CN117132317A - Data processing method, device, equipment, medium and product - Google Patents

Data processing method, device, equipment, medium and product Download PDF

Info

Publication number
CN117132317A
CN117132317A CN202311130717.3A CN202311130717A CN117132317A CN 117132317 A CN117132317 A CN 117132317A CN 202311130717 A CN202311130717 A CN 202311130717A CN 117132317 A CN117132317 A CN 117132317A
Authority
CN
China
Prior art keywords
transaction
user
marketing
scene
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311130717.3A
Other languages
Chinese (zh)
Inventor
李震川
徐昊
华锦芝
呼如生
王健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Unionpay Co Ltd
Original Assignee
China Unionpay Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Unionpay Co Ltd filed Critical China Unionpay Co Ltd
Priority to CN202311130717.3A priority Critical patent/CN117132317A/en
Publication of CN117132317A publication Critical patent/CN117132317A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0203—Market surveys; Market polls
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Landscapes

  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Technology Law (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The application discloses a data processing method, a device, equipment, a medium and a product. Comprising the following steps: acquiring transaction data of a user at a plurality of financial institutions; dividing transaction data into N transaction scenes; for each transaction scenario, obtaining a first evaluation parameter based on second transaction data in the transaction scenario; determining an operation value coefficient of a user in a transaction scene based on the first transaction data and the second transaction data in the transaction scene; the first evaluation parameter and the operation value coefficient are combined, the lifting potential of the user value of the user in the transaction scene is evaluated, and a second evaluation parameter is obtained; and determining an evaluation result of the user by combining N second evaluation parameters of the user in N transaction scenes, wherein the evaluation result is used for representing the promotion potential of the user value of the user in the first financial institution. According to the embodiment of the application, the accurate quantification of the user value improvement potential can be realized.

Description

Data processing method, device, equipment, medium and product
Technical Field
The present application relates to the field of service data processing technologies, and in particular, to a data processing method, apparatus, device, medium, and product.
Background
In recent years, industries have attracted and maintained users through diverse marketing campaigns, operators, and in the process of providing products and services to users. Along with the influence of factors such as internet industry invasion, the market competition of enterprises in the financial industry is aggravated, so that the client is kept active and more clients are attracted by means of internet marketing, and the realization of the co-growth and value conversion of the enterprises and potential clients has become the consensus and trend of the enterprises. In this context, it is particularly important to choose users with higher potential for key operations, in the face of a huge number of guest users, how to evaluate the boosting potential of the user value.
In the related art, quantitative analysis of the user value improvement potential in the industry is generally implemented through an RFM model, and according to historical transaction data of a user at a certain financial institution, the transaction amount of the user at the financial institution is predicted for a period of time in the future, and the predicted transaction amount is used for indicating the user value improvement potential. However, the quantification method lacks grasp of the overall transaction condition of the user at all financial institutions, for example, the user with less transaction at the bank and high growth potential at more transaction at the other bank cannot be determined, so that deviation of the value promotion potential of the quantified user is larger, and the high potential user cannot be accurately screened out.
Disclosure of Invention
The embodiment of the application provides a data processing method, a device, equipment, a medium and a product, which can realize accurate quantification of user value improvement potential and solve the problems that the deviation of the quantified user value improvement potential is large and high-potential users cannot be accurately screened out.
In a first aspect, an embodiment of the present application provides a data processing method, including:
acquiring transaction data of a user at a plurality of financial institutions, wherein the plurality of financial institutions comprises a first financial institution and Z second financial institutions except the first financial institution;
dividing transaction data into N transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions;
for each transaction scene, based on second transaction data in the transaction scene, evaluating the maximum lifting potential of the user value of the user in the transaction scene to obtain a first evaluation parameter;
determining an operation value coefficient of a user in a transaction scene based on the first transaction data and the second transaction data in the transaction scene;
The first evaluation parameter and the operation value coefficient are combined, the lifting potential of the user value of the user in the transaction scene is evaluated, and a second evaluation parameter is obtained;
and determining an evaluation result of the user by combining N second evaluation parameters of the user in N transaction scenes, wherein the evaluation result is used for representing the promotion potential of the user value of the user in the first financial institution.
In a second aspect, an embodiment of the present application provides a data processing apparatus, including:
an acquisition module for acquiring transaction data of a user at a plurality of financial institutions, wherein the plurality of financial institutions comprises a first financial institution and Z second financial institutions except the first financial institution;
the scene dividing module is used for dividing the transaction data into N transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions;
the evaluation module is used for evaluating the maximum lifting potential of the user value of the user in the transaction scene based on the second transaction data in the transaction scene for each transaction scene to obtain a first evaluation parameter;
The determining module is used for determining the operation value coefficient of the user in the transaction scene based on the first transaction data and the second transaction data in the transaction scene;
the evaluation module is also used for evaluating the lifting potential of the user value of the user in the transaction scene by combining the first evaluation parameter and the operation value coefficient to obtain a second evaluation parameter;
the evaluation module is further used for determining an evaluation result of the user by combining N second evaluation parameters of the user in N transaction scenes, wherein the evaluation result is used for representing the lifting potential of the user value of the user in the first financial institution.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory storing computer program instructions; the processor when executing the computer program instructions implements the steps of the data processing method shown in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a program or instructions which, when executed by a processor, implement the steps of the data processing method as shown in the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product stored in a non-volatile storage medium, which when executed by at least one processor implements the steps of the data processing method as shown in the first aspect.
In a sixth aspect, an embodiment of the present application provides a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to execute programs or instructions to implement the steps of the data processing method as in the first aspect.
The embodiment of the application provides a data processing method, a device, equipment, a medium and a product, wherein under the scene that a first financial institution needs to quantify the lifting potential of the user value of each card holding user, transaction data of the user at a plurality of financial institutions need to be acquired, and the plurality of financial institutions can be divided into the first financial institutions and Z second financial institutions except the first financial institutions. In addition, considering the difference of consumption of different transaction scenes on the user value, dividing transaction data into N transaction scenes according to the transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions; and for each transaction scene, based on the second transaction data in the transaction scene, evaluating the maximum lifting potential of the user value of the user in the transaction scene, and obtaining a first evaluation parameter. According to the application, the difference of the business value of the user in different transaction scenes is considered, for example, the user has a certain card using tendency in a certain transaction scene, the card using tendency is converted from the card of the user to the card of the user through a marketing activity, so that the user value is greatly improved, and the business value coefficient of the user in each transaction scene can be determined based on the first transaction data and the second transaction data in the transaction scene. Thus, the whole transaction data of the user at all financial institutions can be mined and analyzed, and the comprehensive consumption condition of the user is fully considered. Compared with the scheme that the user value lifting potential is obtained by only carrying out analysis modeling based on consumption data of a single financial institution in the related art, the method and the system can quantify the maximum lifting potential of the user value under a transaction scene and the operation value coefficient according to more comprehensive transaction data. Based on the above, by combining the first evaluation parameters and the business value coefficients, the promotion potential of the user value of the user in a certain transaction scene can be evaluated more reasonably and accurately, and further, the promotion potential value of the user for the first financial institution is evaluated accurately by summarizing the promotion potential of the same user in all transaction scenes, so that the accurate quantitative evaluation of the promotion potential of the user value of all card holding users of the first financial institution is realized, the promotion of marketing activities with the user value is facilitated, for example, target users with high potential are screened out from all card holding users, so that the first financial institution can develop marketing activities for the target users with high potential, and the user value of the target users in the first financial institution is promoted.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings that are needed to be used in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.
FIG. 1 is a flow chart of an embodiment of a data processing method according to a first aspect of the present application;
FIG. 2 is a flow chart of another embodiment of a data processing method according to the first aspect of the present application;
FIG. 3 is a flow chart of a further embodiment of a data processing method according to the first aspect of the present application;
FIG. 4 is a flow chart of a further embodiment of a data processing method according to the first aspect of the present application;
FIG. 5 is a flow chart of a further embodiment of a data processing method according to the first aspect of the present application;
FIG. 6 is a flow chart of a further embodiment of a data processing method according to the first aspect of the present application;
FIG. 7 is a flow chart of a further embodiment of a data processing method according to the first aspect of the present application;
FIG. 8 is a schematic diagram illustrating an embodiment of a data processing apparatus according to a second aspect of the present application;
fig. 9 is a schematic structural diagram of an embodiment of an electronic device according to a third aspect of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail below with reference to the accompanying drawings and the detailed embodiments. It should be understood that the particular embodiments described herein are meant to be illustrative of the application only and not limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the application by showing examples of the application.
In recent years, industries have attracted and maintained users through diverse marketing campaigns, operators, and in the process of providing products and services to users. Along with the influence of factors such as internet industry invasion, the market competition of enterprises in the financial industry is aggravated, so that the client is kept active and more clients are attracted by means of internet marketing, and the realization of the co-growth and value conversion of the enterprises and potential clients has become the consensus and trend of the enterprises. In this context, it is particularly important to choose users with higher potential for key operations, in the face of a huge number of guest users, how to evaluate the boosting potential of the user value.
In the related art, quantitative analysis of the user value improvement potential in the industry is generally implemented through an RFM model, and according to historical transaction data of a user at a certain financial institution, the transaction amount of the user at the financial institution is predicted for a period of time in the future, and the predicted transaction amount is used for indicating the user value improvement potential. However, the quantification method lacks grasp of the overall transaction condition of the user at all financial institutions, for example, the user with less transaction at the bank and high growth potential at more transaction at the other bank cannot be determined, so that deviation of the value promotion potential of the quantified user is larger, and the high potential user cannot be accurately screened out.
Based on the above-mentioned problems, embodiments of the present application provide a data processing method, apparatus, device, medium, and product, where a first financial institution needs to quantify the lifting potential of the user value of each card-holding user, transaction data of the user at a plurality of financial institutions need to be acquired, where the plurality of financial institutions may be divided into a first financial institution and Z second financial institutions other than the first financial institution. In addition, considering the difference of consumption of different transaction scenes on the user value, dividing transaction data into N transaction scenes according to the transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions; and for each transaction scene, based on the second transaction data in the transaction scene, evaluating the maximum lifting potential of the user value of the user in the transaction scene, and obtaining a first evaluation parameter. According to the application, the difference of the business value of the user in different transaction scenes is considered, for example, the user has a certain card using tendency in a certain transaction scene, the card using tendency is converted from the card of the user to the card of the user through a marketing activity, so that the user value is greatly improved, and the business value coefficient of the user in each transaction scene can be determined based on the first transaction data and the second transaction data in the transaction scene. Thus, the whole transaction data of the user at all financial institutions can be mined and analyzed, and the comprehensive consumption condition of the user is fully considered. Compared with the scheme that the user value lifting potential is obtained by only carrying out analysis modeling based on consumption data of a single financial institution in the related art, the method and the system can quantify the maximum lifting potential of the user value under a transaction scene and the operation value coefficient according to more comprehensive transaction data. Based on the above, by combining the first evaluation parameters and the business value coefficients, the promotion potential of the user value of the user in a certain transaction scene can be evaluated more reasonably and accurately, and further, the promotion potential value of the user for the first financial institution is evaluated accurately by summarizing the promotion potential of the same user in all transaction scenes, so that the accurate quantitative evaluation of the promotion potential of the user value of all card holding users of the first financial institution is realized, the promotion of marketing activities with the user value is facilitated, for example, target users with high potential are screened out from all card holding users, so that the first financial institution can develop marketing activities for the target users with high potential, and the user value of the target users in the first financial institution is promoted.
The data processing method in the embodiment of the application can be applied to the scenes of quantitative evaluation aiming at the promotion potential of the user value of the card holding user of the financial institution, or the scenes of user recommendation with high user value or high potential can be screened after quantitative evaluation.
The data processing method provided by the embodiment of the application is described in detail below through specific embodiments with reference to the accompanying drawings.
The first aspect of the present application provides a data processing method, which is applicable to a financial card transfer clearing mechanism, a payment mechanism, an international card organization, or the like, and the execution subject is not limited to the present application.
Fig. 1 is a flowchart of an embodiment of a data processing method according to the first aspect of the present application. As shown in fig. 1, the data processing method may include steps 110-160.
Step 110, acquiring transaction data of a user at a plurality of financial institutions, wherein the plurality of financial institutions comprise a first financial institution and Z second financial institutions except the first financial institution;
step 120, dividing the transaction data into N transaction scenes to obtain N sets of transaction data corresponding to the N transaction scenes, wherein each set of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions;
Step 130, for each transaction scenario, based on the second transaction data in the transaction scenario, evaluating the maximum lifting potential of the user value of the user in the transaction scenario, to obtain a first evaluation parameter;
step 140, determining an operation value coefficient of the user in the transaction scene based on the first transaction data and the second transaction data in the transaction scene;
step 150, evaluating the lifting potential of the user value of the user in the transaction scene by combining the first evaluation parameter and the operation value coefficient to obtain a second evaluation parameter;
step 160, determining an evaluation result of the user in combination with N second evaluation parameters of the user in N transaction scenarios, wherein the evaluation result is used for representing the promotion potential of the user value of the user in the first financial institution.
In the data processing method provided by the embodiment of the application, under the scene that the first financial institution needs to quantify the lifting potential of the user value of each card holding user, the transaction data of the user at a plurality of financial institutions need to be acquired, and the plurality of financial institutions can be divided into the first financial institution and Z second financial institutions except the first financial institution. In addition, considering the difference of consumption of different transaction scenes on the user value, dividing transaction data into N transaction scenes according to the transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions; and for each transaction scene, based on the second transaction data in the transaction scene, evaluating the maximum lifting potential of the user value of the user in the transaction scene, and obtaining a first evaluation parameter. According to the application, the difference of the business value of the user in different transaction scenes is considered, for example, the user has a certain card using tendency in a certain transaction scene, the card using tendency is converted from the card of the user to the card of the user through a marketing activity, so that the user value is greatly improved, and the business value coefficient of the user in each transaction scene can be determined based on the first transaction data and the second transaction data in the transaction scene. Thus, the whole transaction data of the user at all financial institutions can be mined and analyzed, and the comprehensive consumption condition of the user is fully considered. Compared with the scheme that the user value lifting potential is obtained by only carrying out analysis modeling based on consumption data of a single financial institution in the related art, the method and the system can quantify the maximum lifting potential of the user value under a transaction scene and the operation value coefficient according to more comprehensive transaction data. Based on the above, by combining the first evaluation parameters and the business value coefficients, the promotion potential of the user value of the user in a certain transaction scene can be evaluated more reasonably and accurately, and further, the promotion potential value of the user for the first financial institution is evaluated accurately by summarizing the promotion potential of the same user in all transaction scenes, so that the accurate quantitative evaluation of the promotion potential of the user value of all card holding users of the first financial institution is realized, the promotion of marketing activities with the user value is facilitated, for example, target users with high potential are screened out from all card holding users, so that the first financial institution can develop marketing activities for the target users with high potential, and the user value of the target users in the first financial institution is promoted.
The following describes the specific implementation of the above steps in detail with reference to examples, and is specifically shown below.
Involving step 110, obtaining transaction data for a user at a plurality of financial institutions.
In step 110, the financial institution may be a bank, and the transaction data of the financial institution is observable consumption data when using the financial card issued by the financial institution to consume the financial card, where the consumption data may be in a preset historical period, and the preset historical period may be set according to specific requirements, for example, the preset historical period is set to be 6 months, 3 months, 1 month, or the like, which is not limited in particular by the present application.
The first financial institution is a financial institution to be used for marketing activities, and before marketing activities are carried out, quantitative evaluation is required to be carried out on the promotion potential of the user values of all card holding users of the first financial institution so as to screen target users with high potential from all card holding users, so that the first financial institution can pertinently carry out marketing activities for the target users, and the user values of the target users in the first financial institution are promoted.
Typically, a user holds more than one financial institution, where the present application divides the financial institutions involved in all financial cards under the name of the user into a first financial institution and a second financial institution other than the first financial institution, where the number of second financial institutions is Z, where Z is an integer greater than or equal to zero.
For example, the user a is a card holding user of the bank a, and in a scenario of quantifying the lifting potential of the user value of the user a in the bank a, the bank card transaction data of the user a in the last 6 months needs to be acquired. The 3 bank cards held by the user a relate to 3 banks, namely a bank a, a bank b and a bank c, and the first financial institution is a bank a, and the second financial institution comprises a bank b and a bank c.
Step 120 is involved, dividing the transaction data into N transaction scenarios, and obtaining N sets of transaction data corresponding to the N transaction scenarios.
In step 120, the transaction scenario may be preset, and the transaction scenario may be, for example, an insurance financial scenario, a daily consumption scenario, a high-end consumption scenario, an asset consumption scenario, etc., and the present application may divide all transaction data of the user into each transaction scenario according to a preset consumption scenario division rule.
Referring to the above example, the first financial institution is bank a, and the second financial institution includes bank b and bank c. If the transaction scenario includes a daily consumption scenario, splitting the transaction data of the bank card of the user A in the last 6 months is needed, and for the daily consumption scenario, obtaining first transaction data consumed in the bank a in the last 6 months and second transaction data consumed in the banks b and c in the last 6 months.
Step 130 is involved, for each transaction scenario, based on the second transaction data in the transaction scenario, evaluating the maximum lifting potential of the user value of the user in the transaction scenario, and obtaining the first evaluation parameter.
In step 130, for each transaction scenario, analysis is performed according to the second transaction data of the non-home line (i.e., the second financial institution), so as to obtain the maximum possible value of the user value improvement potential of the user in the transaction scenario, i.e., the first evaluation parameter.
In the related art, when the improvement potential of the user value is quantitatively evaluated through the RFM model, the difference of consumption of different transaction scenes on the user value is not considered, for example, the user value brought by daily consumption scenes to financial institutions is lower than that brought by high-end consumption scenes and the like.
In some embodiments of the present application, in order to reduce the deviation of the user value improvement potential obtained by quantization, fig. 2 is a flowchart of another embodiment of the data processing method provided in the first aspect of the present application, and the step 130 may include steps 210 to 230 shown in fig. 2.
Step 210, based on the second transaction data in the transaction scenario, obtaining transaction total amounts of the user for the Z second financial institutions in the transaction scenario;
Step 220, obtaining a user value weight coefficient matched with a transaction scene;
at step 230, a first evaluation parameter is determined in combination with the transaction amount and the user value weight coefficient.
Specifically, the transaction total is the sum of the Z transaction amounts for the Z second financial institutions; the user value weight coefficient is preset, for example, the weight of the daily consumption scene is 0.5, the high-end consumption scene is 1.0, the insurance financial scene is 1.5, and the like, which is not particularly limited in the application. The user value weight coefficient is determined according to the service contribution degree of the transaction scene to the financial institution, and the higher the service contribution degree is in the transaction scene, the larger the user value weight coefficient corresponding to the transaction scene is.
In step 230, the transaction amount and the user value weight coefficient may be multiplied and the product determined as a first evaluation parameter.
For example, the first evaluation parameter may be determined using equation (1).
vp i ＝m i ×w i (1)
Wherein m is i Is the transaction total amount, w, in the transaction scene i i For user value weight coefficient matching transaction scenario i, vp i The maximum possible value of the potential is promoted for the user value in the transaction scenario i, namely the first evaluation parameter.
In the embodiment of the application, corresponding user value weight coefficients are set for different transaction scenes, the difference of the user values in the different transaction scenes is fully reflected, the consumption amount of the user in a non-home line is weighted according to the user value weight coefficients in the different transaction scenes, more weight values can be distributed for the transaction scenes capable of bringing more user values, so that the maximum potential value of the user value promotion of the user in the different transaction scenes can be reasonably estimated based on the influence of the difference of the user values in the different transaction scenes, the promotion potential value of the user value in the transaction scenes is accurately estimated based on the maximum potential value, and the deviation of the quantized user value promotion potential is reduced.
Step 140 is involved, determining an operational value coefficient of the user in the transaction scenario based on the first transaction data and the second transaction data in the transaction scenario.
In step 140, in the quantitative evaluation process, the transaction data of the user in all financial institutions under each transaction scene is mined, and the comprehensive consumption condition of the user in all financial institutions is combined to obtain the operation value coefficient capable of representing the expected tendency of the user to use cards under the transaction scene.
In some embodiments of the present application, fig. 3 is a flowchart illustrating a further embodiment of the data processing method provided in the first aspect of the present application, and the step 140 may include the steps 310 and 320 shown in fig. 3.
Step 310, determining a variation coefficient of the user in the transaction scene based on the first transaction data and the second transaction data;
step 320, weight adjustment is performed on the coefficient of variation based on the first number of the plurality of financial institutions to obtain the operational value coefficient.
The coefficient of variation is used for representing the use preference of a user on a financial institution under a transaction scene, namely the tendency of a card; the first number is the number of financial institutions involved in all financial cards held by the user, and the first number is z+1.
Illustratively, the coefficient of variation may be weighted in step 320 using equation (2).
Wherein r is i For the operational value coefficient of the user in the scene i, cv i For the coefficient of variation of the user in scene i, b i For a first number of users in scenario i.
In the embodiment of the application, considering the difference of the business value of the user in different transaction scenes, for example, the user uses one financial card of the second financial institution in a certain transaction scene, namely, a certain card using tendency exists, the card using tendency is transferred from the second financial institution to the second financial institution through a marketing activity, so that larger user value improvement can be brought to the first financial institution, and if the user does not have the card using tendency, obvious user value improvement is relatively difficult to bring. Therefore, according to the variation coefficient capable of representing the use preference of the user to the financial institution in the transaction scene, the card consumption tendency of the user can be known, and further, the bank account use preference distribution information of the user in each transaction scene is converted into the user operation value coefficient, so that the operation value of the user in each transaction scene is quantified.
In some embodiments, in step 320, the coefficient of variation may be mapped to a value ranging from 0 to 1 using a normalized mapping function, and then the coefficient of variation is weighted by a first amount.
In some embodiments of the present application, fig. 4 is a flowchart illustrating a further embodiment of the data processing method according to the first aspect of the present application, where the step 320 may include steps 410 to 430 shown in fig. 4.
Step 410, obtaining a plurality of transaction amounts of a user for a plurality of financial institutions in a transaction scenario from the first transaction data and the second transaction data;
step 420, determining a mean value and a standard deviation of a plurality of transaction amounts;
step 430, determining the ratio of standard deviation to mean of the transaction amounts, and obtaining the variation coefficient of the user in the transaction scene.
Illustratively, all consumption records of user u under scenario i are respectively attributed to b i Transaction amount of individual banksThen +.>Mean value mu and standard deviation sigma of sigma/mu as coefficient of variation cv i 。
In the embodiment of the application, under the same transaction scene, based on different consumption amounts generated by using different financial cards of the financial institutions, the use bias of the user under the transaction scene, namely the card using tendency, can be reflected, so that the variation coefficient capable of accurately representing the card using tendency or the use preference is obtained. Therefore, based on the variation coefficient capable of accurately indicating the card tendency, the operation value coefficient in the transaction scene can be accurately and quantitatively evaluated, and the accuracy of the operation value coefficient is improved.
Step 150 is involved, and the first evaluation parameter and the operation value coefficient are combined, so that the promotion potential of the user value of the user in the transaction scene is evaluated, and a second evaluation parameter is obtained.
In step 150, a second evaluation parameter may be obtained by combining the first evaluation parameter and the operation value coefficient, where the second evaluation parameter is a value of the lifting potential of the user value of the user in the transaction scenario.
In some embodiments of the present application, the first evaluation parameter may be multiplied by the operational value coefficient to obtain a second evaluation parameter of the user in the transaction scenario.
Illustratively, in combination with the first evaluation parameter and the operational value coefficient, the second evaluation parameter may be calculated using equation (3).
v i ＝r i ×vp i (3)
Wherein r is i For the operational value coefficient of the user in the scene i, vp i For a first evaluation parameter of a user in a scene i, v i The second evaluation parameter for the user in scenario i.
In the embodiment of the application, the operation value coefficient represents the expected value of the user using the card bias in the transaction scene, so that the second evaluation parameter is calculated in a way of multiplying the expected value of the user value with the maximum hoisting potential value, the second evaluation parameter is the expected value of the user value hoisting potential, and the calculation way has clear business significance, so that the obtained second evaluation parameter can reasonably and accurately represent the hoisting potential of the user value in the transaction scene, and the accurate quantitative evaluation of the hoisting potential value is realized.
In other embodiments of the present application, the first evaluation parameter may be added to the running value coefficient to obtain a second evaluation parameter of the user in the transaction scenario.
Step 160 is involved, and the evaluation result of the user is determined in combination with N second evaluation parameters of the user in N transaction scenarios.
In step 160, the sum of the value of the user's value of the lifting potential in all the transaction scenarios, i.e. N transaction scenarios, may be used as the value of the lifting potential of the user's value of the user in the first financial institution, so as to obtain the evaluation result. And the method can sort the lifting potential values of the user values of all users under the first financial institution from large to small, and identify the target users with higher priority operation potential values.
For example, the evaluation result may be calculated using equation (4) in step 160.
Where N is the number of transaction scenarios,for the accumulated value of N second evaluation parameters of N transaction scenes, V u And (5) evaluating results of the users.
As an example, if the card-holding users of the first financial institution include M users, the user values of the M users may be ranked from large to small to obtain v= { V 1 ,V 2 ,V 3 ,...,V M And (3) screening the users ranked first as target users of the key operation.
In the related art, in the aspect of marketing scenario recommendation, it is common to determine target users who wish to conduct business first, then mine the requirements and preferences of these users, and recommend the consumption scenario where the users are most likely to participate in the marketing campaign for user operation. Firstly, realizing by a basic statistical method, recommending the scene most preferred by the user to be used for developing a marketing campaign by counting the preference degree of all target users to each scene; secondly, a user marketing response prediction model is constructed, the probability of participation of the target user in the marketing activities under each scene is predicted, and the scene with the highest participation probability of all the target users is recommended to be used for developing the marketing activities.
However, in the marketing scene recommendation mode, the possibility of the target user participating in a specific marketing scene only shows the participation rate of the marketing activity, is inconsistent with the final purpose of improving the user value, and does not consider the situation that the probability of the target user participating in the recommended marketing scene is high, but the increase of the user value which is finally driven is not obvious.
In some embodiments of the present application, in order to accurately evaluate the user value increase effect caused by the marketing campaign in each transaction scenario, and further screen out a recommended transaction scenario capable of significantly driving the user value increase, fig. 5 is a flowchart of still another embodiment of the data processing method provided in the first aspect of the present application, which may be applied to the recommended scenario of the marketing scenario, as shown in fig. 5, and after step 160, the method may further include steps 510 to 540 shown in fig. 5.
Step 510, under the condition that the evaluation results of the M users are obtained, screening K target users from the M users based on the sequence of increasing potential of the user values of the M users under the first financial institution from large to small;
step 520, obtaining N marketing response probabilities of each target user under N transaction scenarios respectively;
step 530, for each transaction scenario, determining a first marketing prediction result corresponding to the transaction scenario by combining K marketing response probabilities and K second evaluation parameters of K target users in the transaction scenario;
and step 540, taking the transaction scene of which the first marketing prediction result meets the preset marketing condition as a recommended marketing scene.
K is a positive integer, and the first K users are selected as target users according to the sequence of increasing potential of the user values of the M users under the first financial institution from large to small. The first marketing prediction result is used for representing the increasing value of the user values of the K target users under the marketing activities of the transaction scene, namely, the first marketing prediction result can represent the increasing effect of the user values brought by the marketing activities under the transaction scene.
The preset conditions may include: and determining the transaction scene with the highest user value of the K target users under the marketing activities as the recommended marketing scene.
Illustratively, the K target users may be noted as t= { u 1 ,u 2 ,u 3 ,...u K }。
In the embodiment of the application, when the marketing campaign is developed under a certain transaction scene, the marketing response probability can reflect the possibility that each target user participates in the marketing campaign, and the second evaluation parameter can reflect the user value improving effect brought by each target user after participating in the marketing campaign. Therefore, by combining the marketing response probability and the second evaluation parameter, the user value promotion driven by the marketing activity under a certain transaction scene can be accurately and quantitatively evaluated by combining the participation probability of the user on the marketing activity under the transaction scene and the brought user value, and further, the transaction scene with the best user value promotion effect is screened out from a plurality of transaction scenes to serve as a recommendation scene. Therefore, the marketing scene recommending method based on the scene-based user value improving potential recommends scenes from the angle of improving the user value, and takes the transaction scene capable of improving the user value to the greatest extent for the financial institutions as the recommended marketing scene.
In some embodiments of the present application, the step 520 of obtaining N marketing response probabilities of each target user under N transaction scenarios may specifically include:
acquiring historical transaction characteristics of a target user as input characteristics;
and inputting input features into the target marketing response prediction model to obtain N marketing response probabilities of the target user under N transaction scenes respectively.
In particular, a target marketing response prediction model may be pre-trained from historical marketing data such that the model can accurately predict a likelihood that a user will participate in a marketing campaign in a certain transaction scenario. Historical transaction characteristics may be derived from historical marketing data, which may include, for example, but are not limited to: user transaction amount, user behavior information (characterizing preferences for marketing campaigns), user cardholder information.
In some embodiments, a neural network model may be used to perform multi-task learning to obtain a target marketing response prediction model, so that a single model can be used to predict the probability of a user's marketing response in multiple scenarios.
In some embodiments of the present application, fig. 6 is a flowchart of still another embodiment of the data processing method provided in the first aspect of the present application, and the step 530 may include the step 610 and the step 620 shown in fig. 6.
Step 610, for the same transaction scenario, determining a second marketing prediction effect of each target user based on the marketing response probability and the second evaluation parameter of each target user in the transaction scenario;
step 620, determining the first marketing prediction result by combining the second marketing prediction effects of the K target users in the same transaction scene.
Specifically, the second marketing prediction result is used for representing the promotion effect of the user value of the target user under the marketing activities of the transaction scenes, so that the promotion prediction total value of the user value of the target user, namely the first marketing prediction effect, when the marketing activities are developed under each transaction scene can be reasonably and accurately determined by summarizing the second marketing prediction effects of all the target users under the same transaction scene.
Illustratively, the first marketing prediction resultWherein pv i,j For the second marketing prediction result of the jth target user in the ith transaction scene, summarizing the second marketing prediction result of the K target users in the ith transaction scene, and obtaining the first marketing prediction result PV in the ith transaction scene i Finally, an ordered list PV= { PV of the first marketing prediction result under N transaction scenes is obtained 1 ,PV 2 ,PV 3 ,...PV N }。
In some embodiments of the present application, the step 620 may specifically include:
Multiplying the marketing response probability with a second evaluation parameter to obtain a second marketing prediction result;
or multiplying the marketing response probability, the second evaluation parameter and the third evaluation parameter to obtain a second marketing prediction result;
wherein, the third evaluation parameter is used for representing the transaction amount promotion effect of the target user under the historical marketing activities of the transaction scene, and the third evaluation parameter can be obtained based on the historical marketing data.
In some embodiments, a transaction amount set corresponding to each marketing campaign is obtained from historical marketing data, where the transaction amount set corresponds to each marketing campaign in a transaction scenario within a preset period of time, so as to obtain a plurality of transaction amount sets corresponding to a plurality of marketing campaigns; a third evaluation parameter is determined based on the plurality of transaction amount sets.
The transaction amount set comprises a first transaction amount and a second transaction amount, wherein the first transaction amount is the accumulated transaction amount before the marketing campaign is developed, and the second transaction amount is the accumulated transaction amount after the marketing campaign is developed.
Optionally, calculating a difference value between the first transaction amount and the second transaction amount in each transaction amount set to obtain an amount increase value of each transaction amount set, and taking an average value of a plurality of amount increase values as a third evaluation parameter; or calculating the ratio of the value of the amount of the increase in each transaction amount set to the first transaction amount to obtain the amount of the increase in each transaction amount set, and taking the average value of the amount of the increase in each transaction amount set as a third evaluation parameter.
For example, the second marketing prediction result may be determined using equation (5) or equation (6).
pv i,j ＝p i,j ×v i,j (5)
pv i,j ＝p i,j ×v i,j ×θ j (6)
Wherein p is i,j 、v i,j 、pv i,j Respectively, the probability of marketing response of the jth target user in the ith transaction scene, a second evaluation parameter and a second marketing prediction result, theta i Is a third evaluation parameter in the ith transaction scenario.
In the embodiment of the application, in addition to the marketing response probability and the second evaluation parameter, the second marketing prediction effect is comprehensively determined by combining the third evaluation parameter capable of representing the transaction amount lifting effect of the target user under the historical marketing activities of the transaction scene, so that the accuracy of the user value lifting effect represented by the second marketing prediction result can be further improved.
In some embodiments of the present application, fig. 7 is a flowchart of still another embodiment of the data processing method provided in the first aspect of the present application, and the step 530 may include the steps 710 and 720 shown in fig. 7.
Step 710, obtaining first average values of K marketing response probabilities corresponding to the transaction scenario and second average values of K second evaluation parameters corresponding to the transaction scenario;
step 720, determining a first marketing prediction result by combining the first average value and the second average value.
In the embodiment of the application, for the same transaction scene, the average value of the K marketing response probabilities of the K target users is used as the first average value, so that the first average value can reflect the marketing response probabilities of all the target users in the transaction scene; the average value of K second evaluation parameters of K target users is used as a second average value, so that the second average value can reflect the user value lifting potential of all the target users in the transaction scene. Therefore, the user value improvement values driven by all target users in the same transaction scene can be reasonably and accurately quantitatively evaluated by combining the target user value improvement values and the target user value improvement values.
In some embodiments of the present application, the determining the first marketing prediction result in step 720 may specifically include:
multiplying the first average value by the second average value to obtain a first marketing prediction result;
or multiplying the first average value, the second average value and the third average value to obtain a first marketing result;
the third average value is an average value of K third evaluation parameters of K target users corresponding to the transaction scene, and the third evaluation parameters are used for representing the transaction amount lifting effect of the target users under the historical marketing activities of the transaction scene.
Based on the same inventive concept, a second aspect of the present application provides a data processing apparatus. Fig. 8 is a schematic structural diagram of an embodiment of a data processing apparatus according to a second aspect of the present application.
As shown in fig. 8, the data processing apparatus 800 may specifically include: an acquisition module 810, a scene division module 820, an evaluation module 830, and a determination module 840.
Wherein, the acquiring module 810 is configured to acquire transaction data of a user at a plurality of financial institutions, where the plurality of financial institutions includes a first financial institution and Z second financial institutions other than the first financial institution;
the scenario dividing module 820 is configured to divide the transaction data into N transaction scenarios, to obtain N sets of transaction data corresponding to the N transaction scenarios, where each set of transaction data includes first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions;
the evaluation module 830 is configured to, for each transaction scenario, evaluate, based on the second transaction data in the transaction scenario, a maximum lifting potential of a user value of the user in the transaction scenario, and obtain a first evaluation parameter;
a determining module 840, configured to determine an operational value coefficient of the user in the transaction scenario based on the first transaction data and the second transaction data in the transaction scenario;
The evaluation module 830 is further configured to evaluate a lifting potential of the user value of the user in the transaction scenario by combining the first evaluation parameter and the operation value coefficient, so as to obtain a second evaluation parameter;
the evaluation module 830 is further configured to determine an evaluation result of the user in combination with N second evaluation parameters of the user in N transaction scenarios, where the evaluation result is used to characterize a lifting potential of the user value of the user in the first financial institution.
In the data processing device provided by the embodiment of the application, under the circumstance that the first financial institution needs to quantify the lifting potential of the user value of each card holding user, the transaction data of the user at a plurality of financial institutions need to be acquired, and the plurality of financial institutions can be divided into the first financial institution and Z second financial institutions except the first financial institution. In addition, considering the difference of consumption of different transaction scenes on the user value, dividing transaction data into N transaction scenes according to the transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to a first financial institution and second transaction data corresponding to Z second financial institutions; and for each transaction scene, based on the second transaction data in the transaction scene, evaluating the maximum lifting potential of the user value of the user in the transaction scene, and obtaining a first evaluation parameter. According to the application, the difference of the business value of the user in different transaction scenes is considered, for example, the user has a certain card using tendency in a certain transaction scene, the card using tendency is converted from the card of the user to the card of the user through a marketing activity, so that the user value is greatly improved, and the business value coefficient of the user in each transaction scene can be determined based on the first transaction data and the second transaction data in the transaction scene. Thus, the whole transaction data of the user at all financial institutions can be mined and analyzed, and the comprehensive consumption condition of the user is fully considered. Compared with the scheme that the user value lifting potential is obtained by only carrying out analysis modeling based on consumption data of a single financial institution in the related art, the method and the system can quantify the maximum lifting potential of the user value under a transaction scene and the operation value coefficient according to more comprehensive transaction data. Based on the above, by combining the first evaluation parameters and the business value coefficients, the promotion potential of the user value of the user in a certain transaction scene can be evaluated more reasonably and accurately, and further, the promotion potential value of the user for the first financial institution is evaluated accurately by summarizing the promotion potential of the same user in all transaction scenes, so that the accurate quantitative evaluation of the promotion potential of the user value of all card holding users of the first financial institution is realized, the promotion of marketing activities with the user value is facilitated, for example, target users with high potential are screened out from all card holding users, so that the first financial institution can develop marketing activities for the target users with high potential, and the user value of the target users in the first financial institution is promoted.
In some embodiments of the application, the evaluation module comprises: the acquisition sub-module is used for acquiring transaction total amounts of the Z second financial institutions of the user in the transaction scene based on the second transaction data in the transaction scene; the acquisition sub-module is also used for acquiring a user value weight coefficient matched with the transaction scene; and the determining submodule is used for combining the transaction amount and the user value weight coefficient to determine a first evaluation parameter.
In some embodiments of the application, the determining module comprises: a determining sub-module for determining a coefficient of variation of the user in the transaction scenario based on the first transaction data and the second transaction data, wherein the coefficient of variation is used to characterize a usage preference of the user for the financial institution in the transaction scenario; and the weight adjusting sub-module is used for carrying out weight adjustment on the variation coefficient based on the first quantity of the plurality of financial institutions to obtain an operation value coefficient.
In some embodiments of the application, determining the sub-module comprises: an acquisition unit configured to acquire, from the first transaction data and the second transaction data, a plurality of transaction amounts for a plurality of financial institutions by a user in a transaction scenario; a determining unit configured to determine a mean value and a standard deviation of a plurality of transaction amounts; the determining unit is further used for determining the ratio of the standard deviation to the average value of the transaction amounts to obtain the variation coefficient of the user in the transaction scene.
In some embodiments of the application, the evaluation module is specifically configured to: and multiplying the first evaluation parameter by the operation value coefficient to obtain a second evaluation parameter of the user in the transaction scene.
In some embodiments of the application, the apparatus further comprises: the screening module is used for screening K target users from M users based on the sequence of the increasing potential of the user values of the M users under the first financial institution from large to small under the condition that the evaluation results of the M users are obtained after the evaluation results of the users are determined; the obtaining module 810 is further configured to obtain N marketing response probabilities of each target user under N transaction scenarios respectively; the determining module 840 is further configured to determine, for each transaction scenario, a first marketing prediction result corresponding to the transaction scenario by combining K marketing response probabilities and K second evaluation parameters of K target users in the transaction scenario; the determining module 840 is further configured to use a transaction scenario in which the first marketing prediction result meets the preset marketing condition as a recommended marketing scenario; the first marketing prediction result is used for representing the promotion effect of the user values of K target users under the marketing activities of the transaction scene.
In some embodiments of the application, the acquisition module comprises: the acquisition sub-module is used for acquiring historical transaction characteristics of the target user as input characteristics; and the input sub-module is used for inputting the input characteristics into the target marketing response prediction model to obtain N marketing response probabilities of the target user under N transaction scenes respectively.
In some embodiments of the present application, the determining module 840 includes: the determining submodule is used for determining a second marketing prediction effect of each target user based on the marketing response probability of each target user in the transaction scene and a second evaluation parameter for the same transaction scene, wherein the second marketing prediction result is used for representing the promotion effect of the user value of the target user in the marketing activity of the transaction scene; and the determining submodule is also used for determining a first marketing prediction result by combining second marketing prediction effects of K target users in the same transaction scene.
In some embodiments of the application, the determination submodule is specifically configured to: multiplying the marketing response probability with a second evaluation parameter to obtain a second marketing prediction result; or multiplying the marketing response probability, the second evaluation parameter and the third evaluation parameter to obtain a second marketing prediction result; the third evaluation parameter is used for representing the transaction amount improving effect of the target user under the historical marketing activities of the transaction scene.
In some embodiments of the present application, the determining module 840 includes: the acquisition sub-module is used for acquiring first average values of K marketing response probabilities corresponding to the transaction scene and second average values of K second evaluation parameters corresponding to the transaction scene; and the determining submodule is used for combining the first average value and the second average value to determine a first marketing prediction result.
In some embodiments of the application, the determination submodule is specifically configured to: multiplying the first average value by the second average value to obtain a first marketing prediction result; or multiplying the first average value, the second average value and the third average value to obtain a first marketing result; the third average value is an average value of K third evaluation parameters of K target users corresponding to the transaction scene, and the third evaluation parameters are used for representing the transaction amount lifting effect of the target users under the historical marketing activities of the transaction scene.
The third aspect of the application also provides an electronic device. Fig. 9 is a schematic structural diagram of an embodiment of an electronic device according to a third aspect of the present application. As shown in fig. 9, the electronic device 900 includes a memory 901, a processor 902, and a computer program stored on the memory 901 and executable on the processor 902.
In one example, the processor 902 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present application.
Memory 901 may include Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic disk storage media devices, optical storage media devices, flash Memory devices, electrical, optical, or other physical/tangible Memory storage devices. Thus, in general, the memory comprises one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising 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 data processing method in embodiments according to the first aspect of the application.
The processor 902 executes a computer program corresponding to the executable program code by reading the executable program code stored in the memory 901 for realizing the data processing method in the embodiment of the first aspect described above.
In some examples, electronic device 900 may also include a communication interface 903 and a bus 904. As shown in fig. 9, the memory 901, the processor 902, and the communication interface 903 are connected to each other via a bus 904 and perform communication with each other.
The communication interface 903 is mainly used to implement communication between each module, device, unit, and/or apparatus in the embodiment of the present application. Input devices and/or output devices may also be accessed through communication interface 903.
Bus 904 includes hardware, software, or both, coupling components of electronic device 900 to one another. By way of example, and not limitation, bus 904 may include an accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics Bus, an enhanced industry standard architecture (Enhanced Industry Standard Architecture, EISA) Bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (Industry Standard Architecture, ISA) Bus, an Infiniband interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (Micro Channel Architecture, MCa) Bus, a peripheral component interconnect (Peripheral Component Interconnect, PCI) Bus, a PCI-Express (PCI-E) Bus, a serial advanced technology attachment (Serial Advanced Technology Attachment, SATA) Bus, a video electronics standards association local (Video Electronics Standards Association Local Bus, VLB) Bus, or other suitable Bus, or a combination of two or more of these. Bus 904 may include one or more buses, where appropriate. Although embodiments of the application have been described and illustrated with respect to a particular bus, the application contemplates any suitable bus or interconnect.
In a fourth aspect, the present application provides a computer readable storage medium, where a program or an instruction is stored, where the program or the instruction can implement the data processing method described in the first aspect and achieve the same technical effects when executed by a processor, and in order to avoid repetition, a description is omitted here. The computer readable storage medium may include a non-transitory computer readable storage medium, such as Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk, and the like, but is not limited thereto.
A fifth aspect of the present application provides a computer program product stored in a non-volatile storage medium, which when executed by at least one processor implements the steps of the data processing method as described in the first aspect, and the details of the data processing method may be found in the related description of the above embodiments, which are not repeated herein.
A sixth aspect of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement each process of the embodiment of the data processing method as shown in the first aspect, and achieve the same technical effects, and not described herein again for avoiding repetition.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be understood that, in the present specification, each embodiment is described in an incremental manner, and the same or similar parts between the embodiments are all referred to each other, and each embodiment is mainly described in a different point from other embodiments. For apparatus embodiments, user terminal embodiments, device embodiments, system embodiments, and computer-readable storage medium embodiments, the relevant points may be found in the description of method embodiments. The application is not limited to the specific steps and structures described above and shown in the drawings. Those skilled in the art will appreciate that various alterations, modifications, and additions may be made, or the order of steps may be altered, after appreciating the spirit of the present application. Also, a detailed description of known method techniques is omitted here for the sake of brevity.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that the above-described embodiments are exemplary and not limiting. The different technical features presented in the different embodiments may be combined to advantage. Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in view of the drawings, the description, and the claims. In the claims, the term "comprising" does not exclude other means or steps; the word "a" does not exclude a plurality; the terms "first," "second," and the like, are used for designating a name and not for indicating any particular order. Any reference signs in the claims shall not be construed as limiting the scope. The functions of the various elements presented in the claims may be implemented by means of a single hardware or software module. The presence of certain features in different dependent claims does not imply that these features cannot be combined to advantage.

Claims (15)

1. A method of data processing, the method comprising:
acquiring transaction data of a user at a plurality of financial institutions, wherein the plurality of financial institutions comprises a first financial institution and Z second financial institutions except the first financial institution;
Dividing the transaction data into N transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to the first financial institution and second transaction data corresponding to the Z second financial institutions;
for each transaction scene, based on second transaction data in the transaction scene, evaluating the maximum lifting potential of the user value of the user in the transaction scene to obtain a first evaluation parameter;
determining an operational value coefficient of the user in the transaction scene based on the first transaction data and the second transaction data in the transaction scene;
the first evaluation parameter and the operation value coefficient are combined, and the lifting potential of the user value of the user in the transaction scene is evaluated to obtain a second evaluation parameter;
and determining an evaluation result of the user by combining N second evaluation parameters of the user in the N transaction scenes, wherein the evaluation result is used for representing the promotion potential of the user value of the user in the first financial institution.
2. The method of claim 1, wherein the evaluating the maximum lifting potential of the user value of the user in the transaction scenario based on the second transaction data in the transaction scenario, to obtain the first evaluation parameter, comprises:
Acquiring transaction total amounts of the user for the Z second financial institutions in the transaction scenario based on the second transaction data in the transaction scenario;
acquiring a user value weight coefficient matched with the transaction scene;
and determining the first evaluation parameter by combining the transaction amount and the user value weight coefficient.
3. The method of claim 1, wherein the determining the user's business value coefficient in the transaction scenario based on the first transaction data and the second transaction data in the transaction scenario comprises:
determining a coefficient of variation of the user in the transaction scenario based on the first transaction data and the second transaction data, wherein the coefficient of variation is used to characterize a usage preference of the user for a financial institution in the transaction scenario;
and carrying out weight adjustment on the variation coefficient based on the first quantity of the plurality of financial institutions to obtain the operation value coefficient.
4. The method of claim 3, wherein the determining a coefficient of variation of the user in the transaction scenario based on the first transaction data and the second transaction data comprises:
Acquiring a plurality of transaction amounts of the user for the plurality of financial institutions in the transaction scenario from the first transaction data and the second transaction data;
determining a mean and standard deviation of the plurality of transaction amounts;
and determining the ratio of the standard deviation to the mean value of the transaction amounts to obtain the variation coefficient of the user in the transaction scene.
5. The method according to claim 1, wherein the evaluating the user value of the user for the boost potential in the transaction scenario by combining the first evaluation parameter and the operational value coefficient, to obtain a second evaluation parameter, comprises:
and multiplying the first evaluation parameter by the operation value coefficient to obtain a second evaluation parameter of the user in the transaction scene.
6. The method of claim 1, wherein after said determining the evaluation result of the user, the method further comprises:
under the condition that evaluation results of M users are obtained, K target users are screened out of the M users based on the sequence of the increasing potential of the user values of the M users under the first financial institution from large to small;
Acquiring N marketing response probabilities of each target user under the N transaction scenes respectively;
for each transaction scene, determining a first marketing prediction result corresponding to the transaction scene by combining K marketing response probabilities and K second evaluation parameters of the K target users in the transaction scene;
taking a transaction scene of which the first marketing prediction result meets a preset marketing condition as a recommended marketing scene;
the first marketing prediction result is used for representing the promotion effect of the user values of the K target users under the marketing activities of the transaction scene.
7. The method of claim 6, wherein the obtaining N marketing response probabilities for each target user in the N transaction scenarios, respectively, comprises:
acquiring historical transaction characteristics of the target user as input characteristics;
and inputting the input characteristics into a target marketing response prediction model to obtain N marketing response probabilities of the target user under the N transaction scenes respectively.
8. The method of claim 6, wherein the determining the first marketing prediction result corresponding to the transaction scenario comprises:
For the same transaction scene, determining a second marketing prediction effect of each target user based on the marketing response probability and a second evaluation parameter of each target user in the transaction scene, wherein the second marketing prediction result is used for representing the promotion effect of the user value of the target user in the marketing activities of the transaction scene;
and determining the first marketing prediction result by combining the second marketing prediction effects of the K target users in the same transaction scene.
9. The method of claim 8, wherein said determining the second marketing prediction effect of each of the target users comprises:
multiplying the marketing response probability with the second evaluation parameter to obtain the second marketing prediction result;
or multiplying the marketing response probability, the second evaluation parameter and a third evaluation parameter to obtain the second marketing prediction result;
wherein the third evaluation parameter is used for representing a transaction amount improving effect of the target user under the historical marketing activities of the transaction scene.
10. The method of claim 6, wherein the determining the first marketing prediction result corresponding to the transaction scenario comprises:
Acquiring first average values of K marketing response probabilities corresponding to the transaction scene and second average values of K second evaluation parameters corresponding to the transaction scene;
and combining the first average value and the second average value to determine the first marketing prediction result.
11. The method of claim 10, wherein the determining the first marketing prediction result in combination with the first mean and the second mean comprises:
multiplying the first average value by the second average value to obtain the first marketing prediction result;
or multiplying the first average value, the second average value and the third average value to obtain the first marketing result;
the third average value is an average value of K third evaluation parameters of K target users corresponding to the transaction scene, and the third evaluation parameters are used for representing the transaction amount lifting effect of the target users under the historical marketing activities of the transaction scene.
12. A data processing apparatus, the apparatus comprising:
an acquisition module for acquiring transaction data of a user at a plurality of financial institutions, wherein the plurality of financial institutions comprises a first financial institution and Z second financial institutions except the first financial institution;
The scene dividing module is used for dividing the transaction data into N transaction scenes to obtain N groups of transaction data corresponding to the N transaction scenes, wherein each group of transaction data comprises first transaction data corresponding to the first financial institution and second transaction data corresponding to the Z second financial institutions;
the evaluation module is used for evaluating the maximum lifting potential of the user value of the user in each transaction scene based on the second transaction data in the transaction scene to obtain a first evaluation parameter;
the determining module is used for determining the operation value coefficient of the user in the transaction scene based on the first transaction data and the second transaction data in the transaction scene;
the evaluation module is further configured to evaluate a lifting potential of the user value of the user in the transaction scenario by combining the first evaluation parameter and the operation value coefficient, so as to obtain a second evaluation parameter;
the evaluation module is further configured to determine an evaluation result of the user in combination with N second evaluation parameters of the user in the N transaction scenarios, where the evaluation result is used to characterize a lifting potential of a user value of the user in the first financial institution.
13. An electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a data processing method as claimed in any one of claims 1 to 11.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores thereon a program or instructions which, when executed by a processor, implements the data processing method according to any of claims 1 to 11.
15. A computer program product, characterized in that the computer program product is stored in a non-volatile storage medium, which computer program product, when being executed by at least one processor, implements the data processing method according to any of claims 1 to 11.
CN202311130717.3A 2023-09-01 2023-09-01 Data processing method, device, equipment, medium and product Pending CN117132317A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311130717.3A CN117132317A (en) 2023-09-01 2023-09-01 Data processing method, device, equipment, medium and product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311130717.3A CN117132317A (en) 2023-09-01 2023-09-01 Data processing method, device, equipment, medium and product

Publications (1)

Publication Number Publication Date
CN117132317A true CN117132317A (en) 2023-11-28

Family

ID=88859761

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311130717.3A Pending CN117132317A (en) 2023-09-01 2023-09-01 Data processing method, device, equipment, medium and product

Country Status (1)

Country Link
CN (1) CN117132317A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117993912A (en) * 2024-04-07 2024-05-07 杭州大鱼网络科技有限公司 Insurance online transaction evidence-preserving method and system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117993912A (en) * 2024-04-07 2024-05-07 杭州大鱼网络科技有限公司 Insurance online transaction evidence-preserving method and system

Similar Documents

Publication Publication Date Title
CN109214585B (en) User consumption prediction method and device, electronic equipment and storage medium
CN112862298B (en) Credit evaluation method for user portrait
CN109583966A (en) A kind of high value customer recognition methods, system, equipment and storage medium
CN112541817A (en) Marketing response processing method and system for potential customers of personal consumption loan
CN112116245A (en) Credit risk assessment method, credit risk assessment device, computer equipment and storage medium
CN111340244A (en) Prediction method, training method, device, server and medium
CN117132317A (en) Data processing method, device, equipment, medium and product
CN115545712A (en) Fraud prediction method, device, equipment and storage medium for transaction behaviors
CN112950347A (en) Resource data processing optimization method and device, storage medium and terminal
CN115545886A (en) Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium
CN118134652A (en) Asset configuration scheme generation method and device, electronic equipment and medium
CN108416662B (en) Data verification method and device
Mzoughia et al. An improved customer lifetime value model based on Markov chain
CN113420789A (en) Method, device, storage medium and computer equipment for predicting risk account
CN110796379B (en) Risk assessment method, device and equipment of business channel and storage medium
CN116934341A (en) Transaction risk assessment method, device, electronic equipment and medium
CN111160929A (en) Method and device for determining client type
CN115914363A (en) Message pushing method and device, computer equipment and storage medium
CN114897607A (en) Data processing method and device for product resources, electronic equipment and storage medium
CN110570301B (en) Risk identification method, device, equipment and medium
CN114565460A (en) Information pushing method based on delayed conversion prediction model and related equipment
CN112950225A (en) Customer category determination method, device and storage medium
CN111815204A (en) Risk assessment method, device and system
CN112529236A (en) Target object identification method and device, electronic equipment and storage medium
CN116453141B (en) Identification method and device for bill latent passenger and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination