CN110223107B - Reference advertisement determination method, device and equipment based on similar objects - Google Patents

Reference advertisement determination method, device and equipment based on similar objects Download PDF

Info

Publication number
CN110223107B
CN110223107B CN201910432595.0A CN201910432595A CN110223107B CN 110223107 B CN110223107 B CN 110223107B CN 201910432595 A CN201910432595 A CN 201910432595A CN 110223107 B CN110223107 B CN 110223107B
Authority
CN
China
Prior art keywords
reference advertisement
target
weight
advertisement
objects
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.)
Active
Application number
CN201910432595.0A
Other languages
Chinese (zh)
Other versions
CN110223107A (en
Inventor
朱江波
张立强
丁秀梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN201910432595.0A priority Critical patent/CN110223107B/en
Publication of CN110223107A publication Critical patent/CN110223107A/en
Application granted granted Critical
Publication of CN110223107B publication Critical patent/CN110223107B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides a reference advertisement determination method, a reference advertisement determination device and reference advertisement determination equipment based on similar objects, wherein the method comprises the following steps: determining similarity between each object in the plurality of objects according to the transaction data of the plurality of objects; establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between the objects in the plurality of objects; and under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, adjusting the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being more than or equal to a first preset threshold value or the weight of the reference advertisement. By the scheme, the difference and the similarity among the objects are comprehensively considered, so that the reference advertisement in the established reference advertisement set has more reference value, and the matching degree between the reference advertisement set and the objects and the conversion rate of bank products are improved.

Description

Reference advertisement determination method, device and equipment based on similar objects
Technical Field
The present application relates to the field of computer processing technologies, and in particular, to a method, an apparatus, and a device for determining a reference advertisement based on a similar object.
Background
In the existing mode of determining advertisements to be delivered to customers in banks, the advertisements to be delivered to each customer are determined according to the business requirements of the banks, and the advertisements to be delivered are determined only according to the business requirements of the banks, so that the advertisements to be delivered do not accord with the actual requirements of different customers, and the potential requirements of different customers cannot be discovered. The existing mode of determining the advertisements to be delivered to the customers in the bank is adopted, the matching degree between the bank advertisements and the customers is low, and the conversion rate of popularization of bank products is seriously influenced.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a reference advertisement determination method, a reference advertisement determination device and reference advertisement determination equipment based on similar objects, and aims to solve the problems that in the prior art, the matching degree between bank advertisements and customers is low, and the conversion rate of bank product popularization is seriously influenced.
The embodiment of the application provides a reference advertisement determination method based on similar objects, which comprises the following steps: acquiring transaction data of a plurality of objects; determining similarity between each object in the plurality of objects according to the transaction data of the plurality of objects; establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between each object in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining whether a reference advertisement in a reference advertisement set of a target object among the plurality of objects or a weight of the reference advertisement is changed; and under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, adjusting the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being more than or equal to a first preset threshold value or the weight of the reference advertisement.
In one embodiment, after establishing a corresponding reference advertisement set for each of the plurality of objects according to the transaction data of the plurality of objects and the similarity between each of the plurality of objects, the method further includes: acquiring the total asset amount of a target object in the plurality of objects; according to the weight of each reference advertisement in the reference advertisement set of the target object, performing descending order arrangement on each reference advertisement in the reference advertisement set of the target object; determining the pushed reference advertisement according to the result of the descending order of each reference advertisement in the reference advertisement set of the target object and the total asset amount of the target object; and pushing the determined reference advertisement to the target object.
In one embodiment, determining the pushed reference advertisement according to the result of the descending order of the reference advertisements in the reference advertisement set of the target object and the total asset amount of the target object includes: determining N reference advertisements before sequencing according to the result of descending sequencing of all the reference advertisements in the reference advertisement set of the target object, wherein N is a positive integer greater than or equal to 1; and taking the reference advertisement of which the product of the lowest purchase amount and the preset multiple in the top N reference advertisements in the reference advertisement set of the target object is less than or equal to the total asset amount of the target object as a pushed reference advertisement.
In one embodiment, establishing a corresponding reference advertisement set for each of the plurality of objects according to the transaction data of the plurality of objects and the similarity between each of the plurality of objects includes: determining whether the transaction data amount of the target object is smaller than a second preset threshold value; under the condition that the transaction data volume of the target object is determined to be smaller than a second preset threshold, adding each reference advertisement in a reference advertisement set of a similar object with the similarity degree of the target object being larger than or equal to a first preset threshold to the reference advertisement set of the target object; and taking the value obtained by multiplying the weight of each reference advertisement in the reference advertisement set of the similar object with the similarity of the target object being more than or equal to a first preset threshold value and the similarity between the similar object and the target object as the weight of the corresponding reference advertisement in the reference advertisement set of the target object.
In one embodiment, in a case that it is determined that the reference advertisement in the reference advertisement set of the target object changes, adjusting the reference advertisement in the reference advertisement set of the similar object whose similarity with the target object is greater than or equal to a first preset threshold includes: determining whether the reference advertisement set of the similar object comprises the target reference advertisement under the condition that the reference advertisement set of the target object is determined to be newly added with the target reference advertisement; in an instance in which it is determined that the target reference advertisement is not included in the reference advertisement set of the similar object, adding the target reference advertisement to the reference advertisement set of the similar object; and taking the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object as the weight of the target reference advertisement in the reference advertisement set of the similar object.
In one embodiment, after determining whether the target reference advertisement is included in the reference advertisement set of similar objects, the method further comprises: in the case that the reference advertisement set of the similar object is determined to comprise the target reference advertisement, determining whether the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object is greater than the weight of the target reference advertisement in the reference advertisement set of the similar object; in case that the weight of the target reference advertisement in the reference advertisement set of the similar object is determined to be larger than the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object is adjusted to a value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object by the similarity between the target object and the similar object.
In one embodiment, in a case that it is determined that the weight of the reference advertisement in the reference advertisement set of the target object changes, adjusting the weight of the reference advertisement in the reference advertisement set of the similar object whose similarity with the target object is greater than or equal to a first preset threshold includes: determining whether the target reference advertisement is included in the reference advertisement set of the similar object in case that it is determined that the weight of the target reference advertisement is increased in the reference advertisement set of the target object; in an instance in which it is determined that the target reference advertisement is not included in the reference advertisement set of the similar object, adding the target reference advertisement to the reference advertisement set of the similar object; and taking the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object as the weight of the target reference advertisement in the reference advertisement set of the similar object.
In one embodiment, after determining whether the target reference advertisement is included in the reference advertisement set of similar objects, the method further comprises: in the case that the reference advertisement set of the similar object is determined to comprise the target reference advertisement, determining whether the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object is greater than the weight of the target reference advertisement in the reference advertisement set of the similar object; in case that the weight of the target reference advertisement in the reference advertisement set of the similar object is determined to be larger than the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object is adjusted to a value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object by the similarity between the target object and the similar object.
In one embodiment, in a case that it is determined that the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object changes, adjusting the weight of the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the similar object whose similarity with the target object is greater than or equal to a first preset threshold includes: under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, the target object is taken as the current object, and the following operations are repeatedly executed until the repetition times reach the preset times: acquiring a reference advertisement in a reference advertisement set of a current object or the change of the weight of the reference advertisement; according to the change of the reference advertisement in the reference advertisement set of the current object or the weight of the reference advertisement, adjusting the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object of which the similarity with the current object is more than or equal to a first preset threshold value to obtain the changed weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object of which the similarity with the current object is more than or equal to the first preset threshold value; and taking a similar object with the similarity to the current object being more than or equal to a first preset threshold value as the current object, wherein the similar object with the similarity to the current object being more than or equal to the first preset threshold value does not include a previous object of the current object.
The embodiment of the present application further provides a device for determining a reference advertisement based on similar objects, including: the acquisition module is used for acquiring transaction data of a plurality of objects; the first determination module is used for determining the similarity between the objects in the plurality of objects according to the transaction data of the objects; the establishing module is used for establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between the objects in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; a second determining module, configured to determine whether a reference advertisement in a reference advertisement set of a target object in the plurality of objects or a weight of the reference advertisement changes; and the adjusting module is used for adjusting the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object, of which the similarity with the target object is greater than or equal to a first preset threshold value, under the condition that the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the target object is determined to be changed.
The embodiment of the application also provides a similar object-based reference advertisement determination device, which comprises a processor and a memory for storing processor executable instructions, wherein the processor executes the instructions and the steps of the similar object-based reference advertisement determination method.
Embodiments of the present application also provide a computer-readable storage medium having stored thereon computer instructions, which when executed, implement the steps of the similar object-based reference advertisement determination method.
The embodiment of the application also provides a reference advertisement determining method based on similar objects, which can determine the similarity among the objects according to the transaction data of a plurality of objects. And establishing a corresponding reference advertisement set for each object according to the transaction data of the plurality of objects and the similarity between the objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, each reference advertisement is correspondingly distributed with a weight, and the reference advertisement set established by adopting the mode comprehensively considers the specificity of each object and the similarity between the objects, so that the reference advertisement in the established reference advertisement set has more reference value. Furthermore, under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement in the reference advertisement set of the target object in the plurality of objects is determined to be changed, the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object with the similarity between the reference advertisement and the target object being greater than or equal to the first preset threshold value is adjusted, so that the reference advertisement set of each object can be updated by utilizing the similarity between the objects, the matching degree between the reference advertisement set and the object is further improved, and the conversion rate of bank products is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this application, and are not intended to limit the application. In the drawings:
FIG. 1 is a schematic diagram illustrating steps of a similar object-based reference advertisement determination method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a reference advertisement set for adjusting similar objects according to changes in the reference advertisement set of a target object according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of the similar object-based reference advertisement determination apparatus according to an embodiment of the present application;
fig. 4 is a schematic diagram of the similar object-based reference advertisement determination device according to an embodiment of the present application.
Detailed Description
The principles and spirit of the present application will be described with reference to a number of exemplary embodiments. It should be understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the present application, and are not intended to limit the scope of the present application in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, embodiments of the present application may be embodied as a system, apparatus, device, method or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
In the existing mode of determining the advertisements to be delivered to the customers by the bank, the advertisements to be delivered to each customer are determined according to the business requirements of the bank, and the advertisements are delivered only according to the business requirements of the bank without taking the differences among different customers and the similarities among the customers into consideration, so that the delivered advertisements do not meet the actual requirements of the different customers, the matching degree between bank products and the customers is low, and the conversion rate of popularization of the bank products is reduced.
Based on the above problem, an embodiment of the present invention provides a reference advertisement determination method based on similar objects, as shown in fig. 1, which may include the following steps:
s101: transaction data for a plurality of objects is obtained.
In order to make the reference advertisement in the established reference advertisement set have a reference value, transaction data of a plurality of objects can be obtained in advance, wherein the transaction data can be in a certain period of time or historical transaction data of the plurality of objects in a bank. The transaction data may include, but is not limited to, at least one of: the bank products, the total amount of the transaction, the number of the transaction and the like are purchased, inquired, shared, purchased and collected, and the application is not limited. In an embodiment, object information of the plurality of objects may be obtained in advance, and the object information may include, but is not limited to, at least one of the following: total assets amount, working years, graduates, category of occupation, etc.
S102: and determining the similarity between the objects in the plurality of objects according to the transaction data of the plurality of objects.
In consideration of the similarity among the objects, the similarity among the objects can be determined according to the acquired transaction data of the objects. The calculation method of the similarity may include, but is not limited to, at least one of the following: the euclidean distance, manhattan distance, minkowski distance, cosine similarity, Jaccard similarity coefficient, pearson correlation coefficient, and the specific manner of adoption may be determined according to actual conditions, and the present application does not limit the present invention.
In the case that the target object is a new customer of the bank, the target object has no historical transaction data, or in the case that the historical transaction data of the target object is smaller than a second preset threshold, the similarity between the target object and other objects cannot be accurately obtained only according to the transaction data, so that the similarity between the target object and other objects can be determined according to the object information and the transaction data of each object in some cases.
In one embodiment, a dimension set including multiple dimensions for each customer may be determined according to the object information and the transaction data of each object, and when the dimension set of two objects is determined, the similarity between two customers may be obtained by calculating the similarity of the corresponding matched dimensions in the dimension sets of two customers and then adding the similarities in each dimension, where the dimensions may include, but are not limited to, at least one of the following: risk preference, income hierarchy, job industry, product preference, consumption level.
S103: and establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between each object in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight.
In order to make the reference advertisement in the established reference object set have a reference value, a corresponding reference advertisement set may be established for each object in the plurality of objects according to the transaction data of each object and the similarity between each object. The weight corresponding to each reference advertisement may be determined according to the transaction amount of the object to the product corresponding to the reference advertisement in the transaction data within a period of time, for example, the transaction amount to the product corresponding to the reference advertisement in the past year, or the transaction amount to the product corresponding to the reference advertisement in all historical transaction data of the object, or the total transaction amount of the product corresponding to the reference advertisement in the preset database of the bank, or it may be assumed that the weight corresponding to the reference advertisement is determined in other possible manners, which is not limited in the present application. If weights are determined for the transaction amounts of the products corresponding to the reference advertisements in the transaction data of the object over a period of time, the weights of the same reference advertisement in the reference advertisement sets of different objects may not be the same; if the weight is determined according to the total transaction amount of the product corresponding to the reference advertisement in the preset database of the bank, the weights of the same reference advertisement in the reference advertisement sets of different objects are the same.
For example: the reference ad set a established for object a may include: the method comprises the following steps of determining a reference advertisement 1, a reference advertisement 2, a reference advertisement 5 and a reference advertisement 9, wherein the weight of the reference advertisement 1 is 0.3, the weight of the reference advertisement 2 is 0.5, the weight of the reference advertisement 5 is 0.2 and the weight of the reference advertisement 9 is 0.1 according to the transaction amount of a product corresponding to each reference advertisement; the reference advertisement set B established for object B may include: the method comprises the following steps of (1) determining a reference advertisement 2, a reference advertisement 3 and a reference advertisement 10, wherein the weight of the reference advertisement 2 is 0.5, the weight of the reference advertisement 3 is 0.4 and the weight of the reference advertisement 10 is 0.1 according to the transaction amount of a product corresponding to each reference advertisement; the reference advertisement set C established for object C may include: the reference advertisement 4, the reference advertisement 6, the reference advertisement 7 and the reference advertisement 8 are determined, and the weight of the reference advertisement 4 is 0.7, the weight of the reference advertisement 6 is 0.2, the weight of the reference advertisement 7 is 0.4 and the weight of the reference advertisement 8 is 0.1 according to the transaction amount of a product corresponding to each reference advertisement.
In the case that the transaction data amount of the target object is smaller than the second preset threshold, a reference advertisement set may be initialized for the target object according to the reference advertisement set of the similar object of the target object, and specifically, each reference advertisement in the reference advertisement set of at least one similar object whose similarity to the target object is greater than or equal to the first preset threshold may be added to the reference advertisement set of the target object, or each reference advertisement in the reference advertisement set of the similar object whose similarity to the target object is the highest may be added to the reference advertisement set of the target object. Taking the value obtained by multiplying the weight of each reference advertisement in the reference advertisement set of the similar object with the similarity of the target object being more than or equal to a first preset threshold value and the similarity between the similar object and the target object as the weight of the corresponding reference advertisement in the reference advertisement set of the target object; or the value obtained by multiplying the weight of each reference advertisement in the reference advertisement set of the similar object with the highest similarity with the target object and the similarity between the similar object and the target object is used as the weight of the corresponding reference advertisement in the reference advertisement set of the target object.
For example: in the case that the transaction data amount of the object M is less than 20, it is determined that a similar object with a similarity to the object M of 0.8 or more is the object F, and the similarity between the object F and the object M is 0.85, the reference advertisement set F of the object F may be directly used as the reference advertisement set M of the object M, and the weight of each reference advertisement in the reference advertisement set M of the object M is equal to the value obtained by multiplying the weight of the corresponding reference advertisement in the object F by 0.85.
In order to improve the matching degree between the reference advertisement pushed to the target object and the target object, after the reference advertisement set of the target object is determined, the total asset amount of the target object can be obtained, and the reference advertisements in the reference advertisement set of the target object are sorted in a descending order according to the weight of the reference advertisements in the reference advertisement set of the target object, so that a result of the sorting in the descending order is obtained. And determining the reference advertisement with the top N according to the descending order, wherein N is a positive integer greater than or equal to 1. And taking the reference advertisement of which the product of the lowest purchase amount and the preset multiple in the N reference advertisements before the sorting of the reference advertisement set of the target object is less than or equal to the total asset amount of the target object as a pushed reference advertisement, namely screening out the reference advertisement which meets the consumption capacity of the target object in the N reference advertisements before the sorting.
After the reference advertisement pushed to the target object is determined, the determined reference advertisement may be pushed to the target object, wherein when the advertisement is pushed, the determined reference advertisement may be pushed to the target object all at once, or the determined reference advertisement may be pushed to the target object respectively according to a certain time interval, although any other possible pushing manner may be envisaged, which is not limited in the present application. The advertisement push approach may include, but is not limited to, at least one of the following: the system comprises a mobile phone short message, a client APP, a PC end online bank system, a target bank outlet display screen, a bank self-service equipment display screen and the like.
S104: it is determined whether a reference advertisement in a reference advertisement set of a target object among the plurality of objects or a weight of the reference advertisement is changed.
After the determined reference advertisement is pushed to the target object, the weight of the corresponding reference advertisement or the reference advertisement in the reference advertisement set of the target object may be adjusted according to the behavior of the target object after receiving the pushed reference advertisement, and the specific adjustment mode is not limited in the present application. The reference advertisement in the reference advertisement set of the target object or the change of the weight of the reference advertisement may include, but is not limited to, at least one of: adding a new reference advertisement to the reference advertisement set, deleting the reference advertisement in the reference advertisement set, increasing the weight of the reference advertisement in the reference advertisement set, and decreasing the weight of the reference advertisement in the reference advertisement set.
S105: and under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, adjusting the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being more than or equal to a first preset threshold value or the weight of the reference advertisement.
Because different changes of the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement have different meanings, the reference advertisement set of the target object can be correspondingly adjusted according to the different changes, and specifically, under the condition that the target reference advertisement is newly added in the reference advertisement set of the target object, whether the reference advertisement set of the similar object with the similarity degree with the target object being greater than or equal to a first preset threshold value includes the target reference advertisement or not can be determined, wherein the first preset threshold value is a positive number greater than 0, and a specific value can be determined according to an actual situation, which is not limited in the present application. In a case where it is determined that the reference advertisement set of the similar object does not include the target reference advertisement, the target reference advertisement is added to the reference advertisement set of the similar object, and a value by which a weight of the target reference advertisement in the reference advertisement set of the target object and a similarity between the target object and the similar object are multiplied is taken as the weight of the target reference advertisement in the reference advertisement set of the similar object.
For example: as shown in fig. 2, in the case where the reference advertisement 4 is newly added to the reference advertisement set a of the object a and the weight of the reference advertisement 4 is 0.5, a similar object having a similarity greater than 0.6 with the object a is determined as the object B, and the similarity between the object a and the object B is determined as 0.7. The reference advertisement set B of object B includes: reference advertisement 2, reference advertisement 3, and reference advertisement 10, thereby determining the reference advertisement 4 newly added in the reference advertisement set a excluding the object a in the reference advertisement set B, and therefore, the reference advertisement 4 may be added to the reference advertisement set B of the object B, and the weight of the reference advertisement 4 in the reference advertisement set B is 0.5 × 0.7 — 0.35.
Further, in the case that it is determined that the reference advertisement set of the similar object includes the target reference advertisement, it may be determined whether the weight of the target reference advertisement in the reference advertisement set of the target object multiplied by the similarity between the target object and the similar object is greater than the weight of the target reference advertisement in the reference advertisement set of the similar object, that is, it is determined whether the weight of the target reference advertisement in the reference advertisement set of the similar object is reduced if the weight of the target reference advertisement in the reference advertisement set of the similar object is adjusted according to the weight of the target reference advertisement in the reference advertisement set of the target object, so that the potential demand of the similar object for the target reference advertisement may be ignored.
In case the weight of the target reference advertisement in the reference advertisement set of the similar object is determined to be larger than the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object may be adjusted to a value of the multiplication of the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object. It can be understood that, in the case of determining the weight of the target reference advertisement in the reference advertisement set of the similar object to be less than or equal to the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object may not be adjusted, so as to ensure that the adjusted weight is greater than or equal to the weight before the adjustment.
For example: when the reference advertisement 3 is newly added to the reference advertisement set a of the object a and the weight of the reference advertisement 3 is 0.5, it is determined that the similar object having a similarity greater than 0.6 with the object a is the object B and the similarity between the object a and the object B is 0.7. The reference advertisement set B of object B includes: reference advertisement 2, reference advertisement 3, reference advertisement 10, thereby determining the reference advertisement 3 newly added in the reference advertisement a of the object a in the reference advertisement set B, the weight of the reference advertisement 3 in the reference advertisement set B is 0.4, and since 0.4 > 0.5 × 0.7, the weight of the reference advertisement 3 in the reference advertisement set B is not changed.
The change in the reference ad set of the target object is: in the case where the weight of the target reference advertisement in the reference advertisement set of the target object is increased, it may be determined whether the reference advertisement set of the similar object, of which the degree of similarity with the target object is greater than or equal to a first preset threshold, includes the target reference advertisement, and in the case where it is determined that the reference advertisement set of the similar object does not include the target reference advertisement, the target reference advertisement may be added to the reference advertisement set of the similar object, and the weight of the target reference advertisement in the reference advertisement set of the target object and a value by which the degree of similarity between the target object and the similar object is multiplied may be used as the weight of the target reference advertisement in the reference advertisement set of the similar object.
If the reference advertisement set of the similar object includes the target reference advertisement, whether the weight of the target reference advertisement in the reference advertisement set of the target object and the value of the multiplication of the similarity between the target object and the similar object are greater than the weight of the target reference advertisement in the reference advertisement set of the similar object may be further determined, and in case that it is determined that the value of the multiplication of the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object is greater than the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object may be adjusted to the value of the multiplication of the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object. It will be appreciated that the weight of the target reference advertisement in the reference advertisement set of the similar object may not be changed if the value of the weight of the target reference advertisement multiplied by the degree of similarity between the target object and the similar object is less than or equal to the weight of the target reference advertisement in the reference advertisement set of the similar object.
For example: the weight of the reference advertisement 2 in the reference advertisement set a of the object a is increased to 0.8, a similar object having a similarity greater than 0.6 with the object a is determined to be the object B, and the similarity between the object a and the object B is 0.7. The reference advertisement set B of object B includes: reference advertisement 2, reference advertisement 3, reference advertisement 10, wherein the weight of reference advertisement 2 is 0.5, and since 0.5 < 0.8 × 0.7, the weight of reference advertisement 2 in reference advertisement set B of object B is adjusted to 0.56.
Further, the advertisement can be continuously pushed to the plurality of objects according to the adjusted reference advertisement set in the manner in S103. It is noted, however, that the scope of the varying influence of the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object cannot be unlimited. In other words, when the reference advertisement in the reference advertisement set of the target object is determined or the weight of the reference advertisement is changed, the target object is taken as the current object, and the following operations are repeatedly executed until the number of times of repetition reaches the preset number of times: acquiring a reference advertisement in a reference advertisement set of a current object or a change of the weight of the reference advertisement, adjusting the reference advertisement in the reference advertisement set of a similar object with the similarity to the current object being greater than or equal to a first preset threshold value according to the change of the reference advertisement in the reference advertisement set of the current object or the change of the weight of the reference advertisement, obtaining the weight of the reference advertisement or the reference advertisement after the change of the reference advertisement in the reference advertisement set of the similar object with the similarity to the current object being greater than or equal to the first preset threshold value, and taking the similar object with the similarity to the current object being greater than or equal to the first preset threshold value as the current object, wherein the similar object with the similarity to the current object being greater than or equal to the first preset threshold value does not comprise a previous object of the current object, namely, in the process of cyclic adjustment, the change of the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the target object is not performed according to the change of the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the target object The reference advertisement set of the adjusted subject is repeatedly adjusted. The preset times are positive integers greater than or equal to 1, and can be 1, 2, 3 and the like, and specific values can be determined according to actual conditions, which is not limited in the application.
For example: in the case where the preset number of times is set to 2, the first preset threshold is set to 0.6, and the reference advertisement set a of the object a changes, the reference object set B of the object B having a similarity greater than or equal to 0.6 with respect to the object a may be adjusted according to the change of the reference advertisement set a of the object a, and further, the reference advertisement set E and the reference advertisement set F of the object E and the object F having a similarity greater than 0.6 with respect to the object B may be adjusted according to the change of the reference advertisement set B. The adjustment according to the change of the reference advertisement set A of the object A is finished, and downward adjustment is not continued so as to ensure that the range of change transmission is not unlimited.
From the above description, it can be seen that the embodiments of the present application achieve the following technical effects: the similarity between the respective objects may be determined based on transaction data of a plurality of objects. And establishing a corresponding reference advertisement set for each object according to the transaction data of the plurality of objects and the similarity between the objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, each reference advertisement is correspondingly distributed with a weight, and the reference advertisement set established by adopting the mode comprehensively considers the specificity of each object and the similarity between the objects, so that the reference advertisement in the established reference advertisement set has more reference value. Furthermore, under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement in the reference advertisement set of the target object in the plurality of objects is determined to be changed, the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object with the similarity between the reference advertisement and the target object being greater than or equal to the first preset threshold value is adjusted, so that the reference advertisement set of each object can be updated by utilizing the similarity between the objects, the matching degree between the reference advertisement set and the object is further improved, and the conversion rate of bank products is improved.
The above method is described below with reference to a specific example, however, it should be noted that the specific example is only for better describing the present application and is not to be construed as limiting the present application.
The implementation of the invention provides an advertisement putting method, which comprises the following steps:
step 1: a set of advertisements is maintained for each customer in the bank and each advertisement in the set of advertisements for each customer corresponds to a weight. The set of advertisements may be initialized with historical transactional data for each customer, and the weight of each advertisement may be determined based on the transaction amount of the product to which the advertisement corresponds; or the banking staff can add the advertisement to the client according to the banking business requirements, and the weight can be determined according to the importance degree of the advertisement related business in the bank.
Step 2: selecting the advertisement with the weight of N at the top of the rank from the advertisement set of each client, and putting the selected advertisement to the corresponding client; or screening out advertisements which are capable of being consumed by the client and have the weight of more than 0.5 from the advertisement set of the client according to the total asset amount of the client, and putting the screened advertisements to the client, wherein the advertisements which are capable of being consumed by the client are that the total asset amount of the client is more than or equal to the product of the purchase starting amount of a product corresponding to the advertisements and a preset multiple corresponding to the product. The preset multiple may be preset according to the attribute of each product, and may be any value greater than 0.
And step 3: the similarity between the individual customers may be determined based on the customer information for each customer and historical transaction data. There are various methods for calculating the similarity, and the present application is not limited thereto. In one embodiment, a dimension set including a plurality of dimensions for each customer may be determined according to customer information of the customer and historical transaction data, and when the dimension sets of two customers are determined, a similarity between the two customers may be obtained by calculating similarities on corresponding matched dimensions in the dimension sets of the two customers and then adding the similarities on the dimensions, where the dimensions may include, but are not limited to, at least one of the following: risk preference, income hierarchy, job industry, product preference, consumption level.
And 4, step 4: in the case where the amount of the historical transaction data of the customer C1 is less than the preset amount, similar customers of the customer C1 may be determined according to the customer information. For example: when it is determined that the client C2 and the client C1 are similar clients with similarity greater than 0.8, the advertisement set corresponding to C2 may be directly used as the advertisement set corresponding to C1, and the weight of each advertisement in the advertisement set of the client C1 may be equal to the weight of the corresponding advertisement in the advertisement set of the client C2 multiplied by the value of the similarity between the client C1 and the client C2.
And 5: in the case where the similarity between the client a and the client B is 0.8 or more, when the weights of the advertisement and the advertisement in the advertisement set of the client a are changed, the advertisement and the weights of the advertisement in the advertisement set of the client B may be updated according to the change of the client a. Wherein the updating of the weights needs to satisfy the positive effect: that is, the updated weight is equal to or greater than the weight before the update.
For example: the advertisement g is added to the advertisement set corresponding to the client a, but the advertisement g is not included in the advertisement set corresponding to the client B, and the advertisement g can be directly added to the advertisement set corresponding to the client B, and the corresponding weight can be set as: WBg is WAg × s (a, B), where WAg represents the weight of ad g in the ad set corresponding to customer a, and s (a, B) represents the similarity between customer a and customer B.
For another example: when the weight of the advertisement g in the advertisement set of the client a is reduced, if the advertisement g also exists in the advertisement set of the client B, the advertisement g in the advertisement set of the client B is not updated correspondingly.
For another example: the weight of advertisement g in the advertisement set of client A is increased to V1The weight of the advertisement g in the advertisement set of the client B is V2When the similarity between the client A and the client B is 0.9, if it is 0.9 XV1＜V2Then the weight of ad g in customer B's ad set is kept constant at V2, otherwise the weight of ad g in customer B's ad set is changed to 0.9 × V1.
However, it should be noted that the above listed determination manners and values of the specific threshold are only exemplary descriptions, and other determination manners and values may be selected according to actual needs and situations when the determination is actually implemented, which is not limited in the present application.
Step 6: when the advertisement set and the weights of the advertisements in the advertisement set are updated by utilizing the similarity between the clients, the number of updating transmitted layers is less than or equal to a preset threshold value. When the advertisement set of the client a1 or the weights of the advertisements in the advertisement set change, the advertisement set corresponding to the similar client a2 of the client a1 and the weights of the advertisements in the advertisement set may be updated, and the advertisement sets corresponding to the similar clients A3 and a4 of the client a2 and the weights of the advertisements in the advertisement set may be continuously updated, and the updates may be passed downward layer by layer, but the number of layers to be passed is less than or equal to a preset threshold.
For example: when the preset threshold is set to 1, the weights of the advertisement set corresponding to the similar client a2 of the client a1 and the advertisements in the advertisement set may be updated according to the change of the weights of the advertisement set of the client a1 or the advertisements in the advertisement set, but the weights of the advertisement set corresponding to the similar client A3 and a4 of the client a2 and the advertisements in the advertisement set may not be updated continuously.
However, it should be noted that the above listed determination manners and values of the preset threshold are only exemplary descriptions, and other determination manners and values may be selected according to actual needs and situations when the determination is actually implemented, which is not limited in the present application.
Based on the same inventive concept, the embodiment of the present application further provides a device for determining a reference advertisement based on similar objects, such as the following embodiments. Because the principle of solving the problem of the reference advertisement determination device based on the similar object is similar to the reference advertisement determination method based on the similar object, the implementation of the reference advertisement determination device based on the similar object can refer to the implementation of the reference advertisement determination method based on the similar object, and repeated details are omitted. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 3 is a block diagram of a similar object-based reference advertisement determination apparatus according to an embodiment of the present application, and as shown in fig. 3, the apparatus may include: the obtaining module 301, the first determining module 302, the establishing module 303, the second determining module 304, and the adjusting module 305 are described below.
An obtaining module 301, which may be used to obtain transaction data of a plurality of objects;
a first determining module 302, configured to determine similarity between objects in the plurality of objects according to transaction data of the plurality of objects;
the establishing module 303 may be configured to establish a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between each object in the plurality of objects, where the reference advertisement set of each object includes at least one reference advertisement, and each reference advertisement is correspondingly assigned with a weight;
a second determining module 304, which may be configured to determine whether a reference advertisement in a reference advertisement set of a target object in a plurality of objects or a weight of the reference advertisement is changed;
the adjusting module 305 may be configured to, in a case that it is determined that the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object changes, adjust the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object whose similarity with the target object is greater than or equal to the first preset threshold.
In an embodiment, the adjusting module 305 may further include: a first acquisition unit configured to acquire a total asset amount of a target object among a plurality of objects; the descending order arrangement unit is used for carrying out descending order arrangement on each reference advertisement in the reference advertisement set of the target object according to the weight of each reference advertisement in the reference advertisement set of the target object; the first determining unit is used for determining the pushed reference advertisements according to the result of the descending order of all the reference advertisements in the reference advertisement set of the target object and the total asset amount of the target object; and the pushing unit is used for pushing the determined reference advertisement to the target object.
In one embodiment, the first determining unit may include: the first determining subunit is used for determining N reference advertisements before sequencing according to the result of the descending sequencing of the reference advertisements in the reference advertisement set of the target object, wherein N is a positive integer greater than or equal to 1; and the first processing unit is used for taking the reference advertisement with the product of the lowest purchase amount and the preset multiple which is less than or equal to the total asset amount of the target object in the top N reference advertisements in the reference advertisement set of the target object as the pushed reference advertisement.
In one embodiment, the establishing module 303 may include: a third determination unit for determining whether the transaction data amount of the target object is less than a second preset threshold; the first adding unit is used for adding each reference advertisement in the reference advertisement set of the similar object with the similarity degree of the target object being more than or equal to the first preset threshold value to the reference advertisement set of the target object under the condition that the transaction data volume of the target object is determined to be less than the second preset threshold value; and the second processing unit is used for taking the value obtained by multiplying the weight of each reference advertisement in the reference advertisement set of the similar object with the similarity of the target object being more than or equal to the first preset threshold value and the similarity between the similar object and the target object as the weight of the corresponding reference advertisement in the reference advertisement set of the target object.
In one embodiment, the adjusting module 305 may include: a fourth determining unit, configured to determine whether the reference advertisement set of the similar object includes the target reference advertisement, in a case where it is determined that the target reference advertisement is newly added to the reference advertisement set of the target object; a second adding unit, configured to add the target reference advertisement to the reference advertisement set of the similar object if it is determined that the reference advertisement set of the similar object does not include the target reference advertisement; and the third processing unit is used for taking the weight of the target reference advertisement in the reference advertisement set of the target object and the value of the similarity between the target object and the similar object as the weight of the target reference advertisement in the reference advertisement set of the similar object.
In an embodiment, the adjusting module 305 may further include: a first judging unit, configured to determine whether a value obtained by multiplying a weight of a target reference advertisement in the reference advertisement set of the target object and a similarity between the target object and the similar object is greater than a weight of the target reference advertisement in the reference advertisement set of the similar object, in a case where it is determined that the reference advertisement set of the similar object includes the target reference advertisement; and a first adjusting unit, configured to, in a case where the weight of the target reference advertisement in the reference advertisement set larger than the similar object is determined, adjust the weight of the target reference advertisement in the reference advertisement set of the similar object to a value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object by the similarity between the target object and the similar object.
In an embodiment, the adjusting module 305 may further include: a second judging unit, configured to determine whether the reference advertisement set of the similar object includes the target reference advertisement, in a case where it is determined that the weight of the target reference advertisement is increased in the reference advertisement set of the target object; a third adding unit, configured to add the target reference advertisement to the reference advertisement set of the similar object if it is determined that the reference advertisement set of the similar object does not include the target reference advertisement; and the fourth processing unit is used for taking the weight of the target reference advertisement in the reference advertisement set of the target object and the value of the similarity between the target object and the similar object as the weight of the target reference advertisement in the reference advertisement set of the similar object.
In an embodiment, the adjusting module 305 may further include: a third judging unit, configured to determine whether a value obtained by multiplying a weight of the target reference advertisement in the reference advertisement set of the target object and a similarity between the target object and the similar object is greater than a weight of the target reference advertisement in the reference advertisement set of the similar object, in a case where it is determined that the reference advertisement set of the similar object includes the target reference advertisement; and a second adjusting unit, configured to, in a case where the weight of the target reference advertisement in the reference advertisement set larger than the similar object is determined, adjust the weight of the target reference advertisement in the reference advertisement set of the similar object to a value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object by the similarity between the target object and the similar object.
The embodiment of the present application further provides an electronic device, which may specifically refer to a schematic structural diagram of the electronic device shown in fig. 4 based on the reference advertisement determination method based on the similar object provided in the embodiment of the present application, and the electronic device may specifically include an input device 41, a processor 42, and a memory 43. The input device 41 may be specifically used for inputting transaction data of a plurality of objects. The processor 42 may be specifically configured to determine a similarity between each of the plurality of objects according to the transaction data of the plurality of objects; establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between each object in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining whether a reference advertisement in a reference advertisement set of a target object among a plurality of objects or a weight of the reference advertisement is changed; and under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, adjusting the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being more than or equal to a first preset threshold value or the weight of the reference advertisement. The memory 43 may be specifically configured to store parameters such as transaction data and similarity of a plurality of objects.
In this embodiment, the input device may be one of the main apparatuses for information exchange between a user and a computer system. The input devices may include a keyboard, mouse, camera, scanner, light pen, handwriting input panel, voice input device, etc.; the input device is used to input raw data and a program for processing the data into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may include multiple levels, and in a digital system, memory may be used as long as binary data can be stored; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.
In this embodiment, the functions and effects specifically realized by the electronic device can be explained by comparing with other embodiments, and are not described herein again.
The embodiment of the application also provides a computer storage medium of a reference advertisement determination method based on similar objects, the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium can realize: acquiring transaction data of a plurality of objects; determining the similarity between each object in the plurality of objects according to the transaction data of the plurality of objects; establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between each object in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining whether a reference advertisement in a reference advertisement set of a target object among a plurality of objects or a weight of the reference advertisement is changed; and under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, adjusting the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being more than or equal to a first preset threshold value or the weight of the reference advertisement.
In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.
In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different from that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and many applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the application should, therefore, be determined not with reference to the above description, but instead should be determined with reference to the pending claims along with the full scope of equivalents to which such claims are entitled.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and it will be apparent to those skilled in the art that various modifications and variations can be made in the embodiment of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (12)

1. A reference advertisement determination method based on similar objects is characterized by comprising the following steps:
acquiring transaction data and object information of a plurality of objects in a bank; wherein the object information includes: total asset amount, working year, graduation colleges, occupation category;
determining similarity between each object in the plurality of objects according to the transaction data of the plurality of objects; wherein, include: determining a dimension set of each object comprising a plurality of dimensions according to the object information and the transaction data of each object; calculating the similarity of the corresponding matched dimensions in the dimension sets of the two objects; adding the similarity of the corresponding matched dimensions of the two objects to obtain the similarity between the two objects; the plurality of dimensions includes: risk preference, income level, work industry, product preference, consumption level;
establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between each object in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, each reference advertisement is correspondingly distributed with a weight, and the weight of the reference advertisement is determined according to the transaction amount of a product corresponding to the reference advertisement;
determining whether a reference advertisement in a reference advertisement set of a target object among the plurality of objects or a weight of the reference advertisement is changed;
under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, adjusting the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being more than or equal to a first preset threshold value or the weight of the reference advertisement;
before determining whether the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object in the plurality of objects is changed, the method further comprises: after the determined reference advertisement is pushed to the target object, the corresponding reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object is adjusted according to the behavior data of the target object for receiving the pushed reference advertisement.
2. The method of claim 1, further comprising, after establishing a corresponding set of reference advertisements for each of the plurality of objects based on the transaction data for the plurality of objects and the similarity between each of the plurality of objects:
acquiring the total asset amount of a target object in the plurality of objects;
according to the weight of each reference advertisement in the reference advertisement set of the target object, performing descending order arrangement on each reference advertisement in the reference advertisement set of the target object;
determining the pushed reference advertisement according to the result of the descending order of each reference advertisement in the reference advertisement set of the target object and the total asset amount of the target object;
and pushing the determined reference advertisement to the target object.
3. The method of claim 2, wherein determining the pushed reference advertisement according to the result of the descending order of the reference advertisements in the reference advertisement set of the target object and the total asset amount of the target object comprises:
determining N reference advertisements before sequencing according to the result of descending sequencing of all the reference advertisements in the reference advertisement set of the target object, wherein N is a positive integer greater than or equal to 1;
and taking the reference advertisement of which the product of the lowest purchase amount and the preset multiple in the top N reference advertisements in the reference advertisement set of the target object is less than or equal to the total asset amount of the target object as a pushed reference advertisement.
4. The method of claim 1, wherein establishing a corresponding set of reference advertisements for each of the plurality of objects based on the transactional data for the plurality of objects and the similarity between each of the plurality of objects comprises:
determining whether the transaction data amount of the target object is smaller than a second preset threshold value;
under the condition that the transaction data volume of the target object is determined to be smaller than a second preset threshold, adding each reference advertisement in a reference advertisement set of a similar object with the similarity degree of the target object being larger than or equal to a first preset threshold to the reference advertisement set of the target object;
and taking the value obtained by multiplying the weight of each reference advertisement in the reference advertisement set of the similar object with the similarity of the target object being more than or equal to a first preset threshold value and the similarity between the similar object and the target object as the weight of the corresponding reference advertisement in the reference advertisement set of the target object.
5. The method of claim 1, wherein in a case that it is determined that the reference advertisement in the reference advertisement set of the target object changes, adjusting the reference advertisement in the reference advertisement set of the similar object whose similarity with the target object is greater than or equal to a first preset threshold value comprises:
determining whether the reference advertisement set of the similar object comprises the target reference advertisement under the condition that the reference advertisement set of the target object is determined to be newly added with the target reference advertisement;
in an instance in which it is determined that the target reference advertisement is not included in the reference advertisement set of the similar object, adding the target reference advertisement to the reference advertisement set of the similar object;
and taking the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object as the weight of the target reference advertisement in the reference advertisement set of the similar object.
6. The method of claim 5, further comprising, after determining whether the target reference advertisement is included in the reference advertisement set of similar objects:
in the case that the reference advertisement set of the similar object is determined to comprise the target reference advertisement, determining whether the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object is greater than the weight of the target reference advertisement in the reference advertisement set of the similar object;
in case that the weight of the target reference advertisement in the reference advertisement set of the similar object is determined to be larger than the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object is adjusted to a value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object by the similarity between the target object and the similar object.
7. The method of claim 1, wherein adjusting the weight of the reference advertisement in the reference advertisement set of the similar object with the similarity degree with the target object being greater than or equal to a first preset threshold value in case that the weight of the reference advertisement in the reference advertisement set of the target object is determined to be changed comprises:
determining whether the target reference advertisement is included in the reference advertisement set of the similar object in case that it is determined that the weight of the target reference advertisement is increased in the reference advertisement set of the target object;
in an instance in which it is determined that the target reference advertisement is not included in the reference advertisement set of the similar object, adding the target reference advertisement to the reference advertisement set of the similar object;
and taking the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object as the weight of the target reference advertisement in the reference advertisement set of the similar object.
8. The method of claim 7, further comprising, after determining whether the target reference advertisement is included in the reference advertisement set of similar objects:
in the case that the reference advertisement set of the similar object is determined to comprise the target reference advertisement, determining whether the value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object and the similarity between the target object and the similar object is greater than the weight of the target reference advertisement in the reference advertisement set of the similar object;
in case that the weight of the target reference advertisement in the reference advertisement set of the similar object is determined to be larger than the weight of the target reference advertisement in the reference advertisement set of the similar object, the weight of the target reference advertisement in the reference advertisement set of the similar object is adjusted to a value obtained by multiplying the weight of the target reference advertisement in the reference advertisement set of the target object by the similarity between the target object and the similar object.
9. The method of claim 1, wherein in a case that it is determined that the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object changes, adjusting the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object whose similarity with the target object is greater than or equal to a first preset threshold value comprises:
under the condition that the reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement is determined to be changed, the target object is taken as the current object, and the following operations are repeatedly executed until the repetition times reach the preset times:
acquiring a reference advertisement in a reference advertisement set of a current object or the change of the weight of the reference advertisement;
according to the change of the reference advertisement in the reference advertisement set of the current object or the weight of the reference advertisement, adjusting the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object of which the similarity with the current object is more than or equal to a first preset threshold value to obtain the changed weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object of which the similarity with the current object is more than or equal to the first preset threshold value;
and taking a similar object with the similarity to the current object being more than or equal to a first preset threshold value as the current object, wherein the similar object with the similarity to the current object being more than or equal to the first preset threshold value does not include a previous object of the current object.
10. An apparatus for reference advertisement determination based on similar objects, comprising:
the acquisition module is used for acquiring transaction data and object information of a plurality of objects in a bank; wherein the object information includes: total asset amount, working year, graduation colleges, occupation category;
the first determination module is used for determining the similarity between the objects in the plurality of objects according to the transaction data of the objects; wherein, include: determining a dimension set of each object comprising a plurality of dimensions according to the object information and the transaction data of each object; calculating the similarity of the corresponding matched dimensions in the dimension sets of the two objects; adding the similarity of the corresponding matched dimensions of the two objects to obtain the similarity between the two objects; the plurality of dimensions includes: risk preference, income level, work industry, product preference, consumption level;
the establishing module is used for establishing a corresponding reference advertisement set for each object in the plurality of objects according to the transaction data of the plurality of objects and the similarity between the objects in the plurality of objects, wherein the reference advertisement set of each object comprises at least one reference advertisement, each reference advertisement is correspondingly distributed with a weight, and the weight of the reference advertisement is determined according to the transaction amount of a product corresponding to the reference advertisement;
a second determining module, configured to determine whether a reference advertisement in a reference advertisement set of a target object in the plurality of objects or a weight of the reference advertisement changes; before determining whether the reference advertisement or the weight of the reference advertisement in the reference advertisement set of the target object in the plurality of objects is changed, the method further comprises: after the determined reference advertisement is pushed to the target object, adjusting the corresponding reference advertisement in the reference advertisement set of the target object or the weight of the reference advertisement according to the behavior data of the target object for receiving the pushed reference advertisement;
and the adjusting module is used for adjusting the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the similar object, of which the similarity with the target object is greater than or equal to a first preset threshold value, under the condition that the weight of the reference advertisement or the reference advertisement in the reference advertisement set of the target object is determined to be changed.
11. A similar object based reference advertisement determination device comprising a processor and a memory for storing processor executable instructions which when executed by the processor implement the steps of the method of any of claims 1 to 9.
12. A computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the method of any one of claims 1 to 9.
CN201910432595.0A 2019-05-23 2019-05-23 Reference advertisement determination method, device and equipment based on similar objects Active CN110223107B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910432595.0A CN110223107B (en) 2019-05-23 2019-05-23 Reference advertisement determination method, device and equipment based on similar objects

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910432595.0A CN110223107B (en) 2019-05-23 2019-05-23 Reference advertisement determination method, device and equipment based on similar objects

Publications (2)

Publication Number Publication Date
CN110223107A CN110223107A (en) 2019-09-10
CN110223107B true CN110223107B (en) 2021-12-07

Family

ID=67818174

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910432595.0A Active CN110223107B (en) 2019-05-23 2019-05-23 Reference advertisement determination method, device and equipment based on similar objects

Country Status (1)

Country Link
CN (1) CN110223107B (en)

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101059854A (en) * 2006-04-19 2007-10-24 腾讯科技（深圳）有限公司 On-line advertisement dynamic throwing system and method
CN100462980C (en) * 2007-06-26 2009-02-18 腾讯科技（深圳）有限公司 Content-related advertising identifying method and content-related advertising server
CN101477566A (en) * 2009-01-19 2009-07-08 腾讯科技（深圳）有限公司 Method and apparatus used for putting candidate key words advertisement
CN103685208B (en) * 2012-09-25 2017-07-14 华为技术有限公司 User data mask method, terminal device and server
CN103514239B (en) * 2012-11-26 2016-12-21 Tcl美国研究所 A kind of integrated user behavior and the recommendation method and system of item contents
CN106447372B (en) * 2015-08-10 2022-03-08 北京奇虎科技有限公司 Product information pushing method and device
CN105654201B (en) * 2015-12-30 2020-07-28 上海珍岛信息技术有限公司 Advertisement traffic prediction method and device
CN107016589B (en) * 2016-08-10 2020-10-30 创新先进技术有限公司 Method and device for determining recommended product
CN106886918A (en) * 2017-02-06 2017-06-23 中国联合网络通信集团有限公司 A kind of determination method of targeted customer, apparatus and system
CN107169785A (en) * 2017-03-31 2017-09-15 北京奇艺世纪科技有限公司 A kind of advertisement placement method and device
US11093992B2 (en) * 2017-05-05 2021-08-17 Reai Inc. Smart matching for real estate transactions
CN107146112B (en) * 2017-05-16 2020-08-04 西华大学 Mobile internet advertisement putting method
WO2018214163A1 (en) * 2017-05-26 2018-11-29 Microsoft Technology Licensing, Llc Providing product recommendation in automated chatting
CN107730303B (en) * 2017-09-15 2021-08-10 努比亚技术有限公司 Advertisement pushing method and device and computer readable storage medium
CN108038120A (en) * 2017-11-01 2018-05-15 平安科技（深圳）有限公司 Collaborative filtering recommending method, electronic equipment and computer-readable recording medium
CN108537636A (en) * 2018-04-08 2018-09-14 林凡 Online collaborative filtering commending contents algorithm based on user's dynamic behaviour similitude
CN108595630A (en) * 2018-04-24 2018-09-28 中译语通科技股份有限公司 A kind of user behavior data analysis model and its construction method
CN108985935A (en) * 2018-07-06 2018-12-11 兴业证券股份有限公司 Financial product recommended method and storage medium
CN109636479A (en) * 2018-12-19 2019-04-16 武汉斗鱼鱼乐网络科技有限公司 A kind of advertisement recommended method, device, electronic equipment and storage medium
CN109670153B (en) * 2018-12-21 2023-11-17 北京城市网邻信息技术有限公司 Method and device for determining similar posts, storage medium and terminal
CN109635204A (en) * 2018-12-21 2019-04-16 上海交通大学 Online recommender system based on collaborative filtering and length memory network

Also Published As

Publication number Publication date
CN110223107A (en) 2019-09-10

Similar Documents

Publication Publication Date Title
CN110210899B (en) Advertisement pushing method, device and equipment based on advertisement similarity
US11836615B2 (en) Bayesian nonparametric learning of neural networks
CN110210900B (en) Reference product determination method, device and equipment based on transaction relevance
CN110210898B (en) Advertisement pushing method, device and equipment based on user behaviors
CN112231584B (en) Data pushing method and device based on small sample transfer learning and computer equipment
CN109299356B (en) Activity recommendation method and device based on big data, electronic equipment and storage medium
CN110019774B (en) Label distribution method, device, storage medium and electronic device
CN110750658A (en) Recommendation method of media resource, server and computer readable storage medium
EP3831079A1 (en) Distribution of embedded content items by an online system
CN111932308A (en) Data recommendation method, device and equipment
CN113988221A (en) Insurance user classification model establishing method, classification method, device and equipment
CN110738508A (en) data analysis method and device
CN111158837B (en) Bank software function interface generation method and device
Valizadegan et al. Learning to trade off between exploration and exploitation in multiclass bandit prediction
CN108074108B (en) Method and terminal for displaying net recommendation value
CN110223107B (en) Reference advertisement determination method, device and equipment based on similar objects
JP2019144978A (en) Information processing device, information processing method, and program
CN110322291B (en) Advertisement pushing method and equipment
GB2567929A (en) Digital experience targeting using bayesian approach
CN111666481A (en) Data mining method and device, computer readable medium and electronic equipment
CN113378050A (en) User classification method and device and electronic equipment
CN115129964A (en) Method for pushing content item to be recommended, pushing system and electronic equipment
CN112116405A (en) Data processing method, device, electronic equipment and medium
CN114648258B (en) Task scheduling method and system based on financing lease service system
CN113722602B (en) Information recommendation method and device, electronic equipment and storage medium

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
GR01 Patent grant
GR01 Patent grant