CN116467529A - Financial product recommendation method, device, server and storage medium - Google Patents
Financial product recommendation method, device, server and storage medium Download PDFInfo
- Publication number
- CN116467529A CN116467529A CN202310622997.3A CN202310622997A CN116467529A CN 116467529 A CN116467529 A CN 116467529A CN 202310622997 A CN202310622997 A CN 202310622997A CN 116467529 A CN116467529 A CN 116467529A
- Authority
- CN
- China
- Prior art keywords
- client
- payroll
- group
- screening
- recommended
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012216 screening Methods 0.000 claims abstract description 192
- 238000006243 chemical reaction Methods 0.000 claims abstract description 24
- 230000002787 reinforcement Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- 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
Abstract
The application provides a financial product recommendation method, a financial product recommendation device, a server and a storage medium. The method comprises the steps that a server obtains a screening strategy corresponding to a financial product to be recommended; the server obtains a customer group to be recommended according to the characteristic information of each payroll customer in the payroll customer group and the screening strategy corresponding to the financial products to be recommended; and recommending the financial products to be recommended to the user terminal set corresponding to the client group to be recommended by the server. Thus, the conversion rate of the customer group to be recommended to purchase the financial product is also high.
Description
Technical Field
The present disclosure relates to the field of big data, and in particular, to a financial product recommendation method, a financial product recommendation device, a server, and a storage medium.
Background
With the increasing level of living, more and more users tend to invest in financial (e.g., purchase funds, pay-in, and debt, etc.) to achieve the rise in personal assets. Specifically, the financial system receives a financial request sent by a user mainly in a passive mode, and performs corresponding transaction processing based on a financial product to be purchased in the financial request.
Further, the financial system may currently recommend similar financial products to each user based on the financial products that the user has purchased. Therefore, the current financial system can only passively receive the user financial request, or the similar financial product recommendation is carried out on the purchased financial product users in a scattered manner, namely, the recommended financial products are relatively single, and more diversified choices cannot be brought to the users.
Disclosure of Invention
The application provides a financial product recommending method, a financial product recommending device, a financial product recommending server and a financial product recommending storage medium, which are used for solving the problem that recommended financial products are relatively single and can not bring more diversified selections to users.
In a first aspect, the present application provides a financial product recommendation method, including: the method comprises the steps that a server obtains a screening strategy corresponding to a financial product to be recommended; the server obtains a customer group to be recommended according to the characteristic information of each payroll customer in the payroll customer group and the screening strategy corresponding to the financial products to be recommended; and recommending the financial products to be recommended to the user terminal set corresponding to the client group to be recommended by the server.
In one possible implementation manner, the server obtains a client group to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening policy corresponding to the financial product to be recommended, including: the server obtains characteristic parameters related to the screening strategy in the characteristic information of each payroll client in the payroll client group according to the screening strategy; determining a client group to which each payroll client belongs according to characteristic parameters related to the screening strategy in the characteristic information of each payroll client; the server acquires the client group matched with the screening parameters in the screening strategy from the client group to which the paying client belongs, and takes the matched client group as the client group to be recommended.
Because the client group to which the payroll client belongs is determined according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, the reliability of the determined client group to which the payroll client belongs is high. In addition, the reliability is further improved because the client group to be recommended is a client group which is acquired from the client group to which the paying client belongs and is matched with the screening parameters in the screening strategy.
In one possible implementation manner, the server obtains feature parameters related to the screening policy from feature information of each payroll client in the payroll client group according to the screening policy; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening strategy comprises the enterprise category screening sub-strategy, acquiring the average payroll value in a preset historical time period in the characteristic information of each payroll client in the payroll client group;
the server determines enterprise category groups to which each payroll client belongs according to payroll average values in preset historical time periods in the characteristic information of each payroll client respectively;
The server obtains the client group matched with the screening parameters in the screening strategy, and takes the matched client group as the client group to be recommended, and the method comprises the following steps:
the server determines a sub-enterprise class group matched with the enterprise class screening parameters in the affiliated enterprise class screening sub-strategy from the enterprise class group;
and the server takes the client group of the agent paying clients belonging to the sub-enterprise class group as the client group to be recommended.
In this way, the enterprise class group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
In one possible implementation manner, the server obtains feature parameters related to the screening policy from feature information of each payroll client in the payroll client group according to the screening policy; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening strategy further comprises a net value screening sub-strategy, acquiring customer total assets in characteristic information of each payroll customer in the payroll customer group;
the server determines net value hierarchy groups to which each payroll client belongs according to the total client assets in the characteristic information of each payroll client in the payroll client groups;
The server obtains the client group matched with the screening parameters in the screening strategy, and takes the matched client group as the client group to be recommended, and the method comprises the following steps:
the server determines a sub-equity hierarchy group matched with equity class screening parameters in the equity screening sub-strategy from the equity hierarchy group;
the server takes the client group of the generation payoff client of the home sub-net value hierarchical group as the client group to be recommended.
In this way, the net worth hierarchical group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
In one possible implementation manner, the server obtains feature parameters related to the screening policy from feature information of each payroll client in the payroll client group according to the screening policy; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening strategy further comprises a professional class screening sub-strategy, acquiring professions in characteristic information of each payroll client in the payroll client group;
the server determines the professional class group to which each payroll client belongs according to the profession in the characteristic information of each payroll client in the payroll client group;
The server obtains the client group matched with the screening parameters in the screening strategy, and takes the matched client group as the client group to be recommended, and the method comprises the following steps:
the server determines a sub-occupation class group matched with the occupation class screening parameters in the belonging occupation class screening sub-strategy from the occupation class group;
and the server takes the client group of the generation payroll client belonging to the sub-occupation class group as the client group to be recommended.
In this way, the professional class group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
In one possible implementation manner, the server obtains feature parameters related to the screening policy from feature information of each payroll client in the payroll client group according to the screening policy; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening policy further comprises a customer holding asset screening sub-policy, acquiring customer holding assets in characteristic information of each payroll customer in the payroll customer group;
The server determines a holding level group to which each payroll client belongs according to the client holding assets in the characteristic information of each payroll client in the payroll client group;
the server obtains the client group matched with the screening parameters in the screening strategy, and takes the matched client group as the client group to be recommended, and the method comprises the following steps:
the server determines a sub-holding level class group matched with the holding level screening parameters in the belonging holding level screening sub-strategy from the holding level group;
the server takes the client group of the generation payroll client belonging to the sub-holding level class group as the client group to be recommended.
In this way, the holding level group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
In one possible implementation manner, after the server recommends the financial product to be recommended to the user terminal set corresponding to the client group to be recommended, the method provided by the application further includes:
the server receives feedback results from the user terminal set; wherein the feedback result is sent by the user terminal set in response to feedback operation of the user on the financial product;
The server counts the first number of the user terminals in the user terminal set and the second number of the user terminals for sending the feedback result;
the server determines the conversion rate of the recommended financial products according to the first quantity and the second quantity;
when the conversion rate is lower than a set threshold value, the server updates a screening strategy corresponding to the financial product according to the reinforcement learning model; so that
And the server returns to execute the step of acquiring the client group to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening strategy corresponding to the financial product to be recommended until the conversion rate is greater than or equal to the set threshold value.
In this way, the screening strategy may be continually updated until the conversion rate is greater than or equal to the set threshold value, such that the conversion rate is greater than or equal to the set threshold value, and thus the reliability of the recommended financial product is higher.
In a second aspect, the present application further provides a financial product recommendation device, including: the screening strategy acquisition unit is used for acquiring a screening strategy corresponding to the financial product to be recommended; the to-be-recommended client group acquisition unit is used for acquiring the to-be-recommended client group according to the characteristic information of each generation of payroll client in the generation of payroll client group and the screening strategy corresponding to the to-be-recommended financial product; and the product recommending unit is used for recommending the financial products to be recommended to the user terminal set corresponding to the client group to be recommended.
In a third aspect, the present application further provides a server, including: a processor, a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored in the memory to implement the method as provided in the first aspect of the present application.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are adapted to carry out the method as provided in the first aspect of the present application.
According to the financial product recommending method, the device, the server and the storage medium, the server can acquire the client group to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening strategy corresponding to the financial product to be recommended. It can be appreciated that the characteristic information of the payroll customer may be used to represent the income level of the customer, so that the reliability of the determined customer group to be recommended is high according to the screening policy corresponding to the financial product to be recommended and the income level of the customer. And finally, recommending the financial products to be recommended to a user terminal set corresponding to the client group to be recommended by the server, wherein the recommended financial products can bring more diversified selections to the user, so that the conversion rate of the recommended financial products is high.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is an interaction schematic diagram of a server and a terminal device provided in an embodiment of the present application;
FIG. 2 is a flowchart of a financial product recommendation method according to an embodiment of the present disclosure;
FIG. 3 is a second flowchart of a financial product recommendation method according to an embodiment of the present disclosure;
FIG. 4 is one of the specific flowcharts of S302-S303 provided in the embodiments of the present application;
FIG. 5 is a second flowchart of S302-S303 according to an embodiment of the present application;
FIG. 6 is a third flowchart of the steps S302-S303 according to the embodiment of the present application;
FIG. 7 is a fourth flowchart of the embodiment of S302-S303 provided in the present application;
FIG. 8 is a third flowchart of a financial product recommendation method according to an embodiment of the present disclosure;
FIG. 9 is a functional block diagram of a financial product recommendation device according to an embodiment of the present disclosure;
fig. 10 is a circuit connection block diagram of a server according to an embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
It should be noted that the method and apparatus for recommending financial products, the server and the storage medium provided in the present application may be used in the big data field, and may also be used in any field other than the big data field, and the application fields of the method, apparatus, server and storage medium for recommending financial products provided in the present application are not limited.
With the increasing level of living, more and more users tend to invest in financial (e.g., purchase funds, pay-in, and debt, etc.) to achieve the rise in personal assets. Generally, enterprises such as investment companies or banks providing financial services can recommend financial products to users through network popularization, off-line popularization and other modes. However, the reliability of the financial products recommended to the user in the above manner is low. That is, after recommending the financial product to the user, the conversion rate of purchasing the financial product is low.
Based on the technical problems, the invention concept of the application is as follows: the server may determine the financial product to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening policy corresponding to the financial product to be recommended. And recommending the financial products to be recommended to the user terminal set corresponding to the client group to be recommended by the server.
The application provides a financial product recommendation method, a financial product recommendation device, a financial product recommendation server and a financial product recommendation storage medium, and aims to solve the technical problems in the prior art.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The embodiment of the application provides a financial product recommendation method, which is applied to a server 101. Fig. 1 is an interaction schematic diagram of a server and a terminal device provided in an embodiment of the present application. As shown in fig. 1, a server 101 is communicatively connected to a plurality of user terminals 102. Fig. 2 is a flowchart of a financial product recommendation method according to an embodiment of the present application. As shown in fig. 2, the financial product recommendation method provided in the embodiment of the present application includes:
S201: the server 101 acquires a screening policy corresponding to a financial product to be recommended.
The financial products may be financial products, fund products, national debt products, financial lectures, etc., and are not limited herein. The screening policy corresponding to the financial product may be more than 2W as a payroll average, and the enterprise is a public institution, a high-new enterprise, a national enterprise, and/or more than 100W as a total asset, and/or more than 15W as a holding asset, which is not limited herein.
S202: the server 101 obtains a customer group to be recommended according to the characteristic information of each payroll customer in the payroll customer group and the screening policy corresponding to the financial product to be recommended.
Illustratively, a payroll customer refers to a customer whose bank issues salary to the affiliated bank card monthly. The characteristic information of the payroll client may include, but is not limited to, a professional of the payroll client, a payroll average over a preset history period (e.g., 1 year or half year), a total asset of the payroll client, a holding asset of the payroll client, etc.
For example, the characteristic information of the payroll client a includes that the enterprise is a public institution, the payroll average value in the preset history period is 2.5W, the total asset 110W of the payroll client a, and the holding asset of the payroll client a is 20W; the characteristic information of the payroll client B comprises that an enterprise to which the payroll client B belongs is a public institution, the payroll average value in a preset historical time period is 1.5W, the total asset of the payroll client B is 50W, and the holding asset of the payroll client B is 5W; the characteristic information of the payroll client C comprises that the enterprise is a national enterprise, the payroll average value in a preset history period is 5W, the total asset of the payroll client is 150W, and the holding asset of the payroll client is 50W. When the screening policy corresponding to the financial product can be more than 2W of the average value of the generation, the enterprise is a public institution, a high-new enterprise, a national enterprise, and/or the total asset is more than 100W, and/or the holding asset is more than 15W, the acquired client group to be recommended comprises a generation client a and a generation client C.
S203: the server 101 recommends the financial products to be recommended to the user terminal 102 set corresponding to the client group to be recommended.
For example, on the basis of S202 described above, when the payroll client a and the payroll client C are included in the client group to be recommended, the mobile phone numbers associated with the payroll client a and the payroll client C are found, and the short messages associated with the financial products are collectively sent to the user terminals 102 of the payroll client a and the payroll client C according to the mobile phone numbers associated with the payroll client a and the payroll client C to recommend the financial products.
For another example, on the basis of S202 described above, when the payroll client a and the payroll client C are included in the client group to be recommended, the account numbers of the instant chat applications associated with the payroll client a and the payroll client C are found, and the messages (such as the circle of friends, QQ space) associated with the financial products are sent to the user terminals 102 corresponding to the payroll client a and the payroll client C in a set according to the account numbers of the instant chat applications associated with the payroll client a and the payroll client C, so as to recommend the financial products.
In summary, according to the financial product recommendation method provided by the present application, the server 101 may obtain the customer group to be recommended according to the characteristic information of each payroll customer in the payroll customer group and the screening policy corresponding to the financial product to be recommended. As can be appreciated, the characteristic information of the payroll customer may be used to represent the income level of the customer; thus, the reliability of the determined customer group to be recommended is high according to the screening strategy corresponding to the financial product to be recommended and the income level of the customer. Finally, the server 101 recommends the financial products to be recommended to the user terminal 102 set corresponding to the client group to be recommended, so that the recommended financial products can bring more diversified choices to the user, and the conversion rate of the recommended financial products is high.
Fig. 3 is a schematic diagram of a financial product recommendation method according to an embodiment of the present application, based on an embodiment corresponding to fig. 2. As shown in fig. 3, S202 may specifically include:
s301: the server 101 obtains, according to the screening policy, feature parameters related to the screening policy from feature information of each payroll client in the payroll client group.
For example, the screening policy corresponding to the financial product may be 2W or more of the average of the generation, the enterprise is a public institution, a high-new enterprise, and a national enterprise, and/or 100W or more of the total asset, and/or 15W or more of the holding asset, which is not limited herein. The characteristic information of the payroll client includes, but is not limited to, the identity card number, sex, birthday, payroll average, affiliated enterprise, total asset, and holding asset of the client.
Thus, the obtained characteristic parameters related to the screening policy are the salary mean value of the salary client, the enterprise, the total asset and the holding asset.
S302: the server 101 determines a client group to which each payroll client belongs according to the feature parameters related to the screening policy in the feature information of each payroll client.
For example, the characteristic information of the payroll client a includes that the enterprise is a public institution, the payroll average value in the preset history period is 2.5W, the total asset 110W of the payroll client, and the holding asset of the payroll client is 20W; the characteristic information of the payroll client B comprises that an enterprise to which the payroll client B belongs is a public institution, the payroll average value in a preset historical time period is 1.5W, the total asset of the payroll client is 50W, and the holding asset of the payroll client is 5W; the characteristic information of the payroll client C comprises that the enterprise is a national enterprise, the payroll average value in a preset history period is 5W, the total asset of the payroll client is 150W, and the holding asset of the payroll client is 50W. When the screening policy corresponding to the financial product can be more than 2W of the average generation cost, the enterprise is a public institution, a high and new enterprise, a national enterprise, and/or the total asset is more than 100W, and/or the holding asset is more than 15W, the generation cost client a and the generation cost client C are included in the client group to be recommended. Thus, it can be determined that the payroll client a and payroll client C belong to a high net value client group, and the payroll client B is a medium net value client group.
S303: the server 101 obtains a client group matching with the screening parameters in the screening policy from the client groups to which the payroll client belongs, and takes the matched client group as the client group to be recommended.
The screening parameters of the screening policy corresponding to the financial product may include: the average value of the generation is more than 2W, and the enterprises are public institutions, high and new enterprises and national enterprises, and/or the total assets are more than 100W, and/or the holding assets are 15W.
Based on S302 described above, the customers satisfying the screening parameters of the screening policy corresponding to the financial product are the payroll customer a and the payroll customer C, and therefore the payroll customer a and the payroll customer C are taken as the customer group to be recommended.
Because the client group to which the payroll client belongs is determined according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, the reliability of the determined client group to which the payroll client belongs is high. In addition, the reliability is further improved because the client group to be recommended is a client group which is acquired from the client group to which the paying client belongs and is matched with the screening parameters in the screening strategy.
On the basis of the embodiment corresponding to fig. 2, as shown in fig. 4, fig. 4 is a specific flowchart of S302-S303 provided in the embodiment of the present application. The steps S302 to S303 include:
S401: if the server 101 determines that the screening policy includes the enterprise category screening sub-policy, the server obtains a payroll average value in a preset history period in the feature information of each payroll client in the payroll client group.
S402: the server 101 determines, according to the average value of the payroll in the preset history period in the feature information of each payroll client, the enterprise category group to which each payroll client belongs.
For example, if the average value of the payroll client a in the preset historical period (for example, 1 year) is 8K, determining the enterprise class group to which the payroll client a belongs as a factory; and if the average value of the payroll client B in the preset historical time period (such as 1 year) is 2W, determining that the enterprise class group to which the payroll client B belongs is a high-new enterprise.
S403: the server 101 determines, from among the business category groups, a sub-business category group that matches the business category screening parameters in the belonging business category screening sub-policy.
Based on S402 described above, since the enterprise class group to which the payroll client B belongs is a high-new enterprise. In this way, if the enterprise class screening parameters in the enterprise class screening sub-policy include the high-new enterprise, the public institution and the national enterprise, determining the sub-enterprise class group matched with the enterprise class screening parameters in the enterprise class screening sub-policy is: payroll client B.
S404: the server 101 takes a client group of the payroll client belonging to the sub-enterprise category group as a client group to be recommended.
Based on S403, the sub-business category group matched with the business category filtering parameter in the business category filtering sub-policy is: and (3) taking the payroll client B as a client group to be recommended.
In this way, the enterprise class group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
Fig. 5 is a specific flowchart of S302-S303 provided in the embodiment of the present application, based on the corresponding embodiment of fig. 2. As shown in fig. 5, S302 to S303 described above include:
s501: if the server 101 determines that the screening policy further includes a net value screening sub-policy, then the total client assets in the characteristic information of each payroll client in the payroll client group are obtained.
For example, the total client asset in the characteristic information of the payroll client a is 10W, the total client asset in the characteristic information of the payroll client B is 50W, and the total client asset in the characteristic information of the payroll client C is 100W.
S502: the server 101 determines a net worth hierarchy group to which each payroll client belongs, based on the client total assets in the characteristic information of each payroll client in the payroll client group, respectively.
Illustratively, based on S501 described above, payroll client a may be determined as a low net worth group, payroll client B may be determined as a medium net worth group, and payroll client C may be determined as a high net worth group.
S503: the server 101 determines, from the equity tier groups, sub-equity tier groups that match equity category screening parameters in the equity screening sub-policy to which it belongs.
When the net value class screening parameter in the net value screening sub-strategy is a high net value hierarchy group, the generation payroll client C matched with the net value class screening parameter in the net value screening sub-strategy is determined to be the high net value hierarchy group.
S504: the server 101 regards a client group of the payroll client belonging to the sub-equity hierarchy group as a client group to be recommended.
On the basis of S503, the payroll client C belongs to the high net hierarchy group, and the payroll client C is taken as the client group to be recommended. In this way, the net worth hierarchical group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
Fig. 6 is a specific flowchart of S302-S303 provided in the embodiment of the present application, based on the corresponding embodiment of fig. 2. As shown in fig. 6, S302 to S303 described above include:
S601: if the server 101 determines that the filtering policy further includes a job class filtering sub-policy, a job in the feature information of each payroll client in the payroll client group is acquired.
For example, the profession in the characteristic information of the payroll client a is a worker, the professional in the characteristic information of the payroll client B is an engineer, and the professional in the characteristic information of the payroll client C is a public servicer.
S602: the server 101 determines, based on the profession in the feature information of each payroll client in the payroll client group, the professional class group to which each payroll client belongs, respectively.
Based on the above S601, the professional class group of the payroll client a is blue-collar, the professional class group of the payroll client B is white-collar, and the professional class group of the payroll client C is in the system.
S603: the server 101 determines, from among the occupation category groups, a sub-occupation category group that matches the occupation category screening parameters in the belonging occupation category screening sub-policy.
When the professional class screening parameters in the professional class screening sub-strategy are white collar and in-system, the sub-professional class group matched with the professional class screening parameters in the professional class screening sub-strategy is white collar and in-system.
In this way, the professional class group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
S604: the server 101 takes a client group of the agent payroll client belonging to the sub-occupation category group as a client group to be recommended.
On the basis of S602 described above, the payroll client B and the payroll client C are taken as the client groups to be recommended.
In this way, the holding level group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
Fig. 7 is a specific flowchart of S302-S303 provided in the embodiment of the present application, based on the corresponding embodiment of fig. 2. As shown in fig. 7, S302 to S303 may include:
s701: if the server 101 determines that the screening policy further includes a customer holding asset screening sub-policy, then the customer holding asset in the characteristic information of each payroll customer in the payroll customer group is obtained.
For example, the customer holding asset in the characteristic information of the payroll customer a is 100W, the customer holding asset in the characteristic information of the payroll customer B is 120W, and the customer holding asset in the characteristic information of the payroll customer C is 20W.
The holding property may be classified into a type of a product of a holding target bank, whether it is a loan of the target bank, a client of an information card, or the like, and is not limited herein.
S702: the server 101 determines a holding level group to which each payroll client belongs, based on the client holding assets in the characteristic information of each payroll client in the payroll client group, respectively.
Based on the above-described S701, it can be confirmed that the holding level group to which the payroll client a and the payroll client B belong is a high net holding level group and the holding level group to which the payroll client C belongs is a low net holding level group.
S703: the server 101 determines, from among the holding level groups, a sub-holding level class group that matches the holding level screening parameters in the belonging holding level screening sub-policy.
And confirming sub-holding level class groups matched with the holding level screening parameters in the holding level screening sub-policies of the generation salary client A and the generation salary client B when the holding level screening parameters in the holding level screening sub-policies of the generation salary client A and the generation salary client B are the high net value holding level group and the medium net value holding level group.
S704: the server 101 takes a client group of the generation payroll client belonging to the sub-holding level class group as a client group to be recommended.
Based on S703 described above, the payroll client a and the payroll client B can be regarded as a client group to be recommended.
In this way, the holding level group to which the payroll client belongs can be accurately determined, and the client group to be recommended can be accurately screened from the client groups of the payroll client.
In addition, on the basis of the embodiment corresponding to fig. 2, after S203, fig. 8 is a flowchart of a financial product recommendation method provided in the embodiment of the present application. As shown in fig. 8, the method provided in the embodiment of the present application further includes:
s801: the server receives feedback results from the user terminal set; and the feedback result is sent by the user terminal set in response to the feedback operation of the user on the financial product.
When each user browses to the recommended financial product at the personal user terminal 102, feedback operations (such as purchasing, consultation, etc.) may be performed on the financial product, which may be omitted. Thus, the server 101 receives a feedback result transmitted in response to a feedback operation of the user on the financial product by a part of the user terminals 102 in the set of user terminals 102.
S802: the server 101 counts a first number of user terminals 102 in the set of user terminals 102 and a second number of user terminals 102 that send feedback results.
For example, when the first number of user terminals 102 of the set of user terminals 102 is 1000, the second number of user terminals 102 that send feedback results may be 400.
S803: the server 101 determines a conversion rate of the recommended financial product based on the first quantity and the second quantity.
Based on S202 described above, since the first number of user terminals 102 of the set of user terminals 102 is 1000 and the second number of user terminals 102 transmitting the feedback result may be 400, the conversion rate of the recommended financial product may be determined to be 40%.
S804: when the conversion rate is lower than the set threshold, the server 101 updates the screening policy corresponding to the financial product according to the reinforcement learning model, and returns to execution S201.
For example, the set threshold may be 60%, and when the conversion rate 40% is lower than 60%, it is indicated that the reliability of the screening policy corresponding to the financial product is low, and thus, the screening policy corresponding to the financial product may be updated using the reinforcement learning model until the conversion rate is greater than or equal to the set threshold. The method comprises the steps of selecting a screening strategy corresponding to a financial product, updating the screening strategy corresponding to the financial product to obtain an action of the reinforced learning model, and obtaining a conversion rate to obtain rewards of the reinforced learning module, wherein the screening strategy corresponding to the financial product is the state of the reinforced learning model.
In this way, the screening strategy may be continually updated until the conversion rate is greater than or equal to the set threshold value, such that the conversion rate is greater than or equal to the set threshold value, and thus the reliability of the recommended financial product is higher.
Referring to fig. 9, the embodiment of the present application further provides a financial product recommendation device 900, and it should be noted that, for brevity, the basic principle and the technical effects of the financial product recommendation device 900 provided in the embodiment of the present application are the same as those of the embodiment corresponding to fig. 2, and for brevity, reference may be made to the corresponding contents in the embodiment of the present application. The financial product recommendation device 900 provided by the present application includes a screening policy acquisition unit 901, a to-be-recommended client group acquisition unit 902, and a product recommendation unit 903, wherein,
the screening policy obtaining unit 901 is configured to obtain a screening policy corresponding to a financial product to be recommended.
The to-be-recommended client group acquiring unit 902 is configured to acquire a to-be-recommended client group according to the characteristic information of each generation payroll client in the generation payroll client group and the screening policy corresponding to the to-be-recommended financial product.
The product recommending unit 903 is configured to recommend a financial product to be recommended to a user terminal set corresponding to a customer group to be recommended.
In a possible implementation manner, the to-be-recommended client group obtaining unit 902 is specifically configured to obtain, according to a screening policy, a characteristic parameter related to the screening policy in the characteristic information of each payroll client in the payroll client group; determining a client group to which each payroll client belongs according to characteristic parameters related to the screening strategy in the characteristic information of each payroll client; and acquiring a client group matched with the screening parameters in the screening strategy from the client group to which the paying client belongs, and taking the matched client group as the client group to be recommended.
In a possible implementation manner, the to-be-recommended client group obtaining unit 902 is specifically configured to obtain an average value of the payroll in a preset historical time period in the characteristic information of each payroll client in the payroll client group if it is determined that the screening policy includes the enterprise class screening sub-policy; determining enterprise class groups to which each payroll client belongs according to payroll means in a preset historical time period in the characteristic information of each payroll client; determining a sub-enterprise class group matched with the enterprise class screening parameters in the affiliated enterprise class screening sub-strategy from the enterprise class group; and taking the client group of the agent paying clients belonging to the sub-enterprise class group as the client group to be recommended.
In a possible implementation manner, the to-be-recommended client group obtaining unit 902 is specifically configured to obtain a client total asset in the feature information of each payroll client in the payroll client group if the screening policy is determined to further include a net value screening sub-policy, and determine a net value hierarchy group to which each payroll client belongs according to the client total asset in the feature information of each payroll client in the payroll client group; determining a sub-equity hierarchy group matched with equity category screening parameters in the equity screening sub-strategy from the equity hierarchy group; and taking the client group of the generation payoff clients belonging to the sub-net value hierarchical group as the client group to be recommended.
In a possible implementation manner, the to-be-recommended client group obtaining unit 902 is specifically configured to obtain the profession in the feature information of each payroll client in the payroll client group if it is determined that the screening policy further includes a professional class screening sub-policy; determining the professional class group to which each payroll client belongs according to the profession in the characteristic information of each payroll client in the payroll client group; determining a sub-occupation class group matched with the occupation class screening parameters in the belonging occupation class screening sub-strategy from the occupation class group; and taking the client group of the generation payoff clients belonging to the sub-occupation class group as the client group to be recommended.
In a possible implementation manner, the to-be-recommended client group obtaining unit 902 is specifically configured to obtain the client holding asset in the characteristic information of each of the payroll clients in the payroll client group if it is determined that the screening policy further includes a client holding asset screening sub-policy; determining a holding level group to which each payroll client belongs according to the client holding assets in the characteristic information of each payroll client in the payroll client group; determining a sub-holding level class group matched with the holding level screening parameters in the belonging holding level screening sub-strategy from the holding level group; and taking the client group of the generation paying clients belonging to the sub-holding level class group as the client group to be recommended.
In one possible implementation, the financial product to be recommended is to be recommended at the server. The apparatus 900 provided in the embodiment of the present application further includes: and the information receiving unit is used for receiving feedback results from the user terminal set, wherein the feedback results are sent by the user terminal set in response to feedback operation of the user on the financial product.
And the data statistics unit is used for counting the first number of the user terminals in the user terminal set and the second number of the user terminals for sending the feedback result.
And the conversion rate determining unit is used for determining the conversion rate of the recommended financial product according to the first quantity and the second quantity.
And the data updating unit is used for updating the screening strategy corresponding to the financial product according to the reinforcement learning model when the conversion rate is lower than the set threshold value.
And the operation return unit is used for returning to execute the step of acquiring the client group to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening strategy corresponding to the financial product to be recommended until the conversion rate is greater than or equal to the set threshold value.
FIG. 10 is a block diagram of a server, which may include one or more of the following components, according to an example embodiment: processor 1002, memory 1004, power supply component 1006, and communication component 1016.
The processor 1002 generally controls the overall operation of the apparatus 1000, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processor 1002 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processor 1002 may include one or more modules to facilitate interactions between the processor 1002 and other components. In particular, the processor 1002 may be configured to implement a method of processing transaction data as provided in fig. 2 in accordance with an embodiment of the present application.
The memory 1004 is configured to store various types of data to support operations at the apparatus 1000. Examples of such data include instructions for any application or method operating on the device 1000, contact data, phonebook data, messages, pictures, videos, and the like. The memory 1004 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 1006 provides power to the various components of the device 1000. The power components 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1000.
The communication component 1016 is configured to facilitate communication between the apparatus 1000 and other devices, either wired or wireless. The device 1000 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 1016 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel.
In an exemplary embodiment, the apparatus 1000 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1004, including instructions executable by processor 820 of apparatus 1000 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
The embodiments of the present application also provide a non-transitory computer readable storage medium, which when executed by a processor of a server, enables the server to perform the above-described transaction data processing method.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method of recommending a financial product, the method comprising:
the method comprises the steps that a server obtains a screening strategy corresponding to a financial product to be recommended;
the server acquires a client group to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening strategy corresponding to the financial product to be recommended;
and recommending the financial products to be recommended to the user terminal set corresponding to the client group to be recommended by the server.
2. The method of claim 1, wherein the server obtains a customer group to be recommended according to the characteristic information of each payroll customer in the payroll customer group and the screening policy corresponding to the financial product to be recommended, and the method comprises:
the server acquires characteristic parameters related to the screening strategy from the characteristic information of each payroll client in the payroll client group according to the screening strategy; determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client;
And the server acquires a client group matched with the screening parameters in the screening strategy from the client group to which the agent payoff client belongs, and takes the matched client group as the client group to be recommended.
3. The method of claim 2, wherein the server obtains, according to the screening policy, feature parameters associated with the screening policy from feature information of each payroll client in the payroll client group; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening policy comprises the enterprise category screening sub-policy, acquiring a payroll average value in a preset historical time period in the characteristic information of each payroll client in the payroll client group;
the server determines enterprise category groups to which each payroll client belongs according to payroll means in a preset historical time period in the characteristic information of each payroll client;
the server obtains a client group matched with the screening parameters in the screening policy, and takes the matched client group as the client group to be recommended, including:
The server determines a sub-enterprise class group matched with the enterprise class screening parameters in the belonging enterprise class screening sub-strategy from the enterprise class group;
and the server takes the client group of the agent payoff client belonging to the sub-enterprise class group as the client group to be recommended.
4. The method of claim 2, wherein the server obtains, according to the screening policy, feature parameters associated with the screening policy from feature information of each payroll client in the payroll client group; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening policy further comprises a net value screening sub-policy, acquiring customer total assets in characteristic information of each payroll customer in the payroll customer group;
the server determines net value hierarchical groups to which each payroll client belongs according to the client total assets in the characteristic information of each payroll client in the payroll client groups respectively;
the server obtains a client group matched with the screening parameters in the screening policy, and takes the matched client group as the client group to be recommended, including:
The server determines a sub-equity hierarchy group matched with equity category screening parameters in the equity screening sub-strategy from the equity hierarchy group;
the server takes a client group of the payroll client belonging to the sub-net value hierarchical group as a client group to be recommended.
5. The method of claim 2, wherein the server obtains, according to the screening policy, feature parameters associated with the screening policy from feature information of each payroll client in the payroll client group; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening policy further comprises a professional class screening sub-policy, acquiring professions in the characteristic information of each payroll client in the payroll client group;
the server determines the professional class group to which each payroll client belongs according to the profession in the characteristic information of each payroll client in the payroll client group;
the server obtains a client group matched with the screening parameters in the screening policy, and takes the matched client group as the client group to be recommended, including:
The server determines a sub-occupation class group matched with the occupation class screening parameters in the belonging occupation class screening sub-strategy from the job class group;
and the server takes the client group of the agent payoff client belonging to the sub-occupation class group as the client group to be recommended.
6. The method of claim 2, wherein the server obtains, according to the screening policy, feature parameters associated with the screening policy from feature information of each payroll client in the payroll client group; and determining a client group to which each payroll client belongs according to the characteristic parameters related to the screening strategy in the characteristic information of each payroll client, comprising:
if the server determines that the screening policy further comprises a customer holding asset screening sub-policy, acquiring customer holding assets in characteristic information of each payroll customer in the payroll customer group;
the server determines a holding level group to which each payroll client belongs according to the client holding assets in the characteristic information of each payroll client in the payroll client group;
the server obtains a client group matched with the screening parameters in the screening policy, and takes the matched client group as the client group to be recommended, including:
The server determines a sub-holding level class group matched with the holding level screening parameters in the belonging holding level screening sub-strategy from the holding level group;
and the server takes the client group of the payroll client belonging to the sub-holding level class group as the client group to be recommended.
7. The method according to any one of claims 1-6, wherein after the server recommends the financial product to be recommended to the set of user terminals corresponding to the client group to be recommended, the method further comprises:
the server receives feedback results from the user terminal set; wherein the feedback result is sent by the user terminal set in response to feedback operation of the user on the financial product;
the server counts the first number of user terminals in the user terminal set and the second number of user terminals for sending the feedback result;
the server determines the conversion rate of recommending the financial product according to the first quantity and the second quantity;
when the conversion rate is lower than a set threshold value, the server updates a screening strategy corresponding to the financial product according to the reinforcement learning model;
And the server returns to execute the step of acquiring the client group to be recommended according to the characteristic information of each payroll client in the payroll client group and the screening strategy corresponding to the financial product to be recommended until the conversion rate is greater than or equal to the set threshold value.
8. A financial product recommendation device, the device comprising:
the screening strategy acquisition unit is used for acquiring a screening strategy corresponding to the financial product to be recommended;
the to-be-recommended client group acquisition unit is used for acquiring a to-be-recommended client group according to the characteristic information of each generation of payroll client in the generation of payroll client group and the screening strategy corresponding to the to-be-recommended financial product;
and the product recommending unit is used for recommending the financial products to be recommended to the user terminal set corresponding to the client group to be recommended.
9. A server, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310622997.3A CN116467529A (en) | 2023-05-29 | 2023-05-29 | Financial product recommendation method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310622997.3A CN116467529A (en) | 2023-05-29 | 2023-05-29 | Financial product recommendation method, device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116467529A true CN116467529A (en) | 2023-07-21 |
Family
ID=87175626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310622997.3A Pending CN116467529A (en) | 2023-05-29 | 2023-05-29 | Financial product recommendation method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116467529A (en) |
-
2023
- 2023-05-29 CN CN202310622997.3A patent/CN116467529A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325729B (en) | Method and server for generating electronic contract | |
| CN108805632B (en) | Charging method and device | |
| US10291789B2 (en) | Sharing data and points with group members | |
| CN110597919A (en) | Data management method, device and equipment based on block chain and storage medium | |
| CN110706093A (en) | Accounting processing method and device | |
| US20150038181A1 (en) | Short Code Management for Messaging Campaigns | |
| CN111209060A (en) | Capability development platform processing method and device | |
| CN114997448A (en) | Service processing method and device | |
| CN114185941A (en) | Report data query method and device, electronic equipment and storage medium | |
| CN110300222B (en) | Short message display method, system, terminal equipment and computer readable storage medium | |
| WO2020135393A1 (en) | Nuisance call prevention method and device, terminal, and storage medium | |
| CN112035676A (en) | User operation behavior knowledge graph construction method and device | |
| CN116467529A (en) | Financial product recommendation method, device, server and storage medium | |
| CN114140203A (en) | Data determination method and device, electronic equipment and storage medium | |
| WO2022038455A1 (en) | System and method for network usage product provisioning | |
| KR102107454B1 (en) | System for multiplication of financial payment networks, method for financial services using the same and computer program for the same | |
| CN112102058A (en) | Management system parameter configuration method and device | |
| CN109741055A (en) | Blacklist call method, device, server and storage medium | |
| CN111429125A (en) | Account management method and device, storage medium and electronic equipment | |
| CN115665074B (en) | Message flow-limiting sending method, device, equipment and storage medium | |
| US10778849B2 (en) | Customized service plan generation | |
| US20180302348A1 (en) | System And Method For Parsing A Natural Language Communication From A User And Automatically Generating A Response | |
| CN114240649A (en) | Fee deduction method, fee deduction device, computer equipment, storage medium and program product | |
| CN116681146A (en) | Financial business reservation method, device, server and storage medium | |
| EP3621006A1 (en) | A method and apparatus for extended workforce management |
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 |