CN113450158A - Bank activity information pushing method and device - Google Patents

Abstract

Translated fromChinese

本发明公开了一种银行活动信息推送方法及装置，应用于大数据技术领域，其中该方法包括：获取用户的手机银行操作日志、征信信息和风险承受能力信息；将用户的手机银行操作日志、征信信息和风险承受能力信息，输入银行活动信息预测模型，输出预测的银行活动信息；将预测的银行活动信息推送给用户。本发明根据用户的手机银行操作日志、结合用户的征信信息和风险承受能力信息，利用银行活动信息预测模型得到预测的银行活动信息，可以实现在低成本场景下银行活动信息精准推送到用户，提高活动消息决策的效率，有利于手机银行获客、增强用户的粘性。

The invention discloses a method and device for pushing banking activity information, which are applied to the field of big data technology. The method includes: acquiring a user's mobile banking operation log, credit information and risk tolerance information; , credit information and risk tolerance information, input the bank activity information prediction model, output the predicted bank activity information; push the predicted bank activity information to the user. According to the user's mobile banking operation log, combined with the user's credit information and risk tolerance information, the present invention obtains the predicted bank activity information by using the bank activity information prediction model, and can realize the accurate push of the bank activity information to the user in a low-cost scenario. Improving the efficiency of event message decision-making is beneficial for mobile banking to acquire customers and enhance user stickiness.

Description

Bank activity information pushing method and device

Technical Field

The invention relates to the technical field of big data, in particular to a bank activity information pushing method and device.

Background

This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

The traditional business pushing of the existing bank faces the following difficulties: as the financial transaction handled by the user is changed to be online, the traditional bank website pushing mode is increased and weak; the short message pushing can not carry out service recommendation according to different preferences of each user; the traditional pushing mode is characterized in that the resource investment is large and depends on the business proficiency of the hall manager through the mode of transmitting the leaflet and explaining by the hall manager. Therefore, how to realize accurate pushing of bank activity information to a user under the condition of small investment resources is a technical problem to be solved urgently at present.

Disclosure of Invention

The embodiment of the invention provides a bank activity information pushing method, which is used for solving the technical problem that the existing bank activity information is difficult to realize accurate pushing to users in a low-cost scene, and comprises the following steps:

acquiring a mobile banking operation log, credit investigation information and risk bearing capacity information of a user;

inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of the user into a banking activity information prediction model, and outputting predicted banking activity information; the bank activity information prediction model is obtained by training a machine learning model according to historical user data, wherein the historical user data comprises: the method comprises the steps that mobile phone banking operation logs, credit investigation information and risk bearing capacity information of historical users and bank activity information recommended for the historical users are obtained;

and pushing the predicted bank activity information to the user.

The embodiment of the invention also provides a device for pushing the bank activity information, which is used for solving the technical problem that the existing bank activity information is difficult to realize accurate pushing to users in a low-cost scene, and comprises:

an acquisition module: the system comprises a mobile phone bank, a risk management server and a risk management server, wherein the mobile phone bank is used for acquiring mobile phone bank operation logs, credit investigation information and risk bearing capacity information of a user;

a prediction module: the system is used for inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of a user into a banking activity information prediction model and outputting predicted banking activity information; the bank activity information prediction model is obtained by training a machine learning model according to historical user data, wherein the historical user data comprises: the method comprises the steps that mobile phone banking operation logs, credit investigation information and risk bearing capacity information of historical users and bank activity information recommended for the historical users are obtained;

a pushing module: for pushing the predicted banking activity information to the user.

The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the bank activity information pushing method when executing the computer program.

The embodiment of the invention also provides a computer readable storage medium, which stores a computer program for executing the bank activity information pushing method.

In the embodiment of the invention, the operation log, credit investigation information and risk bearing capacity information of a mobile phone bank of a user are obtained; inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of the user into a banking activity information prediction model, and outputting predicted banking activity information; the bank activity information prediction model is obtained by training a machine learning model according to historical user data, wherein the historical user data comprises: the method comprises the steps that mobile phone banking operation logs, credit investigation information and risk bearing capacity information of historical users and bank activity information recommended for the historical users are obtained; pushing the predicted bank activity information to the user; compared with the technical scheme of traditional bank website pushing in the prior art, the method has the advantages that the predicted bank activity information is obtained by utilizing the bank activity information prediction model according to the mobile phone bank operation log of the user and by combining the credit investigation information and the risk bearing capacity information of the user, the bank activity information can be accurately pushed to the user in a low-cost scene, the activity information decision efficiency is improved, the mobile phone bank can obtain customers, and the stickiness of the user is enhanced.

Drawings

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

FIG. 1 is a flow chart of a method for pushing bank activity information according to an embodiment of the present invention;

FIG. 2 is a flowchart of an embodiment of a method for pushing information about banking activities according to an embodiment of the present invention;

FIG. 3 is a flowchart of an embodiment of a method for pushing information about banking activities according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a bank activity information pushing device according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an embodiment of a bank activity information pushing device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.

In order to realize accurate pushing of bank activity information to a user in a low-cost scene, the embodiment of the invention obtains the predicted bank activity information by using the bank activity information prediction model according to the mobile banking operation log of the user and by combining credit investigation information and risk bearing capacity information of the user, and realizes accurate pushing of the bank activity information to the user in the low-cost scene. Fig. 1 is a flowchart of a method for pushing bank activity information according to an embodiment of the present invention. As shown in fig. 1, the method for pushing bank activity information in the embodiment of the present invention may include:

step 101, acquiring a mobile banking operation log, credit investigation information and risk bearing capacity information of a user;

102, inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of a user into a banking activity information prediction model, and outputting predicted banking activity information; the bank activity information prediction model is obtained by training a machine learning model according to historical user data, wherein the historical user data comprises: the method comprises the steps that mobile phone banking operation logs, credit investigation information and risk bearing capacity information of historical users and bank activity information recommended for the historical users are obtained;

and 103, pushing the predicted bank activity information to the user.

It can be known from the flow shown in fig. 1 that the method for pushing bank activity information in the embodiment of the present invention is different from the technical scheme of short message pushing in the prior art, and the method obtains the predicted bank activity information by using the bank activity information prediction model according to the mobile banking operation log of the user and by combining the credit investigation information and the risk tolerance information of the user, so as to realize accurate pushing of the bank activity information to the user in a low-cost scenario.

In one embodiment, obtaining the cell phone banking operation log of the user may include: the method includes the steps of embedding a Software Development Kit (SDK) for data collection in a mobile banking system, and calling a data collection system to obtain an operation log of a user, where the operation log may include: and recording important operation and business operation of the user. The acquiring of the credit investigation information of the user may include: and acquiring credit investigation information of the user through the bank background. The credit investigation information may include, for example, personal credit information collected, organized, maintained by a personal credit database established by a particular institution, used to provide credit report inquiry services for commercial banks and individuals, and used to provide information-related services for other purposes such as monetary policy making, financial regulation, and legal and regulatory provisions. Obtaining the risk tolerance information of the user may include obtaining the risk tolerance information of the user through a bank background. The risk tolerance information may include, for example, information about the ability to bear risks, i.e., how much investment loss can be borne without affecting normal life, and the risk tolerance information is comprehensively measured and related to personal asset conditions, family conditions, working conditions, and the like, and may be obtained by a bank through a user completing a risk tolerance test.

In one embodiment, after the mobile banking operation log, the credit investigation information and the risk tolerance information of the user are obtained, the mobile banking operation log, the credit investigation information and the risk tolerance information of the user are input into a bank activity information prediction model, and predicted bank activity information is output. The bank activity information prediction model is obtained by training a machine learning model according to historical user data. The historical user data includes: the mobile phone banking operation log, credit investigation information and risk bearing capacity information of the historical user, and the banking activity information recommended by the historical user. For example, the bank activity information prediction model can be obtained by selecting characteristic variables with relatively large correlation based on historical guest mobile phone bank operation logs, credit investigation information, risk tolerance information and the like, and bank activity information recommended for historical users, and training a machine learning model through a machine learning algorithm. After the bank activity information prediction model is obtained, characteristic variables such as mobile phone bank operation logs, credit investigation information and risk bearing capacity information of the user are input, the business which the user wants to handle at present or the activity which the user wants to participate in, namely the predicted bank activity information, can be predicted, and therefore accurate bank activity information pushing is achieved. For example, the mobile phone bank operation log, credit investigation information and risk tolerance information of the historical user and the bank activity information recommended by the historical user are obtained, a machine learning algorithm is adopted to train a machine learning model to obtain a bank activity information prediction model, and the mobile phone bank operation log, the credit investigation information and the risk tolerance information of the user are input into the well-constructed bank activity information prediction model to obtain predicted bank activity information.

In one embodiment, after inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of the user into the banking activity information prediction model and outputting the predicted banking activity information, the predicted banking activity information is pushed to the user. For example, after obtaining the predicted banking information, the banking information is pushed to the user through a virtual medium such as an online internet. For another example, after the predicted bank activity information is obtained, the bank activity information is pushed to the user through a mobile banking system.

In order to improve the accuracy of predicting the bank activity information, in one embodiment, the mobile banking operation log of the user records at least one of the following information: the user clicks the page, the time period when the user transacts the service, and the location area when the user transacts the service. As an example, a user clicks a financial page for multiple times in a mobile phone bank, the user behavior of clicking the financial page for multiple times is collected into a mobile phone bank operation log, credit investigation information and risk bearing capacity information of the user are combined and input into a bank activity information prediction model, predicted bank activity information is output to be bank activity information related to financial management, and then the bank activity information related to financial management can be pushed to the user; the time period of business handling of the user is usually within the range of nine o ' clock and half to eleven o ' clock and one to three o ' clock in the afternoon, the time period of business handling of the user is collected into a mobile banking operation log, credit information and risk bearing capacity information of the user are combined and input into a banking activity information prediction model, predicted banking activity information is output to be banking activity information related to stock speculation, and then the banking activity information related to stock speculation can be pushed to the user; the location area of the user when handling the business is Beijing, the mobile banking operation log is collected when the user handles the business, the credit investigation information and the risk bearing capacity information of the user are combined and input into the banking activity information prediction model, the predicted banking activity information is output to be the banking activity information related to the Beijing, and then the banking activity information related to the Beijing can be pushed to the user.

Fig. 2 is a flowchart of an embodiment of a method for pushing bank activity information according to the embodiment of the present invention. As shown in fig. 2, before inputting the mobile banking operation log, credit investigation information, and risk tolerance information of the user into the banking activity information prediction model, the method for pushing banking activity information in the embodiment of the present invention may further include:

step 201, obtaining historical user data;

step 202, dividing historical user data into a training set and a test set;

step 203, training the machine learning model by using a training set to obtain a bank activity information prediction model;

and 204, testing the bank activity information prediction model by using the test set, and optimizing the bank activity information prediction model according to the test result.

As can be seen from the flow shown in fig. 2, in the bank activity information pushing method according to the embodiment of the present invention, the bank activity information prediction model is constructed by combining the mobile phone bank operation log, credit investigation information, and risk tolerance information of the historical user, and the historical user data of the bank activity information recommended for the historical user, which are divided into the training set to train the machine learning model, obtain the bank activity information prediction model, and test the bank activity information prediction model by the test set, and the bank activity information prediction model is optimized according to the test result, so that the mobile phone bank operation log, credit investigation information, and risk tolerance information of the historical user, and the bank activity information recommended for the historical user are combined to construct the bank activity information prediction model capable of accurate prediction.

In one embodiment, the obtaining of historical user data may be: the method comprises the steps of obtaining the past objective mobile banking operation logs, credit investigation information and risk tolerance information of a user, wherein the user purchases a financial product, fills a new piece of personal information and tests the risk tolerance in the mobile banking operation seven days ago.

In one embodiment, after obtaining historical user data, the historical user data is divided into training sets and test sets. For example, the historical user data is divided into two mutually exclusive sets, one set is a training set, and the remaining set is a test set, for example, the training set accounts for 80% of the historical user data, the test set accounts for 20% of the historical user data, and both are randomly extracted from the sample, so that the consistency of the data distribution in the training set and the test set can be maintained, and the model trained by the historical user data in the training set can obtain the best performance on the test set.

In one embodiment, after the historical user data is divided into a training set and a testing set, the machine learning model is trained by the training set to obtain a bank activity information prediction model. For example, the data included in the training set is used to train the machine learning model, that is, parameters such as weight and bias of the machine learning model are determined, and the bank activity information prediction model is obtained, for example, the machine learning model is used, the training set is input into an input layer of a neural network as features, then training is performed, each neuron performs log-probability regression in training, and after the training is performed on an output layer, the well-constructed bank activity information prediction model is obtained.

In one embodiment, after the machine learning model is trained by using the training set to obtain the bank activity information prediction model, the bank activity information prediction model is tested by using the testing set, and the bank activity information prediction model is optimized according to the test result. For example, the test set is used when evaluating the generalization ability of the final bank activity information prediction model after training is completed, for example, the operation of clicking the financial transaction by the user in the test set is input to the bank activity information prediction model, whether the bank activity information prediction model can output the predicted bank activity information about financial transaction is checked, and the bank activity information prediction model is optimized according to whether the predicted bank activity information matches the operation of clicking the financial transaction by the user in the input test set.

Fig. 3 is a flowchart of an embodiment of a method for pushing bank activity information according to the embodiment of the present invention. As shown in fig. 3, in the method for pushing bank activity information, acquiring a mobile banking operation log, credit investigation information, and risk tolerance information of a user may include:

301, acquiring a mobile phone bank operation log of a user uploaded by a mobile phone bank in real time;

and 302, acquiring credit investigation information and risk bearing capacity information of the user after the data volume of the acquired mobile phone bank operation log exceeds a threshold value.

As can be known from the flow shown in fig. 3, the bank activity information pushing method according to the embodiment of the present invention obtains the mobile banking operation log in real time, and obtains the credit investigation information and the risk tolerance information of the user after the data volume of the mobile banking operation log exceeds the threshold, so as to avoid that the resource for transmitting information is occupied by frequently obtaining the credit investigation information and the risk tolerance information of the user.

In one embodiment, the obtaining of the mobile banking operation log of the user uploaded by the mobile banking in real time may be: the method comprises the steps of acquiring a mobile phone operation log of a user in real time by an SDK installed in a mobile phone bank, for example, when the user clicks a credit card application button, recording the operation into the mobile phone operation log by the SDK and acquiring the operation log in real time.

In one embodiment, after the mobile phone bank operation log of the user sent by the mobile phone bank in real time is obtained, the credit investigation information and the risk tolerance information of the user are obtained after the data volume of the obtained mobile phone bank operation log exceeds a threshold value. For example, when the obtained mobile banking operation log amount reaches a certain value, credit investigation information and risk tolerance information are obtained, model analysis is input, for example, when the obtained mobile banking operation log amount reaches a threshold of one thousand, the credit investigation information and the risk tolerance information of the user are obtained again.

In order to improve the timeliness of the predicted bank activity information, in one embodiment, the obtaining of the mobile banking operation log, the credit investigation information and the risk tolerance information of the user may include: and acquiring the mobile banking operation log, credit investigation information and risk bearing capacity information of the user according to a preset timing task. For example, a timing task is preset to obtain a mobile banking operation log of a user in a timing period, so that the latest operation of the user is obtained and dynamically input into a banking activity information analysis model, and the banking activity information can be pushed more accurately; and the task acquires credit investigation information and risk bearing capacity information of the user in preset time so as to prevent the predicted bank activity information from being inaccurate due to the change of the credit investigation information and the risk bearing capacity information of the user. For example, a mobile banking operation log of a user is acquired once in seven preset days, the location of the user operation business is changed from Xian to Beijing within the seven days, the mobile banking operation log is acquired for the Beijing at the location where the user handles the business, the bank activity information prediction model is input by combining credit investigation information and risk bearing capacity information of the user, and the predicted bank activity information is output to be related bank activity information of the Beijing; acquiring credit investigation information and risk bearing capacity information of the user once every three months, refilling a risk bearing capacity test by the user within three months to cause the risk bearing capacity to be reduced, changing corresponding risk bearing capacity information, and making a prediction in time when bank activity information is pushed.

In one embodiment, the banking activity information may include: bank financial activity information, and/or bank credit card activity information.

In one embodiment, the banking activity information may include: mobile phone recharging, public utility fee inquiry and payment information.

In one embodiment, the banking activity information may include: credit card payments, game point card payments, and lottery betting information.

In one embodiment, pushing the predicted banking activity information to the user may include: and pushing the predicted bank activity information to the user through the mobile phone bank.

In one embodiment, pushing the predicted banking activity information to the user may include: and pushing the predicted bank activity information to the user through the mobile phone short message.

In one embodiment, pushing the predicted banking activity information to the user may include: and pushing the predicted bank activity information to the user through mobile phone WeChat.

In one embodiment, pushing the predicted banking activity information to the user may include: and pushing the predicted bank activity information to the user through the mobile payment bank.

The embodiment of the invention also provides a bank activity information pushing device, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to the bank activity information pushing method, the implementation of the device can refer to the implementation of the bank activity information pushing method, and repeated parts are not described again.

Fig. 4 is a schematic structural diagram of a bank activity information pushing device in the embodiment of the present invention. As shown in fig. 4, the bank activity information pushing apparatus in the embodiment of the present invention may include:

the acquisition module 401: the system comprises a mobile phone bank, a risk management server and a risk management server, wherein the mobile phone bank is used for acquiring mobile phone bank operation logs, credit investigation information and risk bearing capacity information of a user;

the prediction module 402: the system is used for inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of a user into a banking activity information prediction model and outputting predicted banking activity information; the bank activity information prediction model is obtained by training a machine learning model according to historical user data, wherein the historical user data comprises: the method comprises the steps that mobile phone banking operation logs, credit investigation information and risk bearing capacity information of historical users and bank activity information recommended for the historical users are obtained;

the pushing module 403: for pushing the predicted banking activity information to the user.

In one embodiment, the cell phone banking operation log of the user records at least one of the following information: the user clicks the page, the time period when the user transacts the service, and the location area when the user transacts the service.

Fig. 5 is a schematic structural diagram of an embodiment of a bank activity information pushing device according to an embodiment of the present invention. As shown in fig. 5, the bank activity information pushing device in the embodiment of the present invention may further include:

the model obtaining module 501: the system is used for acquiring historical user data before the mobile banking operation log, credit investigation information and risk bearing capacity information of a user are input into a bank activity information prediction model by aprediction module 402; dividing historical user data into a training set and a test set; training the machine learning model by using a training set to obtain a bank activity information prediction model; and testing the bank activity information prediction model by using the test set, and optimizing the bank activity information prediction model according to the test result.

In an embodiment, the obtainingmodule 401 is specifically configured to: acquiring a mobile phone bank operation log of a user uploaded by a mobile phone bank in real time; and after the data volume of the obtained mobile phone bank operation log exceeds a threshold value, acquiring credit investigation information and risk bearing capacity information of the user.

In an embodiment, the obtainingmodule 401 is specifically configured to: and acquiring the mobile banking operation log, credit investigation information and risk bearing capacity information of the user according to a preset timing task.

In one embodiment, the banking activity information includes: bank financial activity information, and/or bank credit card activity information.

In one embodiment, the banking activity information may include: mobile phone recharging, public utility fee inquiry and payment information.

In one embodiment, the banking activity information may include: credit card payments, game point card payments, and lottery betting information.

In one embodiment, the pushingmodule 403 is specifically configured to: and pushing the predicted bank activity information to the user through the mobile phone bank.

In one embodiment, the pushingmodule 403 is specifically configured to: and pushing the predicted bank activity information to the user through the mobile phone short message.

In one embodiment, the pushingmodule 403 is specifically configured to: and pushing the predicted bank activity information to the user through mobile phone WeChat.

In one embodiment, the pushingmodule 403 is specifically configured to: and pushing the predicted bank activity information to the user through the mobile payment bank.

The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the bank activity information pushing method when executing the computer program.

The embodiment of the invention also provides a computer readable storage medium, which stores a computer program for executing the bank activity information pushing method.

In the embodiment of the invention, the operation log, credit investigation information and risk bearing capacity information of a mobile phone bank of a user are obtained; inputting the mobile banking operation log, credit investigation information and risk bearing capacity information of the user into a banking activity information prediction model, and outputting predicted banking activity information; the bank activity information prediction model is obtained by training a machine learning model according to historical user data, wherein the historical user data comprises: the method comprises the steps that mobile phone banking operation logs, credit investigation information and risk bearing capacity information of historical users and bank activity information recommended for the historical users are obtained; pushing the predicted bank activity information to the user; compared with the technical scheme of traditional bank website pushing in the prior art, the method has the advantages that the predicted bank activity information is obtained by utilizing the bank activity information prediction model according to the mobile phone bank operation log of the user and by combining the credit investigation information and the risk bearing capacity information of the user, the bank activity information can be accurately pushed to the user in a low-cost scene, the activity information decision efficiency is improved, the mobile phone bank can obtain customers, and the stickiness of the user is enhanced.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (16)

Translated fromChinese

1.一种银行活动信息推送方法，其特征在于，包括：1. a method for pushing bank activity information, characterized in that, comprising:获取用户的手机银行操作日志、征信信息和风险承受能力信息；Obtain the user's mobile banking operation log, credit information and risk tolerance information;将用户的手机银行操作日志、征信信息和风险承受能力信息，输入银行活动信息预测模型，输出预测的银行活动信息；其中，银行活动信息预测模型是根据历史用户数据对机器学习模型进行训练得到的，所述历史用户数据包括：历史用户的手机银行操作日志、征信信息和风险承受能力信息，以及为历史用户推荐过的银行活动信息；Input the user's mobile banking operation log, credit information and risk tolerance information into the bank activity information prediction model, and output the predicted bank activity information; wherein, the bank activity information prediction model is obtained by training a machine learning model based on historical user data , the historical user data includes: the mobile banking operation log, credit information and risk tolerance information of the historical user, and the recommended banking activity information for the historical user;将预测的银行活动信息推送给用户。Push predicted banking activity information to users.2.如权利要求1所述的方法，其特征在于，用户的手机银行操作日志，记录有以下至少一种信息：2. The method of claim 1, wherein the user's mobile banking operation log is recorded with at least one of the following information:用户点击页面、用户办理业务时所在时间段、用户办理业务时所在位置区域。The user clicks on the page, the time period when the user handles the business, and the location area where the user handles the business.3.如权利要求1所述的方法，其特征在于，将用户的手机银行操作日志、征信信息和风险承受能力信息，输入银行活动信息预测模型之前，还包括：3. The method of claim 1, wherein before inputting the user's mobile banking operation log, credit information and risk tolerance information into the banking activity information prediction model, it also includes:获取历史用户数据；Get historical user data;将历史用户数据划分为训练集和测试集；Divide historical user data into training set and test set;利用训练集对机器学习模型进行训练，获得银行活动信息预测模型；Use the training set to train the machine learning model to obtain the banking activity information prediction model;利用测试集对银行活动信息预测模型进行测试，根据测试结果对银行活动信息预测模型进行优化。Use the test set to test the bank activity information prediction model, and optimize the bank activity information prediction model according to the test results.4.如权利要求1所述的方法，其特征在于，获取用户的手机银行操作日志、征信信息和风险承受能力信息，包括：4. The method of claim 1, wherein acquiring the user's mobile banking operation log, credit information and risk tolerance information, comprising:获取手机银行实时上送的用户的手机银行操作日志；Obtain the user's mobile banking operation log sent by mobile banking in real time;在获取的手机银行操作日志的数据量超过阈值后，获取用户的征信信息和风险承受能力信息。After the data volume of the obtained mobile banking operation log exceeds the threshold, obtain the user's credit information and risk tolerance information.5.如权利要求1所述的方法，其特征在于，获取用户的手机银行操作日志、征信信息和风险承受能力信息，包括：5. The method of claim 1, wherein obtaining the user's mobile banking operation log, credit information and risk tolerance information, comprising:根据预设的定时任务，获取用户的手机银行操作日志、征信信息和风险承受能力信息。Obtain the user's mobile banking operation log, credit information and risk tolerance information according to preset timing tasks.6.如权利要求1所述的方法，其特征在于，银行活动信息包括：6. The method of claim 1, wherein the banking activity information comprises:银行理财活动信息、和/或银行信用卡活动信息。Bank financial activity information, and/or bank credit card activity information.7.如权利要求1所述的方法，其特征在于，将预测的银行活动信息推送给用户，包括：7. The method of claim 1, wherein pushing the predicted banking activity information to the user, comprising:将预测的银行活动信息通过手机银行推送给用户。Push the predicted banking activity information to users via mobile banking.8.一种银行活动信息推送装置，其特征在于，包括：8. A bank activity information push device, characterized in that, comprising:获取模块：用于获取用户的手机银行操作日志、征信信息和风险承受能力信息；Acquisition module: used to acquire the user's mobile banking operation log, credit information and risk tolerance information;预测模块：用于将用户的手机银行操作日志、征信信息和风险承受能力信息，输入银行活动信息预测模型，输出预测的银行活动信息；其中，银行活动信息预测模型是根据历史用户数据对机器学习模型进行训练得到的，所述历史用户数据包括：历史用户的手机银行操作日志、征信信息和风险承受能力信息，以及为历史用户推荐过的银行活动信息；Prediction module: It is used to input the user's mobile banking operation log, credit information and risk tolerance information into the bank activity information prediction model, and output the predicted bank activity information; among them, the bank activity information prediction model is based on historical user data. Obtained from the training of the learning model, the historical user data includes: the mobile banking operation log, credit information and risk tolerance information of the historical user, and the recommended banking activity information for the historical user;推送模块：用于将预测的银行活动信息推送给用户。Push module: used to push the predicted banking activity information to users.9.如权利要求8所述的装置，其特征在于，用户的手机银行操作日志，记录有以下至少一种信息：9. The device according to claim 8, wherein the mobile banking operation log of the user is recorded with at least one of the following information:用户点击页面、用户办理业务时所在时间段、用户办理业务时所在位置区域。The user clicks on the page, the time period when the user handles the business, and the location area where the user handles the business.10.如权利要求8所述的装置，其特征在于，还包括模型获得模块，用于在预测模块将用户的手机银行操作日志、征信信息和风险承受能力信息，输入银行活动信息预测模型之前：10. The device according to claim 8, further comprising a model obtaining module for inputting the user's mobile banking operation log, credit information and risk tolerance information into the banking activity information prediction model before the prediction module. :获取历史用户数据；Get historical user data;将历史用户数据划分为训练集和测试集；Divide historical user data into training set and test set;利用训练集对机器学习模型进行训练，获得银行活动信息预测模型；Use the training set to train the machine learning model to obtain the banking activity information prediction model;利用测试集对银行活动信息预测模型进行测试，根据测试结果对银行活动信息预测模型进行优化。Use the test set to test the bank activity information prediction model, and optimize the bank activity information prediction model according to the test results.11.如权利要求8所述的装置，其特征在于，所述获取模块具体用于：11. The apparatus according to claim 8, wherein the acquisition module is specifically configured to:获取手机银行实时上送的用户的手机银行操作日志；Obtain the user's mobile banking operation log sent by mobile banking in real time;在获取的手机银行操作日志的数据量超过阈值后，获取用户的征信信息和风险承受能力信息。After the data volume of the obtained mobile banking operation log exceeds the threshold, obtain the user's credit information and risk tolerance information.12.如权利要求8所述的装置，其特征在于，所述获取模块具体用于：12. The apparatus according to claim 8, wherein the acquisition module is specifically configured to:根据预设的定时任务，获取用户的手机银行操作日志、征信信息和风险承受能力信息。Obtain the user's mobile banking operation log, credit information and risk tolerance information according to preset timing tasks.13.如权利要求8所述的装置，其特征在于，银行活动信息包括：13. The apparatus of claim 8, wherein the banking activity information comprises:银行理财活动信息、和/或银行信用卡活动信息。Bank financial activity information, and/or bank credit card activity information.14.如权利要求8所述的装置，其特征在于，所述推送模块具体用于：14. The apparatus of claim 8, wherein the push module is specifically used for:将预测的银行活动信息通过手机银行推送给用户。Push the predicted banking activity information to users via mobile banking.15.一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至7任一所述方法。15. A computer device comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements any of claims 1 to 7 when the processor executes the computer program the method.16.一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有执行权利要求1至7任一所述方法的计算机程序。16. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing any one of the methods of claims 1 to 7.

Images