Information Push Method, Device, Equipment and Medium

Abstract

The present disclosure provides an information push method, apparatus, device and medium, which can be applied to the fields of big data technology and financial technology. The information push method includes: obtaining transaction difference data of a financial institution within a preset time period; analyzing the transaction difference data by using a difference analysis model to obtain product value type information, where the product value type information represents the type of reason causing the transaction difference of the financial institution; determining a target product according to the product value type information; obtaining attribute information of a target customer group from a customer database according to the target product, where the target customer group represents a customer group that meets a first preset condition among the customers who have traded the target product; inputting the attribute information of the target customer group into a feature extraction model to output customer feature information; determining a target customer according to the customer feature information; and pushing recommendation information about the target product to the target customer.

Description

Technical Field

[0001] The present disclosure relates to the fields of big data technology and financial technology, and particularly to an information push method, apparatus, device, medium, and program product. Background Art

[0002] With the development of financial technology and big data technology, the product competition pressure among financial institutions has gradually increased. In order to meet the needs of users, many financial institutions push product information to users in various ways, hoping to attract the attention of users.

[0003] In the process of implementing the present disclosure, the inventors found the following problems in the related art: At present, the pertinence of information push is poor, and it is impossible to push truly useful information to users, resulting in a low effective response rate of information push. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides an information push method, apparatus, device, medium, and program product.

[0005] According to one aspect of the present disclosure, there is provided an information push method, including:

[0006] Obtaining transaction difference data of a financial institution within a preset time period, where the transaction difference data represents the difference data between the expected total transaction amount and the actual total transaction amount of the financial institution within the preset time period;

[0007] Analyzing the transaction difference data by using a difference analysis model to obtain product value type information, where the product value type information represents the type of reason causing the transaction difference of the financial institution;

[0008] Determining a target product according to the product value type information;

[0009] Obtaining attribute information of a target customer group from a customer database according to the target product, where the target customer group represents a customer group that meets a first preset condition among the customers who have traded the target product;

[0010] Inputting the attribute information of the target customer group into a feature extraction model to output customer feature information;

[0011] Determining a target customer according to the customer feature information; and

[0012] Pushing recommendation information about the target product to the target customer.

[0013] According to an embodiment of the present disclosure, analyzing the transaction difference data by using a difference analysis model to obtain product value type information, including

[0014] Analyze the transaction difference data using a difference analysis model to determine the cause types of the transaction differences of a financial institution;

[0015] Determine the product value type information according to the cause types.

[0016] According to an embodiment of the present disclosure, determine a target product according to the product value type information, including:

[0017] Determine the product corresponding to the product value type information that meets the second preset condition as the target product.

[0018] According to an embodiment of the present disclosure, obtain the attribute information of the target customer group from the customer database according to the target product, including:

[0019] Determine the target customer group information according to the target product;

[0020] Obtain the attribute information of the target customer group from the customer database according to the target customer group information.

[0021] According to an embodiment of the present disclosure, the customer feature information includes customer attribute feature information and the proportion information of customers with customer attribute feature information in the target customer group. According to the customer feature information, determine the target customer, including:

[0022] Determine the target customer attribute feature information according to the proportion information;

[0023] Determine the target customer according to the target customer attribute feature information.

[0024] According to an embodiment of the present disclosure, the above information pushing method further includes:

[0025] Construct a target customer portrait according to the target customer attribute feature information;

[0026] Display the target customer portrait through a visualization interface.

[0027] According to an embodiment of the present disclosure, the training method of the feature extraction model includes:

[0028] Obtain a sample data set, wherein the sample data set includes a plurality of data samples, and each data sample includes customer attribute feature data and a customer group type label;

[0029] Input the customer attribute feature data and the customer group type label into a preset model for training to obtain a trained feature extraction model.

[0030] Another aspect of the present disclosure provides an information push device, including: a first acquisition module, an analysis module, a first determination module, a second acquisition module, a feature extraction module, a second determination module, and a push module. Among them, the first acquisition module is used to acquire the transaction difference data of financial institutions within a preset time period, where the transaction difference data represents the difference data between the expected total transaction amount and the actual total transaction amount of financial institutions within the preset time period. The analysis module is used to analyze the transaction difference data by using a difference analysis model to obtain product value type information, where the product value type information represents the type of reason causing the transaction difference of financial institutions. The first determination module is used to determine a target product according to the product value type information. The second acquisition module is used to acquire the attribute information of the target customer group from the customer database according to the target product, where the target customer group represents the customer group that meets the first preset condition among the customers who have traded the target product. The feature extraction module is used to input the attribute information of the target customer group into a feature extraction model and output customer feature information. The second determination module is used to determine a target customer according to the customer feature information. The push module is used to push recommendation information about the target product to the target customer.

[0031] According to an embodiment of the present disclosure, the analysis module includes a first determination unit and a second determination unit. Among them, the first determination unit is used to analyze the transaction difference data by using a difference analysis model to determine the type of reason causing the transaction difference of financial institutions. The second determination unit is used to determine the product value type information according to the type of reason.

[0032] According to an embodiment of the present disclosure, the first determination module includes a third determination unit. Among them, the third determination unit is used to determine the product corresponding to the product value type information that meets the second preset condition as the target product.

[0033] According to an embodiment of the present disclosure, the second acquisition module includes a fourth determination unit and an acquisition unit. Among them, the fourth determination unit is used to determine the target customer group information according to the target product. The acquisition unit is used to acquire the attribute information of the target customer group from the customer database according to the target customer group information.

[0034] According to an embodiment of the present disclosure, the fourth determination unit includes a first determination subunit and a second determination subunit. Among them, the first determination subunit is used to determine the target customer attribute feature information according to the proportion information. The second determination subunit is used to determine the target customer according to the target customer attribute feature information.

[0035] According to an embodiment of the present disclosure, the above information push device further includes a construction module and a display module. Among them, the construction module is used to construct a target customer portrait according to the target customer attribute feature information. The display unit is used to display the target customer portrait through a visual interface.

[0036] According to an embodiment of the present disclosure, the above information push device further includes a training module, configured to obtain a sample data set, where the sample data set includes a plurality of data samples, and each data sample includes customer attribute feature data and a customer group type label; input the customer attribute feature data and the customer group type label into a preset model for training to obtain a trained feature extraction model.

[0037] Another aspect of the present disclosure provides an electronic device, including: one or more processors; a memory for storing one or more programs, where when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the above information push method.

[0038] Another aspect of the present disclosure further provides a computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute the above information push method.

[0039] Another aspect of the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above information push method is implemented.

[0040] According to an embodiment of the present disclosure, by analyzing the transaction difference data of a financial institution, product value type information is determined, a target product is determined according to the product value type information, then customer feature information is extracted from the attribute information of the customer group of the target product, a target customer is determined according to the customer feature information, and recommendation information about the target product is pushed to the target customer. Since the target product is a valuable product obtained by analyzing the transaction difference data of the financial institution, and then a valuable target customer is determined from the customer group attribute features of the valuable target product, it thus realizes the targeted pushing of the valuable target product to the valuable target customer, improving the pertinence of information push and the effective response rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Through the following description of the embodiments of the present disclosure with reference to the drawings, the above content and other objects, features, and advantages of the present disclosure will become clearer. In the drawings:

[0042] Figure 1 Schematically shows an application scenario diagram of the information push method, device, equipment, medium, and program product according to an embodiment of the present disclosure;

[0043] Figure 2 Schematically shows a flowchart of the information push method according to an embodiment of the present disclosure;

[0044] Figure 3 Schematically shows a flowchart of determining product value type information according to an embodiment of the present disclosure;

[0045] Figure 4 Schematically shows a visualization diagram of a target customer profile according to an embodiment of the present disclosure.

[0046] Figure 5 Schematically shows a flowchart of a training method for a feature extraction model according to an embodiment of the present disclosure;

[0047] Figure 6 Schematically shows a structural block diagram of an information push device according to an embodiment of the present disclosure; and

[0048] Figure 7 Schematically shows a block diagram of an electronic device suitable for implementing an information push method according to an embodiment of the present disclosure. Detailed implementation manners

[0049] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0050] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0051] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0052] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but not be limited to a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C).

[0053] It should be noted that the information push method and device of the present disclosure can be used in the financial technology field and the big data technology field, and can also be used in any field other than the financial field. The application fields of the information push method and device of the present disclosure are not limited.

[0054] In the technical solution of the present disclosure, the processing of the collection, storage, use, processing, transmission, provision, disclosure, and application of the user's personal information complies with the provisions of relevant laws and regulations, adopts necessary confidentiality measures, and does not violate public order and good customs.

[0055] In the technical solution of the present disclosure, before obtaining or collecting the user's personal information, the authorization or consent of the user is obtained.

[0056] An embodiment of the present disclosure provides an information push method. By analyzing the transaction difference data of financial institutions, the product value type information is determined. According to the product value type information, the target product is determined. Then, the customer feature information is extracted from the attribute information of the customer group of the target product. According to the customer feature information, the target customer is determined, and the recommendation information about the target product is pushed to the target customer. Since the target product is a valuable product obtained by analyzing the transaction difference data of financial institutions, and then the valuable target customer is determined from the attribute characteristics of the customer group of the valuable target product, it is possible to push the valuable target product to the valuable target customer in a targeted manner, thereby improving the pertinence of information push.

[0057] Figure 1 Fig. schematically shows an application scenario diagram of the information push method according to an embodiment of the present disclosure.

[0058] As Figure 1 shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or fiber optic cables, etc.

[0059] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0060] The terminal devices 101, 102, 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0061] The server 105 may be a server that provides various services. For example, it may be a background management server (only for example) that supports the websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process data such as user requests received, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0062] It should be noted that the information push method provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the information push device provided by the embodiments of the present disclosure can generally be set in the server 105. The information push method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105. Correspondingly, the information push device provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105.

[0063] It should be understood that Figure 1 the numbers of the terminal devices, the network, and the servers in

[0064] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 1 The following will be based on Figures 2 to 4 the described scenario, and will describe the information push method of the public embodiments in detail through

[0065] Figure 2 FIG. schematically shows a flowchart of the information push method according to an embodiment of the present disclosure.

[0066] As Figure 2 shown, the information push method of this embodiment includes operations S210 to S270.

[0067] In operation S210, obtain the transaction difference data of financial institutions within a preset time period, where the transaction difference data represents the difference data between the expected total transaction amount and the actual total transaction amount of financial institutions within the preset time period.

[0068] According to the embodiments of the present disclosure, the transaction difference data may include the income difference data of financial institutions. The preset time period can be set to one year, two years, etc. For example: if the expected total transaction amount of financial institution A in a certain year is m, and the actual total transaction amount in that year is n, the transaction difference data of financial institution A in this concept can be determined as m - n.

[0069] In operation S220, the transaction difference data is analyzed using a difference analysis model to obtain product value type information, where the product value type information characterizes the type of reason that causes transaction differences in financial institutions.

[0070] According to an embodiment of the present disclosure, the difference analysis model can be a difference analysis tool for management accounting in a financial system. The product value type information may include: "both volume and price increase" type, "both volume and price decrease" type, "make up for volume with price" type, "price fails to make up for volume" type, "make up for price with volume" type, "volume fails to make up for price" type, and so on. The "both volume and price increase" type can be a product value type where both the business volume and the price increase compared with the same period. The "both volume and price decrease" can be a product value type where both the business volume and the price decrease compared with the same period. The "make up for volume with price" type can be a product value type where the price increases compared with the same period, the business volume decreases compared with the same period, but the transaction increases compared with the same period. The "price fails to make up for volume" type can be a product value type where the price increases compared with the same period, the business volume decreases compared with the same period, but the transaction decreases compared with the same period. The "make up for price with volume" type can be a product value type where the business volume increases compared with the same period, the price decreases compared with the same period, but the transaction increases compared with the same period. The "volume fails to make up for price" type can be a product value type where the business volume increases compared with the same period, the price decreases compared with the same period, but the transaction decreases compared with the same period.

[0071] In operation S230, a target product is determined according to the product value type information.

[0072] According to an embodiment of the present disclosure, products of the product type with transactions increasing compared with the same period can be determined as target products. For example: products of the "both volume and price increase" type, "make up for volume with price" type, "make up for price with volume" type.

[0073] According to an embodiment of the present disclosure, in order to improve the pertinence of the customer group, generally one product in the same product value type is determined as the target product. For example: time deposit products, and so on.

[0074] In operation S240, according to the target product, attribute information of the target customer group is obtained from the customer database, where the target customer group characterizes the customer group that meets the first preset condition among the customers who have traded the target product.

[0075] According to an embodiment of the present disclosure, for the customer group holding the target product, the customer group holding the target product can be classified according to the holding quantity and holding price of the customer. For example: the customer group with both the holding quantity and the holding price rising compared with the same period is determined as the "quantity and price rising simultaneously" customer group; the customer group with the holding quantity rising compared with the same period, the holding price falling compared with the same period, and the institution's transactions rising compared with the same period is determined as the "compensating price with quantity" customer group; the customer group with the holding quantity rising compared with the same period, the holding price falling compared with the same period, and the institution's transactions falling compared with the same period is determined as the "quantity not compensating price" customer group; the customer group with the holding price rising compared with the same period, the holding quantity falling compared with the same period, and the institution's transactions rising compared with the same period is determined as the "compensating quantity with price" customer group.

[0076] According to an embodiment of the present disclosure, the first preset condition can be the customer group with the institution's transactions rising compared with the same period, then the target customer group can include the "quantity and price rising simultaneously" customer group, the "compensating price with quantity" customer group, and the "compensating quantity with price" customer group.

[0077] According to an embodiment of the present disclosure, the attribute information of the target customer group can include customer group basic attribute information, product attribute information, behavior attribute information, evaluation attribute information, risk attribute information, etc. Among them, the basic attribute information such as: age, occupation, etc. The product attribute information such as: regular balance, current balance, fund balance, etc. The behavior attribute information such as: number of transactions, number of cross-bank transactions, etc. The evaluation attribute information such as evaluation level, etc. The risk attribute information such as credit risk, information integrity, etc.

[0078] In operation S250, the attribute information of the target customer group is input into the feature extraction model, and customer feature information is output.

[0079] According to an embodiment of the present disclosure, the customer feature information can include the common significant features of the target customer group. Taking the "quantity and price rising simultaneously" customer group as an example, among them, more than 60% of the customers are aged between 30 and 40 years old; more than 50% of the customers are salary-receiving customers; more than 40% of the customers are customers using the third-party payment function; more than 10% of the customers are aged between 50 and 60 years old. Then the customer feature information output by the feature extraction model can include being aged between 30 and 40 years old, salary-receiving, using the third-party payment function, etc.

[0080] In operation S260, the target customers are determined according to the customer feature information.

[0081] According to an embodiment of the present disclosure, for example: the customers who are aged between 30 and 40 years old, salary-receiving, and using the third-party payment function are determined as the target customers.

[0082] In operation S270, recommendation information about the target product is pushed to the target customers.

[0083] According to an embodiment of the present disclosure, for example, if the determined target product is a time deposit product with an annualized interest rate of m%, recommendation information about the "time deposit product with an annualized interest rate of m%" can be pushed to customers who are "aged between 30 and 40, have salary disbursement, and use the third-party payment function".

[0084] According to an embodiment of the present disclosure, by analyzing the transaction difference data of a financial institution, product value type information is determined. Based on the product value type information, a target product is determined. Then, customer characteristic information is extracted from the attribute information of the customer group of the target product. Based on the customer characteristic information, target customers are determined, and recommendation information about the target product is pushed to the target customers. Since the target product is a valuable product obtained by analyzing the transaction difference data of a financial institution, and valuable target customers are determined from the attribute characteristics of the customer group of the valuable target product, it thus realizes the targeted pushing of valuable target products to valuable target customers, improving the pertinence of information pushing.

[0085] Figure 3 A flowchart for determining product value type information according to an embodiment of the present disclosure is schematically shown.

[0086] As Figure 3 shown, the flowchart for determining product value type information in this embodiment includes operations S310 to S320.

[0087] In operation S310, a difference analysis model is used to analyze the transaction difference data to determine the type of reason causing the transaction difference of the financial institution.

[0088] According to an embodiment of the present disclosure, the type of reason may include reasons for business volume difference, price difference, risk cost difference, etc. The reason for business volume difference may be the difference between the current transaction and the same-period transaction caused by the change in business volume, such as: the change in the average daily balance of deposits and loans, the change in sales amount, etc. The reason for price difference may be the difference between the current transaction and the same-period transaction caused by the change in price, such as: the change in deposit and loan interest rates, the change in internal fund transfer prices, etc. The reason for risk cost difference may be the risk cost difference due to different asset qualities.

[0089] According to an embodiment of the present disclosure, a difference analysis tool of management accounting can be used to analyze the transaction difference data to determine the type of reason causing the transaction difference of the financial institution. For example: by analyzing the transaction difference data, if it is determined that the reason for the difference between the current transaction and the same-period transaction is the increase in the business volume and price of a certain type of product, the type of reason can be determined as the increase in business volume and price, that is, "both volume and price increase".

[0090] In operation S320, based on the type of reason, product value type information is determined.

[0091] According to an embodiment of the present disclosure, for example, if it is determined that the difference between the current transactions and the same - period transactions of a certain type of product is due to an increase in business volume and an increase in price, then the value type of this type of product can be determined as "both volume and price increase". This type of product can include a variety of specific financial products, such as: wealth management investment products, merger and acquisition loan products, personal housing loan products, and so on.

[0092] According to an embodiment of the present disclosure, by analyzing the transaction difference data of financial institutions, the reasons for the transaction differences are determined, and then the product value type is determined. Thus, the target products to be pushed to users are determined according to the product value, realizing the determination of the target products to be pushed according to the product value, and improving the pertinence of information push from the product side.

[0093] According to an embodiment of the present disclosure, determining the target products according to the product value type information includes:

[0094] Determining the products corresponding to the product value type information that meet the second preset condition as the target products.

[0095] According to an embodiment of the present disclosure, the second preset condition can be the product value type that has increased compared with the same - period transactions, such as: "both volume and price increase" type, "compensating price with volume" type, "compensating volume with price" type, and so on.

[0096] According to an embodiment of the present disclosure, taking the products of the "both volume and price increase" type as an example, it can include a variety of specific products, such as: wealth management investment, personal housing loan, and so on. In order to improve the pertinence of information push, the target products determined in the embodiments of the present disclosure are a specific target product among the products of the "both volume and price increase" type, such as: wealth management investment.

[0097] According to an embodiment of the present disclosure, determining the target products to be pushed to users according to the product value realizes the determination of the target products to be pushed according to the product value, and improves the pertinence of information push from the product side.

[0098] According to an embodiment of the present disclosure, according to the target products, obtaining the attribute information of the target customer group from the customer database includes:

[0099] Determining the target customer group information according to the target products;

[0100] Obtaining the attribute information of the target customer group from the customer database according to the target customer group information.

[0101] According to an embodiment of the present disclosure, taking a wealth management investment product as an example of the target product, the customer groups holding the wealth management investment product can be classified according to the differences in the holding amounts and holding prices of the customers holding the wealth management investment product. For example: If the holding amount and holding price of customer A's wealth management investment product both increase compared to the same period, then customer A can be classified into the "both quantity and price increase" customer group. If the holding amount of customer B's wealth management product increases compared to the same period, the holding price decreases compared to the same period, but the institutional transactions increase compared to the same period, then customer B can be classified into the "compensate price with quantity" customer group.

[0102] According to an embodiment of the present disclosure, the target customer group can be determined from the customer groups of the target product according to the first preset condition. For example: The first preset condition can be the customer group with institutional transactions increasing compared to the same period, then the target customer group can include the "both quantity and price increase" customer group, the "compensate price with quantity" customer group, and the "compensate quantity with price" customer group. The target customer group information can include the "both quantity and price increase" identification information, the "compensate price with quantity" identification information, and the "compensate quantity with price" identification information.

[0103] According to an embodiment of the present disclosure, wherein the customer characteristic information includes the customer attribute characteristic information and the proportion information of the customers with the customer attribute characteristic information in the target customer group. According to the customer characteristic information, determining the target customer includes:

[0104] Determining the target customer attribute characteristic information according to the proportion information;

[0105] Determining the target customer according to the target customer attribute characteristic information.

[0106] According to an embodiment of the present disclosure, the customer attribute characteristic information can include customer age information, occupation information, transaction information, etc. Taking the customer age information as an example, in the target customer group of time deposits, the customers under 35 years old account for 10% of the total number of customers in the target customer group, and it can be determined that the customer attribute characteristic information is that the proportion of customers under 35 years old in the target customer group is 10%.

[0107] According to an embodiment of the present disclosure, the customer attribute characteristic information can be sorted according to the proportion information, and the top n customer attribute characteristic information can be determined as the target customer attribute information, where the value range of n is related to the number of customer attribute characteristics in the actual application scenario, and no specific limitation is made in the embodiments of the present disclosure. For example: The customers under 35 years old account for 10% of the total number of customers in the target customer group, the customers aged 35 to 45 years old account for 30% of the total number of customers in the target customer group, the customers aged 45 to 60 years old account for 50% of the total number of customers in the target customer group, and the customers over 60 years old account for 10% of the total number of customers in the target customer group. It can be determined that the target customer attribute characteristics are aged 35 to 45 years old and aged 45 to 60 years old.

[0108] According to an embodiment of the present disclosure, customers aged between 35 and 45 years old and between 45 and 60 years old can be determined as target customers.

[0109] According to an embodiment of the present disclosure, by analyzing the customer group holding the target product, the target customer group is determined, and then significant target customer attribute features are extracted from the attribute features of the target customer group, thereby determining the target customers, which improves the pertinence of the recipients in the information push process.

[0110] According to an embodiment of the present disclosure, the above information push method further includes:

[0111] Constructing a target customer portrait according to the target customer attribute feature information;

[0112] Displaying the target customer portrait through a visualization interface.

[0113] According to an embodiment of the present disclosure, the target customer attribute feature information and the proportion information in the target customer group with the target customer attribute feature information can be used to construct a target customer portrait by using a bubble chart or a pie chart, and then the target customer portrait is displayed through a visualization interface.

[0114] Figure 4 Schematically shows a target customer portrait display diagram according to an embodiment of the present disclosure.

[0115] As Figure 4 shown, it can be seen from the target customer portrait that the attribute feature information of the target customers includes middle-aged, payroll, and active third-party payment. And the proportion of each target attribute feature information in the target customer group, for example: 60% middle-aged customers, 50% payroll customers, and 40% active third-party payment customers.

[0116] According to an embodiment of the present disclosure, constructing a target customer portrait according to the target customer attribute feature information and displaying it through a visualization interface improves the timeliness of information and facilitates the management level to timely understand the situation of the target customer group and adjust the business strategy.

[0117] Figure 5 Schematically shows a flowchart of a training method for a feature extraction model according to an embodiment of the present disclosure.

[0118] As Figure 5 shown, the feature extraction model training method of this embodiment includes operations S510 to S520.

[0119] In operation S510, a sample data set is obtained, where the sample data set includes a plurality of data samples, and each data sample includes customer attribute feature data and a customer group type label.

[0120] In operation S520, the customer attribute feature data and the customer group type labels are input into a preset model for training to obtain a trained feature extraction model.

[0121] According to an embodiment of the present disclosure, the preset model can be constructed based on the Lightgbm algorithm. The customer attribute feature data can include age attribute data, occupation attribute data, transaction attribute data, and so on. The customer group type labels can include "both volume and price rising" type, "both volume and price falling" type, and so on.

[0122] According to an embodiment of the present disclosure, the customer attribute feature data and the customer group type labels are input into the preset model for training. Taking the customers of the "both volume and price rising" type as an example, the labels of the customer attribute features of the customers with both volume and price rising can be set to 1, and the labels of the customer attribute features of the customers who are not of the "both volume and price rising" type can be set to 0 for model training, and the importance of the customer attribute features is output.

[0123] According to an embodiment of the present disclosure, the target customer attribute features can be determined according to the importance of the customer attribute features. Then, the binning algorithm is used to bin the target customer attribute features. For example, the tree binning algorithm can be used. Then, the third-order difference is calculated for the target customer attribute features to calculate the proportion information of the customer group. For example, the target customer attribute features include age, fund balance, and the number of counter transactions in the past year. The age segments are less than 20 years old, 20 to 35 years old, 36 to 49 years old, 50 to 66 years old, and greater than 66 years old; the fund balance segments are: less than 100,000, greater than or equal to 100,000; the number of scale transactions in the past year segments are: less than 1 transaction, 1 to 2 transactions, 3 to 4 transactions, and more than 4 transactions. The third-order cross is to combine the values of the three features, such as customers who are less than 20 years old and have a fund balance of less than 100,000 and the number of scale transactions in the past year is 1 to 2 transactions.

[0124] According to an embodiment of the present disclosure, the combined features of the three features can be used as the final output feature attributes.

[0125] According to an embodiment of the present disclosure, by training the feature extraction model, the significant features in each customer group are obtained, and then the target customers are determined according to the significant features, effectively improving the effectiveness of the target product push information.

[0126] Based on the above information push method, the present disclosure also provides an information push device. The following will be combined with Figure 6 This device will be described in detail.

[0127] Figure 6 The structural block diagram of the information push device according to an embodiment of the present disclosure is schematically shown.

[0128] As Figure 6As shown in the figure, the information push device 600 of this embodiment includes a first acquisition module 610, an analysis module 620, a first determination module 630, a second acquisition module 640, a feature extraction module 650, a second determination module 660, and a push module 670.

[0129] The first acquisition module 610 is configured to acquire the transaction difference data of a financial institution within a preset time period. The transaction difference data represents the difference data between the expected total transaction amount and the actual total transaction amount of the financial institution within the preset time period. In one embodiment, the first acquisition module 610 may be configured to perform the operation S210 described above, which will not be elaborated here.

[0130] The analysis module 620 is configured to analyze the transaction difference data by using a difference analysis model to obtain product value type information. The product value type information represents the cause type that causes the transaction difference of the financial institution. In one embodiment, the analysis module 620 may be configured to perform the operation S220 described above, which will not be elaborated here.

[0131] The first determination module 630 is configured to determine a target product according to the product value type information. In one embodiment, the first determination module 630 may be configured to perform the operation S230 described above, which will not be elaborated here.

[0132] The second acquisition module 640 is configured to acquire the attribute information of a target customer group from a customer database according to the target product. The target customer group represents the customer group that meets the first preset condition among the customers who have traded the target product. In one embodiment, the second acquisition module 640 may be configured to perform the operation S240 described above, which will not be elaborated here.

[0133] The feature extraction module 650 is configured to input the attribute information of the target customer group into a feature extraction model and output customer feature information. In one embodiment, the feature extraction module 650 may be configured to perform the operation S240 described above, which will not be elaborated here.

[0134] The second determination module 660 is configured to determine a target customer according to the customer feature information. In one embodiment, the second determination module 660 may be configured to perform the operation S260 described above, which will not be elaborated here.

[0135] The push module 670 is configured to push recommendation information about the target product to the target customer. In one embodiment, the push module 670 may be configured to perform the operation S270 described above, which will not be elaborated here.

[0136] According to an embodiment of the present disclosure, the analysis module includes a first determination unit and a second determination unit. Among them, the first determination unit is used to analyze transaction difference data by using a difference analysis model to determine the cause type of the transaction difference of a financial institution. The second determination unit is used to determine product value type information according to the cause type.

[0137] According to an embodiment of the present disclosure, the first determination module includes a third determination unit. Among them, the third determination unit is used to determine the product corresponding to the product value type information that meets the second preset condition as the target product.

[0138] According to an embodiment of the present disclosure, the second acquisition module includes a fourth determination unit and an acquisition unit. Among them, the fourth determination unit is used to determine target customer group information according to the target product. The acquisition unit is used to obtain the attribute information of the target customer group from the customer database according to the target customer group information.

[0139] According to an embodiment of the present disclosure, the fourth determination unit includes a first determination subunit and a second determination subunit. Among them, the first determination subunit is used to determine target customer attribute characteristic information according to the proportion information. The second determination subunit is used to determine the target customer according to the target customer attribute characteristic information.

[0140] According to an embodiment of the present disclosure, the above information push device further includes a construction module and a display module. Among them, the construction module is used to construct a target customer portrait according to the target customer attribute characteristic information. The display unit is used to display the target customer portrait through a visualization interface.

[0141] According to an embodiment of the present disclosure, the above information push device further includes a training module, which is used to obtain a sample data set. Among them, the sample data set includes a plurality of data samples, and each data sample includes customer attribute characteristic data and a customer group type label; input the customer attribute characteristic data and the customer group type label into a preset model for training to obtain a trained feature extraction model.

[0142] According to an embodiment of the present disclosure, any of the first acquisition module 610, analysis module 620, first determination module 630, second acquisition module 640, feature extraction module 650, second determination module 660, and push module 670 may be combined and implemented in one module, or any one of them may be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first acquisition module 610, analysis module 620, first determination module 630, second acquisition module 640, feature extraction module 650, second determination module 660, and push module 670 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), programmable logic array (PLA), system on chip, system on substrate, system on package, application specific integrated circuit (ASIC), or any other reasonable manner that can integrate or package circuits, etc., implemented by hardware or firmware, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in an appropriate combination of any several of them. Alternatively, at least one of the first acquisition module 610, analysis module 620, first determination module 630, second acquisition module 640, feature extraction module 650, second determination module 660, and push module 670 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0143] Figure 7 Schematically shows a block diagram of an electronic device suitable for implementing the information push method according to an embodiment of the present disclosure.

[0144] As Figure 7 shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to the program stored in the read only memory (ROM) 702 or the program loaded from the storage section 708 into the random access memory (RAM) 703. The processor 701 may include, for example, a general microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), etc. The processor 701 may also include on board memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0145] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 702 and / or the RAM 703. It should be noted that the programs may also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 may also perform various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.

[0146] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, and the input / output (I / O) interface 705 is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read from thereon is installed into the storage portion 708 as needed.

[0147] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

[0148] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the above-described ROM 702 and / or RAM 703 and / or one or more memories other than ROM 702 and RAM 703.

[0149] An embodiment of the present disclosure also includes a computer program product, which includes a computer program that contains program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to enable the computer system to implement the above method provided by the embodiment of the present disclosure.

[0150] When the computer program is executed by the processor 701, it executes the above functions defined in the system / apparatus of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0151] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and be downloaded and installed through the communication part 709, and / or be installed from the removable medium 711. The program code included in the computer program may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0152] In such an embodiment, the computer program may be downloaded and installed from the network through the communication part 709, and / or be installed from the removable medium 711. When the computer program is executed by the processor 701, it executes the above functions defined in the system of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0153] In accordance with embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedures and / or product-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0154] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0155] Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present disclosure can be combined or / and combined in various ways, even if such combinations or combinations are not explicitly recited in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features recited in the various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0156] The embodiments of the present disclosure have been described above. However, these embodiments are merely for illustrative purposes and not for limiting the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. An information push method, comprising: Obtaining transaction difference data of a financial institution within a preset time period, where the transaction difference data represents the difference data between the expected total transaction amount and the actual total transaction amount of the financial institution within the preset time period; Analyzing the transaction difference data by using a difference analysis model to determine the cause type of the transaction difference of the financial institution; Determining product value type information according to the cause type, where the product value type information represents the cause type of the transaction difference of the financial institution; Determining the product corresponding to the product value type information that meets the second preset condition as the target product; Determining target customer group information according to the target product; Obtaining the attribute information of the target customer group from the customer database according to the target customer group information, where the target customer group represents the customer group that meets the first preset condition among the customers who have traded the target product; Inputting the attribute information of the target customer group into a feature extraction model to output customer feature information, where the training method of the feature extraction model includes: Obtaining a sample data set, where the sample data set includes multiple data samples, and each data sample includes customer attribute feature data and a customer group type label; inputting the customer attribute feature data and the customer group type label into a preset model for training to obtain the trained feature extraction model; Determining target customer attribute feature information according to the proportion information; Determining the target customer according to the target customer attribute feature information, where the customer feature information includes the customer attribute feature information and the proportion information of the customers with the customer attribute feature information in the target customer group; and Pushing recommendation information about the target product to the target customer.

2. The method according to claim 1, further comprising: Constructing a target customer portrait according to the target customer attribute feature information; Displaying the target customer portrait through a visualization interface.

3. An information push device, comprising: A first acquisition module for acquiring transaction difference data of a financial institution within a preset time period, where the transaction difference data represents the difference data between the expected total transaction amount and the actual total transaction amount of the financial institution within the preset time period; An analysis module for analyzing the transaction difference data by using a difference analysis model to obtain product value type information, and the analysis module includes a first determination unit and a second determination unit; The first determination unit for analyzing the transaction difference data by using a difference analysis model to determine the cause type of the transaction difference of the financial institution; The second determination unit for determining the product value type information according to the cause type, where the product value type information represents the cause type of the transaction difference of the financial institution; A first determination module for determining a target product according to the product value type information, and the first determination module includes a third determination unit; The third determination unit for determining the product corresponding to the product value type information that meets the second preset condition as the target product; A second acquisition module, configured to acquire the attribute information of the target customer group from the customer database according to the target product. The second acquisition module includes a fourth determination unit and an acquisition unit; The fourth determination unit is configured to determine the target customer group information according to the target product; The acquisition unit is configured to acquire the attribute information of the target customer group from the customer database according to the target customer group information, where the target customer group represents the customer group that meets the first preset condition among the customers who have traded the target product; The feature extraction module is configured to input the attribute information of the target customer group into the feature extraction model and output the customer feature information; The training module is configured to acquire a sample data set, where the sample data set includes a plurality of data samples, and each data sample includes customer attribute feature data and a customer group type label; input the customer attribute feature data and the customer group type label into a preset model for training to obtain the trained feature extraction model; A second determination module, configured to determine the target customer according to the customer feature information. The second determination module includes a fifth determination unit and a sixth determination unit; The fifth determination unit is configured to determine the target customer attribute feature information according to the proportion information; The sixth determination unit is configured to determine the target customer according to the target customer attribute feature information, where the customer feature information includes the customer attribute feature information and the proportion information of the customers with the customer attribute feature information in the target customer group; and The push module is configured to push the recommendation information about the target product to the target customer.

4. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of claims 1 to 2.

5. A computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 2.

6. A computer program product, comprising a computer program, where when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images