Service strategy generation method and device, equipment, medium and program product

By generating asset change trend information and associated user tags, the limitations of generating user tags in a single asset total dimension are solved, and more accurate service strategy matching and user needs satisfaction are achieved.

CN119128644APending Publication Date: 2024-12-13CHINA CONSTRUCTION BANK +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411246914.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-12-13

AI Technical Summary

Technical Problem

In the prior art, it is difficult to fully capture the dynamic characteristics of user asset changes based on the dimension of single asset total, resulting in the inaccurate push of service information and the inability to effectively meet the actual needs of users.

Method used

By obtaining the user's asset data within multiple time intervals, generating asset change trend information, and generating more refined and accurate user tags based on the association relationship between this information and user tags, a personalized service strategy is formulated.

Benefits of technology

It realizes a more accurate judgment of user asset status and potential needs, and the generated service strategies are more personalized and accurate, which can more effectively meet the actual needs of users.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119128644A_ABST
    Figure CN119128644A_ABST
Patent Text Reader

Abstract

The invention discloses a service strategy generation method and device, equipment, a medium and a program product, and is applied to the technical field of data processing, and the method comprises the steps: obtaining asset data of a service user in a time interval, the asset data comprising the resource quantity of user resources of the service user in each sub-interval in M sub-intervals; according to the resource quantity of the user resources of the service user in each of the M sub-intervals and a preset rule, asset change trend information of the service user is generated, and the asset change trend information is used for representing the change trend of the resource quantity of the user resources in a time interval under the preset rule; obtaining a user label of the service user corresponding to the asset change trend information of the service user based on a preset association relationship between the asset change trend information and the user label; and generating a service strategy of the service user according to the user tag of the service user. According to the method, the service strategy meeting user requirements can be generated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a service strategy generation method, device, equipment, medium and program product. Background Art

[0002] The service recommendation system of a financial institution can push relevant service information to users based on the service strategy corresponding to the user tag. For example, based on the key indicator of the total amount of assets of the user in the financial institution, a personalized service strategy is formulated to push relevant financial services to the user.

[0003] In the related art, user tags are usually generated based on the total amount of assets of users in financial institutions. However, using the total amount of assets of users in financial institutions as a single dimension to generate user tags makes it difficult to fully capture the dynamic characteristics of user asset changes, which can easily lead to misjudgment of user asset status and potential needs, and thus make the pushed service information inaccurate and difficult to effectively meet the actual needs of users. Summary of the invention

[0004] The embodiments of the present application provide a service strategy generation method, apparatus, device, medium and program product, which can more accurately judge the asset status and potential needs of the user, and effectively solve the limitation of using a single asset total amount dimension to generate user tags.

[0005] In a first aspect, an embodiment of the present application provides a service policy generation method, the method comprising:

[0006] Acquire asset data of the service user in a time interval, where the time interval includes M subintervals, and the asset data includes the resource amount of user resources of the service user in each of the M subintervals, where the user resources are resources in a financial account of the service user under a financial institution;

[0007] Generate asset change trend information of the service user according to the resource amount of the user resource in each subinterval of the M subintervals and the preset rules, where the asset change trend information is used to characterize the change trend of the resource amount of the user resource within the time interval under the preset rules;

[0008] Based on the association relationship between the preset asset change trend information and the user tag, obtaining the user tag of the service user corresponding to the asset change trend information of the service user;

[0009] Generate a service policy for the service user based on the user tag of the service user.

[0010] In a second aspect, an embodiment of the present application provides a service policy generating device, the device comprising:

[0011] A first acquisition module is used to acquire asset data of a service user in a time interval, where the time interval includes M sub-intervals, and the asset data includes the resource amount of user resources of the service user in each of the M sub-intervals, where the user resources are resources in a financial account of the service user at a financial institution;

[0012] A first generating module, configured to generate asset change trend information of a service user according to the resource amount of the user resources in each subinterval of the M subintervals and a preset rule, wherein the asset change trend information is used to characterize the change trend of the resource amount of the user resources within a time interval under the preset rule;

[0013] A second acquisition module is used to acquire a user tag of a service user corresponding to the asset change trend information of the service user based on the association relationship between the preset asset change trend information and the user tag;

[0014] The second generating module is used to generate a service policy for the service user according to the user tag of the service user.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:

[0016] A processor and a memory storing computer program instructions; when the processor executes the computer program instructions, any one of the above service policy generation methods is implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, any one of the above-mentioned service policy generation methods is implemented.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is able to execute any one of the above-mentioned service policy generation methods.

[0019] The service strategy generation method, device, equipment, medium and program product of the embodiment of the present application, through the asset change trend information generated based on the resource amount of the user resources of the service user in each sub-interval of M sub-intervals and preset rules, reveals the law and characteristics of the resource amount of the user resources of the service user changing over time. Based on this resource change trend analysis method that integrates the resource amount and time characteristics of the user resources, compared with the resource value of a single dimension, an in-depth analysis of the resource amount of the user resources of the service user is achieved. Then, the user tag generated based on the asset change trend information more comprehensively reflects the characteristics of the user resource change of the service user, making the user classification more refined and accurate. Then, the service policy of the service user is generated according to the user tag, and the accurate matching of the user tag and the service policy is achieved, so as to help the business end to more accurately judge the asset status and potential needs of the user according to the user tag, and effectively solve the limitation of generating user tags using a single asset total dimension. The service strategy generated based on this is more personalized and accurate, and can more effectively meet the actual needs of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 A schematic diagram showing a flow chart of a service strategy generation method provided by some embodiments of the present application;

[0022] Figure 2 A flowchart showing a specific implementation of step 120 provided in some embodiments of the present application is shown;

[0023] Figure 3 A flowchart showing a specific implementation of step 121 provided in some embodiments of the present application is shown;

[0024] Figure 4 A flowchart showing a specific implementation of step 122 provided in some embodiments of the present application is shown;

[0025] Figure 5 A flowchart showing a specific implementation of step 122 provided in other embodiments of the present application is shown;

[0026] Figure 6 A flowchart showing a specific implementation of step 122 provided in some other embodiments of the present application is shown;

[0027] Figure 7A flowchart showing a specific implementation of step 122 provided in some further embodiments of the present application is shown;

[0028] Figure 8 A flowchart showing a specific implementation of step 120 provided in other embodiments of the present application is shown;

[0029] Fig. 9 A flowchart showing a specific implementation of step 140 provided in some embodiments of the present application is shown;

[0030] Fig.10 A schematic diagram of the structure of a service strategy generating device provided in some embodiments of the present application is shown;

[0031] Fig.11 A schematic diagram of the structure of an electronic device provided in some embodiments of the present application is shown. DETAILED DESCRIPTION

[0032] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0033] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0034] It should be noted that the acquisition, storage, use and processing of data in the embodiments of the present application are in compliance with the relevant provisions of national laws and regulations.

[0035] 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.

[0036] In order to solve the problems in the related art, the embodiments of the present application provide a service strategy generation method, device, equipment, medium and program product. Figure 1 To Attachment Fig. 9 , the service strategy generation method provided by the embodiment of the present application is described in detail through specific embodiments and their application scenarios.

[0037] Figure 1 FIG. 1 is a flow chart showing a method for generating a service strategy according to some embodiments of the present invention. Figure 1 As shown, the service policy generating method may include steps 110 to 140.

[0038] Step 110, obtaining the asset data of the service user in a time interval, the time interval includes M sub-intervals, the asset data includes the resource amount of the user resources of the service user in each of the M sub-intervals, and the user resources are the resources in the financial account of the service user under the financial institution.

[0039] Step 120, based on the resource amount of user resources in each of the M subintervals and preset rules, generates asset change trend information for the service user, where the asset change trend information is used to characterize the change trend of the resource amount of user resources within a time interval under the preset rules.

[0040] Step 130: Based on the association relationship between the preset asset change trend information and the user tag, obtain the user tag of the service user corresponding to the asset change trend information of the service user.

[0041] Step 140: Generate a service policy for the service user according to the user tag of the service user.

[0042] Thus, by generating asset change trend information based on the resource amount of user resources in each of the M subintervals and preset rules, the law and characteristics of the resource amount of user resources of the service user over time are revealed. Based on this resource change trend analysis method that integrates the resource amount and time characteristics of user resources, an in-depth analysis of the resource amount of user resources of the service user is achieved compared to the resource value of a single dimension. Next, the user tags generated based on the asset change trend information more comprehensively reflect the characteristics of the user resource changes of the service user, making the user classification more refined and accurate. Then, the service policy for the service user is generated based on the user tag, which realizes the precise matching of the user tag and the service policy, thereby helping the business end to more accurately judge the user's asset status and potential needs based on the user tag, and effectively solving the limitation of using a single asset total dimension to generate user tags. The service strategy generated based on this is more personalized and accurate, and can more effectively meet the actual needs of users.

[0043] The above steps are described in detail below, as shown below.

[0044] First, the meanings of the service users, time intervals, user resources and asset data involved in step 110 of the embodiment of the present application are specifically explained.

[0045] Service users refer to individuals or enterprises that use the services of financial institutions, and service users have financial accounts opened at financial institutions.

[0046] A time interval refers to a specific time period used to analyze asset changes of service users. This time period is further subdivided into M subintervals to observe the details of asset changes in more detail. A subinterval refers to a smaller time period within a time interval. For example, if the time interval is the past year, each month is a subinterval, and the time interval can be divided into 12 subintervals. The business end collects the account balance of the service user at the end of each month in these 12 months as the resource amount of the user resource.

[0047] User resources refer to the sum of various financial assets and liabilities held by service users in financial institutions, including but not limited to deposits in their financial accounts, the holding value of various investment products and loan balances.

[0048] Asset data is the specific quantitative information about the amount of user resources in each sub-interval, including but not limited to the specific amount of user deposits, the market value of investment products and detailed data on loan balances.

[0049] In some embodiments of the present application, service users refer to user groups with a specific asset size under a financial institution, so as to more effectively analyze their asset change trends and generate personalized service strategies. Based on this, before the above step 110, a step of screening service users from multiple users of the financial institution may also be included, that is, before the above step 110, the service strategy generation method may also include:

[0050] Obtain asset data of each user among multiple users in each of the M subintervals;

[0051] A service user who meets a preset condition is screened from multiple users, and a resource amount of user resources of the service user in each sub-interval of the M sub-intervals is greater than a preset threshold.

[0052] Exemplarily, the preset condition can filter service users according to the monthly average daily asset management scale (Asset Under Management, AUM) of the user in the time interval. Specifically, taking one sub-interval as one month, the service user can be a user whose user AUM in each of the 6 sub-intervals is greater than 2,000 yuan. User AUM is an indicator for a user to measure the scale of user assets currently managed by a financial institution, reflecting the user's financial status and the value of the investment portfolio. Specifically, AUM refers to the total market value of user assets currently managed by a financial institution, including but not limited to cash, deposits, bonds, stocks, funds and real estate.

[0053] Secondly, the meaning of the preset rules and asset change trend information involved in step 120 of the embodiment of the present application is specifically explained.

[0054] Preset rules refer to the rules set by the business end based on the business needs of financial institutions, which are used to analyze changes in the asset data of service users, such as growth rate, volatility, etc.

[0055] Asset change trend information refers to information calculated based on the asset data of service users in each sub-interval within a time interval and combined with preset rules, which is used to describe the direction and speed of user asset changes.

[0056] In some embodiments of the present application, the preset rules include I preset rules, each of the I preset rules includes an indicator statistical algorithm and a judgment condition, and the asset change trend information of the service user includes the change trend of the resource amount of the user resource within the time interval under each preset rule in the I preset rules. The preset rules are a predefined series of conditions for analyzing and evaluating specific aspects of user resource changes. Exemplarily, the I preset rules are for different dimensions or characteristics of user resource changes. Each preset rule contains one or more indicator statistical algorithms for calculating the specific values ​​of user resources in a time interval, such as average value, growth rate, volatility, etc. The judgment condition corresponds to the indicator statistical algorithm, and the judgment condition is used to evaluate whether the indicator value calculated according to the corresponding indicator statistical algorithm meets a specific standard or threshold, thereby generating corresponding asset change trend information. Based on this, if Figure 2 As shown, step 120 may specifically include steps 121 to 122.

[0057] Step 121, calculate the i-th indicator value of the service user under the i-th preset rule according to the resource amount of the user resources of each sub-interval in the M sub-intervals and the indicator statistical algorithm of the i-th preset rule in the I preset rules, i∈[1,2,…,I].

[0058] Exemplarily, for each service user, M subintervals are traversed. In each subinterval, the indicator value corresponding to the resource amount of the user resource is calculated according to the indicator statistical algorithm of the i-th preset rule. If the i-th preset rule focuses on the growth rate of the resource amount of the user resource, the indicator statistical algorithm calculates the percentage growth of the resource amount of the service user in the adjacent subinterval. For service user A, if the resource amount of service user A in the first subinterval is 100 and the resource amount in the second subinterval is 110, then the growth rate of the resource amount of service user A is (110-100) / 100=10%.

[0059] Step 122, based on the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value, generate the asset change trend information of the service user under the i-th preset rule, and the asset change trend information under the i-th preset rule is used to characterize the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule.

[0060] Exemplarily, the asset change trend information may include trend type and trend strength. Specifically, the trend type may include rising, falling, stable, etc., and the trend strength may be divided into different levels or types, such as linear change, continuous change, sharp change, slight change, drastic change, etc. The index value calculated according to step 121 is compared with the judgment condition for the index value in the i-th preset rule. If the index value meets the judgment condition, such as the growth rate exceeds a certain threshold, the corresponding asset change trend information is generated. If the i-th preset rule focuses on the growth rate of resource volume, the index statistical algorithm is an algorithm for calculating the percentage growth of resource volume in adjacent sub-intervals.

[0061] In the embodiment of the present application, by setting 1 preset rule, multiple aspects of user resource changes can be covered, thereby realizing a refined analysis of the user resource change trend. At the same time, by subdividing the time interval into multiple subintervals, and combining the indicator statistical algorithm and judgment conditions, it is possible to capture the subtle differences and trend changes in user resource changes. This refined analysis method helps the business end to understand user needs more accurately, provide more personalized services, and thus enhance user satisfaction.

[0062] Next, the specific implementation methods of the above steps 121 to 122 of the present application will be further explained in combination with multiple embodiments.

[0063] In some embodiments of the present application, the ith indicator value under the ith preset rule in the above step 121 includes M-1 first resource change amounts and M-1 first resource change rates. Correspondingly, the indicator statistical algorithm under the ith preset rule includes an algorithm for quantifying and analyzing the changes in resource amounts in a time series. Based on this, Figure 3 As shown, step 121 may specifically include steps 1211a to 1213a.

[0064] Step 1211a: Based on the resource amount of user resources in each sub-interval and the indicator statistical algorithm of the i-th preset rule among I preset rules, calculate the first resource change amount of the user resources of the service user in the m-th sub-interval relative to the user resources in the m-1-th sub-interval, and obtain M-1 first resource change amounts, m∈[1,2,…,M].

[0065] Exemplarily, the first resource change refers to the difference in the resource amount of the user resources in two adjacent subintervals. M-1 first resource change amounts correspond to the resource amount changes between M-1 adjacent subintervals. Correspondingly, the indicator statistical algorithm includes using the following formula (1) to calculate the first resource change amount ΔR of the resource amount of the user resources in the mth subinterval relative to the resource amount of the user resources in the m-1th subinterval: m .

[0066] ΔR m =R m -R m-1 (1)

[0067] Among them, R m represents the amount of user resources in the mth subinterval, R m-1 Indicates the resource amount of user resources in the m-1th sub-interval.

[0068] Step 1212a: Calculate the first resource change rate of the amount of user resources of the service user in the mth subinterval relative to the amount of user resources in the m-1th subinterval based on the amount of user resources in each subinterval, the indicator statistical algorithm of the i-th preset rule among I preset rules, and the first resource change of the amount of user resources of the service user in the m-th subinterval relative to the amount of user resources in the m-1th subinterval.

[0069] Exemplarily, the first resource change rate refers to the relative change degree of the user resource amount in two adjacent sub-intervals, which can be expressed in percentage. Correspondingly, the indicator statistical algorithm includes using the following formula (2) to calculate the first resource change rate CR of the user resource amount in the mth sub-interval relative to the user resource amount in the m-1th sub-interval: m .

[0070]

[0071] In the formula, R m represents the amount of user resources in the mth subinterval, R m-1 Indicates the resource amount of user resources in the m-1th sub-interval.

[0072] Step 1213a: Generate M-1 first resource change rates based on the first resource change rate of the resource amount of the user resource of the service user in the mth sub-interval relative to the resource amount of the user resource in the m-1th sub-interval.

[0073] Exemplarily, the M-1 first resource change rates correspond to the relative change degrees of the resource quantities between the M-1 adjacent sub-intervals.

[0074] In the embodiment of the present application, the first resource change amount and the first resource change rate provide a direct and relative measure of the change in the resource amount of the user resources of the service user in different time periods, which helps to deeply understand the dynamic change characteristics of the user resources. Specifically, the first resource change amount directly reflects the increase or decrease in the user resource amount in two adjacent sub-intervals, and the first resource change rate shows the relative degree of resource amount change in percentage form, so that the changes of the same user in different adjacent sub-intervals can be compared, so as to determine the asset change trend information of the service user based on the first resource change amount and the first resource change rate.

[0075] In some embodiments of the present application, in order to generate asset change trend information of the service user under the i-th preset rule based on the above M-1 first resource change rates and M-1 first resource change amounts. The judgment condition in the above step 122 may include a first judgment condition and a second judgment condition. The second judgment condition may include a first sub-judgment condition and a second sub-judgment condition, and the asset change trend information includes first change trend information and second change trend information. Based on this, Figure 4 As shown, the above step 122 may specifically include steps 1221a to 1223a.

[0076] Step 1221a: When M-1 first resource changes satisfy the first judgment condition, the asset change trend information of the service user under the i-th preset rule is judged through the second judgment condition.

[0077] Exemplarily, the first judgment condition is to judge whether the resource amount of the user resource reflected by the analysis result corresponding to the M-1 first resource change amounts has a condition of continuous change. Meeting the first judgment condition means that the resource amount of the user resource serving the user has changed significantly in multiple consecutive time subintervals. For example, whether the first judgment condition is met is calculated or analyzed based on the M-1 first resource change amounts, such as the first resource change amounts of multiple consecutive subintervals all exceed a certain threshold. If met, the judgment process of the second judgment condition is entered.

[0078] Step 1222a, when M-1 first resource change rates meet the first sub-judgment condition, the first change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the first change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a continuous upward state.

[0079] Exemplarily, the first sub-judgment condition is a condition for judging whether each of the M-1 first resource change rates is greater than or equal to the first preset change rate; the first sub-judgment condition is used to identify whether the resource amount of the user resource serving the user is in a continuous increase. As an example, if the resource change rate of each sub-interval is greater than 5%, it is judged that the resource amount is in a continuous increase state in the entire time interval, and the corresponding first change trend information is generated.

[0080] Step 1223a, when M-1 first resource change rates meet the second sub-judgment condition, the second change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the second change trend is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a continuous downward state.

[0081] Exemplarily, the second sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is less than or equal to the second preset change rate, and the second sub-judgment condition is used to identify whether the resource amount of the user resource serving the user is in a continuous decline. As an example, if the resource change rate of each sub-interval is less than -5%, it is judged that the resource amount is in a continuous decline in the entire time interval, and the corresponding second change trend information is generated.

[0082] In an embodiment of the present application, by combining the dual judgments of the first resource change amount and the first resource change rate, the continuous increase or decrease trend of the resource amount of user resources can be more accurately identified, which helps to generate user tags that match the service users and formulate service strategies that meet the user needs of the service users.

[0083] In some other embodiments of the present application, in order to generate asset change trend information of the service user under the i-th preset rule based on the above M-1 first resource change rates and M-1 first resource change amounts, the judgment condition in the above step 122 may include a third judgment condition and a fourth judgment condition. The fourth judgment condition includes a third sub-judgment condition and a fourth sub-judgment condition, and the asset change trend information includes the third change trend information and the fourth change trend information. Based on this, Figure 5 As shown, the above step 122 may specifically include steps 1221b to 1223b.

[0084] Step 1221b: When the M-1 first resource changes satisfy the third judgment condition, the asset change trend information of the service user under the i-th preset rule is judged through the fourth judgment condition.

[0085] Exemplarily, the third judgment condition is a condition for judging whether there is a linear relationship between the resource amount of the user resources of the service user reflected by the analysis results corresponding to the M-1 first resource changes and the time change. Satisfying the third judgment condition means that the change in the resource amount of the user resources of the service user shows a stable increase or decrease trend over time, and this trend can be approximated by a straight line. As an example, if the time interval is 6 months, the M subintervals are 6 subintervals, and the resource amount of the user resources is the monthly average daily AUM, the third judgment condition can be judged by the following steps 1 to 5.

[0086] Step 1: Standardization. The average AUM_AVG of the six-month daily AUM is calculated using the following formula (3), and the monthly AUM value is standardized using the following formula (4) to obtain A m , to eliminate the impact of different cardinalities.

[0087]

[0088] Among them, y m Represents the monthly average daily AUM of the mth subinterval.

[0089]

[0090] Among them, y m represents the monthly average daily AUM of the mth subinterval, m∈[1,2,…,6].

[0091] Step 2: Difference calculation. Use the following formula (5) to perform difference calculation on the standardized AUM values ​​of two consecutive months to obtain the difference sequence DLT m , and calculate the differential sequence DLT by the following formula (6): m The mean DLT_AVG.

[0092] DLT m =A m -A m-1 (5)

[0093] Among them, A m represents the monthly average AUM after standardization in the mth sub-interval, A m-1 Represents the normalized monthly average daily AUM for the m-1th sub-interval.

[0094]

[0095] Among them, A m represents the monthly average AUM after standardization in the mth sub-interval, A m-1 Represents the normalized monthly average daily AUM for the m-1th sub-interval.

[0096] Step 3: Preliminary iteration: Based on the difference mean, perform preliminary iterations using the following formulas (7) and (8) to calculate (DLT_ITER1) to estimate the slope of the linear trend.

[0097]

[0098] DLT_ITER1=DLT_AVG+DLT_RERR1 (8)

[0099] Step 4: Error adjustment: Calculate the residual DLT_RERR1 using the above formula (7) and the residual DLT_RERR2 using the following formula (9), and adjust the iteration value DLT_ITER2 using the following formula (10) to further optimize the linear trend fitting.

[0100]

[0101] DLT_ITER2=DLT_RERR1+DLT_RERR2 (10)

[0102] Step 5: Final residual evaluation: The total residual RERR_LNR of all points relative to the fitted line is calculated using the following formula (11) to evaluate the goodness of fit of the linear trend.

[0103]

[0104] This is verified by calculating the mean DLT_AVG of the difference sequence and performing linear regression analysis. As an example, when RERR_LNR<=0.01 and DLT_RERR2>=0.05, it means that under the condition of strict linear fitting, AUM grows by more than 5% per month on average, satisfying the third judgment condition.

[0105] After the third judgment condition is satisfied, the fourth judgment condition is further used to specifically judge whether the change trend of the resource amount of the user resource is a linear increase or a linear decrease.

[0106] Step 1222b, when the M-1 first resource change rates meet the third sub-judgment condition, the third change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the third change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a linear upward state.

[0107] Exemplarily, the third sub-judgment condition is to judge that each of the M-1 first resource change rates is greater than or equal to the third preset change rate, which is used to identify the condition that the resource amount is in a linearly increasing state. After confirming that there is a linear relationship between the change in the resource amount of the user resource and time, it is further checked whether the M-1 first resource change rates are all greater than or equal to the third preset change rate. If this condition, that is, the third sub-judgment condition, is met, it is determined that the resource amount of the user resource is in a linearly increasing state, and the corresponding third change trend information is generated. Further, in order to improve the stability and reliability of the data, the upper limit of the third sub-judgment condition can be set to effectively avoid overestimation due to data anomalies such as noise, erroneous records, etc. As an example, if the resource change rate of each sub-interval satisfies ≥0.8 and ≤1.2, it is judged that the resource amount of the user resource is in a linearly increasing state throughout the time interval.

[0108] Step 1223b, when the M-1 first resource change rates meet the fourth sub-judgment condition, the fourth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the fourth change trend is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a linear downward state.

[0109] Exemplarily, the fourth sub-judgment condition is to judge that each of the M-1 first resource change rates is less than or equal to the fourth preset change rate, which is used to identify the condition that the resource amount is in a linear decline state. Similarly, after confirming that there is a linear relationship between the change in the resource amount of the user resource and time, check whether the M-1 first resource change rates are all less than or equal to the fourth preset change rate. If this condition, that is, the fourth sub-judgment condition, is met, it is determined that the resource amount of the user resource is in a linear decline state, and the corresponding fourth change trend information is generated. Further, in order to improve the stability and reliability of the data, the upper limit of the fourth sub-judgment condition can be set to effectively eliminate overestimation caused by data anomalies such as noise, erroneous records, etc. As an example, if the resource change rate of each sub-interval satisfies ≤0.8 and ≥1.2, it is judged that the resource amount of the user resource is in a linear decline state throughout the time interval.

[0110] In the embodiment of the present application, by introducing the judgment of linear relationships, it is possible to more accurately identify the trend pattern of user resource changes over time, reduce misjudgments caused by data fluctuations or outliers, and enhance the accuracy of the asset change trend information generated for service users under the i-th preset rules, thereby improving the pertinence of the service strategy generated based on the asset change trend information.

[0111] In some embodiments of the present application, the M sub-intervals include P first sub-intervals, where P is an integer greater than 1 and less than M, and the i-th indicator value under the i-th preset rule in the above step 121 includes the average resource amount amplitude value of each first sub-interval in the P first sub-intervals. Correspondingly, the indicator statistical algorithm under the i-th preset rule includes an algorithm for calculating the average resource amount amplitude value of each first sub-interval in the P first sub-intervals. Based on this, the step 121 may specifically include calculating the average resource amount amplitude value of the resource amount of the user resource in each first sub-interval in the P first sub-intervals according to the resource amount of the user resource in each first sub-interval in the P first sub-intervals, the P-1 target resource change amount, and the indicator statistical algorithm of the i-th preset rule in the I preset rules, and the P-1 target resource change amount is a first resource change amount selected from the M-1 first resource change amounts and corresponding to the P first sub-intervals.

[0112] Exemplarily, the average resource amount fluctuation value of each first sub-interval in the P first sub-intervals is used to measure the average fluctuation degree of the resource amount of the user resources in the P first sub-intervals. The target resource change amount is a change amount selected from the resource change amounts between the M-1 adjacent sub-intervals and corresponding to the P first sub-intervals, so as to analyze the change of the resource amount of the user resources of the service user between the P first sub-intervals.

[0113] Referring to the above example, if the resource volume of user resources is the monthly average daily AUM, the time interval is 6 months, each subinterval is 1 month, and the P first subintervals represent the first 3 months of the 6 months, the average resource volume volatility value, that is, the monthly average volatility MAV, can be calculated by the following formula (12).

[0114]

[0115] Where AUM max represents the maximum value of the monthly average AUM in the first P sub-intervals, AUM min represents the minimum value of the monthly average AUM in the first P sub-intervals, AUM b Indicates the benchmark resource volume, used to standardize the amplitude value.

[0116] In the embodiment of the present application, by selecting specific P first sub-intervals for analysis, it is possible to pay more attention to the changes in the user resource quantity in a specific time period, thereby discovering potential patterns or problems. Specifically, by calculating the average resource quantity fluctuation value of each first sub-interval in the P first sub-intervals, it is possible to more accurately reflect the fluctuation of the user resource quantity in the P first sub-intervals, effectively avoiding the deviation that may be caused by the data at a single time point.

[0117] In some other embodiments of the present application, in order to generate asset change trend information for the service user under the i-th preset rule based on the above-mentioned M-1 first resource change rates and M-1 first resource change amounts. The M sub-intervals also include Q second sub-intervals, P first sub-intervals occur earlier than the second sub-intervals, Q is an integer greater than 1 and less than M, and the i-th indicator value also includes Q-1 target resource change rates, and the Q-1 target resource change rates are the first resource change rates corresponding to the Q second sub-intervals selected from the M-1 first resource change rates. The judgment condition in the above-mentioned step 122 can be the fifth judgment condition and the sixth judgment condition, and the sixth judgment condition includes the fifth sub-judgment condition and the sixth sub-judgment condition. The asset change trend information includes the fifth change trend information and the sixth change trend information. Based on this, if Figure 6 As shown, the above step 122 may specifically include steps 1221c to 1223c.

[0118] Step 1221c: When the average resource amplitude values ​​of the P first sub-intervals meet the fifth judgment condition, the asset change trend information of the service user under the i-th preset rule is judged through the sixth judgment condition.

[0119] For example, the fifth judgment condition is a condition for judging whether the average resource volume fluctuation value is within a preset fluctuation range. The fifth judgment condition is used to screen out sub-intervals whose fluctuation range is within the preset range, which helps to exclude data with excessively stable or abnormally drastic fluctuations, thereby focusing on meaningful fluctuation intervals. Then, the sixth judgment condition is used to further refine the analysis to determine the specific asset change trend.

[0120] Step 1222c, when the change rates of Q-1 target resources meet the fifth sub-judgment condition, the fifth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the fifth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a sharply rising state.

[0121] Exemplarily, the fifth sub-judgment condition is a condition for judging that each target resource change rate among Q-1 target resource change rates is greater than or equal to the fifth preset change rate. The fifth sub-judgment condition is used to quantify the standard of "sharp rise", ensuring that only when the target resource change rate is continuously and significantly higher than a certain threshold value, it is judged as a sharp rise. As an example, if the preset amplitude value range is -4% to 4%, it means that only when the average resource amount amplitude value of each first sub-interval in P first sub-intervals falls within this range, the asset change trend of the service user is analyzed through the fifth sub-judgment condition or the sixth sub-judgment condition. Specifically, when the target resource change rate is continuously and significantly higher than a certain 8%, the asset change trend information of the service user under the i-th preset rule is judged as a sharp rise.

[0122] Step 1223c, when the Q-1 target resource change rates meet the sixth sub-judgment condition, the sixth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the sixth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a sharply declining state.

[0123] Exemplarily, the sixth sub-judgment condition is a condition for judging that each of the Q-1 target resource change rates is less than or equal to the sixth preset change rate. The sixth sub-judgment condition is used to quantify the standard of "sharp decline", ensuring that only when the resource change rate is continuously and significantly lower than a certain threshold value, it is judged as a sharp decline. Specifically, when the target resource change rate is continuously and significantly lower than -8%, the asset change trend information of the service user under the i-th preset rule is judged as a sharp decline.

[0124] In the embodiment of the present application, through double screening, namely the amplitude value range and the possible further sixth judgment condition, irrelevant data interference is eliminated, and focus is placed on data that can truly reflect the asset change trend of the user resource volume of the service user, thereby effectively ensuring the accuracy and effectiveness of the data analysis, thereby improving the accuracy of the asset change trend information generated by the service user under the i-th preset rule.

[0125] In some other embodiments of the present application, the i-th indicator value includes a fluctuation variance. Correspondingly, the indicator statistical algorithm is an algorithm for calculating the fluctuation variance of the resource amount of the user resources in the M subintervals. Based on this, step 121 may specifically include calculating the fluctuation variance of the resource amount of the user resources of the service user in the M subintervals according to the resource amount of the user resources of each subinterval in the M subintervals and the indicator statistical algorithm of the i-th preset rule in the I preset rules.

[0126] For example, the following formula (13) can be used to calculate the fluctuation variance, which is used to quantify the fluctuation of user resources in different time periods. The larger the value of the fluctuation variance, the more drastic the change in the amount of user resources in the time interval; otherwise, it means that the change is relatively stable.

[0127]

[0128] Among them, A m Indicates the amount of normalized user resources in the mth subinterval.

[0129] In the embodiment of the present application, the fluctuation variance is an important statistic to measure the degree of data dispersion, which can reflect the stability and volatility of the changes of user resources in different time periods. By calculating the fluctuation variance, the changes in the amount of user resources in the time interval can be more accurately understood.

[0130] In some other embodiments of the present application, in order to generate asset change trend information for the service user under the i-th preset rule based on the above-mentioned M-1 first resource change rates and M-1 first resource change amounts. The judgment condition includes the seventh judgment condition and the eighth judgment condition. The seventh judgment condition is the condition for judging that the volatility variance is a positive number, and the eighth judgment condition is the condition for judging that the volatility variance is greater than or equal to the preset volatility threshold; the asset change trend information includes the seventh change trend information and the eighth change trend information. Based on this, if Figure 7 As shown, the above step 122 may specifically include steps 1221d to 1223d.

[0131] 1221d, when the volatility variance satisfies the seventh judgment condition, the asset change trend information of the service user under the i-th preset rule is judged through the eighth judgment condition.

[0132] 1222d. When the volatility variance satisfies the eighth judgment condition, the seventh change trend information is determined as the asset change trend information of the service user under the i-th preset rule. The seventh change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a state of violent fluctuation.

[0133] 1223d. When the fluctuation variance does not meet the eighth judgment condition, the eighth change trend information is determined as the asset change trend information of the service user under the i-th preset rule. The eighth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is slightly fluctuating.

[0134] In an embodiment of the present application, through the seventh judgment condition and the eighth judgment condition, the business end can accurately identify the asset change trend of the service user under specific preset rules, which can specifically include identifying the violent fluctuation state and slight fluctuation state of the asset change, and based on the association between the identified asset change trend information and the user tag, obtain the user tag that matches the current asset change trend of the service user, thereby helping to generate a service strategy that meets the individual needs of the service user.

[0135] In some embodiments of the present application, the preset rules include I preset rules, each of which includes an indicator statistical algorithm, a first target judgment condition and a second target judgment condition; Figure 8 As shown, the above step 120 may also include steps 801 to 805.

[0136] Step 801, taking the i-th preset rule as the current rule, executing the indicator statistical algorithm based on the resource amount of the user resources of the service user in each sub-interval of the M sub-intervals and the indicator of the current rule, and calculating the indicator value of the service user under the current rule, i∈[1,2,…,I].

[0137] Step 802, determine whether the indicator value under the current rule meets the first target determination condition under the current rule. If the determination result is no, proceed to step 803 for execution, and if the determination result is yes, proceed to step 804 for execution.

[0138] Step 803, update i=i+1, and return to execute step 801.

[0139] Step 804: determine the current rule as the target rule and determine the indicator value of the target user under the current rule as the target indicator value.

[0140] Step 805, generates asset change trend information of the service user under the target rule based on the target indicator value and the second target judgment condition for the target indicator value. The asset change trend information under the target rule is used to characterize the change trend of the resource amount of the user's resources within the time interval under the target rule.

[0141] In an embodiment of the present application, by defining I preset rules, the business end can flexibly adapt to different analysis needs. Each rule contains a specific indicator statistical algorithm, a first target judgment condition and a second target judgment condition, so that the system can perform customized analysis for different types of user resources or different analysis targets. By looping through steps A1 to A2, the business end can automatically traverse all preset rules until a rule that satisfies the first target judgment condition is found. After finding the rule that satisfies the first target judgment condition, i.e., the target rule, asset change trend information is generated based on the target indicator value and the corresponding second target judgment condition. This generation method based on clear judgment conditions ensures the accuracy of the analysis results and helps to more accurately determine the change trend of the resource volume of user resources.

[0142] As an example, the indicator statistical algorithm under the i-th preset rule is an algorithm for calculating M-1 first resource change amounts and M-1 first resource change rates. The first target judgment condition is a condition for judging whether there is a continuous change in the resource amount of user resources reflected by the analysis results corresponding to the M-1 first resource change amounts. The second target judgment condition is a condition for judging the relationship between each of the M-1 first resource change rates and the preset change rate. At this time, the indicator statistical algorithm under the i+1th preset rule is an algorithm for calculating the average resource amplitude value of each first sub-interval in P first sub-intervals and Q-1 target resource change rates, the M sub-intervals include P first sub-intervals and Q second sub-intervals, the P first sub-intervals are earlier in time than the Q second sub-intervals, P and Q are integers greater than 1, the first target judgment condition under the i+1th preset rule is the condition for judging that the average resource amplitude value is within the preset amplitude value range, and the second target judgment condition under the i+1th preset rule is the condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate condition.

[0143] As another example, the indicator statistical algorithm under the i-th preset rule is an algorithm for calculating M-1 first resource change amounts and M-1 first resource change rates. The first target judgment condition is a condition for judging that there is a linear relationship between the resource amount of user resources reflected by the analysis results corresponding to the M-1 first resource change amounts, and the second target judgment condition is a condition for judging the relationship between each of the M-1 first resource change rates and the preset change rate. At this time, the indicator statistical algorithm under the i+1th preset rule is an algorithm for calculating the average resource amplitude value of each first sub-interval in P first sub-intervals and Q-1 target resource change rates, the M sub-intervals include P first sub-intervals and Q second sub-intervals, the P first sub-intervals are earlier in time than the Q second sub-intervals, P and Q are integers greater than 1, the first target judgment condition under the i+1th preset rule is the condition for judging that the average resource amplitude value is within the preset amplitude value range, and the second target judgment condition under the i+1th preset rule is the condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate condition.

[0144] As another example, the M subintervals include P first subintervals and Q second subintervals, the P first subintervals are earlier in time than the Q second subintervals, and P and Q are integers greater than 1. The indicator statistical algorithm under the i-th preset rule is an algorithm for calculating the average resource amount amplitude value and Q-1 target resource change rates of each first subinterval in the P first subintervals, the first target judgment condition under the i-th preset rule is a condition for judging that the average resource amount amplitude value is within the preset amplitude value range, and the second target judgment condition under the i-th preset rule is a condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate. At this time, the indicator statistical algorithm under the i+1th preset rule is an algorithm for calculating the fluctuation variance of the resource amount of the user resources of the service user in the M subintervals, the first target judgment condition under the i+1th preset rule is a condition for judging that the fluctuation variance is a positive number, and the second target judgment condition under the i+1th preset rule is a condition for judging the relationship between the fluctuation variance and the preset fluctuation threshold.

[0145] It is often difficult for a single rule to comprehensively cover all situations. In the above three examples of this application, through the sequential judgment of multiple preset rules, the scope of analysis can be gradually narrowed and the accuracy of the final judgment result can be improved. Each preset rule targets specific data features, so as to more accurately locate the core of the problem. In the case of limited data resources, sequential judgment can optimize the use of resources. Through sequential judgment, multiple rules can be combined to deal with complex data features and analysis goals. Each rule can be optimized and adjusted for specific data features or analysis goals, so as to achieve effective analysis of complex scenarios.

[0146] Furthermore, in step 130, the user tag is a short identifier for describing the user's characteristics or attributes, which may include, but are not limited to, linear increase, continuous increase, sharp increase, sharp fluctuation, sharp decrease, linear decrease, continuous decrease, and slight fluctuation.

[0147] Then, step 140 is involved. A service strategy refers to a service plan or action plan developed for a specific user or user group, which is intended to meet the specific needs of the user or achieve a specific goal. Specifically, it may include investment advice, risk management measures, product recommendations, user service plans, and other forms. After identifying the user characteristics or attributes represented by the user tag, the corresponding service strategy is selected or customized in the preset service strategy library according to these characteristics or attributes. This selection or customization process may involve the evaluation, adjustment, and optimization of the service strategy to ensure that it meets the actual needs and preferences of the user.

[0148] As an example, for users with the user label "sharply rising", a service strategy for asset conversion should be formulated for this type of users. Specifically, it may include improving the user level of this type of users in financial institutions and assigning business liaison personnel to users if no business liaison personnel have been assigned yet, so as to establish and deepen the relationship with the users, fully understand the users' needs, and then make accurate asset allocation recommendations.

[0149] As another example, for users with the user label of "sharp decline", a service strategy for asset retention should be formulated for this type of users. Specifically, it can be divided into two directions. The first is to issue business opportunities to encourage business liaison personnel to respond quickly, deeply understand the specific reasons for the loss of users' funds, and formulate personalized fund retention strategies accordingly; the second is to design and launch marketing activities to improve the lost funds and meet the standards, using preferential treatment, rewards and other means to attract users to reinvest the lost funds into financial institutions.

[0150] As another example, for users with user labels of "violent fluctuations", asset allocation strategies should be formulated for such users, which can include customer asset allocation optimization strategies. This service strategy should focus on data analysis based on information such as user work attributes and fund flow characteristics. For users with periodic fund changes, the business end provides customized asset allocation suggestions, guiding users to maintain and increase the value of assets and improve the overall asset yield through reasonable allocation of short-term financial management, cash management and other products.

[0151] In some embodiments of the present application, the user tag of the service user includes multiple user tags. Fig. 9 As shown, the above step 140 may specifically include steps 141 to 142.

[0152] Step 141 : based on the preset association relationship between the user tag and the priority, a target user tag associated with the target priority is filtered from multiple user tags.

[0153] As an example, user tags may include linear increase, continuous increase, sharp increase, violent fluctuation, sharp decrease, linear decrease, continuous decrease, and slight fluctuation. The priorities of these user tags are arranged from high to low as follows: linear increase, continuous increase, sharp increase, violent fluctuation, sharp decrease, linear decrease, continuous decrease, and slight fluctuation.

[0154] Step 142: Generate a service policy for the service user according to the target user tag.

[0155] In an embodiment of the present application, by giving priority to user tags associated with target priorities, the business end can more accurately grasp the core characteristics and needs of users, thereby generating more targeted service strategies.

[0156] The service policy generation method provided in the embodiment of the present application can be executed by a service policy generation device. In the embodiment of the present application, the service policy generation device executing service policy generation is taken as an example to illustrate the device of the service policy generation method provided in the embodiment of the present application.

[0157] Based on the same inventive concept, the present application also provides a service strategy generation device. Fig.10 Provide detailed explanation.

[0158] Fig.10 A schematic diagram of the structure of a service strategy generating device provided in some embodiments of the present application is shown.

[0159] like Fig.10 As shown, the service policy generating device can be applied to an electronic device, and the service policy generating device can specifically include:

[0160] The first acquisition module 1010 is used to acquire asset data of the service user in a time interval, where the time interval includes M sub-intervals, and the asset data includes the resource amount of user resources of the service user in each of the M sub-intervals, where the user resources are resources in the financial account of the service user under the financial institution;

[0161] The first generating module 1020 is used to generate asset change trend information of the service user according to the resource amount of the user resource in each sub-interval of the M sub-intervals and the preset rule, where the asset change trend information is used to characterize the change trend of the resource amount of the user resource within the time interval under the preset rule;

[0162] The second acquisition module 1030 is used to acquire the user tag of the service user corresponding to the asset change trend information of the service user based on the association relationship between the preset asset change trend information and the user tag;

[0163] The second generating module 1040 is used to generate a service policy for the service user according to the user tag of the service user.

[0164] Thus, the resource amount of the user resources of the service user in each of the M subintervals is obtained by the first acquisition module 1010, and then, the asset change trend information is generated by the first generation module 1020 based on the resource amount of the user resources of the service user in each of the M subintervals and the preset rules, revealing the law and characteristics of the resource amount of the user resources of the service user changing over time. Based on this resource change trend analysis method that integrates the resource amount and time characteristics of the user resources, compared with the resource value of a single dimension, an in-depth analysis of the resource amount of the user resources of the service user is achieved. Then, the user tag of the service user corresponding to the asset change trend information obtained by the second acquisition module 1030 more comprehensively reflects the characteristics of the user resource change of the service user, making the user classification more refined and accurate. Then, the service policy of the service user is generated according to the user tag by the second generation module 1040, realizing the accurate matching of the user tag and the service policy, so as to help the business end to more accurately judge the asset status and potential needs of the user according to the user tag, and effectively solve the limitation of generating user tags using a single asset total dimension. The service policy generated based on this is more personalized and accurate, and can more effectively meet the actual needs of the user.

[0165] The service policy generating device in the embodiment of the present application is described in detail below, as shown below.

[0166] In some embodiments of the present application, the first generating module 1020 may specifically include:

[0167] A first calculation submodule is used to calculate the i-th indicator value of the service user under the i-th preset rule according to the amount of user resources of the service user in each subinterval of M subintervals and the indicator statistical algorithm of the i-th preset rule among the I preset rules, when the preset rules include I preset rules, each of the I preset rules includes an indicator statistical algorithm and a judgment condition, and the asset change trend information of the service user includes a change trend of the resource amount of the user resources within a time interval under each preset rule among the I preset rules, i∈[1,2,...,I];

[0168] The first generating submodule is used to generate the asset change trend information of the service user under the i-th preset rule based on the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value. The asset change trend information under the i-th preset rule is used to characterize the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule.

[0169] In some embodiments of the present application, the first calculation submodule may be specifically used to, when the i-th indicator value includes M-1 first resource change amounts and M-1 first resource change rates, calculate the first resource change amount of the resource amount of the user resource of the service user in the m-th sub-interval relative to the resource amount of the user resource of the m-1-th sub-interval according to the resource amount of the user resource of each sub-interval and the indicator statistical algorithm of the i-th preset rule in I preset rules, to obtain M-1 first resource change amounts, m∈[1,2,…,M];

[0170] Calculate a first resource change rate of the amount of user resources of the service user in the mth subinterval relative to the amount of user resources of the m-1th subinterval according to the amount of user resources of each subinterval, the indicator statistical algorithm of the i-th preset rule among the I preset rules, and the first resource change amount of the amount of user resources of the service user in the m-th subinterval relative to the amount of user resources of the m-1th subinterval;

[0171] Based on a first resource change rate of a resource amount of a user resource of a service user in an m-th sub-interval relative to a resource amount of a user resource in an m-1-th sub-interval, M-1 first resource change rates are generated.

[0172] In some embodiments of the present application, the first generation submodule may specifically include:

[0173] A first judgment unit is used for, when the judgment condition includes a first judgment condition and a second judgment condition, the first judgment condition is a condition for judging that the resource amount of the user resource reflected by the analysis result corresponding to the M-1 first resource change amounts has a continuous change, the second judgment condition includes a first sub-judgment condition and a second sub-judgment condition, the first sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is greater than or equal to a first preset change rate; the second sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is less than or equal to a second preset change rate, and when the asset change trend information includes the first change trend information and the second change trend information, and when the M-1 first resource change amounts meet the first judgment condition, judging the asset change trend information of the service user under the i-th preset rule through the second judgment condition;

[0174] A first determination unit is used to determine the first change trend information as the asset change trend information of the service user under the i-th preset rule when the M-1 first resource change rates meet the first sub-judgment condition, and the first change trend information is used to represent that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a continuously rising state;

[0175] The second determination unit is used to determine the second change trend information as the asset change trend information of the service user under the i-th preset rule when the M-1 first resource change rates meet the second sub-judgment condition. The second change trend is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a continuous downward state.

[0176] In some other embodiments of the present application, the first generating submodule may specifically include:

[0177] The second judgment unit is used for judging that the conditions include a third judgment condition and a fourth judgment condition, the third judgment condition is a condition for judging that there is a linear relationship between the resource amount of the user resource of the service user reflected by the analysis result corresponding to the M-1 first resource change amounts and the time change, the fourth judgment condition includes a third sub-judgment condition and a fourth sub-judgment condition, the third sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is greater than or equal to a third preset change rate; the fourth sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is less than or equal to a fourth preset change rate, the asset change trend information includes the third change trend information and the fourth change trend information; when the M-1 first resource change amounts meet the third judgment condition, the asset change trend information of the service user under the i-th preset rule is judged by the fourth judgment condition;

[0178] A third determination unit is used to determine the third change trend information as the asset change trend information of the service user under the i-th preset rule when the M-1 first resource change rates meet the third sub-judgment condition, and the third change trend information is used to represent that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a linearly increasing state;

[0179] The fourth determination unit is used to determine the fourth change trend information as the asset change trend information of the service user under the i-th preset rule when the M-1 first resource change rates meet the fourth sub-judgment condition. The fourth change trend is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a linear downward state.

[0180] In some embodiments of the present application, the first calculation submodule can be specifically used to, when M subintervals include P first subintervals, P is an integer greater than 1 and less than M, and the i-th indicator value includes the average resource quantity amplitude value of each first subinterval in the P first subintervals, calculate the average resource quantity amplitude value of the user resource in each first subinterval in the P first subintervals according to the resource quantity of the user resources in each first subinterval in the P first subintervals, P-1 target resource changes, and the indicator statistical algorithm of the i-th preset rule in I preset rules, where the P-1 target resource change amount is a first resource change amount selected from the M-1 first resource change amounts and corresponding to the P first subintervals.

[0181] In some embodiments of the present application, the first generation submodule may specifically include:

[0182] A third judgment unit is used for, when the M sub-intervals also include Q second sub-intervals, the P first sub-intervals occur earlier than the second sub-intervals, Q is an integer greater than 1 and less than M, the i-th indicator value also includes Q-1 target resource change rates, and the Q-1 target resource change rate is a first resource change rate selected from the M-1 first resource change rates and corresponding to the Q second sub-intervals; the judgment condition includes a fifth judgment condition and a sixth judgment condition, the fifth judgment condition is a condition for judging that the average resource quantity amplitude value is within a preset amplitude value range, the sixth judgment condition includes a fifth sub-judgment condition and a sixth sub-judgment condition, the fifth sub-judgment condition is a condition for judging that each target resource change rate in the Q-1 target resource change rates is greater than or equal to the fifth preset change rate; the sixth sub-judgment condition is a condition for judging that each target resource change rate in the Q-1 target resource change rates is less than or equal to the sixth preset change rate, and when the asset change trend information includes the fifth change trend information and the sixth change trend information, and when the average resource quantity amplitude value satisfies the fifth judgment condition, the asset change trend information of the service user under the i-th preset rule is judged by the sixth judgment condition;

[0183] a fifth determination unit, configured to determine the fifth change trend information as the asset change trend information of the service user under the i-th preset rule when the Q-1 target resource change rates meet the fifth sub-judgment condition, wherein the fifth change trend information is used to characterize that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a sharply rising state;

[0184] The sixth determination unit is used to determine the sixth change trend information as the asset change trend information of the service user under the i-th preset rule when the Q-1 target resource change rates meet the sixth sub-judgment condition. The sixth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a sharply declining state.

[0185] In some embodiments of the present application, the first calculation submodule can be specifically used to calculate the fluctuation variance of the amount of user resources serving the user in M ​​subintervals based on the amount of user resources serving the user in each subinterval in M ​​subintervals and the indicator statistical algorithm of the i-th preset rule in I preset rules, when the i-th indicator value includes the fluctuation variance.

[0186] In some embodiments of the present application, the first generation submodule may specifically include:

[0187] a fourth judgment unit, configured to, when the judgment conditions include the seventh judgment condition and the eighth judgment condition, the seventh judgment condition is a condition for judging that the volatility variance is a positive number, and the eighth judgment condition is a condition for judging that the volatility variance is greater than or equal to a preset volatility threshold; and the asset change trend information includes the seventh change trend information and the eighth change trend information, and when the volatility variance satisfies the seventh judgment condition, judge the asset change trend information of the service user under the i-th preset rule through the eighth judgment condition;

[0188] a seventh determination unit, configured to determine, when the fluctuation variance satisfies the eighth judgment condition, the seventh change trend information as the asset change trend information of the service user under the i-th preset rule, wherein the seventh change trend information is used to characterize that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a state of violent fluctuation;

[0189] The eighth determination unit is used to determine the eighth change trend information as the asset change trend information of the service user under the i-th preset rule when the fluctuation variance does not meet the eighth judgment condition. The eighth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is slightly fluctuating.

[0190] In some other embodiments of the present application, the first generating module 1020 may further include:

[0191] The second calculation submodule is used to take the i-th preset rule as the current rule, execute the indicator statistical algorithm based on the resource amount of the user resources of the service user in each sub-interval of the M sub-intervals and the indicator of the current rule, and calculate the indicator value of the service user under the current rule, i∈[1,2,…,I].

[0192] The judgment submodule is used to judge whether the indicator value under the current rule meets the first target judgment condition under the current rule. If the judgment result is no, the update submodule is executed, and if the judgment result is yes, the determination submodule is executed.

[0193] The updating submodule is used to update i=i+1 and transfer to the second calculation submodule for execution.

[0194] The determination submodule is used to determine the current rule as the target rule and determine the indicator value of the service user under the current rule as the target indicator value.

[0195] The second generation submodule is used to generate asset change trend information of the service user under the target rules based on the target indicator value and the second target judgment condition for the target indicator value. The asset change trend information under the target rules is used to characterize the change trend of the resource quantity of the user resources within the time interval under the target rules.

[0196] In some embodiments of the present application, the first generation module 1020 may also include: the indicator statistical algorithm under the i-th preset rule is an algorithm for calculating M-1 first resource change amounts and M-1 first resource change rates, the first target judgment condition is a condition for judging whether the resource amount of user resources reflected by the analysis results corresponding to the M-1 first resource change amounts has a continuous change, and the second target judgment condition is a condition for judging the relationship between each first resource change rate in the M-1 first resource change rates and the preset change rate; the indicator statistical algorithm under the i+1-th preset rule is used to calculate P first An algorithm for calculating the average resource amplitude value of each first sub-interval in a sub-interval and Q-1 target resource change rates, wherein the M sub-intervals include P first sub-intervals and Q second sub-intervals, the P first sub-intervals are earlier in time than the Q second sub-intervals, P and Q are integers greater than 1, the first target judgment condition under the i+1th preset rule is a condition for judging that the average resource amplitude value is within a preset amplitude value range, and the second target judgment condition under the i+1th preset rule is a condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate condition.

[0197] In some embodiments of the present application, the first generation module 1020 may also include: the indicator statistical algorithm under the i-th preset rule is an algorithm for calculating the average resource quantity amplitude value and Q-1 target resource change rates, the M sub-intervals include P first sub-intervals and Q second sub-intervals, the P first sub-intervals are earlier in time than the Q second sub-intervals, P and Q are integers greater than 1, the first target judgment condition under the i-th preset rule is a condition for judging that the average resource quantity amplitude value is within the preset amplitude value range, and the second target judgment condition under the i-th preset rule is a condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate; the indicator statistical algorithm under the i+1-th preset rule is used to calculate the fluctuation variance of the resource quantity of the user resources of the service user in the M sub-intervals, the first target judgment condition under the i+1-th preset rule is a condition for judging that the fluctuation variance is a positive number, and the second target judgment condition under the i+1-th preset rule is a condition for judging the relationship between the fluctuation variance and the preset fluctuation threshold.

[0198] In some embodiments of the present application, the second generation module 1040 can be specifically used to, when the user tag of the service user includes multiple user tags, filter the target user tag associated with the target priority from the multiple user tags based on the preset association relationship between the user tag and the priority, and generate a service policy for the service user according to the target user tag.

[0199] The service strategy generation device provided in the embodiment of the present application can achieve Figures 1 to 9 The various processes implemented in the service policy generation method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0200] Fig.11 A schematic diagram of the structure of an electronic device provided in some embodiments of the present application is shown.

[0201] The electronic device may include a processor 1110 and a memory 1120 storing computer program instructions.

[0202] Specifically, the processor 1110 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0203] The memory 1120 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1120 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 1120 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 1120 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 1120 is a non-volatile solid-state memory.

[0204] In a particular embodiment, the memory 1120 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, typically, the memory 1120 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the service policy generation method according to the first aspect of the present application.

[0205] The processor 1110 implements any one of the service policy generation methods in the above embodiments by reading and executing computer program instructions stored in the memory 1120 .

[0206] In some examples, the electronic device may further include a communication interface 1130 and a bus 1140. Fig.11 As shown, the processor 1110, the memory 1120, and the communication interface 1130 are connected via a bus 1140 and communicate with each other.

[0207] The communication interface 1130 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0208] Bus 1140 includes hardware, software or both, and the components of online data flow billing equipment are coupled to each other. For example, but not limitation, bus 1140 may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 1140 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0209] Exemplarily, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).

[0210] The electronic device can execute the service strategy generation method in the embodiment of the present application, thereby realizing the combination Figures 1 to 10 The invention describes a method and apparatus for generating a service strategy.

[0211] In addition, in combination with the service policy generation method in the above embodiment, the embodiment of the present application also provides a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the service policy generation methods in the above embodiment is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0212] The embodiment of the present application also provides a computer program product, which is stored in a storage medium and may specifically include a computer program or instruction, and when the computer program or instruction is executed by a processor, any one of the service policy generation methods in the above embodiments is implemented. The program product is executed by at least one processor to implement the various processes of the above service policy generation method embodiment, and can achieve the same technical effect, so it will not be repeated here to avoid repetition.

[0213] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0214] Aspects of the present disclosure are described above 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 disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of 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, or other programmable service strategy generation device to produce a machine so that these instructions executed by the processor of the computer or other programmable service strategy generation device enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0215] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A service strategy generation method, characterized in that: include: Acquire asset data of a service user in a time interval, the time interval including M sub-intervals, the asset data including the resource amount of user resources of the service user in each of the M sub-intervals, the user resources being resources in a financial account of the service user at a financial institution; Generate asset change trend information of the service user according to the resource amount of the user resource in each subinterval of the M subintervals and a preset rule, wherein the asset change trend information is used to characterize the change trend of the resource amount of the user resource within a time interval under the preset rule; Based on the association relationship between the preset asset change trend information and the user tag, obtaining the user tag of the service user corresponding to the asset change trend information of the service user; A service policy for the service user is generated according to the user tag of the service user.

2. The method according to claim 1, characterized in that The preset rules include I preset rules, each of the I preset rules includes an indicator statistical algorithm and a judgment condition, and the asset change trend information of the service user includes a change trend of the resource amount of the user resource within a time interval under each preset rule in the I preset rules; The generating the asset change trend information of the service user according to the resource amount of the user resources of each subinterval of the M subintervals and a preset rule includes: Calculate the i-th indicator value of the service user under the i-th preset rule according to the resource amount of the user resources of each subinterval in the M subintervals and the indicator statistical algorithm of the i-th preset rule in the I preset rules, i∈[1,2,...,I]; Based on the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value, the asset change trend information of the service user under the i-th preset rule is generated, and the asset change trend information under the i-th preset rule is used to characterize the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule.

3. The method according to claim 2, characterized in that The i-th indicator value includes M-1 first resource change amounts and M-1 first resource change rates; The calculating, according to the resource amount of the user resource of each subinterval of the M subintervals and the indicator statistical algorithm of the i-th preset rule among the I preset rules, the i-th indicator value of the service user under the i-th preset rule comprises: According to the resource amount of the user resources in each sub-interval and the indicator statistical algorithm of the i-th preset rule in the I preset rules, calculate the first resource change amount of the user resources of the service user in the m-th sub-interval relative to the user resources in the m-1-th sub-interval, and obtain M-1 first resource change amounts, m∈[1,2,...,M]; Calculate a first resource change rate of the amount of user resources of the service user in the mth subinterval relative to the amount of user resources of the m-1th subinterval according to the amount of user resources of each subinterval, the indicator statistical algorithm of the i-th preset rule among the I preset rules, and the first resource change amount of the amount of user resources of the service user in the m-th subinterval relative to the amount of user resources of the m-1th subinterval; The M-1 first resource change rates are generated based on a first resource change rate of the resource amount of the user resource of the service user in the m-th sub-interval relative to the resource amount of the user resource in the m-1-th sub-interval.

4. The method according to claim 3, characterized in that The judgment condition includes a first judgment condition and a second judgment condition, the first judgment condition is a condition for judging that the resource amount of the user resource reflected by the analysis result corresponding to the M-1 first resource change amounts has a continuous change, the second judgment condition includes a first sub-judgment condition and a second sub-judgment condition, the first sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is greater than or equal to a first preset change rate; the second sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is less than or equal to a second preset change rate, and the asset change trend information includes first change trend information and second change trend information; The generating, according to the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value, the asset change trend information of the service user under the i-th preset rule comprises: In the case where the M-1 first resource changes satisfy the first judgment condition, the asset change trend information of the service user under the i-th preset rule is judged by the second judgment condition; In the case where the M-1 first resource change rates satisfy the first sub-judgment condition, the first change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the first change trend information is used to characterize that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a continuously rising state; When the M-1 first resource change rates satisfy the second sub-judgment condition, the second change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the second change trend is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a continuous downward state.

5. The method according to claim 3, characterized in that: The judgment condition includes a third judgment condition and a fourth judgment condition, the third judgment condition is a condition for judging that there is a linear relationship between the resource amount of the user resource of the service user reflected by the analysis result corresponding to the M-1 first resource change amounts and the time change, the fourth judgment condition includes a third sub-judgment condition and a fourth sub-judgment condition, the third sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is greater than or equal to a third preset change rate; the fourth sub-judgment condition is a condition for judging that each of the M-1 first resource change rates is less than or equal to a fourth preset change rate, and the asset change trend information includes third change trend information and fourth change trend information; The generating, according to the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value, the asset change trend information of the service user under the i-th preset rule comprises: In the case where the M-1 first resource changes satisfy the third judgment condition, the asset change trend information of the service user under the i-th preset rule is judged by the fourth judgment condition; In the case where the M-1 first resource change rates meet the third sub-judgment condition, the third change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the third change trend information is used to characterize that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a linearly increasing state; When the M-1 first resource change rates satisfy the fourth sub-judgment condition, the fourth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the fourth change trend is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a linear downward state.

6. The method according to claim 3, characterized in that The M sub-intervals include P first sub-intervals, where P is an integer greater than 1 and less than M, and the i-th indicator value includes an average resource amplitude value of each first sub-interval in the P first sub-intervals; The calculating, according to the resource amount of the user resource of each subinterval of the M subintervals and the indicator statistical algorithm of the i-th preset rule among the I preset rules, the i-th indicator value of the service user under the i-th preset rule comprises: According to the resource amount of user resources in each of the P first sub-intervals, P-1 target resource changes and the indicator statistical algorithm of the i-th preset rule in the I preset rules, the average resource amount fluctuation value of the resource amount of the user resources in each of the P first sub-intervals is calculated, and the P-1 target resource change amounts are the first resource change amounts selected from the M-1 first resource change amounts and corresponding to the P first sub-intervals.

7. The method according to claim 6, characterized in that The M subintervals further include Q second subintervals, the P first subintervals occur earlier than the second subintervals, Q is an integer greater than 1 and less than M, and the i-th indicator value further includes Q-1 target resource change rates, and the Q-1 target resource change rates are first resource change rates selected from the M-1 first resource change rates and corresponding to the Q second subintervals; The judgment condition includes a fifth judgment condition and a sixth judgment condition, the fifth judgment condition is a condition for judging that the average resource amplitude value is within a preset amplitude value range, the sixth judgment condition includes a fifth sub-judgment condition and a sixth sub-judgment condition, the fifth sub-judgment condition is a condition for judging that each target resource change rate among Q-1 target resource change rates is greater than or equal to a fifth preset change rate; the sixth sub-judgment condition is a condition for judging that each target resource change rate among Q-1 target resource change rates is less than or equal to a sixth preset change rate, and the asset change trend information includes fifth change trend information and sixth change trend information; The generating, according to the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value, the asset change trend information of the service user under the i-th preset rule comprises: In the case where the average resource amplitude value satisfies the fifth judgment condition, the asset change trend information of the service user under the i-th preset rule is judged by the sixth judgment condition; In the case where the Q-1 target resource change rates meet the fifth sub-judgment condition, the fifth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the fifth change trend information is used to characterize that the change trend of the resource amount of the user resource within the time interval under the i-th preset rule is in a sharply rising state; When the Q-1 target resource change rates satisfy the sixth sub-judgment condition, the sixth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the sixth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a sharply declining state.

8. The method according to claim 2, characterized in that: The i-th indicator value includes volatility variance; The calculating, according to the resource amount of the user resource of each subinterval of the M subintervals and the indicator statistical algorithm of the i-th preset rule among the I preset rules, the i-th indicator value of the service user under the i-th preset rule comprises: According to the resource amount of user resources of the service user in each of the M subintervals and the indicator statistical algorithm of the i-th preset rule in the I preset rules, the fluctuation variance of the resource amount of user resources of the service user in the M subintervals is calculated.

9. The method according to claim 8, characterized in that The judgment condition includes a seventh judgment condition and an eighth judgment condition, wherein the seventh judgment condition is a condition for judging that the fluctuation variance is a positive number, and the eighth judgment condition is a condition for judging that the fluctuation variance is greater than or equal to a preset fluctuation threshold; The asset change trend information includes seventh change trend information and eighth change trend information; The generating, according to the i-th indicator value of the service user under the i-th preset rule and the judgment condition for the i-th indicator value, the asset change trend information of the service user under the i-th preset rule comprises: In the case where the volatility variance satisfies the seventh judgment condition, the asset change trend information of the service user under the i-th preset rule is judged by the eighth judgment condition; When the fluctuation variance satisfies the eighth judgment condition, the seventh change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the seventh change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is in a state of violent fluctuation. When the fluctuation variance does not satisfy the eighth judgment condition, the eighth change trend information is determined as the asset change trend information of the service user under the i-th preset rule, and the eighth change trend information is used to characterize that the change trend of the resource amount of the user's resources within the time interval under the i-th preset rule is slightly fluctuating.

10. The method according to claim 1, characterized in that The preset rules include 1 preset rules, each of which includes an indicator statistical algorithm, a first target judgment condition, and a second target judgment condition; The generating the asset change trend information of the service user according to the resource amount of the user resources of each subinterval of the M subintervals and a preset rule includes: Taking the i-th preset rule as the current rule, the following steps A1 to A2 are executed cyclically until the indicator value of the service user under the current rule meets the first target judgment condition under the current rule, i∈[1,2,…,I]: A1: Calculate the index value of the service user under the current rule according to the resource amount of the user resources of each sub-interval of the M sub-intervals and the index statistical algorithm of the current rule; A2: if the indicator value of the service user under the current rule does not meet the first target judgment condition under the current rule, update i=i+1; Determining the current rule as a target rule and determining the index value of the service user under the current rule as a target index value; Based on the target indicator value and the second target judgment condition for the target indicator value, the asset change trend information of the service user under the target rule is generated, and the asset change trend information under the target rule is used to characterize the change trend of the resource amount of the user's resources within the time interval under the target rule.

11. The method according to claim 10, characterized in that The M subintervals include P first subintervals and Q second subintervals, the P first subintervals are earlier in time than the Q second subintervals, and P and Q are integers greater than 1; The indicator statistical algorithm under the i-th preset rule is an algorithm for calculating the M-1 first resource change amounts and the M-1 first resource change rates, the first target judgment condition is a condition for judging that the resource amount of the user resource reflected by the analysis result corresponding to the M-1 first resource change amounts has a continuous change, and the second target judgment condition is a condition for judging the relationship between each of the M-1 first resource change rates and the preset change rate; The indicator statistical algorithm under the i+1th preset rule is an algorithm for calculating the average resource amplitude value of each first sub-interval in P first sub-intervals and Q-1 target resource change rates, the first target judgment condition under the i+1th preset rule is a condition for judging that the average resource amplitude value is within the preset amplitude value range, and the second target judgment condition under the i+1th preset rule is a condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate condition.

12. The method according to claim 10 or 11, characterized in that: The M subintervals include P first subintervals and Q second subintervals, the P first subintervals are earlier in time than the Q second subintervals, and P and Q are integers greater than 1; The indicator statistical algorithm under the i-th preset rule is an algorithm for calculating the average resource amplitude value of each first sub-interval in P first sub-intervals and Q-1 target resource change rates, the first target judgment condition under the i-th preset rule is a condition for judging that the average resource amplitude value is within a preset amplitude value range, and the second target judgment condition under the i-th preset rule is a condition for judging the relationship between each target resource change rate in the Q-1 target resource change rates and the preset change rate condition; The indicator statistical algorithm under the i+1th preset rule is an algorithm for calculating the fluctuation variance of the resource amount of user resources of the service user in the M sub-intervals, the first target judgment condition under the i+1th preset rule is the condition for judging that the fluctuation variance is a positive number, and the second target judgment condition under the i+1th preset rule is the condition for judging the relationship between the fluctuation variance and the preset fluctuation threshold.

13. The method according to claim 1, characterized in that The user tag of the service user includes multiple user tags; Generating a service policy for the service user according to the user tag of the service user includes: Based on a preset association relationship between user tags and priorities, filtering a target user tag associated with a target priority from the multiple user tags; A service policy for the service user is generated according to the target user tag.

14. A service strategy generating device, characterized in that: The device comprises: A first acquisition module is used to acquire asset data of a service user in a time interval, the time interval includes M sub-intervals, the asset data includes the resource amount of user resources of the service user in each of the M sub-intervals, and the user resources are resources in a financial account of the service user at a financial institution; A first generating module, configured to generate asset change trend information of the service user according to the resource amount of the user resource of each subinterval of the M subintervals and a preset rule, wherein the asset change trend information is used to characterize the change trend of the resource amount of the user resource within a time interval under the preset rule; A second acquisition module, configured to acquire a user tag of a service user corresponding to the asset change trend information of the service user based on a preset association relationship between the asset change trend information and the user tag; The second generating module is used to generate a service policy for the service user according to the user tag of the service user.

15. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the service policy generation method according to any one of claims 1 to 13 is implemented.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the service policy generation method according to any one of claims 1 to 13 is implemented.

17. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the service policy generating method as described in any one of claims 1 to 13.

Citation Information

Patent Citations

  • Service strategy determination method and device and electronic equipment

    CN111598360A

  • Personalized service recommendation method and device based on knowledge graph, equipment and medium

    CN116228367A

  • Personalized bank asset management method and system based on artificial intelligence driving

    CN118071513A

  • Financial planning and management system and method

    US10943298B1