CN112200607A

Movatterモバイル変換

Info

Publication number: CN112200607A
Application number: CN202011065854.XA
Authority: CN
Inventors: 黄文强; 黄雅楠; 胡传杰; 浮晨琪; 徐晨敏
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2020-09-30
Filing date: 2020-09-30
Publication date: 2021-01-08

Abstract

Translated fromChinese

本申请提供了一种推广信息的推送方法，应用于推送系统，所述推送系统包括自助终端和服务器，该方法包括：根据用户的画像信息利用贝叶斯模型确定向用户是否推送推广信息，然后用户自己输入是否接收推广信息的选择信息，据此对贝叶斯结果表进行更新，最后根据贝叶斯结果表向用户推送推广信息。该方法对不同用户根据不同的需求进行针对性定制，同时用户可以获得自己感兴趣的推送内容，提高了用户体验，提高了推送的效率。

The present application provides a method for pushing promotion information, which is applied to a push system. The push system includes a self-service terminal and a server. The method includes: using a Bayesian model to determine whether to push promotion information to the user according to the user's portrait information, and then The user inputs the selection information of whether to receive the promotion information, updates the Bayesian result table accordingly, and finally pushes the promotion information to the user according to the Bayesian result table. The method performs targeted customization for different users according to different needs, and at the same time, the users can obtain the push content that they are interested in, which improves the user experience and improves the push efficiency.

Description

Promotion information pushing method, device, equipment and medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for pushing promotion information.

Background

With the continuous development of electronic commerce, mobile payment technology is produced. To accommodate mobile payment technology, many banks have introduced cell phone banks. The user can complete various functions such as transfer, consumption, investment and the like through the mobile phone bank.

With the increasing scale of users of mobile banking, many banks increase popularization information in the mobile banking. For example, the advertisement in the form of characters, pictures, videos and the like is presented to the user on an open screen page, a login page or a homepage, and the advertisement is used for promoting information, such as promoting bank financing products.

However, the existing pushing method has poor pushing effect and is difficult to meet the service requirement.

Disclosure of Invention

The application provides a promotion information pushing method, which determines promotion information according to portrait information of a user, realizes personalized pushing, improves promotion efficiency, updates results through interaction with the user, enables pushing to meet user requirements, and improves pushing effect. The application also provides a device, equipment, a computer readable storage medium and a computer program product corresponding to the method.

In a first aspect, the present application provides a method for pushing promotion information, which is applied to a pushing system, where the pushing system includes a self-service terminal and a server, and the method includes: the method comprises the steps that a self-service terminal obtains portrait information of a user handling business at the self-service terminal, then whether popularization information is pushed to the user or not is predicted by a naive Bayesian model according to the portrait information, a prediction result is obtained, the prediction result is stored in a Bayesian result table, configuration information input by the user is received, the configuration information comprises selection information of whether the user receives the popularization information or not, a server determines whether the Bayesian result table and an updating range of the Bayesian result table are updated or not by the aid of a pushing model according to the selection information, and finally the popularization information is pushed to the user according to the updated Bayesian result table.

In some possible implementations, the push model determines whether to update the bayesian result table and the update range of the bayesian result table by machine learning.

In some possible implementations, the method includes:

and when the difference value between the inconsistent proportion of the selection information of the target area and the prediction result in the Bayesian result table and the inconsistent proportion of other areas is larger than a preset value, the server updates the target area.

In some possible implementations, the method includes:

and when the proportion of the inconsistency of the selected information and the prediction result in the Bayesian result table reaches a preset proportion, the server updates all the areas of the Bayesian result table.

In some possible implementations, the receiving, by the self-service terminal, the configuration information input by the user includes:

and the self-service terminal receives the configuration information input by the user through the identification code.

In some possible implementations, the method further includes:

and the server updates the Bayesian result table according to feedback information of business handling after the user updates the Bayesian result table.

In a second aspect, the present application provides a promotion information pushing device, an application pushing system, where the pushing system includes a self-service terminal and a server, including:

the communication module is used for acquiring portrait information of a user handling services at the self-service terminal;

the prediction module is used for predicting whether promotion information is pushed to the user or not by utilizing a naive Bayesian model according to the portrait information to obtain a prediction result, and the prediction result is stored in a Bayesian result table;

the communication module is configured to receive configuration information input by the user, where the configuration information includes selection information of whether the user receives the promotion information;

the determining module is used for determining whether to update the Bayesian result table and the updating range of the Bayesian result table by using a push model according to the selection information;

and the pushing module is used for pushing the promotion information to the user according to the updated Bayesian result table.

In some possible implementations, the determining module is specifically configured to:

In some possible implementations, the communication module is specifically configured to:

and receiving the configuration information input by the user through the identification code.

In some possible implementations, the apparatus further includes:

and the updating module is used for updating the Bayesian result table according to the feedback information of the business transacted after the user updates the Bayesian result table.

In a third aspect, the present application provides an apparatus comprising a processor and a memory. The processor and the memory are in communication with each other. The processor is configured to execute the instructions stored in the memory to cause the device to perform the method of pushing promotional information as in the first aspect or any implementation manner of the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and the instructions instruct a device to execute the method for pushing promotion information according to the first aspect or any implementation manner of the first aspect.

In a fifth aspect, the present application provides a computer program product containing instructions, which when run on a device, causes the device to perform the method for pushing promotional information according to the first aspect or any implementation manner of the first aspect.

The present application can further combine to provide more implementations on the basis of the implementations provided by the above aspects.

According to the technical scheme, the embodiment of the application has the following advantages:

the embodiment of the application provides a promotion information pushing method, which can determine whether promotion information is pushed to a user or not by utilizing a Bayesian model according to portrait information of the user, then the user inputs selection information whether promotion is received or not, updates a Bayesian result table according to the selection information, and finally pushes the promotion information to the user according to a Bayesian result. The method solves the problems that the content of the popularization information is numerous and complicated at present, different users cannot be customized according to different requirements, and the popularization information is wasted, and meanwhile, the users can obtain the interested push content, so that the user experience is improved, and the push efficiency is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

Fig. 1 is a schematic view of an application scenario of a method for pushing promotion information according to an embodiment of the present application;

fig. 2 is a flowchart of a method for pushing promotion information according to an embodiment of the present application;

fig. 3 is a structural diagram of a push device for promotion information according to an embodiment of the present application.

Detailed Description

The scheme in the embodiments provided in the present application will be described below with reference to the drawings in the present application.

The terms "first," "second," and the like in the description and in the claims of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely descriptive of the various embodiments of the application and how objects of the same nature can be distinguished.

In order to facilitate understanding of the technical solutions of the present application, some technical terms related to the present application are described below.

The promotion means that the advertising effect can be achieved through means such as media. The promoted object can be a product, the product can be a solid product, such as precious metal like gold, and the product can also be a virtual product, such as a digitalized financial product and the like.

The promotion information refers to information for promoting an object to be promoted. Generally, the promotional information refers to advertisements. The promotion information may be of various types, such as a text type, a picture type, a video type, an audio type, or a combination of the above different types. The embodiments of the present application do not limit this.

The Bayesian classification is a generic term of a class of classification algorithms, and the class of algorithms is based on Bayesian theorem, so the classification algorithms are collectively called Bayesian classification. Bayes' theorem is a theorem in probability theory describing the probability of an event occurring under known conditions. For example, if a cancer is known to be life-related, using Bayesian theorem, the person's age can be known to more accurately calculate his probability of getting cancer. Naive bayes classification is a common classification method in bayes classification. The Bayesian formula is as follows:

at present, a self-service terminal can show promotion information such as financial advertisements and credit advertisements to a user while providing services, but the advertisements are various and cannot meet the user requirements in a targeted manner, so that the efficiency of promoting the information is not high.

In view of this, the present application provides a method for pushing promotion information. The method is applied to a push system comprising a self-service terminal 102 and aserver 104, as shown in fig. 1. The self-service terminal 102 may be a self-service deposit/withdrawal machine of a bank, an APP of a mobile banking, or other self-service terminal equipment capable of providing services.

In the method, the self-service terminal determines whether promotion information is pushed to a user or not by using the Bayesian model according to the portrait information of the user, then the user inputs selection information whether promotion is received or not by himself through the identification code, the Bayesian model is updated accordingly, and finally the promotion information is pushed to the user according to the Bayesian result. According to the method, the promotion information meeting the user requirements is customized according to the user characteristics, and meanwhile, the promotion information is updated through interaction with the user, so that the promotion information is pushed to meet the user requirements better, and the promotion information efficiency is improved.

Next, a method for designing popularization information provided by the embodiment of the present application will be described with reference to the drawings.

Referring to a flowchart of a method for pushing promotion information shown in fig. 2, the method includes the following steps:

s202: self-service terminal 102 obtains, fromserver 104, portrait information of a user transacting business at self-service terminal 102.

In some possible implementations, the portrait information of the user may include characteristic factors of the user's academic calendar, age, gender, job condition, personality, and the like.

Specifically, the user logs in an account via the self-service terminal 102, and through the account, the self-service terminal 102 acquires user image information corresponding to the account, such as the user's academic calendar, age, sex, work status, character, and the like, from theserver 104.

The self-service terminal 102 may be a self-service deposit and withdrawal machine of a bank, the self-service deposit and withdrawal machine is directly connected with a bank background system, and a user interacts with the self-service deposit and withdrawal machine.

Theserver 104 is controlled by the bank side, and user portrait information corresponding to the user personal account is stored therein.

S204: and the self-service terminal 102 predicts whether promotion information is pushed to the user or not by using a naive Bayesian model according to the portrait information to obtain a prediction result.

In some possible implementations, the forming of the naive bayes model comprises: (1) let x ═ { a1, a2, …, Am } be the pictorial information of a customer to be classified, a be the characteristic attribute of x, where the characteristic attribute may be one or more of academic calendar, age, sex, work condition, character, and the like. (2) The presence category set C is (Y1, Y2) and indicates whether or not the promotion information is pushed to the user, Y1 indicates that the promotion information is pushed, and Y2 indicates that the promotion information is not pushed. (3) P (Y1| x), P (Y2| x), is calculated, as is the probability of whether or not to push an advertisement to a client under the new feature attributes. By comparing the sizes of P (Y1| x) and P (Y2| x), the corresponding result is obtained.

S206: self-service terminal 102 receives the configuration information entered by the user.

In some possible implementations,kiosk 102 may present an identification code to the user, with which the user customizes configuration information that includes information that the user selects whether to receive the promotional information. When the self-service terminal 102 is a self-service deposit and withdrawal machine, the identification code presented to the user may be a two-dimensional code or a bar code, and the user enters a configuration information interface by scanning the two-dimensional code or the bar code to set configuration information.

S208:kiosk 102 sends the obtained selection information toserver 104.

Thereby, theserver 104 obtains the selection information set by the user himself.

S210: theserver 104 determines whether to update the bayesian result table and the updating range of the bayesian result table by using a push model according to the selection information set by the user.

In some possible implementations, the push model is established by machine learning. And obtaining a method for updating the optimized data by adopting a method of induction and summarization through historical analysis of data modification in the historical data using process.

In specific implementation, the background system inputs the obtained selection information set by the user into an output result table of the naive Bayes classifier, and updates a Bayes data table. The background system records how many users change the results of the users, and starts to update the classification result table when the results reach a certain degree.

The specific method is carried out through a push model, a naive Bayes classification table and a user change result are input into the push model, and the push model outputs whether the table needs to be updated or not and the update range of the table.

The push model can adopt an Adaboost algorithm, different classifiers are trained by the Adaboost algorithm aiming at the same training set, and then the classifiers are collected to form a stronger final classifier. The algorithm is implemented by changing data distribution, and determines the weight of each sample according to whether the classification of each sample in each training set is correct and the accuracy of the last overall classification. And new data of the modified weight is sent to a lower-layer classifier for training, and then the classifiers obtained by each training are fused to be used as a final decision classifier, so that the learning precision of the algorithm is obviously improved.

Similarly, the push model may employ an Artificial Neural Network (ANN) algorithm. Neural networks are widely interconnected parallel networks of simple units with adaptability, whose organization can simulate the biological nervous system's interaction with real-world objects. In the invention, a simple M-P neuron model can be adopted, and the model is trained through a Back Propagation (BP) algorithm, so that the precision can meet the requirement.

When the difference between the inconsistent ratio of the selection information of the target area in the bayesian result table and the prediction result and the inconsistent ratio of other areas is greater than the predicted value, theserver 104 replaces the target area.

And when the proportion of the inconsistency between the selected information and the prediction result in the Bayesian result table reaches a preset proportion, theserver 104 updates all the areas of the Bayesian result table.

Specifically, when the difference between the prediction result predicted according to the bayesian model and the selection information input by the user is small for the promotion information to be pushed, the corresponding part is updated, and when the difference is large, that is, the difference exceeds a set threshold, for example, 3%, all data is updated.

Therefore, the Bayesian model can be continuously updated according to the selection information input by the user, so that the user requirements can be better met.

S212:server 104 sends the update results to self-service terminal 102.

Thus, the self-service terminal 102 obtains the Bayesian result table updated according to the input selection information of the user, and the Bayesian result table is more in line with the requirements of the user.

S214: and the self-service terminal 102 pushes promotion information to the user according to the updated Bayesian result table.

In some possible implementation manners, when the user transacts business through the autonomous teller machine, the feedback information of the user can be acquired after the pushed promotion information is acquired according to the scheme described in the application, so that the Bayesian result table is updated.

The feedback information of the user refers to information that the user can provide the emotion of the user, such as facial expressions, languages, characters and the like after the user acquires the pushed popularization information, and if the user has the dislike emotion, the Bayesian result table is optimized again, so that the automatic updating of the data table is realized, and the user's requirements are met.

Based on the above description, the embodiment of the present application provides a method for pushing promotion information, which is applied to a pushing system, where the pushing system includes a self-service terminal 102 and aserver 104, the method can determine whether to push promotion information to a user by using a bayesian model according to portrait information of the user, then the user inputs selection information whether to receive promotion by himself through an identification code, updates the bayesian model accordingly, and finally pushes promotion information to the user according to a bayesian result. The method solves the problem that the pushed advertisement is wasted because the content of the currently promoted information is numerous and complicated, and different users cannot be customized according to different requirements, and meanwhile, the users can obtain the pushed content which are interested by themselves, so that the user experience is improved, and the pushing efficiency is improved.

The method for designing the promotion information provided by the embodiment of the present application is described in detail with reference to fig. 2, and then, a device and an apparatus for pushing the promotion information provided by the embodiment of the present application are described with reference to the accompanying drawings.

Referring to the schematic structural diagram of the push apparatus for promoting information shown in fig. 3, as shown in fig. 3, the apparatus 300 applies a push system, where the push system includes a self-service terminal 102 and aserver 104, and includes: the method comprises the following steps: a communication module 302, a prediction module 304, a determination module 306, and a push module 308.

A communication module 302 for obtaining portrait information of a user transacting business at the self-service terminal 102;

the prediction module 304 is configured to predict whether promotion information is pushed to the user by using a naive bayesian model according to the portrait information to obtain a prediction result, where the prediction result is stored in a bayesian result table;

the communication module 302 is configured to receive configuration information input by the user, where the configuration information includes selection information of whether to receive the promotion information by the user;

a determining module 306, configured to determine whether to update the bayesian result table and an update range of the bayesian result table by using a push model according to the selection information;

a pushing module 308, configured to push the promotion information to the user according to the updated bayesian result table.

In some possible implementations, the determining module 306 is specifically configured to:

when the difference between the inconsistent ratio of the selection information of the target area in the bayesian result table and the prediction result and the inconsistent ratio of other areas is greater than a preset value, theserver 104 updates the target area.

when the proportion of the inconsistency between the selected information and the predicted result in the bayesian result table reaches a preset proportion, theserver 104 updates all the areas of the bayesian result table.

In some possible implementations, the apparatus further includes:

The push device 300 for promoting information according to the embodiment of the present application may correspond to performing the method described in the embodiment of the present application, and the above and other operations and/or functions of each module of the push device 300 for promoting information are respectively for implementing corresponding flows of each method in fig. 2, and are not described herein again for brevity.

The application provides equipment for realizing a pushing method of promotion information. The apparatus includes a processor and a memory. The processor and the memory are in communication with each other. The processor is configured to execute the instructions stored in the memory to cause the device to perform the pushing method of the promotion information.

The application provides a computer-readable storage medium, which stores instructions that, when executed on a device, cause the device to execute the above-mentioned push method for promotion information.

The present application provides a computer program product containing instructions that, when run on a device, cause the device to perform the above-mentioned push method of promotional information.

It should be noted that the above-described embodiments of the apparatus are merely schematic, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiments of the apparatus provided in the present application, the connection relationship between the modules indicates that there is a communication connection therebetween, and may be implemented as one or more communication buses or signal lines.

Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus necessary general-purpose hardware, and certainly can also be implemented by special-purpose hardware including special-purpose integrated circuits, special-purpose CPUs, special-purpose memories, special-purpose components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions may be various, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, the implementation of a software program is more preferable. Based on such understanding, the technical solutions of the present application may be substantially embodied in the form of a software product, which is stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, an exercise device, or a network device) to execute the method according to the embodiments of the present application.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, training device, or data center to another website site, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a training device, a data center, etc., that incorporates one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.