CN110210899B

CN110210899B - Advertisement pushing method, device and equipment based on advertisement similarity

Info

Publication number: CN110210899B
Application number: CN201910432638.5A
Authority: CN
Inventors: 朱江波; 张盛素; 丁平
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2019-05-23
Filing date: 2019-05-23
Publication date: 2023-06-20
Anticipated expiration: 2039-05-23
Also published as: CN110210899A

Abstract

The application provides an advertisement pushing method, device and equipment based on advertisement similarity, wherein the method comprises the following steps: acquiring characteristic data of a plurality of advertisements from a preset database; determining the similarity between the advertisements according to the characteristic data of the advertisements; acquiring historical transaction data and total asset amount of a target user; establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining a reference advertisement pushed to the target user from the reference advertisement set according to the total asset amount of the target user; pushing the determined reference advertisement to the target user. By the scheme, the matching degree between the reference advertisement pushed to the target user and the target user is improved, and the conversion rate of the bank product is further improved.

Description

Advertisement pushing method, device and equipment based on advertisement similarity

Technical Field

The present disclosure relates to the field of computer processing technologies, and in particular, to an advertisement pushing method, apparatus, and device based on advertisement similarity.

Background

The conventional advertisement delivery mode of the bank is to push advertisements to clients according to the business requirements of the bank, and only the advertisements are pushed according to the business requirements of the bank, so that the pushed advertisements do not meet the actual requirements of different clients and the potential requirements of different clients cannot be found out. The existing advertisement putting mode of the bank is adopted, the matching degree between the advertisement pushed by the bank and the client is low, and the conversion rate of popularization of the bank products is seriously affected.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the application provides an advertisement pushing method, device and equipment based on advertisement similarity, which are used for solving the problem of low matching degree between advertisements pushed by banks and clients in the prior art.

The embodiment of the application provides an advertisement pushing method based on advertisement similarity, which comprises the following steps: acquiring characteristic data of a plurality of advertisements from a preset database; according to the characteristic data of the advertisements, determining the similarity between the advertisements in the advertisements; acquiring historical transaction data and total asset amount of a target user; establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining a reference advertisement pushed to the target user from the reference advertisement set according to the total asset amount of the target user; pushing the determined reference advertisement to the target user.

In one embodiment, after pushing the determined reference advertisement to the target user, further comprising: acquiring behavior data of the target user within a preset time after pushing the determined reference advertisement to the target user; and adjusting the reference advertisement or the weight of the reference advertisement in the reference advertisement set according to the behavior data of the target user and the similarity between the advertisements in the plurality of advertisements.

In one embodiment, the behavioral data includes at least one of: query behavior, collection behavior, purchasing behavior, sharing behavior, and purchasing behavior.

In one embodiment, adjusting the reference advertisement or the weight of the reference advertisement in the reference advertisement set according to the behavior data of the target user and the similarity between the advertisements in the plurality of advertisements includes: determining whether the purchasing behavior of the target reference advertisement in the determined reference advertisement exists in the behavior data of the target user; determining whether behavior data of the target user except for purchasing behavior exists in the behavior data of the target user under the condition that the purchasing behavior of the target reference advertisement does not exist in the behavior data of the target user; determining whether the number of the behavior data of the target user except the purchasing behavior is larger than or equal to a first preset threshold value or not under the condition that the behavior data of the target user except the purchasing behavior exists in the behavior data of the target user; and removing the target reference advertisement from the reference advertisement set of the target user under the condition that the number of the behavior data of the target user except the purchasing behavior is larger than or equal to a first preset threshold value.

In one embodiment, after removing the targeted reference advertisement from the targeted user's reference advertisement set, further comprising: determining the advertisement with the highest similarity with the target reference advertisement according to the similarity between the advertisements in the advertisements; taking the advertisement with the highest similarity with the target reference advertisement as a standby advertisement of the target user; and adding the standby advertisement of the target user into the reference advertisement set of the target user, and determining the weight of the standby advertisement of the target user according to the weight of the target reference advertisement and the similarity between the standby advertisement of the target user and the target reference advertisement.

In one embodiment, after removing the targeted reference advertisement from the targeted user's reference advertisement set, further comprising: determining at least one advertisement with the similarity to the target reference advertisement being greater than or equal to a second preset threshold according to the similarity between each advertisement in the plurality of advertisements; at least one advertisement with the similarity with the target reference advertisement being greater than or equal to a second preset threshold value is used as a standby advertisement set of the target user; determining the matching degree between each standby advertisement in the standby advertisement set of the target user and the target user according to the historical transaction data of the target user and the similarity between each advertisement in the plurality of advertisements; adding the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target user into the reference advertisement set of the target user, and determining the weight of the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target user according to the weight of the target reference advertisement and the similarity between the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target reference advertisement.

In one embodiment, after establishing a reference advertisement set for the target user according to historical transaction data of the target user and similarities among the advertisements of the plurality of advertisements, the method further comprises: according to the similarity between the advertisements in the advertisements, determining the similarity between the reference advertisements in the reference advertisement set of the target user; determining whether the similarity between two reference advertisements is greater than or equal to a third preset threshold according to the similarity between each reference advertisement in the reference advertisement set of the target user; and under the condition that the similarity between the two reference advertisements is larger than or equal to a third preset threshold value, comparing the weights of the two reference advertisements with the similarity larger than or equal to the third preset threshold value, and removing the reference advertisement with smaller weight from the reference advertisement set of the target user.

In one embodiment, after establishing a reference advertisement set for the target user according to historical transaction data of the target user and similarities among the advertisements of the plurality of advertisements, the method further comprises: according to the similarity between the advertisements in the advertisements, determining the similarity between the reference advertisements in the reference advertisement set of the target user; determining whether the similarity between two reference advertisements is greater than or equal to a third preset threshold according to the similarity between each reference advertisement in the reference advertisement set of the target user; determining whether an absolute value of a difference of weights of the two reference advertisements with the similarity being greater than or equal to a third preset threshold value is less than or equal to a fourth preset threshold value under the condition that the similarity between the two reference advertisements is greater than or equal to the third preset threshold value; and removing any one of the two reference advertisements with the similarity greater than or equal to the third preset threshold value from the reference advertisement set of the target user under the condition that the absolute value of the difference of the weights of the two reference advertisements with the similarity greater than or equal to the third preset threshold value is smaller than or equal to a fourth preset threshold value.

In one embodiment, determining a reference advertisement to push to the target user from the reference advertisement set based on the total asset amount of the target user comprises: according to the weight of each reference advertisement in the reference advertisement set of the target user, carrying out descending order arrangement on each reference advertisement in the reference advertisement set of the target user; determining the reference advertisements pushed to the target user from the reference advertisement set according to the result of descending order arrangement of each reference advertisement in the reference advertisement set of the target user and the total asset amount of the target user.

In one embodiment, determining a reference advertisement to push to the target user from the reference advertisement set based on a result of a descending order of individual reference advertisements in the reference advertisement set of the target user and a total asset amount of the target user, comprises: determining N reference advertisements before sequencing according to the descending order arrangement result of each reference advertisement in the reference advertisement set of the target user, wherein N is a positive integer greater than or equal to 1; and the reference advertisement, of which the value of the multiplication of the lowest purchase amount and the preset multiple in the N before the sequencing in the reference advertisement set of the target user is smaller than or equal to the total asset amount of the target user, is used as the reference advertisement pushed to the target user.

The embodiment of the application also provides an advertisement pushing device based on advertisement similarity, which comprises: the first acquisition module is used for acquiring characteristic data of a plurality of advertisements from a preset database; the first determining module is used for determining the similarity between the advertisements in the advertisements according to the characteristic data of the advertisements; the second acquisition module is used for acquiring historical transaction data and total asset amount of the target user; the establishing module is used for establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; the second determining module is used for determining the reference advertisements pushed to the target user from the reference advertisement sets according to the total asset amount of the target user; and the pushing module is used for pushing the determined reference advertisement to the target user.

The embodiment of the application also provides advertisement pushing equipment based on advertisement similarity, which comprises a processor and a memory for storing executable instructions of the processor, wherein the processor realizes the steps of the advertisement pushing method based on advertisement similarity when executing the instructions.

The embodiment of the application also provides a computer readable storage medium, wherein computer instructions are stored on the computer readable storage medium, and the instructions are executed to realize the steps of the advertisement pushing method based on advertisement similarity.

The embodiment of the application provides an advertisement pushing method based on advertisement similarity, which can determine the similarity between advertisements by acquiring characteristic data of a plurality of advertisements from a preset database, and the data in a bank database is used as support, so that the obtained similarity between the advertisements has reliability according to the data. Further, a reference advertisement set can be established for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, each reference advertisement is correspondingly allocated with a weight, the reference advertisement set belonging to the target user is established according to the historical transaction data of the target user, the specificity of different users is taken into consideration, and the reference advertisements in the established reference advertisement set have more referential. According to the total asset amount of the target user, the reference advertisement pushed to the target user is determined from the reference advertisement set, and the determined reference advertisement is pushed to the target user, so that the matching degree between the advertisement pushed to the target user and the target user is improved, and the conversion rate of popularization of bank products is improved.

Drawings

The accompanying drawings are included to provide a further understanding of the application, and are incorporated in and constitute a part of this application. In the drawings:

FIG. 1 is a schematic diagram of an advertisement pushing system provided according to an embodiment of the present application;

FIG. 2 is a schematic diagram of steps of an advertisement pushing method based on advertisement similarity according to an embodiment of the present application;

FIG. 3 is a schematic diagram of adjusting a reference advertisement set for a target user provided in accordance with an embodiment of the present application;

FIG. 4 is a schematic diagram of an advertisement pushing device based on advertisement similarity provided according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an advertisement pushing device based on advertisement similarity according to an embodiment of the present application.

Detailed Description

The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are presented merely to enable one skilled in the art to better understand and 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.

Those skilled in the art will appreciate that embodiments of the present application may be implemented as a system, apparatus device, method, or computer program product. Accordingly, the present disclosure may be embodied in the following forms, namely: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.

According to the conventional advertisement delivery mode of the bank, the advertisement is pushed to the client only according to the business requirement of the bank, so that the matching degree between a bank product and the client is low, and the conversion rate of popularization of the bank product is reduced.

Based on this, there is provided in the present application an advertisement pushing system of a bank, as shown in fig. 1, may include: the user can initiate a transaction operation in a banking system through the terminal equipment 101, the banking server 102 can respond to a transaction operation request which is finished by the user, determine a reference advertisement pushed to the user from a database preset by the bank, and push the determined reference advertisement pushed to the user to the terminal equipment 101.

The terminal device 101 may be a terminal device or software used by a user operation. Specifically, the terminal device may be a terminal device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch or other wearable devices, or may be a robot device or the like. Of course, the terminal device 101 may be software that can be executed in the terminal device. For example: banking system applications, payment applications, browsers, etc.

The bank server 102 may be a single server or a server cluster, where the bank server 102 may be connected to a plurality of terminal devices, or may be a server with a strong bank transaction database, and may determine a reference advertisement pushed to a user based on a transaction operation performed by the user.

Based on the advertisement pushing system, the embodiment of the invention provides an advertisement pushing method based on advertisement similarity, as shown in fig. 2, which may include the following steps:

s201: and acquiring characteristic data of a plurality of advertisements from a preset database.

Since each advertisement has different attributes, benefits, risks and other characteristics, the characteristic data of a plurality of advertisements can be obtained from a database preset by a bank in advance, wherein the characteristic data of the advertisements can include but is not limited to at least one of the following: conversion rate, click rate, number of impressions, profit, loss, risk level, purchase amount, total transaction amount, category, purchase frequency of corresponding products of advertisement.

S202: and determining the similarity between the advertisements in the advertisements according to the characteristic data of the advertisements.

In consideration of the fact that different advertisements have different degrees of variability, the similarity between the advertisements in the advertisements can be determined according to the acquired characteristic data of the advertisements, so that the similarity between the advertisements can be measured. The method for calculating the similarity may include, but is not limited to, at least one of: the euclidean distance, manhattan distance, markov distance, cosine similarity, jaccard similarity coefficient, pearson correlation coefficient, and the specific manner of use may be determined according to the actual situation, which is not limited in this application.

In one embodiment, a dimension set of each advertisement may be determined according to feature data of a plurality of advertisements, where each dimension set of each advertisement includes at least one dimension subset, and when the dimension sets of two advertisements are determined, a similarity between corresponding matched dimension subsets in the dimension sets of two advertisements may be calculated, and the similarities between the respective dimension subsets may be added, so that a similarity between the two advertisements may be obtained, where the dimension subsets may include, but are not limited to, at least one of: conversion rate, click rate, number of impressions, profit, loss, risk level, purchase amount, total transaction amount, category, purchase frequency of corresponding products of advertisement.

S203: historical transaction data and a total asset amount of the target user are obtained.

In order to make the reference advertisements in the reference advertisement set have reference value, historical transaction data and total asset amount of the target user can be obtained in advance, wherein the historical transaction data can be the historical transaction data of the target user in a certain period of time or all the historical transaction data of the target user in a bank, and the total asset amount can be the current total asset amount of the target user or the total asset amount of a certain specific time point. Wherein, the historical transaction data may include, but is not limited to, at least one of the following: purchasing, inquiring, sharing, purchasing, collecting bank products, transaction total amount, transaction number and the like, which are not limited in the application; the total asset amount may include a deposit of the user in the bank and a purchased bank product.

S204: and establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity among the advertisements in the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly allocated with a weight.

A reference advertisement set can be established for the target user according to the acquired historical transaction data of the target user, so that the reference advertisements in the reference advertisement set can discover the potential demands of the target user. Further, the weight corresponding to each reference advertisement may be determined according to the transaction amount of the target user for the product corresponding to the reference advertisement in the historical transaction data within a period of time, for example, the transaction amount of the target user for the product corresponding to the reference advertisement in the past year, the transaction amount of the target user for the product corresponding to the reference advertisement in all the historical transaction data, the total transaction amount of the products corresponding to each reference advertisement in the bank preset database, or other possible manners are also contemplated.

For example: the reference advertisement set a established for user a may include: reference advertisement 1, reference advertisement 2, reference advertisement 5, reference advertisement 9, the weight of reference advertisement 1 can be determined to be 0.3, the weight of reference advertisement 2 is 0.5, the weight of reference advertisement 5 is 0.2, and the weight of reference advertisement 9 is 0.1 according to the transaction amount of the products corresponding to each reference advertisement; the reference advertisement set B established for user B may include: reference advertisement 2, reference advertisement 3, reference advertisement 10, the weight of reference advertisement 2 can be determined to be 0.5, the weight of reference advertisement 3 is 0.4, the weight of reference advertisement 10 is 0.1 according to the transaction amount of the products corresponding to each reference advertisement; the reference advertisement set C established for the user C may include: 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 products corresponding to the reference advertisements.

Further, when the reference advertisement set is established for the target user, the similarity between the reference advertisements in the initial reference advertisement set obtained according to the historical transaction data of the target user can be determined according to the similarity between the advertisements in the plurality of advertisements, whether two reference advertisements with the similarity greater than or equal to a third preset threshold value exist in the reference advertisement set of the target user or not is determined according to the determined similarity between the reference advertisements, if the similarity between the two reference advertisements is greater than or equal to the third preset threshold value, the weights of the two reference advertisements with the similarity greater than or equal to the third preset threshold value can be compared, the reference advertisement with the smaller weight is removed from the reference advertisement set of the target user, and the reference advertisement with the larger weight is reserved, so that the reference advertisement set adjusted according to the similarity between the advertisements is obtained.

It may be understood that after determining whether two reference advertisements with a similarity equal to or greater than a third preset threshold exist in the reference advertisement set of the target user, it may be further determined whether an absolute value of a difference value of weights of the two reference advertisements with a similarity equal to or greater than the third preset threshold is equal to or less than a fourth preset threshold, and in the case where it is determined that the absolute value of the difference value of weights of the two reference advertisements with a similarity equal to or greater than the third preset threshold is equal to or less than the fourth preset threshold, any one of the two reference advertisements with a similarity equal to or greater than the third preset threshold may be randomly removed from the reference advertisement set of the target user. The third preset threshold and the fourth preset threshold are positive numbers greater than 0, and specific values may be determined according to practical situations, which is not limited in the present application.

In one embodiment, if the target user is a new user, i.e., the target user has no historical transaction data or the amount of historical transaction data for the target is less than a predetermined threshold, a reference advertisement set may be initialized for the target user based on the total asset amount of the target user and the business needs of the bank, such as: under the condition that the historical transaction data amount for target is smaller than a preset threshold value, acquiring the total asset amount of the target user as 8000 yuan, initializing a reference advertisement set for the target user according to the total asset amount of the target user and the business requirement of the bank, wherein the minimum purchase amount of a product corresponding to the reference advertisement in the reference advertisement set is smaller than 8000 yuan and is a product with larger banking business requirement. In the case that the target user does not have sufficient asset information at the bank, an advertisement set can be directly initialized for the target user according to the business requirements of the bank. It should be noted, however, that how to build the reference advertisement set for the target user may be determined according to the actual situation, and the application is not limited. The service requirement may be determined according to the profit situation of each product in the bank, the purchase frequency of the user, the total purchase amount of the user, and the like, which is not limited in this application.

S205: and determining the reference advertisement pushed to the target user from the reference advertisement set according to the total asset amount of the target user.

In order to improve the matching degree between the reference advertisements pushed to the target user and the target user, before the advertisements are pushed to the target user, the reference advertisements in the reference advertisement set of the target user can be arranged in a descending order according to the weights of the reference advertisements in the reference advertisement set of the target user, so that a descending order result is obtained. And determining N reference advertisements before the sequencing in the reference advertisement set according to the descending order arrangement result, wherein N is a positive integer which is more than or equal to 1 and less than or equal to the total number of the reference advertisements in the reference advertisement set. And after the reference advertisements of the N before sequencing are obtained, the reference advertisement, of which the value of the multiplication of the lowest purchase amount in the reference advertisement of the N before sequencing and the preset multiple is less than or equal to the total asset amount of the target user, is used as the advertisement pushed to the target user, namely, the reference advertisement conforming to the consumption capability of the target user in the reference advertisement of the N before sequencing is determined.

The preset multiple is a positive number greater than 0, and may have values of 2, 3, 4.8, etc., which may be specifically determined according to practical situations, and the application is not limited. In the banking system, a corresponding preset multiple may be set for each reference advertisement according to the attribute of the product corresponding to each reference advertisement, that is, different preset multiple corresponding to different reference advertisements, it may be understood that the same preset multiple may be set for different reference advertisements in some cases, and specifically may be determined according to practical situations, which is not limited in this application.

For example: the reference advertisement set A established for the user A comprises the following steps: reference advertisement 1, reference advertisement 2, reference advertisement 5 and 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. The reference advertisements in the reference advertisement set of the user A are arranged in a descending order, and the descending order results are as follows: reference advertisement 2, reference advertisement 1, reference advertisement 5, reference advertisement 9. In the case where N is set to 2, the reference advertisement of weight ranking front 2 is: reference advertisement 2 and reference advertisement 1. The total asset amount of the user A is 12000 yuan, the lowest purchase amount of the reference advertisement 1 is 1000 yuan, the lowest purchase amount of the reference advertisement 2 is 5000 yuan, and the preset multiple is 3. Since 1000×3 < 12000, reference advertisement 1 is taken as the advertisement pushed to user a; since 5000×3 > 12000, reference advertisement 2 cannot be served as an advertisement pushed to user a.

S206: pushing the determined reference advertisement to the target user.

After determining the reference advertisement pushed to the target user, the determined reference advertisement may be pushed to the target user, where the determined reference advertisement may be pushed to the target user all at once during the advertisement pushing, or the determined reference advertisement may be respectively pushed to the target user at a certain time interval, although any other possible pushing manner is also conceivable, which is not limited in this application. Approaches to advertisement pushing may include, but are not limited to, at least one of: a mobile phone short message, a client APP, a PC end online banking system, a target banking website display screen, a banking self-service equipment display screen and the like.

After pushing the determined reference advertisement to the target user, behavior data of the target user within a predetermined time may be acquired, for example: the present application does not limit this to obtaining behavior data of the target user within 6 months after seeing the pushed reference advertisement, or obtaining behavior data of the target user after seeing the pushed reference advertisement for 2 months, or obtaining behavior data of the target user between 3 months and 6 months after seeing the pushed reference advertisement, or other possible manners. The behavior data may include, but is not limited to, at least one of: query behavior, collection behavior, purchasing behavior, sharing behavior, and purchasing behavior.

Further, the reference advertisement set of the target user can be adjusted according to the acquired behavior data of the target user, so that the reference advertisement in the reference advertisement set of the target user accords with the actual requirement of the target user. Specifically, whether the purchasing behavior of the target reference advertisement in the reference advertisement set exists can be determined first, after the purchasing behavior of the target reference advertisement does not exist, whether the behavior data of the target user except the purchasing behavior of the target reference advertisement exists can be determined, and when the behavior data of the target user except the purchasing behavior exists, the target reference advertisement is described as the interest advertisement of the target user, but the product corresponding to the advertisement is not purchased yet. Therefore, whether the number of the behavior data of the target user except the purchasing behavior is larger than or equal to a first preset threshold value can be determined, and the target user is lower in possibility of purchasing a product corresponding to the target reference advertisement under the condition that the number of the behavior data of the target user except the purchasing behavior is larger than or equal to the first preset threshold value, and the target reference advertisement can be removed from the reference advertisement set of the target user.

Taking into account that multiple user queries, purchases or shares, etc., indicate that the user is interested in targeting the content of the reference advertisement, but may be limited by factors such as, for example: purchase amount, risk, expected revenue, etc. Thus, after the targeted reference advertisement is removed from the targeted user's reference advertisement set, an advertisement having a higher similarity to the targeted reference advertisement may be added to the targeted user's reference advertisement set, and the advertisement having a higher similarity to the targeted reference advertisement added to the targeted user's reference advertisement set may be determined as follows:

mode one: the advertisement with the highest similarity to the target reference advertisement can be determined according to the similarity between the advertisements in the advertisements, the advertisement with the highest similarity to the target reference advertisement is used as the standby advertisement of the target user, the standby advertisement of the target user is added to the reference advertisement set of the target user, and the weight of the standby advertisement of the target user is determined according to the weight of the target reference advertisement and the similarity between the standby advertisement of the target user and the target reference advertisement. The weight of the target reference advertisement in the reference advertisement set of the target user can be directly used as the weight of the standby advertisement, or the product of the weight of the target reference advertisement in the reference advertisement set of the target user and the similarity between the two advertisements can be used as the weight of the standby advertisement, or the weight of the standby advertisement can be determined in other manners, which is not limited in the application.

For example: as shown in fig. 3, in the case where the first preset threshold value is set to 5, the user a does not have purchase behavior of the reference advertisement 1 in behavior data within six months after seeing the pushed reference advertisement 1, the query behavior for the reference advertisement 1 is 4 times, the purchasing behavior is 1 time, and the sharing behavior is 1, 6 times in total, is greater than the first preset threshold value, and therefore, the reference advertisement 1 is removed from the reference advertisement set a of the user a, and the reference advertisement 6 having the highest similarity with the reference advertisement 1 is added to the reference advertisement set a.

Mode two: according to the similarity between each advertisement in the advertisements, at least one advertisement with the similarity larger than or equal to a second preset threshold value is determined, and at least one advertisement with the similarity larger than or equal to the second preset threshold value is used as a standby advertisement set of the target user.

The weight of the target reference advertisement in the reference advertisement set of the target user can be directly used as the weight of the standby advertisement with the highest matching degree with the target user, or the product of the weight of the target reference advertisement in the reference advertisement set of the target user and the similarity between the two advertisements can be used as the weight of the standby advertisement with the highest matching degree with the target user, or the weight of the standby advertisement can be determined in other modes, which is not limited in the application. The second preset threshold is a positive number greater than 0, and the specific value may be determined according to practical situations, which is not limited in this application.

In the second mode, the matching degree between each standby advertisement in the standby advertisement set of the target user and the target user is determined, and the matching degree between the target user and the standby advertisement can be determined by firstly establishing a dimension set of the standby advertisement and the target user and then utilizing the dimension set according to the historical transaction data of the target user and the characteristic data of a plurality of advertisements. And the matching degree between each alternative advertisement in the alternative advertisement set of the target user and the target user can be determined according to the historical transaction data of the target user and the similarity between each advertisement in the bank. For example: and under the condition that the target user purchases a plurality of products, weighting and summing the similarity between the advertisements corresponding to the products purchased by the target user and the standby advertisements, so as to obtain the matching degree between the target user and the standby advertisements.

After the reference advertisement set of the target user is adjusted according to the behavior data of the target user in the preset time, the reference advertisement pushed to the target user can be determined according to the adjusted reference advertisement set, and the determined advertisement is pushed to the target user in a preset mode.

From the above description, it can be seen that the following technical effects are achieved in the embodiments of the present application: feature data of a plurality of advertisements can be obtained from a preset database, so that the similarity among the advertisements is determined, and the data in the bank database is used as support, so that the obtained similarity among the advertisements has reliability. Further, a reference advertisement set can be established for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, each reference advertisement is correspondingly allocated with a weight, the reference advertisement set of the target user is established according to the historical transaction data of the target user, the specificity of different users is taken into consideration, and the reference advertisements in the established reference advertisement set have more referential. According to the total asset amount of the target user, the reference advertisement pushed to the target user is determined from the reference advertisement set, and the determined reference advertisement is pushed to the target user, so that the matching degree between the advertisement pushed to the target user and the target user is improved, and the conversion rate of popularization of bank products is improved.

The above method is described below in connection with a specific embodiment, however, it should be noted that this specific embodiment is only for better illustrating the present application and is not meant to be a undue limitation on the present application.

The invention provides an advertisement pushing method based on advertisement similarity, which comprises the following steps:

step 1: one advertisement set is maintained for each customer in the bank, and each advertisement in each customer's advertisement set corresponds to a weight. The corresponding advertisement sets may be initialized with historical transaction data for each customer, which may include banking products that the customer has purchased or queried. For example: customer a often purchases financial management or queries for insurance, and may then add related advertisements for financial management or insurance to the initialized advertisement collection. For a new customer, an advertisement collection may be initialized based on the customer's economics. For example: the new customer B can recommend financial products with higher purchase amount if the bank deposit is relatively large.

The weight of each advertisement can be determined according to the transaction amount of the product corresponding to the advertisement, and the larger the transaction amount of the product is, the larger the weight of the advertisement corresponding to the product is. The transaction amount herein refers to: the transaction amount of the customer in the specified time range may of course include a historical total transaction amount, or may be a total transaction amount of the product in the specified time range in the bank, which is not limited in this application.

In one embodiment, the banking personnel can also add advertisements to the advertisement set of the client according to the banking requirement, and the weight can be determined according to the importance degree of the advertisement related business in the bank. If a client in the bank has no historical transaction data or the historical transaction data amount is smaller than a preset threshold value, at least one advertisement can be randomly generated according to the business condition of the bank, each advertisement is correspondingly assigned with a weight, and the generated advertisement is added into an advertisement set corresponding to the client.

Step 2: the similarity between the advertisements in the bank can be determined according to the characteristic information of each advertisement in the bank and the historical transaction data, wherein the characteristic information of the advertisements can comprise at least one of the following, but is not limited to: conversion rate, click rate, number of impressions, profit, loss, risk level, purchase amount, total transaction amount, category, purchase frequency of corresponding products of advertisement. There are various methods for calculating the similarity, and this application is not limited thereto. In one embodiment, the dimension set of each advertisement in the bank may be determined according to the feature information and the historical transaction number of each advertisement in the bank, where each dimension set of each advertisement includes at least one dimension subset, and when the dimension sets of two advertisements are determined, the similarity between the corresponding matched dimension subsets in the dimension sets of the two advertisements may be calculated, and then the similarity between the respective dimension subsets may be added, so that the similarity between the two advertisements may be obtained, where the dimension subsets may include, but are not limited to, at least one of the following: conversion rate, click rate, number of impressions, profit, loss, risk level, purchase amount, total transaction amount, category, purchase frequency of corresponding products of advertisement.

Step 3: updating the advertisement set corresponding to each client, and if the similarity of two advertisements A and B in the advertisement set of one client is greater than or equal to a certain threshold value, only the advertisement with larger weight is reserved in the advertisement set; or if the absolute value of the difference in the weights of two advertisements is less than a certain threshold, one of the advertisements may be randomly retained.

Step 4: selecting N advertisements before weight sequencing from the advertisement set of each client, and putting the selected advertisements to the corresponding client, wherein N is a positive integer greater than or equal to 1; or screening advertisements which are capable of being consumed by the client and have weights larger than a certain threshold value from the advertisement set of the client according to the total asset information of the client, and putting the screened advertisements into the client, wherein the advertisements which are capable of being consumed by the client are products of the purchase amount of a product corresponding to the advertisement and a preset multiple corresponding to the product, and the preset multiple can be preset according to the attribute of each product and can be any value larger than 0; or selecting advertisements with the client capable of consuming from the advertisements with the N before the weight ordering from the advertisement set of each client, and putting the selected advertisements to the client.

Step 5: if the client inquires about the product corresponding to the advertisement and the client does not purchase the product corresponding to the advertisement when the inquired times reach a certain threshold value within a period of time (such as 6 months) after the client sees the put advertisement, the advertisement is deleted from the advertisement set corresponding to the client, meanwhile, the advertisement with the highest similarity with the advertisement is added into the advertisement set corresponding to the client, and the weight of the newly added advertisement with the highest similarity is determined by the weight of the deleted advertisement and the similarity between the two advertisements. The weight of the deleted advertisement may be directly equal to the weight of the deleted advertisement or may be the product of the weight of the deleted advertisement and the similarity between the two advertisements, which is not limited in this application.

Step 6: in the step 5, the newly added advertisement may be obtained by combining the following two steps: and taking the advertisement with the similarity to the advertisement to be deleted being greater than a certain threshold value as an alternative advertisement set of the advertisement to be deleted, or ordering the first M advertisements with the similarity to the advertisement to be deleted to form the alternative advertisement set of the advertisement to be deleted. The alternative advertisement set is to delete an advertisement in step 5, and at the same time add a similar advertisement to the deleted advertisement to the customer's advertisement set to mine the customer's potential needs. And selecting the advertisement with the largest matching degree with the client from the alternative advertisement sets, and taking the advertisement as the newly added advertisement. At this time, the weight of the newly added advertisement is determined by the weight of the deleted advertisement and the similarity of the two advertisements.

The matching degree between the candidate advertisement and the client can be determined by first establishing a dimension set of the candidate advertisement and the client in a similar manner to the similarity between the advertisements in the bank determined in the step 2, and then determining the matching degree between the client and the candidate advertisement by utilizing the dimension set. Further, the matching degree between each candidate advertisement in the candidate advertisement set of the advertisement to be deleted and the client can be determined according to the historical transaction data of the client and the similarity between each advertisement in the bank. For example: when the matching degree between the client a and the advertisement a is determined, in the case that the client purchases a plurality of products, the similarity between the advertisement corresponding to each product purchased by the client a and the advertisement a can be weighted and summed, so that the matching degree between the client a and the advertisement a is obtained.

Based on the same inventive concept, the embodiment of the application also provides an advertisement pushing device based on advertisement similarity, as described in the following embodiment. Because the principle of solving the problem by the advertisement pushing device based on the advertisement similarity is similar to that of the advertisement pushing method based on the advertisement similarity, the implementation of the advertisement pushing device based on the advertisement similarity can be referred to the implementation of the advertisement pushing method based on the advertisement similarity, and the repetition is not repeated. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated. FIG. 4 is a block diagram of an advertisement pushing device based on advertisement similarity according to an embodiment of the present application, as shown in FIG. 4, may include: the first acquisition module 401, the first determination module 402, the second acquisition module 403, the establishment module 404, the second determination module 405, and the pushing module 406 are described below.

The first obtaining module 401 may be configured to obtain feature data of a plurality of advertisements from a preset database;

a first determining module 402, configured to determine a similarity between each advertisement in the plurality of advertisements according to the feature data of the plurality of advertisements;

a second acquisition module 403, operable to acquire historical transaction data and a total asset amount for the target user;

the establishing module 404 may be configured to establish a reference advertisement set for the target user according to historical transaction data of the target user and a similarity between advertisements in the plurality of advertisements, where the reference advertisement set includes at least one reference advertisement, and each reference advertisement is assigned a weight correspondingly;

a second determining module 405, configured to determine, from the reference advertisement set, a reference advertisement pushed to the target user according to the total asset amount of the target user;

the pushing module 406 may be configured to push the determined reference advertisement to the target user.

In one embodiment, the advertisement pushing device based on advertisement similarity may further include: the third acquisition module is used for acquiring behavior data of the target user within a preset time after pushing the determined reference advertisement to the target user; and the adjusting module is used for adjusting the reference advertisement or the weight of the reference advertisement in the reference advertisement set according to the behavior data of the target user and the similarity among the advertisements in the plurality of advertisements.

In one embodiment, the advertisement pushing device based on advertisement similarity may further include: a third determining module, configured to determine whether a purchase behavior of a target reference advertisement in the determined reference advertisements exists in behavior data of the target user; a fourth determining module, configured to determine, if it is determined that there is no purchasing behavior for the target reference advertisement in the behavior data of the target user, whether there is behavior data other than purchasing behavior for the target reference advertisement in the behavior data of the target user; a fifth determining module, configured to determine, when it is determined that behavior data other than purchasing behavior for the target reference advertisement exists in the behavior data of the target user, whether the number of behavior data other than purchasing behavior for the target reference advertisement in the behavior data of the target user is greater than or equal to a first preset threshold; and the first removing module is used for removing the target reference advertisement from the reference advertisement set of the target user under the condition that the number of the behavior data of the target user except the purchasing behavior is larger than or equal to a first preset threshold value.

In one embodiment, the advertisement pushing device based on advertisement similarity may further include: a sixth determining module, configured to determine, according to the similarity between each advertisement in the plurality of advertisements, an advertisement with a highest similarity with the target reference advertisement; the first processing module is used for taking the advertisement with the highest similarity with the target reference advertisement as a standby advertisement of the target user; and the second processing module is used for adding the standby advertisement of the target user into the reference advertisement set of the target user and determining the weight of the standby advertisement of the target user according to the weight of the target reference advertisement and the similarity between the standby advertisement of the target user and the target reference advertisement.

In one embodiment, the advertisement pushing device based on advertisement similarity may further include: a seventh determining module, configured to determine, according to the similarity between each advertisement in the plurality of advertisements, at least one advertisement having a similarity with the target reference advertisement greater than or equal to a second preset threshold; a third processing module, configured to use at least one advertisement with a similarity to the target reference advertisement being greater than or equal to a second preset threshold as a standby advertisement set of the target user; an eighth determining module, configured to determine, according to historical transaction data of the target user and a similarity between each advertisement in the plurality of advertisements, a matching degree between each standby advertisement in a standby advertisement set of the target user and the target user; and a fourth processing module, configured to add the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target user to the reference advertisement set of the target user, and determine the weight of the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target user according to the weight of the target reference advertisement and the similarity between the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target reference advertisement.

In one embodiment, the advertisement pushing device based on advertisement similarity may further include: a ninth determining module, configured to determine, according to the similarity between each advertisement in the plurality of advertisements, the similarity between each reference advertisement in the reference advertisement set of the target user; a tenth determining module, configured to determine, according to the similarity between each reference advertisement in the reference advertisement set of the target user, whether there is a similarity between two reference advertisements that is greater than or equal to a third preset threshold; and the second removing module is used for comparing the weights of the two reference advertisements with the similarity larger than or equal to a third preset threshold value and removing the reference advertisement with smaller weight from the reference advertisement set of the target user under the condition that the similarity between the two reference advertisements is larger than or equal to the third preset threshold value.

In one embodiment, the advertisement pushing device based on advertisement similarity may further include: the first judging module is used for determining the similarity between each reference advertisement in the reference advertisement set of the target user according to the similarity between each advertisement in the advertisements; the second judging module is used for determining whether the similarity between the two reference advertisements is greater than or equal to a third preset threshold value according to the similarity between the reference advertisements in the reference advertisement set of the target user; a third judging module, configured to determine, when it is determined that there is a similarity between the two reference advertisements that is greater than or equal to a third preset threshold, whether an absolute value of a difference between weights of the two reference advertisements that is greater than or equal to the third preset threshold is less than or equal to a fourth preset threshold; and the third removing module is used for removing any one of the two reference advertisements with the similarity larger than or equal to the third preset threshold from the reference advertisement set of the target user under the condition that the absolute value of the difference of the weights of the two reference advertisements with the similarity larger than or equal to the third preset threshold is smaller than or equal to a fourth preset threshold.

In one embodiment, the second determining module 405 may include: a descending order arrangement unit, configured to descending order each reference advertisement in the reference advertisement set of the target user according to the weight of each reference advertisement in the reference advertisement set of the target user; and the processing unit is used for determining the reference advertisements pushed to the target user from the reference advertisement set according to the result of descending order of each reference advertisement in the reference advertisement set of the target user and the total asset amount of the target user.

In one embodiment, the processing unit may include: a determining subunit, configured to determine N reference advertisements before ordering according to a result of descending order of each reference advertisement in the reference advertisement set of the target user, where N is a positive integer greater than or equal to 1; and the processing subunit is used for multiplying the lowest purchase amount of the N reference advertisements before the sequencing in the reference advertisement set of the target user by a preset multiple to obtain the reference advertisement with the total asset amount smaller than or equal to the total asset amount of the target user, and the reference advertisement is used as the reference advertisement pushed to the target user.

The embodiment of the application further provides an electronic device, and in particular, referring to a schematic diagram of an electronic device composition structure of the advertisement pushing method based on the advertisement similarity provided in the embodiment of the application shown in fig. 5, the electronic device may specifically include an input device 51, a processor 52, and a memory 53. Wherein the input device 51 may be used for inputting characteristic data of a plurality of advertisements in particular. The processor 52 may be specifically configured to determine, according to the feature data of the plurality of advertisements, a similarity between each advertisement in the plurality of advertisements; acquiring historical transaction data and total asset amount of a target user; establishing a reference advertisement set for the target user according to historical transaction data of the target user and the similarity among advertisements in the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining a reference advertisement pushed to the target user from the reference advertisement set according to the total asset amount of the target user; pushing the determined reference advertisement to the target user. The memory 53 may be used to store parameters such as similarity between advertisements of the plurality of advertisements, historical transaction data and total asset amount of the target user, reference advertisement sets of the target user, and the like.

In this embodiment, the input device may specifically be one of the main apparatuses for exchanging information between the user and the computer system. The input device may include a keyboard, mouse, camera, scanner, light pen, handwriting input board, voice input device, etc.; the input device is used to input raw data and a program for processing these numbers into the computer. The input device may also acquire and receive data transmitted from other modules, units, and devices. The processor may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor, and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable logic controller, and an embedded microcontroller, among others. The memory may in particular be a memory device for storing information in modern information technology. The memory may comprise a plurality of levels, and in a digital system, may be memory as long as binary data can be stored; in an integrated circuit, a circuit with a memory function without a physical form is also called a memory, such as a RAM, a FIFO, etc.; 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 specific functions and effects of the electronic device may be explained in comparison with other embodiments, which are not described herein.

The embodiment of the application also provides a computer storage medium of the advertisement pushing method based on advertisement similarity, wherein the computer storage medium stores computer program instructions, and the computer program instructions can be realized when executed: acquiring characteristic data of a plurality of advertisements from a preset database; according to the characteristic data of the advertisements, determining the similarity between the advertisements in the advertisements; acquiring historical transaction data and total asset amount of a target user; establishing a reference advertisement set for the target user according to historical transaction data of the target user and the similarity among advertisements in the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight; determining a reference advertisement pushed to the target user from the reference advertisement set according to the total asset amount of the target user; pushing the determined reference advertisement to the target user.

In the present embodiment, the storage medium includes, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk (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 of the program instructions stored in the computer storage medium may be explained in comparison with other embodiments, and are not described herein.

It will be apparent to those skilled in the art that the modules or steps of the embodiments of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps 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 appended claims, along with the full scope of equivalents to which such claims are entitled.

The foregoing description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and variations may be made to the embodiment of the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An advertisement pushing method based on advertisement similarity is characterized by comprising the following steps:

acquiring characteristic data of a plurality of advertisements from a preset database;

according to the characteristic data of the advertisements, determining the similarity between the advertisements in the advertisements;

acquiring historical transaction data and total asset amount of a target user;

establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight;

determining a reference advertisement pushed to the target user from the reference advertisement set according to the total asset amount of the target user;

pushing the determined reference advertisement to the target user;

Wherein after establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity between the advertisements in the plurality of advertisements, the method further comprises:

according to the similarity between the advertisements in the advertisements, determining the similarity between the reference advertisements in the reference advertisement set of the target user;

determining whether the similarity between two reference advertisements is greater than or equal to a third preset threshold according to the similarity between each reference advertisement in the reference advertisement set of the target user;

and under the condition that the similarity between the two reference advertisements is larger than or equal to a third preset threshold value, comparing the weights of the two reference advertisements with the similarity larger than or equal to the third preset threshold value, and removing the reference advertisement with smaller weight from the reference advertisement set of the target user.

2. The method of claim 1, further comprising, after pushing the determined reference advertisement to the target user:

acquiring behavior data of the target user within a preset time after pushing the determined reference advertisement to the target user;

and adjusting the reference advertisement or the weight of the reference advertisement in the reference advertisement set according to the behavior data of the target user and the similarity between the advertisements in the plurality of advertisements.

3. The method of claim 2, wherein the behavioral data comprises at least one of: query behavior, collection behavior, purchasing behavior, sharing behavior, and purchasing behavior.

4. The method of claim 3, wherein adjusting the reference advertisement or the weight of the reference advertisement in the reference advertisement set based on the behavioral data of the target user and the similarity between each advertisement in the plurality of advertisements comprises:

determining whether purchasing behavior of a target reference advertisement in the determined reference advertisements exists in behavior data of the target user;

determining whether behavior data of the target user except for purchasing behavior exists in the behavior data of the target user under the condition that the purchasing behavior of the target reference advertisement does not exist in the behavior data of the target user;

determining whether the number of the behavior data of the target user except the purchasing behavior is larger than or equal to a first preset threshold value or not under the condition that the behavior data of the target user except the purchasing behavior exists in the behavior data of the target user;

And removing the target reference advertisement from the reference advertisement set of the target user under the condition that the number of the behavior data of the target user except the purchasing behavior is larger than or equal to a first preset threshold value.

5. The method of claim 4, further comprising, after removing the targeted reference advertisement from the targeted user's reference advertisement set:

determining the advertisement with the highest similarity with the target reference advertisement according to the similarity between the advertisements in the advertisements;

taking the advertisement with the highest similarity with the target reference advertisement as a standby advertisement of the target user;

and adding the standby advertisement of the target user into the reference advertisement set of the target user, and determining the weight of the standby advertisement of the target user according to the weight of the target reference advertisement and the similarity between the standby advertisement of the target user and the target reference advertisement.

6. The method of claim 4, further comprising, after removing the targeted reference advertisement from the targeted user's reference advertisement set:

Determining at least one advertisement with the similarity to the target reference advertisement being greater than or equal to a second preset threshold according to the similarity between each advertisement in the plurality of advertisements;

at least one advertisement with the similarity with the target reference advertisement being greater than or equal to a second preset threshold value is used as a standby advertisement set of the target user;

determining the matching degree between each standby advertisement in the standby advertisement set of the target user and the target user according to the historical transaction data of the target user and the similarity between each advertisement in the plurality of advertisements;

adding the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target user into the reference advertisement set of the target user, and determining the weight of the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target user according to the weight of the target reference advertisement and the similarity between the standby advertisement with the highest matching degree between the standby advertisement set of the target user and the target reference advertisement.

7. The method of claim 1, further comprising, after establishing a reference advertisement set for the target user based on historical transaction data of the target user and similarities between individual advertisements of the plurality of advertisements:

determining whether an absolute value of a difference of weights of the two reference advertisements with the similarity being greater than or equal to a third preset threshold value is less than or equal to a fourth preset threshold value under the condition that the similarity between the two reference advertisements is greater than or equal to the third preset threshold value;

and removing any one of the two reference advertisements with the similarity greater than or equal to the third preset threshold value from the reference advertisement set of the target user under the condition that the absolute value of the difference of the weights of the two reference advertisements with the similarity greater than or equal to the third preset threshold value is smaller than or equal to a fourth preset threshold value.

8. The method of claim 1, wherein determining the reference advertisement pushed to the target user from the reference advertisement set based on the total asset amount of the target user comprises:

According to the weight of each reference advertisement in the reference advertisement set of the target user, carrying out descending order arrangement on each reference advertisement in the reference advertisement set of the target user;

determining the reference advertisements pushed to the target user from the reference advertisement set according to the result of descending order arrangement of each reference advertisement in the reference advertisement set of the target user and the total asset amount of the target user.

9. The method of claim 8, wherein determining the reference advertisements pushed to the target user from the reference advertisement set based on the result of the descending order of the individual reference advertisements in the reference advertisement set of the target user and the total asset amount of the target user comprises:

determining N reference advertisements before sequencing according to the descending order arrangement result of each reference advertisement in the reference advertisement set of the target user, wherein N is a positive integer greater than or equal to 1;

and the reference advertisement, of which the value of the multiplication of the lowest purchase amount and the preset multiple in the N before the sequencing in the reference advertisement set of the target user is smaller than or equal to the total asset amount of the target user, is used as the reference advertisement pushed to the target user.

10. An advertisement pushing device based on advertisement similarity, comprising:

the first acquisition module is used for acquiring characteristic data of a plurality of advertisements from a preset database;

the first determining module is used for determining the similarity between the advertisements in the advertisements according to the characteristic data of the advertisements;

the second acquisition module is used for acquiring historical transaction data and total asset amount of the target user;

the establishing module is used for establishing a reference advertisement set for the target user according to the historical transaction data of the target user and the similarity among the advertisements, wherein the reference advertisement set comprises at least one reference advertisement, and each reference advertisement is correspondingly distributed with a weight;

the second determining module is used for determining the reference advertisements pushed to the target user from the reference advertisement sets according to the total asset amount of the target user;

the pushing module is used for pushing the determined reference advertisement to the target user;

11. An advertisement push device based on advertisement similarity comprising a processor and a memory for storing processor executable instructions, which processor, when executing the instructions, implements 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 of claims 1 to 9.