CN112907266A - User screening model acquisition method, financial information pushing method and related device - Google Patents
User screening model acquisition method, financial information pushing method and related device Download PDFInfo
- Publication number
- CN112907266A CN112907266A CN201911137349.9A CN201911137349A CN112907266A CN 112907266 A CN112907266 A CN 112907266A CN 201911137349 A CN201911137349 A CN 201911137349A CN 112907266 A CN112907266 A CN 112907266A
- Authority
- CN
- China
- Prior art keywords
- user
- financial
- data
- sample
- information
- 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
Links
- 238000012216 screening Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012549 training Methods 0.000 claims abstract description 17
- 230000006399 behavior Effects 0.000 claims description 58
- 238000001914 filtration Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q40/06—Asset management; Financial planning or analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a user screening model obtaining method, a financial information pushing method and a related device. The method for acquiring the user screening model comprises the following steps: acquiring user data of a sample user, wherein the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user; acquiring financial behavior information data corresponding to the sample user; and training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model. According to the scheme, the third-party users can be accurately screened, and the financial information pushing accuracy is improved.
Description
Technical Field
The present application relates to the field of information technologies, and in particular, to an obtaining method of a user screening model, a financial information pushing method, and a related apparatus.
Background
With the rapid development of internet technology and affordable finance, third-party enterprises such as electronic commerce and instant messaging gradually start to cooperate with financial institutions, so that the flow of the third-party users is realized in a financial scene in a cooperative diversion mode, a joint loan-putting mode and the like. Through the cooperation mode, a third-party enterprise with a large number of users can convert own flow resources into actual benefits, and simultaneously provides popular financial services for users of own products, and financial institutions can acquire a large number of new clients by means of the flow advantages of the cooperation parties, so that quick client acquisition is realized.
However, in the prior cooperation process of a third party and a financial institution, financial information such as publicity, display and registration channels of related products of the financial institution is often pushed to the user in a 'rough' manner, and the user is attracted to click to go to the financial institution, so that the third party user is recommended to the financial institution. In view of this, how to accurately screen the third-party users and improve the accuracy of financial information push becomes an urgent problem to be solved.
Disclosure of Invention
The technical problem mainly solved by the application is to provide an acquisition method of a user screening model, a financial information pushing method and a related device, which can accurately screen third-party users and improve the accuracy of financial information pushing.
In order to solve the above problem, a first aspect of the present application provides a method for obtaining a user screening model, including: acquiring user data of a sample user, wherein the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user; acquiring financial behavior information data corresponding to the sample user; and training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model.
In order to solve the above problem, a second aspect of the present application provides a financial information pushing method, including: screening target users with financial requirements from users pushed by a third party by using a user screening model, wherein the user screening model is obtained by the method for obtaining the user screening model in the first aspect; and pushing the financial information to the target user.
In order to solve the above problems, a third aspect of the present application provides an apparatus for obtaining a user screening model, including a sample user obtaining module, a user information obtaining module, and a training module, where the sample user obtaining module is configured to obtain user data of a sample user, where the user data of the sample user includes user tag data, registration information data of the sample user, and browsing behavior information data, and the user tag data is used to represent a financial demand level of the user; the user information acquisition module is used for acquiring financial behavior information data corresponding to the sample user; and the training module is used for training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model.
In order to solve the above problems, a fourth aspect of the present application provides a financial information pushing apparatus, including a screening module and a pushing module, where the screening module is configured to screen a target user with a financial requirement from users pushed by a third party by using a user screening model, where the user screening model is obtained by the method for obtaining the user screening model in the first aspect; and the pushing module is used for pushing the financial information to the target user.
In order to solve the above problem, a fifth aspect of the present application provides an electronic device, which includes a memory and a processor coupled to each other, where the processor is configured to execute program instructions stored in the memory to implement the above-mentioned method for acquiring a user screening model or the above-mentioned method for pushing financial information based on a user screening model.
In order to solve the above problems, a sixth aspect of the present application provides a storage device storing program instructions executable by a processor, the program instructions being configured to implement the method for acquiring a user filtering model in the above first aspect, or implement the method for pushing financial information based on a user filtering model in the above second aspect.
According to the scheme, user data of a sample user is obtained, the user data of the sample user comprises user tag data, registration information data of the sample user and browsing behavior information data, and the user tag data is used for representing the financial demand level of the user; and acquiring financial behavior information data corresponding to the sample user, and training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model. According to the embodiment, the registration information, the browsing behavior information and the financial behavior information of the sample user can be fused to train the sample user data, so that the obtained user screening model can screen the user of the third party, the blind pushing of the subsequent financial information is avoided, the accuracy of screening the user of the third party is improved, and the accuracy of the subsequent financial information pushing is improved.
Drawings
FIG. 1 is a schematic flowchart of an embodiment of a method for obtaining a user screening model according to the present application;
FIG. 2 is a schematic flow chart diagram illustrating an embodiment of a method for pushing financial information according to the present application;
FIG. 3 is a schematic flow chart diagram illustrating another embodiment of a method for pushing financial information according to the present application;
FIG. 4 is a schematic diagram of a framework of an embodiment of an apparatus for obtaining a user screening model according to the present application;
FIG. 5 is a schematic diagram of a framework of another embodiment of an apparatus for obtaining a user filtering model according to the present application;
FIG. 6 is a block diagram of an embodiment of a financial information pushing apparatus according to the present application;
FIG. 7 is a block diagram of another embodiment of a financial information pushing device according to the present application;
FIG. 8 is a block diagram of an embodiment of a memory device according to the present application.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
The acquisition of user data in this context is obtained under user authorization.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of a method for obtaining a user screening model according to the present application. Specifically, the method may include the steps of:
step S11: user data of a sample user is obtained.
The user data of the sample user can be obtained by a third party, the third party can be a data platform, including an electronic commerce platform, an instant messaging platform and the like, and the third party has a large number of users registered to the platform.
In this embodiment, in order to train the user screening model, a plurality of sample user data may be randomly extracted from the third-party user data, for example: 100, 1000, etc., and the embodiment is not limited in this respect.
In this embodiment and the following embodiments, the user data of the sample user includes user tag data, registration information data of the user, and browsing behavior information data, where the user tag data is used to represent a financial demand level of the user; for example: there is no financial demand, there is a slight financial demand, there is a strong financial demand, etc., and this embodiment is no longer one by one here, and in other implementation scenarios, the financial demand level can also be assessed by adopting the score according to needs, for example, the financial demand level is assessed by adopting 0-10, where 0 represents no financial demand, and 10 represents that the financial demand is very strong.
In an implementation scenario, in order to accurately obtain a user tag in user data of a sample user, financial information may be pushed to a sample user corresponding to selected sample user data, and user tag data in the sample user data may be determined based on a click condition of the sample user on the financial information. Specifically, financial information can be pushed to the sample user, and the click amount of the sample user on the financial information and the browsing time of a single click in a unit time can be counted, so as to determine the user tag data in the sample user data. For example, if the sample user a does not click on the financial information within one month, it may be determined that the user tag in the sample user data of the sample user a is "no financial requirement", and the sample user b clicks on the financial information 10 times within one month, and each browsing is performed for more than 5 minutes, so as to determine that the sample user b has a strong financial requirement. In a specific implementation scenario, for a third-party enterprise with a mature system, the above-mentioned manner may be adopted to perform early-stage simulation data accumulation, so as to obtain response information of the sample user, such as clicking and browsing the financial information, as a user tag in the sample user data of the sample user.
In another implementation scenario, in order to quickly obtain the user tag in the sample user data, financial behavior information data corresponding to the sample user may be searched in a target database according to the sample user data, and the user tag data of the sample user may be determined according to the searched financial behavior information data of the sample user. Specifically, the target database includes a database of the financial institution, and data matching the data of the sample user can be searched in the database of the financial institution, and if the data can be searched, it indicates that the sample user is registered in the financial institution, in this case, the user tag data in the data of the sample user can be further determined according to the financial behavior data (such as loan and financing) of the sample user in the financial institution. For example, if the sample user a is not found in the database of the financial institution, the user tag data in the sample user data of the sample user a may be determined to be "no financial demand", the sample user B is found in the database of the financial institution, but the financial behavior of the sample user B in the financial institution is not further found, which indicates that the sample user B is registered with the financial institution but has no strong financial demand, it may be determined that the user tag data in the sample user data of the sample user b is "with a slight financial demand", and furthermore, the sample user C is found in the database of the financial institution, and the financial behaviors of the sample user C, such as loan and loan, in the financial institution are further found, the user tag data in the sample user data of the sample user c may be determined to be "having a strong financial demand". In addition, the financial requirements of the user can be further defined according to the specific financial behaviors of the sample user in the financial institution, such as loan periods, the amount of financial products, and the like, which is not illustrated herein. In a specific implementation scenario, for an enterprise without related experience, the database collision matching is performed with the database of the financial institution in the above manner, and the financial demand level of the sample user is determined according to the matching condition.
In addition, in this embodiment and the following embodiments, the sample user data further includes registration information data and browsing behavior information data of the user. The registration information data may include, but is not limited to: the age, sex, academic history, unit type (e.g., civil enterprise, foreign enterprise, national enterprise, public institution, etc.) of the sample user are not illustrated herein. The browsing behavior information data includes, but is not limited to: the login frequency of the sample user (e.g., twice a day, three times a day, etc.), the browsing duration (e.g., five minutes each, ten minutes each, etc.), and the embodiment is not further exemplified herein.
Step S12: and acquiring financial behavior information data corresponding to the sample user.
In this embodiment, the financial behavior information includes, but is not limited to: the credit information, the borrowing information, and the payment overdue information of the user are sampled, which is not illustrated in this embodiment.
Step S13: and training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model.
The initial model may be a pre-set neural network including, but not limited to: CNN (Convolutional Neural Networks) model, RNN (recurrent Neural Networks) model.
In an implementation scenario, in order to further improve the accuracy of user screening and improve the recognition capability of the trained user screening model for the financial institution target user, sample user data whose financial behavior information does not meet preset conditions may also be removed before training. In practical application, target users of a financial institution often have two conditions of financial requirements and good credit investigation, so that sample user data of which financial behavior information does not meet preset conditions are removed before training, the sample user data can be excluded from sample user data to be trained subsequently, and users with financial requirements and good credit investigation can be identified by the trained user screening model. The preset condition can be any one or combination of the following conditions: good credit and low overdue risk. By the aid of the method, data islands can be broken, sample user data with high financial requirements and low credit level are excluded from sample user data needing training subsequently, and target user identification capacity is improved.
According to the scheme, user data of a sample user is obtained, wherein the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user; acquiring financial behavior information data corresponding to the sample user; the initial model is trained by utilizing the user data of the sample user and the financial behavior information data to obtain the user screening model, the registration information, the browsing behavior information and the financial behavior information of the sample user can be fused to train the sample user data, and then the obtained user screening model can screen the user of a third party, so that the blind pushing of subsequent financial information is avoided, the accuracy of screening the user of the third party is improved, and the accuracy of the pushing of the subsequent financial information is improved.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a financial information pushing method according to an embodiment of the present application. Specifically, the method may include the steps of:
step S21: and screening out target users with financial requirements from the users pushed by the third party by using the user screening model.
In this embodiment, the user screening model is obtained through the steps in any of the above embodiments of the method for obtaining a user screening model.
In an implementation scenario, before training, the user screening model in this embodiment eliminates sample user data of sample users whose financial behavior information does not meet a preset condition, so that high-quality customers with financial requirements and good credit can be screened.
Step S22: and pushing the financial information to the target user.
The financial information may be obtained by including, but not limited to: the information is pushed to the target user in the form of short message, email, webpage embedding, popup window, etc., and this embodiment is not limited specifically here.
In one implementation scenario, in addition to pushing financial information to the target user, the target user may be directly recommended to the financial institution to enable the financial institution to have active access to the recommended target user, including but not limited to: telephone, email, short message.
According to the scheme, the target users with financial requirements are screened out from the users pushed by the third party by utilizing the user screening model, so that financial information is pushed to the target users, and further, an explicit user screening mechanism can be used in the pushing process of the financial information, the blind pushing of the follow-up financial information can be avoided, the accuracy of screening the third party users is improved, and the accuracy of financial information pushing is improved.
Referring to fig. 3, fig. 3 is a schematic flowchart of another embodiment of a financial information pushing method according to the present application, and specifically, fig. 3 is a schematic flowchart of an embodiment of a method for differentially pushing financial information, including the following steps:
step S31: and screening out the target users by using the screening model, and acquiring the financial demand level of each target user.
In this embodiment, the user screening model is obtained through the steps in any of the above embodiments of the method for obtaining a user screening model.
In an implementation scenario, before training, the user screening model in this embodiment eliminates sample users whose financial behavior information does not satisfy the preset condition among the sample users, so that high-quality customers with financial requirements and good credit can be screened.
In one implementation scenario, the financial demand level of the target user may include, but is not limited to: in other implementation scenarios, the financial demand level of the target user may also be evaluated by using a score, for example, the financial demand level may be evaluated by using 0 to 10, where 0 represents no financial demand, and 10 represents a very strong financial demand. The embodiment is not particularly limited herein.
Step S32: and acquiring financial information corresponding to the financial demand level of the target user based on the financial demand level of the target user.
For example, for a target user with a strong financial demand level, the pushed financial information may include a high-risk high-profit financial product, and for a target user with a low financial demand level, the pushed financial information may include a low-risk low-profit financial product. The financial information corresponding to the financial demand level of the target user may be set according to an actual situation, and in an actual application, other setting manners are not excluded, and this embodiment is not illustrated one by one.
Step S33: and pushing the corresponding financial information to the target user.
After the financial information corresponding to the financial demand level of the target user is obtained, the corresponding financial information may be pushed to the target user.
Financial information may include, but is not limited to: short messages, emails, third-party webpage embedded, advertisement pop-up windows, etc., and the embodiment is not limited in particular.
In one implementation scenario, in addition to pushing financial information to the target user, the target user may be recommended to a financial institution to enable the financial institution to make active follow-up based on the recommended target user.
According to the scheme, the target users are screened out by utilizing the screening model, the financial demand level of each target user is obtained, the financial information corresponding to the financial demand level of the target users is obtained based on the financial demand level of the target users, the corresponding financial information is pushed to the target users, the financial information corresponding to the financial demand level of the target users can be pushed to the target users based on the different financial demand levels of the target users, the financial information is pushed differentially, and therefore the flow rate change conversion efficiency is improved.
Referring to fig. 4, fig. 4 is a schematic diagram of a framework of an embodiment of an obtaining apparatus 40 for a user screening model according to the present application. The obtaining device 40 of the user screening model comprises a sample user obtaining module 41, a user information obtaining module 42 and a learning training module 43, wherein the sample user obtaining module 41 is used for obtaining user data of a sample user, the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user; the user information obtaining module 42 is configured to obtain financial behavior information data corresponding to the sample user; the training module 43 is configured to train an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model. In one implementation scenario, the financial activity information data includes credit information, debit information, and payment overdue information.
According to the scheme, user data of a sample user is obtained, wherein the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user; acquiring financial behavior information data corresponding to the sample user; the initial model is trained by utilizing the user data of the sample user and the financial behavior information data to obtain the user screening model, the registration information, the browsing behavior information and the financial behavior information of the sample user can be fused to train the sample user data, and then the obtained user screening model can screen the user of a third party, so that the blind pushing of subsequent financial information is avoided, the accuracy of screening the user of the third party is improved, and the accuracy of the pushing of the subsequent financial information is improved.
In some embodiments, the sample user obtaining module 41 includes an information pushing sub-module for pushing financial information to a plurality of sample users, and the sample user obtaining module 41 further includes a tag determining sub-module for determining user tags of the plurality of sample users based on clicks of the financial information by the plurality of sample users.
In some embodiments, the sample user obtaining module 41 includes a data searching sub-module, configured to search, according to the sample user data, financial behavior information corresponding to the sample user in a target database, and determine the user tag of the sample user according to the searched financial behavior information of the sample user.
In some embodiments, the obtaining device 40 of the user screening model further includes a user sample rejecting module, configured to reject sample users whose financial behavior information does not meet the preset condition.
Referring to fig. 5, fig. 5 is a schematic diagram of a frame of an embodiment of a financial information pushing apparatus 50 according to the present application. The financial information pushing device 50 comprises a screening module 51 and a pushing module 52, wherein the screening module 51 is configured to screen a target user with a financial requirement from users pushed by a third party by using a user screening model, and the user screening model is obtained through the steps in any one of the above embodiments of the method for obtaining the user screening model; the pushing module 52 is used for pushing financial information to the target user.
According to the scheme, the target users with financial requirements are screened out from the users pushed by the third party by utilizing the user screening model, so that financial information is pushed to the target users, and further, an explicit user screening mechanism can be used in the pushing process of the financial information, the blind pushing of the follow-up financial information can be avoided, the accuracy of screening the third party users is improved, and the accuracy of financial information pushing is improved.
In some embodiments, the filtering module 51 is specifically configured to filter out the target users by using the filtering model and obtain the financial requirement level of each target user, the pushing module 52 includes a financial information obtaining sub-module configured to obtain financial information corresponding to the financial requirement level of the target user based on the financial requirement level of the target user, and the pushing module 52 further includes a financial information pushing sub-module configured to push the corresponding financial information to the target user.
Different from the embodiment, the target users are screened out by using the screening model, and the financial demand level of each target user is acquired, so that the financial information corresponding to the financial demand level of the target user is acquired based on the financial demand level of the target user, the corresponding financial information is pushed to the target user, and the financial information corresponding to the financial demand level of the target user can be pushed to the target user based on the different financial demand levels of the target user, so that the differential pushing of the financial information is realized, and the traffic change conversion efficiency is improved.
In some embodiments, the financial information pushing device 50 further includes a recommending module for recommending the target user to the financial institution.
In some embodiments, an electronic device is provided, which includes a memory and a processor coupled to each other, and the processor is configured to execute program instructions stored in the memory to implement the steps in any of the above-mentioned embodiments of the method for acquiring a user filtering model or the steps in any of the above-mentioned embodiments of the method for acquiring a user filtering model. The method specifically comprises the following steps: the device comprises an acquisition device for the user screening model or a financial information pushing device for the user screening model.
Referring to fig. 6, fig. 6 is a schematic diagram of a framework of an embodiment of an apparatus 60 for obtaining a user screening model according to the present application. The user screening model obtaining device 60 includes a memory 61 and a processor 62 coupled to each other, and the processor 62 is configured to execute program instructions stored in the memory 61 to implement the steps in any of the above embodiments of the user screening model obtaining method.
In particular, the processor 62 is configured to control itself and the memory 61 to implement the steps in any of the above embodiments of the user screening model obtaining method. The processor 62 may also be referred to as a CPU (Central Processing Unit). The processor 62 may be an integrated circuit chip having signal processing capabilities. The Processor 62 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 62 may be commonly implemented by a plurality of integrated circuit chips.
According to the scheme, the registration information, the browsing behavior information and the financial behavior information of the sample user can be fused to train the sample user data, so that the obtained user screening model can screen the user of the third party, the blind pushing of the subsequent financial information is avoided, the accuracy of screening the user of the third party is improved, and the accuracy of the subsequent financial information pushing is improved.
Referring to fig. 7, fig. 7 is a schematic diagram of a financial information pushing apparatus 70 according to an embodiment of the present application. The financial information pushing apparatus 70 includes a memory 71 and a processor 72 coupled to each other, and the processor 72 is configured to execute program instructions stored in the memory 71 to implement the steps in any of the above-mentioned embodiments of the financial information pushing method based on the user screening model.
In particular, the processor 72 is configured to control itself and the memory 71 to implement the steps in any of the above embodiments of the user screening model obtaining method. The processor 72 may also be referred to as a CPU (Central Processing Unit). The processor 72 may be an integrated circuit chip having signal processing capabilities. The Processor 72 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. Additionally, processor 72 may be commonly implemented by a plurality of integrated circuit chips.
According to the scheme, an explicit user screening mechanism can be used in the financial information pushing process, blind pushing of subsequent financial information can be avoided, the accuracy of screening third-party users is improved, and the financial information pushing accuracy is improved.
Referring to fig. 8, fig. 8 is a schematic diagram of a memory device 80 according to an embodiment of the present application. The storage device 80 stores program instructions 81 capable of being executed by the processor, and the program instructions 81 are used for implementing the steps in any of the embodiments of the method for acquiring the user screening model or implementing the steps in any of the embodiments of the method for pushing financial information based on the user screening model.
According to the scheme, the registration information data, the browsing behavior information data and the financial behavior information data of the sample user can be fused to train the sample user data, so that the obtained user screening model can screen the user of the third party, the blind pushing of the subsequent financial information is avoided, the accuracy of screening the user of the third party is improved, and the accuracy of financial information pushing is improved.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Claims (10)
1. A method for obtaining a user screening model is characterized by comprising the following steps:
acquiring user data of a sample user, wherein the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user;
acquiring financial behavior information data corresponding to the sample user;
and training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model.
2. The method for acquiring the user screening model according to claim 1, wherein the process of determining the user tag data specifically includes:
pushing financial information to the sample user;
determining user tag data of the sample user based on the click condition of the sample user on the financial information;
or,
searching financial behavior information data corresponding to the sample user in a target database according to the sample user data;
and determining the user label data of the sample user according to the searched financial behavior information data of the sample user.
3. The method of claim 1, wherein before the initial model is trained by using the user data of the sample user and the financial behavior information data to obtain the user screening model, the method further comprises:
and eliminating the data of the sample user of which the financial behavior information data does not meet the preset condition.
4. The method for acquiring the user screening model according to claim 1, wherein the financial behavior information data includes credit information, debit information, and payment overdue information.
5. A financial information pushing method is characterized by comprising the following steps:
screening target users with financial requirements from users pushed by a third party by using a user screening model, wherein the user screening model is obtained by the acquisition method of the user screening model according to any one of claims 1 to 4;
and pushing financial information to the target user.
6. The method of claim 5, wherein the step of screening the target users with financial requirements from the users pushed by the third party by using the user screening model comprises:
screening the target users by using the screening model, and acquiring the financial demand level of each target user;
the pushing financial information to the target user comprises:
acquiring financial information corresponding to the financial demand level of the target user based on the financial demand level of the target user;
pushing the corresponding financial information to the target user, and/or recommending the target user to a financial institution.
7. An apparatus for obtaining a user screening model, comprising:
the system comprises a sample user acquisition module, a sample user acquisition module and a sample user management module, wherein the sample user acquisition module is used for acquiring user data of a sample user, the user data of the sample user comprises user tag data, registration information data and browsing behavior information data of the sample user, and the user tag data is used for representing the financial demand level of the user;
the user information acquisition module is used for acquiring financial behavior information data corresponding to the sample user;
and the training module is used for training an initial model by using the user data of the sample user and the financial behavior information data to obtain the user screening model.
8. A financial information pushing apparatus, comprising:
the screening module is used for screening target users with financial requirements from users pushed by a third party by using a user screening model, wherein the user screening model is obtained by the obtaining method of the user screening model according to any one of claims 1 to 4;
and the pushing module is used for pushing the financial information to the target user.
9. An electronic device, comprising a memory and a processor coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the method for acquiring a user screening model according to any one of claims 1 to 4 or the method for pushing financial information based on a user screening model according to any one of claims 5 to 6.
10. A storage device storing program instructions executable by a processor to implement the method for acquiring a user filtering model according to any one of claims 1 to 4 or the method for pushing financial information based on a user filtering model according to any one of claims 5 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911137349.9A CN112907266A (en) | 2019-11-19 | 2019-11-19 | User screening model acquisition method, financial information pushing method and related device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911137349.9A CN112907266A (en) | 2019-11-19 | 2019-11-19 | User screening model acquisition method, financial information pushing method and related device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112907266A true CN112907266A (en) | 2021-06-04 |
Family
ID=76104653
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911137349.9A Pending CN112907266A (en) | 2019-11-19 | 2019-11-19 | User screening model acquisition method, financial information pushing method and related device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112907266A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114418376A (en) * | 2022-01-14 | 2022-04-29 | 上海明胜品智人工智能科技有限公司 | Enterprise task issuing method and device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241427A (en) * | 2018-09-04 | 2019-01-18 | 中国平安人寿保险股份有限公司 | Information-pushing method, device, computer equipment and storage medium |
CN109325796A (en) * | 2018-08-13 | 2019-02-12 | 中国平安人寿保险股份有限公司 | Potential user's screening technique, device, computer equipment and storage medium |
WO2019153518A1 (en) * | 2018-02-08 | 2019-08-15 | 平安科技(深圳)有限公司 | Information pushing method and device, computer device and storage medium |
CN110135896A (en) * | 2019-04-23 | 2019-08-16 | 上海淇玥信息技术有限公司 | A kind of marketing message method for pushing, device, system and the recording medium of financial product |
-
2019
- 2019-11-19 CN CN201911137349.9A patent/CN112907266A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019153518A1 (en) * | 2018-02-08 | 2019-08-15 | 平安科技(深圳)有限公司 | Information pushing method and device, computer device and storage medium |
CN109325796A (en) * | 2018-08-13 | 2019-02-12 | 中国平安人寿保险股份有限公司 | Potential user's screening technique, device, computer equipment and storage medium |
CN109241427A (en) * | 2018-09-04 | 2019-01-18 | 中国平安人寿保险股份有限公司 | Information-pushing method, device, computer equipment and storage medium |
CN110135896A (en) * | 2019-04-23 | 2019-08-16 | 上海淇玥信息技术有限公司 | A kind of marketing message method for pushing, device, system and the recording medium of financial product |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114418376A (en) * | 2022-01-14 | 2022-04-29 | 上海明胜品智人工智能科技有限公司 | Enterprise task issuing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10699204B2 (en) | Knowledge discovery from belief networks | |
US10108919B2 (en) | Multi-variable assessment systems and methods that evaluate and predict entrepreneurial behavior | |
US20170178199A1 (en) | Method and system for adaptively providing personalized marketing experiences to potential customers and users of a tax return preparation system | |
CN106997549A (en) | The method for pushing and system of a kind of advertising message | |
CN112418932B (en) | Marketing information pushing method and device based on user tag | |
US11734728B2 (en) | Method and apparatus for providing web advertisements to users | |
CN108154379B (en) | Media information publishing method and device | |
US10685374B2 (en) | Exploration for search advertising | |
US11144939B2 (en) | Cross-device consumer identification and device type determination | |
CN113077276A (en) | Behavior data processing method and system, storage medium and processor | |
US11410203B1 (en) | Optimized management of online advertising auctions | |
CN112581226A (en) | Product recommendation method and system | |
CN113393299A (en) | Recommendation model training method and device, electronic equipment and storage medium | |
CN110717758B (en) | Abnormal transaction identification method and device | |
US9306958B2 (en) | Methods, systems and media for detecting non-intended traffic using co-visitation information | |
JP7344234B2 (en) | Method and system for automatic call routing without caller intervention using anonymous online user behavior | |
CN117951283A (en) | Portrait construction method, training method and related devices | |
US20190080208A1 (en) | System and method for learning from the images of raw data | |
CN112907266A (en) | User screening model acquisition method, financial information pushing method and related device | |
US20210019781A1 (en) | Omnichannel multivariate testing platform | |
CN110852338A (en) | User portrait construction method and device | |
CN113496005B (en) | Information management method and device, electronic equipment and storage medium | |
CN114662001A (en) | Resource interaction prediction model training method and device and resource recommendation method and device | |
CN112308639B (en) | Aging prediction method and device for target event | |
US20190114701A1 (en) | Smart mortgage-broker customer relationship management systems |
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 |