go to step S33.

[0046] Specifically, the type of the user portrait is determined according to the number of deviation dimensions from the reference user portrait, specifically including a first type of deviation type, a second type of deviation type, and a third type of deviation type.

[0047] Specifically, as Figure 5 shown, the method for determining the analysis and processing model of the transaction data of the merchant on the current date is as follows: Based on the transaction data volumes of different types of user portraits on the current date, determine the quantities of different types of user portraits, and use the quantities of different types of user portraits to determine the distribution ratios of different types of user portraits on the current date; Determine the distribution ratios of the merchant in different types of user portraits according to the distribution data of the reference user portrait; According to the deviation situation between the distribution ratios of different types of user portraits on the current date and the distribution ratios of the merchant in different types of user portraits, determine the types of user portraits with deviated distribution ratios on the current date, and use the number of trading users of the types of user portraits with deviated distribution ratios on the current date to determine the analysis and processing model of the transaction data of the merchant on the current date.

[0048] It should be noted that using the number of trading users of the types of user portraits with deviated distribution ratios on the current date to determine the analysis and processing model of the transaction data of the merchant on the current date specifically includes: When the number of trading users of the types of user portraits with deviated distribution ratios on the current date is greater than the preset deviation trading user number, then use the preset analysis model to analyze and process the transaction data of the merchant; When the number of trading users of the types of user portraits with deviated distribution ratios on the current date is not greater than the preset deviation trading user number, then use the second preset analysis model to analyze and process the transaction data of the merchant.

[0049] Furthermore, the preset analysis model takes all the transaction data of the merchant as the input quantity and uses the analysis model to analyze and process the transaction data of the merchant on the current date.

[0050] It can be understood that the second preset analysis model takes the analysis results of the historical transaction data of the merchant and the transaction data on the current date as the input quantity and uses the analysis model to analyze and process the transaction data of the merchant on the current date.

[0051] Specifically, the analysis and processing results of the transaction data on the current date include the reference user portrait of the merchant, the matching user portraits of different types of commodities, and the sales popularity of different types of commodities in different types of user portraits.

[0052] Embodiment 2 Second aspect, as Figure 6As shown in the figure, the present application provides an intelligent merchant data analysis system, which adopts the above-mentioned intelligent merchant data analysis method, and specifically includes: A data change date analysis module, a change risk assessment module, and an analysis model determination module; The data change date analysis module is responsible for determining the change date of transaction data in the date. The change risk assessment module is responsible for determining whether the change risk of the user portrait of the merchant meets the requirements. The analysis model determination module is responsible for determining the analysis and processing model of the transaction data of the merchant on the current date.

[0053] Optionally, it is determined whether the merchant needs to perform data analysis and processing using a preset time period, specifically including: Based on the historical transaction data volumes of the merchant on different dates, the average value of the historical transaction data volumes of the merchant on different dates is determined. When the average value of the historical transaction data volumes of the merchant on different dates is greater than the preset transaction data volume threshold, it is determined that the merchant needs to perform data analysis and processing using a preset time period; When the average value of the historical transaction data volumes of the merchant on different dates is not greater than the preset transaction data volume threshold: When the average value of the historical transaction data volumes of the merchant on different dates is less than the preset data volume threshold, it is determined that the merchant does not need to perform data analysis and processing using a preset time period; When the average value of the historical transaction data volumes of the merchant on different dates is not less than the preset data volume threshold: When it is determined from the historical transaction data volumes on different dates that there is no date with a historical transaction data volume greater than the preset transaction data volume, it is determined that the merchant does not need to perform data analysis and processing using a preset time period; When it is determined from the historical transaction data volumes on different dates that there is a date with a historical transaction data volume greater than the preset transaction data volume: Taking the date with a historical transaction data volume greater than the preset transaction data volume as the effective transaction date, when the number of effective transaction dates is greater than the preset number of effective dates, it is determined that the merchant needs to perform data analysis and processing using a preset time period; When the number of effective transaction dates is not greater than the preset number of effective dates: According to the proportion of the number of effective transaction dates in different divided time periods, the proportion of the number of effective dates in different divided time periods is determined. Through the proportion of the number of effective dates in different divided time periods, the effective divided time periods in the divided time periods are determined. When the number of effective divided time periods is greater than the number of effective divided time periods, it is determined that the merchant needs to perform data analysis and processing using a preset time period; When the number of the effective division time periods is not greater than the number of the effective division time periods: Determine the transaction data frequency coefficient of the merchant according to the number of the effective division time periods, the proportion of the number of effective dates in different effective division time periods, and the historical transaction data volume of different effective transaction dates, and determine whether the merchant needs to perform data analysis processing using a preset time period by using the transaction data frequency coefficient of the merchant.

[0054] It should be noted that when the transaction data frequency coefficient of the merchant is greater than the preset frequency coefficient threshold, it is determined that the merchant needs to perform data analysis processing using a preset time period.

[0055] Optionally, the method for determining the analysis processing model of the transaction data of the merchant on the current date is as follows: Determine the number of transaction users on the current date according to the transaction data volume of different types of user portraits on the current date, and combine the associated transaction data of different transaction users and different dimensions of user portraits to determine the data processing complexity coefficient on the current date. When the data processing complexity coefficient on the current date is less than the preset processing complexity coefficient threshold, use the second preset analysis model to perform data analysis processing on the transaction data of the merchant; When the data processing complexity coefficient on the current date is not less than the preset processing complexity coefficient threshold: Determine the number of different types of user portraits according to the transaction data volume of different types of user portraits on the current date, and use the number of different types of user portraits to determine the distribution proportion of different types of user portraits on the current date. Determine the distribution proportion of the merchant in different types of user portraits according to the distribution data of the reference user portrait; When the deviation situation between the distribution proportion of different types of user portraits on the current date and the distribution proportion of the merchant in different types of user portraits does not meet the requirements, use the preset analysis model to perform data analysis processing on the transaction data of the merchant; When the deviation situation between the distribution proportion of different types of user portraits on the current date and the distribution proportion of the merchant in different types of user portraits meets the requirements: Determine the type of user portrait with a deviation in the distribution proportion on the current date according to the deviation situation between the distribution proportion of different types of user portraits on the current date and the distribution proportion of the merchant in different types of user portraits. When the number of transaction users of the type of user portrait with a deviation in the distribution proportion on the current date does not meet the requirements, use the preset analysis model to perform data analysis processing on the transaction data of the merchant; When the number of transaction users of the type of user portrait with a deviation in the distribution proportion on the current date meets the requirements: Based on the deviation of the distribution proportions of different types of user portraits from those of the merchant among different types of user portraits, the number of trading users of different types of user portraits, and the associated transaction data of different trading users with user portraits of different dimensions, determine the analysis and processing requirement coefficient for the current date, and use the analysis and processing requirement coefficient to determine the analysis and processing model for the merchant's transaction data on the current date.

[0056] Further, using the analysis and processing requirement coefficient to determine the analysis and processing model for the merchant's transaction data on the current date specifically includes: When the analysis and processing requirement coefficient is greater than the preset requirement coefficient threshold, determine that the analysis and processing model for the merchant's transaction data on the current date is the preset analysis model; When the analysis and processing requirement coefficient is not greater than the preset requirement coefficient threshold, determine that the analysis and processing model for the merchant's transaction data on the current date is the second preset analysis model.

[0057] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus, device, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0058] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be executed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] The above is only one or more embodiments of this specification and is not used to limit this specification. For those skilled in the art, one or more embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A smart merchant data analysis method, characterized in that: Specifically include: S1 uses the merchant's historical transaction data on different dates to determine whether the merchant needs to use a preset time period for data analysis and processing. If so, proceed to step S4; if not, proceed to the next step; S2: based on the historical transaction data of the merchant, determine the user profiles of the merchant's transaction users on different dates, and determine the date of change of the transaction data on the date according to the amount of historical transaction data on different dates, the deviation of the user profiles of the transaction users and the benchmark user profiles of the merchant; S3 obtains the historical transaction data volume of different transaction data change dates, and combines the distribution data of the transaction data change date and the deviation of the user profile from the benchmark user profile, and when it is determined that the user profile change risk of the merchant does not meet the requirements, proceeds to the next step; S4 determines an analysis and processing model for the merchant's transaction data on the current date based on the transaction data volume of different types of user portraits on the current date and the distribution deviation from the benchmark user portrait.

2. The intelligent merchant data analysis method according to claim 1, characterized in that: The amount of historical transaction data includes the number of transaction users on different dates and the amount of associated transaction data of different transaction data.

3. The intelligent merchant data analysis method according to claim 1, characterized in that: Determining whether the merchant needs to use a preset time period for data analysis and processing specifically includes: Based on the historical transaction data volume of the merchant on different dates, determine the date when the historical transaction data volume is greater than the preset transaction data volume, and use it as the valid transaction date; According to the proportion of the number of valid trading dates in different divided time periods, the proportion of the number of valid dates in different divided time periods is determined; By using the average value of the proportion of the number of valid dates in different divided time periods, it is determined whether the merchant needs to use a preset time period for data analysis and processing.

4. The intelligent merchant data analysis method according to claim 3, characterized in that: When the average value of the percentage of the number of valid dates in different divided time periods is greater than a preset threshold value of the percentage of valid dates, it is determined that the merchant needs to use a preset time period for data analysis and processing.

5. The intelligent merchant data analysis method according to claim 1, characterized in that: The user profile of the transaction user includes churn risk, loyalty, shopping preferences and payment channels.

6. The intelligent merchant data analysis method according to claim 1, characterized in that: The benchmark user portrait is constructed based on the user portrait of the largest number of transaction users corresponding to the analysis results of the merchant's historical transaction data.

7. The intelligent merchant data analysis method according to claim 1, characterized in that: The method for determining the analysis and processing model of the merchant's transaction data on the current date is: Determine the number of different types of user portraits based on the transaction data volume of different types of user portraits on the current date, and determine the distribution ratio of different types of user portraits on the current date based on the number of different types of user portraits; Determine the distribution ratio of the merchant in different types of user portraits according to the distribution data of the benchmark user portrait; According to the deviation between the distribution ratios of different types of user portraits on the current date and the distribution ratios of different types of user portraits of the merchant, the type of user portrait with a deviation in the distribution ratio on the current date is determined, and the number of transaction users of the type of user portrait with a deviation in the distribution ratio on the current date is used to determine the analysis and processing model of the merchant's transaction data on the current date.

8. The intelligent merchant data analysis method according to claim 7, characterized in that: The analysis and processing model of the merchant's transaction data on the current date is determined by using the number of transaction users of the type of user portraits with deviations in distribution ratio on the current date, specifically including: When the number of transaction users of the type of user portrait with a deviation in the distribution ratio on the current date is greater than the preset deviation transaction user number, the preset analysis model is used to analyze and process the merchant's transaction data; When the number of transaction users of the type of user portrait with a deviation in the distribution ratio on the current date is not greater than the preset deviation transaction user number, the second preset analysis model is used to analyze and process the merchant's transaction data.

9. The intelligent merchant data analysis method according to claim 1, characterized in that: The preset analysis model takes all transaction data of the merchant as input, and uses the analysis model to analyze and process the transaction data of the merchant on the current date.

10. An intelligent merchant data analysis system, using an intelligent merchant data analysis method according to any one of claims 1 to 9, characterized in that: Specifically include: Data change date analysis module, change risk assessment module, analysis model determination module; The data change date analysis module is responsible for determining the transaction data change date in the date; The change risk assessment module is responsible for determining whether the merchant's user profile change risk meets the requirements; The analysis model determination module is responsible for determining the analysis and processing model of the merchant's transaction data on the current date.

Images