Recommended customer group determination method and device, electronic equipment and computer program product

Abstract

The invention discloses a method and a device for determining a recommended customer group, electronic equipment and a computer program product. Relates to the field of artificial intelligence, and the method comprises the steps: obtaining transaction information of a financial institution, and extracting a target customer who transacts with a historical customer from the transaction information, the historical customer being a customer who has purchased a financial product in the financial institution, and the target customer being a new customer who has not purchased the financial product in the financial institution; customer information of a target customer is obtained, the customer information is input into a target model, a recommendation intention evaluation value of the target customer is obtained, the target model is obtained through training of multiple sets of training samples, and each set of training samples comprises historical customer information and a historical recommendation intention evaluation value; and when the recommendation intention evaluation value is greater than or equal to an evaluation value threshold, determining the target customer as a to-be-recommended customer, and determining a recommended customer group based on the to-be-recommended customer. Through the method and the device, the problem of relatively low efficiency of obtaining the to-be-recommended customer of the financial product in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a method, device, electronic device, and computer program product for determining a recommended customer group. Background Art

[0002] In the related art, the customer base of financial institutions is basically in a stable state, and the efficiency of expanding the customer base is low. In the related art, the way to obtain new customer bases is to use traditional publicity methods such as large-scale advertising to obtain new customer bases. This method of obtaining new customer bases is relatively inefficient, and it is also difficult to obtain basic information about customer bases, and it is difficult to obtain a large amount of information about new customer bases. In addition, the publicity effect of the publicity target group and the probability of whether the transaction of the new customer group can be obtained are unclear, and the publicity effect cannot be estimated.

[0003] With respect to the problem of low efficiency in obtaining customers to be recommended financial products in related technologies, no effective solution has been proposed so far. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device, electronic device and computer program product for determining a recommended customer group, so as to solve the problem of low efficiency in obtaining customers to be recommended for financial products in related technologies.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining a recommended customer group is provided. The method comprises: obtaining transaction information of a financial institution, extracting target customers who have conducted transactions with historical customers from the transaction information, wherein historical customers are customers who have purchased financial products at a financial institution, and target customers are new customers who have not purchased financial products at a financial institution; obtaining customer information of the target customer, inputting the customer information into a target model, and obtaining a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, determining the target customer as a customer to be recommended, and determining a recommended customer group based on the customer to be recommended.

[0006] Optionally, the target model is obtained by: obtaining the financial institution's historical evaluation records of customers, extracting each customer's historical customer information and historical recommendation intention evaluation values ​​from the historical evaluation records; determining each customer's historical customer information and historical recommendation intention evaluation values ​​as a set of training samples to obtain multiple sets of training samples; training a machine learning model based on the multiple sets of training samples to obtain a target model.

[0007] Optionally, extracting each customer's historical customer information and historical recommendation intention evaluation value from the historical evaluation records includes: determining each customer's historical customer information from the historical evaluation records, and for each customer, extracting at least one of the following from the customer's historical customer information: enterprise registration information, operating information, transaction information and credit information; determining the customer's investment capacity evaluation value based on the transaction information, determining the customer's enterprise scale evaluation value based on the enterprise registration information, determining the customer's capital income and expenditure evaluation value based on the operating information, and determining the customer's stability evaluation value based on the credit information; determining the customer's historical recommendation intention evaluation value based on at least one of the following: investment capacity evaluation value, enterprise scale evaluation value, capital income and expenditure evaluation value and stability evaluation value.

[0008] Optionally, before determining the target customer as the customer to be recommended, the method also includes: determining a target transaction between the target customer and historical customers, and judging whether the target transaction affects the target customer's financial status within a preset period; if the target transaction does not affect the target customer's financial status within the preset period, executing the step of determining the target customer as the customer to be recommended; if the target transaction affects the target customer's financial status within the preset period, marking the target customer as a non-intended customer within the preset period; updating the target customer's customer information after the preset period, and executing the step of inputting the customer information into the target model based on the updated customer information to obtain a recommendation intention evaluation value of the target customer.

[0009] Optionally, after obtaining the recommendation intention evaluation value of the target customer, the method also includes: when the recommendation intention evaluation value is less than the evaluation value threshold, detecting change information of the target customer, wherein the change information includes at least one of the following: business change information, bidding information and tender information; when the change information of the target customer is detected, updating the customer information of the target customer based on the change information; determining an updated recommendation intention evaluation value based on the updated customer information, and when the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, determining the target customer as a customer to be recommended; when the updated recommendation intention evaluation value is less than the evaluation value threshold, repeating the step of detecting change information of the target customer until the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, or the detection duration is greater than or equal to the detection duration threshold.

[0010] Optionally, after determining the recommended customer group based on the customers to be recommended, the method also includes: for each customer to be recommended in the recommended customer group, determining the financial products that the customer to be recommended has purchased; determining the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customer to be recommended; and when the financial product coverage rate is less than or equal to a coverage rate threshold, recommending the target financial product to the customer to be recommended.

[0011] Optionally, determining the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customers to be recommended includes: determining the purchase amount of the purchased financial products from the product information, and determining the investment amount of the target customers within the target period from the transaction information; calculating the ratio of the purchase amount to the investment amount to obtain the financial product coverage rate.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for determining a recommended customer group is provided. The device includes: an acquisition unit, which is used to acquire transaction information of a financial institution, and extract target customers who have conducted transactions with historical customers from the transaction information, wherein historical customers are customers who have purchased financial products at a financial institution, and target customers are new customers who have not purchased financial products at a financial institution; an input unit, which is used to acquire customer information of the target customer, and input the customer information into a target model to obtain a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; a first determination unit, which is used to determine the target customer as a customer to be recommended when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, and determine the recommended customer group based on the customer to be recommended.

[0013] In an embodiment of the present application, transaction information of a financial institution is obtained, and target customers who have conducted transactions with historical customers are extracted from the transaction information, wherein historical customers are customers who have purchased financial products at a financial institution, and target customers are new customers who have not purchased financial products at a financial institution; customer information of the target customer is obtained, and the customer information is input into a target model to obtain a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; when the recommendation intention evaluation value is greater than or equal to an evaluation value threshold, the target customer is determined as a customer to be recommended, and a recommended customer group is determined based on the customer to be recommended. By mining the customer to be recommended from the target customers who have conducted transactions with historical customers, the customer information of the target customer is obtained and a recommendation intention evaluation value is determined, and then the customer to be recommended is determined based on the recommendation intention evaluation value, thereby achieving the purpose of efficiently mining the customer to be recommended, thereby achieving the technical effect of improving the customer acquisition efficiency of new customers of financial institutions, and thereby solving the technical problem of low efficiency in acquiring customers to be recommended for financial products. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0015] Figure 1A hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for determining a recommended customer group is shown;

[0016] Figure 2 is a flow chart of a method for determining a recommended customer group according to an embodiment of the present application;

[0017] Figure 3 is a schematic diagram of a device for determining a recommended customer group according to an embodiment of the present application;

[0018] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0022] Example 1

[0023] According to an embodiment of the present application, a method embodiment for determining a recommended customer group is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for determining a recommended customer group. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (shown as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as an MCU (Microcontroller Unit) or an FPGA (Field-Programmable Gate Array), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a USB (Universal Serial Bus) port (which may be included as one of the ports of a BUS (Business)), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0025] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0026] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the recommended customer group in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned method for determining the recommended customer group is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] The display may be, for example, a touch screen liquid crystal display that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0029] In the above operating environment, the present application provides a method for determining a recommended customer group. Figure 2 is a flow chart of a method for determining a recommended customer group according to an embodiment of the present application, such as Figure 2 As shown, the method includes:

[0030] Step S201, obtain transaction information of the financial institution, and extract target customers who have conducted transactions with historical customers from the transaction information, wherein historical customers are customers who have purchased financial products from the financial institution, and target customers are new customers who have not purchased financial products from the financial institution.

[0031] In step S201, the transaction information may be historical transaction records obtained from the transaction system of the financial institution, including but not limited to the transaction date, transaction amount, transaction type, customer IDs of both parties to the transaction, etc. Invalid or erroneous transaction records are eliminated, such as test transactions, revoked transactions, etc., to ensure the accuracy and completeness of the data. All historical customer information (such as customer ID, transaction records, etc.) is sorted and stored in a database. A specific identifier is added to each historical customer in the database to distinguish it from the target customer. The counterparty information in each transaction record is analyzed, and all unidentified counterparties, i.e., target customers, are identified by comparing the historical customer database. Target customers may be enterprises or corporate institutions that have not yet cooperated with financial institutions.

[0032] Step S202, obtaining customer information of the target customer, inputting the customer information into the target model, and obtaining the recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values.

[0033] In step S202, the customer information may include the customer's corporate registration information, business information, transaction information, credit information, etc. Based on the customer's actual purchase behavior or feedback in the historical customer information, a quantitative evaluation is performed on the historical customer's financial service product recommendation intention to determine the historical recommendation intention evaluation value corresponding to the historical customer information.

[0034] Process the collected historical customer information and extract features that have predictive value for recommendation intention, such as transaction frequency, transaction amount, credit score, industry type, enterprise size, etc. Eliminate outliers and missing values, process duplicate data, and ensure data quality. Select machine learning algorithms suitable for classification or regression tasks, such as random forests, support vector machines, neural networks, etc., or use deep learning models such as long short-term memory networks to process time series data to predict the target customer's recommendation intention evaluation value.

[0035] Divide the preprocessed data set (i.e., multiple sets of training samples) into a training set and a validation set. Use the training set to train the selected machine learning model and adjust the model parameters to optimize the prediction effect. Use the validation set to evaluate the generalization ability of the model to ensure that the target model can effectively predict the recommendation intention evaluation value on unseen data. After the target model is trained, the customer information of the target customer can be input into the model, and the model will evaluate the recommendation intention evaluation value of the target customer based on the patterns learned during training.

[0036] The target customer's recommendation intention evaluation value output by the target model can be a probability value or a continuous score, indicating the target customer's potential interest in a specific financial service product or service. Based on the evaluation value, financial institutions can prioritize the target customers with higher evaluation values ​​to formulate financial service recommendation strategies to improve recommendation efficiency and transaction success rate.

[0037] Step S203, when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, the target customer is determined as a customer to be recommended, and a recommended customer group is determined based on the customer to be recommended.

[0038] In step S203, based on historical data and business objectives, the financial institution can set an evaluation value threshold for the recommendation intention evaluation value. The setting of the threshold can be based on factors such as the financial institution's promotion resources, market positioning, product characteristics, and potential needs of the target customer group. For example, if the financial institution wants to give priority to high-value customers, the evaluation value threshold can be set higher. The recommendation intention evaluation value output by the target model is compared with the set evaluation value threshold. For target customers whose recommendation intention evaluation value is greater than or equal to the evaluation value threshold, they are determined as customers to be recommended. By screening out potential customers who are most likely to be interested in the recommended financial products or services from a large number of target customers, the scope of promotion activities is narrowed and the efficiency of resource utilization is improved.

[0039] Further analysis is performed on the selected recommended customers to determine the final recommended customer groups. Customer groups can be segmented, for example, based on characteristics such as customer industry, enterprise size, credit rating or geographical location, to divide the recommended customers into different customer groups so that financial institutions can develop more targeted promotion strategies.

[0040] It should be noted that after determining the recommended customer group, you can formulate a personalized promotion strategy for financial products or services based on their characteristics and needs. You can choose the promotion channel that best matches the recommended customer group (such as email, social media, offline activities, etc.), design promotion information to attract the recommended customer group, and determine the best promotion time.

[0041] The method for determining the recommended customer group provided in the embodiment of the present application obtains the transaction information of the financial institution, extracts the target customers who have conducted transactions with the historical customers from the transaction information, wherein the historical customers are customers who have purchased financial products at the financial institution, and the target customers are new customers who have not purchased financial products at the financial institution; obtains the customer information of the target customers, inputs the customer information into the target model, and obtains the recommendation intention evaluation value of the target customers, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, determines the target customer as a customer to be recommended, and determines the recommended customer group based on the customer to be recommended, by mining the customer to be recommended from the target customers who have conducted transactions with the historical customers, obtaining the customer information of the target customer and determining the recommendation intention evaluation value, and then determining the customer to be recommended based on the recommendation intention evaluation value, thereby achieving the purpose of efficiently mining the customer to be recommended, thereby achieving the technical effect of improving the customer acquisition efficiency of the financial institution's new customers, and thereby solving the technical problem of low efficiency in acquiring customers to be recommended for financial products.

[0042] In order to determine the recommendation intention evaluation value of the target customer, it is necessary to train a target model. Optionally, in the method for determining the recommended customer group provided in the embodiment of the present application, the target model is obtained by the following method: obtaining the historical evaluation records of the financial institution on the customer, extracting the historical customer information and historical recommendation intention evaluation value of each customer from the historical evaluation records; determining the historical customer information and historical recommendation intention evaluation value of each customer as a set of training samples to obtain multiple sets of training samples; training the machine learning model based on the multiple sets of training samples to obtain the target model.

[0043] In some examples, historical customer information and historical recommendation intention evaluation values ​​of all relevant customers are collected from the historical evaluation records of financial institutions. The information may include basic information of customers (such as business size, industry type), transaction records, credit scores, historical financial service usage, etc., as well as historical evaluation values ​​of financial product or service recommendation intentions for these customers. Invalid or erroneous data, such as missing values ​​or outliers, are removed to ensure the integrity and accuracy of the data. The collected historical customer information is processed to extract features that are valuable for predicting recommendation intentions, which may include but are not limited to transaction amount, transaction frequency, customer type, credit rating, etc. Non-numeric features (such as customer type, industry type) are converted into numerical codes so that the machine learning model can process them.

[0044] For each customer, their historical customer information and the corresponding historical recommendation intention evaluation values ​​are used as a set of training samples. According to the nature of the prediction task, select an appropriate machine learning model, such as logistic regression, decision tree, random forest, support vector machine, neural network, etc. Divide the prepared multiple sets of training samples into training sets and validation sets. The training set is used for model training, and the validation set is used for model validation and parameter adjustment. Use the training set data to train the machine learning model, and optimize the model's predictive ability for recommendation intention evaluation values ​​by continuously adjusting the model parameters. Test the prediction performance of the target model on the validation set, such as accuracy, recall, etc., to ensure that the model can effectively generalize to unseen data.

[0045] This embodiment uses the historical evaluation records of financial institutions to construct a training sample set and trains a machine learning model to obtain a target model that can predict the evaluation value of customer recommendation intentions. This improves the customer analysis and promotion strategy formulation capabilities of financial institutions, improves the efficiency of resource allocation, and provides customers with more personalized and accurate services.

[0046] The historical recommendation intention evaluation value can be determined by the investment ability evaluation value, the enterprise scale evaluation value, the capital income and expenditure evaluation value and the stability evaluation value. Optionally, in the method for determining the recommended customer group provided in the embodiment of the present application, extracting each customer's historical customer information and the historical recommendation intention evaluation value from the historical evaluation record includes: determining each customer's historical customer information from the historical evaluation record, and for each customer, extracting at least one of the following from the customer's historical customer information: enterprise registration information, business information, transaction information and credit information; determining the customer's investment ability evaluation value based on the transaction information, determining the customer's enterprise scale evaluation value based on the enterprise registration information, determining the customer's capital income and expenditure evaluation value based on the business information, and determining the customer's stability evaluation value based on the credit information; determining the customer's historical recommendation intention evaluation value based on at least one of the following: investment ability evaluation value, enterprise scale evaluation value, capital income and expenditure evaluation value and stability evaluation value.

[0047] In some examples, historical customer information may include enterprise registration information: including registration time, registered name, registered scale, registered assets, business field, registered address, legal person information, etc. Business information: such as annual revenue, cost, profit, cash flow status, business stability, etc. Transaction information: involving transaction records in financial institutions, including transaction amount, transaction frequency, transaction type, etc. Credit information: including credit score, default record, financial health, etc.

[0048] By analyzing the transaction amount and frequency in the transaction information, the client's investment capacity and capital liquidity are evaluated to obtain the investment capacity evaluation value. According to the registered scale and registered assets in the enterprise registration information, the client's enterprise scale and market influence are evaluated to obtain the enterprise scale evaluation value. Combined with the income, expenditure and cash flow status in the operating information, the client's capital health and needs are evaluated to obtain the capital income and expenditure evaluation value. Based on the credit score and financial health in the credit information, the long-term stability of the client's cooperation with the financial institution is evaluated to obtain the stability evaluation value.

[0049] For example, the business registration information of customers obtained from the business registration system includes registration time, registration name, registration scale, registered assets, business field, registered address, legal person information, etc. There is also company property information such as factory property rental fees, water and electricity payments, etc.; intellectual property rating information, such as whether it is a high-tech industry, patent status, and science and technology enterprise rating information; financial transaction flow information, amount, direction, counterparty; risk credit evaluation information, etc.

[0050] In some examples, the evaluation criteria for the historical recommendation intention assessment value can be based on the company's size, stability, healthy capital receipts and expenditures, strong demand for financial services, etc., which can bring a large amount of stable income to financial institutions. At the same time, it can also be a key supported enterprise or a high-tech potential enterprise.

[0051] In some examples, the historical recommendation intention evaluation value can also be determined based on an evaluation model, which can be a linear model, a decision tree model, or a neural network model, which is used to predict the historical recommendation intention evaluation value based on the above-mentioned investment capacity evaluation value, enterprise scale evaluation value, capital income and expenditure evaluation value, and stability evaluation value.

[0052] This embodiment extracts multi-dimensional evaluation values ​​from historical customer information and trains the model to predict historical recommendation intention evaluation values, so that financial institutions can understand the needs and potential interests of each customer more comprehensively and accurately. This helps financial institutions optimize product and service recommendation strategies, improve promotion effects, and increase customer satisfaction and loyalty, thereby enhancing the market competitiveness of financial institutions.

[0053] In order to ensure the accuracy of the evaluation of the target customer to be recommended, it is necessary to timely update the customer information according to the target transaction of the target customer. Optionally, in the method for determining the recommended customer group provided in the embodiment of the present application, before determining the target customer as the customer to be recommended, the method also includes: determining the target transaction between the target customer and the historical customer, and judging whether the target transaction affects the financial status of the target customer within a preset period; if the target transaction does not affect the financial status of the target customer within the preset period, executing the step of determining the target customer as the customer to be recommended; if the target transaction affects the financial status of the target customer within the preset period, marking the target customer as a non-intended customer within the preset period; updating the customer information of the target customer after the preset period, and executing the step of inputting the customer information into the target model based on the updated customer information to obtain the recommendation intention evaluation value of the target customer.

[0054] In some examples, if there is a target transaction for the recommended customer in a financial institution, the target transaction may cause changes in the funds of the recommended customer in the future, affecting the success rate of the transaction. Identify target transactions between target customers and historical customers, which may involve large capital flows, purchases of high-risk financial products, etc. Evaluate the impact of the target transaction on the target customer's capital status within a preset period (such as one month, one quarter), such as changes in capital balances, liquidity risks, changes in debt levels, and investment return expectations.

[0055] If the target transaction is evaluated as not having a negative impact on the target customer's financial status within the preset period, such customers can be determined as customers to be recommended. On the contrary, if the target transaction may have a negative impact on the target customer's financial status within the preset period, the customer is temporarily marked as a non-intended customer to avoid promotion activities during the period to avoid increasing their financial burden. After the preset period ends, the target customer's information is updated, including the latest transaction records, financial status, credit rating, etc. The updated customer information is re-entered into the target model to obtain the latest recommendation intention evaluation value to determine whether the customer has become a customer to be recommended again.

[0056] This embodiment avoids recommending financial services during a period of tight financial pressure on customers, thereby reducing customer dissatisfaction caused by financial pressure and improving customer experience. Customers who will not be short of funds due to target transactions within a preset period can be promoted first to improve resource utilization efficiency. Non-intended customers are marked within the preset period to avoid recommending products that may increase financial risks to customers, which helps financial institutions in risk management.

[0057] In order to ensure the timeliness of the recommendation intention evaluation value, it is necessary to timely update the customer information according to the change information of the target customer. Optionally, in the method for determining the recommended customer group provided in the embodiment of the present application, after obtaining the recommendation intention evaluation value of the target customer, the method also includes: when the recommendation intention evaluation value is less than the evaluation value threshold, detecting the change information of the target customer, wherein the change information includes at least one of the following: business change information, bidding information and tendering information; when the change information of the target customer is detected, updating the customer information of the target customer based on the change information; determining an updated recommendation intention evaluation value based on the updated customer information, and when the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, determining the target customer as a customer to be recommended; when the updated recommendation intention evaluation value is less than the evaluation value threshold, repeating the step of detecting the change information of the target customer until the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, or the detection duration is greater than or equal to the detection duration threshold.

[0058] In some examples, because customer information is constantly changing, the information mastery, cognition, methods and approaches of recommending customers, and the financial service products to be recommended may need to change accordingly. Customer change information includes sudden changes in business conditions, increased risks, sudden public opinion storms, sudden changes in industry fields, changes in roles, corporate level upgrades, site relocation, changes in business focus areas, acquisitions and sales of subsidiaries, etc. Business change information (such as corporate expansion, contraction, industry transformation, etc.), bidding information (such as information on participating in corporate bidding projects), bidding information (publishing bidding notices, seeking information on suppliers or partners), etc. These changes may affect customers' demand and interest in financial services.

[0059] Once the target customer's change information is detected, immediately update its customer information, including but not limited to new business conditions, financial data, credit records, etc. Re-enter the updated customer information into the target model to obtain an updated recommendation intention evaluation value. If the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, it indicates that the target customer's needs or interests may have changed. At this time, it can be determined as a customer to be recommended and corresponding financial service promotion activities can be carried out. If the updated recommendation intention evaluation value is still lower than the threshold, keep the target customer as an intended customer, but continue to monitor its change information until the threshold condition is met or the detection time threshold is reached.

[0060] By setting a detection time threshold, you can avoid monitoring a customer indefinitely and prevent wasting resources. If the target customer's recommendation intention evaluation value still does not reach the threshold when the detection time threshold is reached, you can temporarily put the customer on hold or adjust its customer classification so that it can be re-evaluated at a more appropriate time in the future.

[0061] By continuously detecting the change information of target customers, this embodiment enables financial institutions to adjust customer classification and promotion strategies in a timely manner to adapt to changes in customer needs. When it is detected that a customer's needs or interests have changed, the recommendation status can be quickly adjusted to provide more in-demand financial services, thereby enhancing customer satisfaction and response rate. By setting a detection time threshold, excessive monitoring of low-intent customers is avoided, and the promotion resource allocation of financial institutions is optimized to ensure that resources are used for the most potential customer groups.

[0062] After determining the recommended customer group, the recommendation timing of the target financial product can also be determined based on the financial product coverage rate. Optionally, in the method for determining the recommended customer group provided in the embodiment of the present application, after determining the recommended customer group based on the customers to be recommended, the method also includes: for each customer to be recommended in the recommended customer group, determining the financial products that the customer to be recommended has purchased; determining the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customer to be recommended; and recommending the target financial product to the customer to be recommended when the financial product coverage rate is less than or equal to the coverage rate threshold.

[0063] In some examples, for each customer to be recommended, the information of purchased financial products is extracted from the transaction records of the financial institution, including product type, purchase time, transaction amount, transaction frequency, etc. The financial product coverage is calculated based on the purchased product information and customer transaction information. The coverage can be calculated in the following ways: Product type coverage: the proportion of the types of financial products purchased by the customer to all the types of products that can be purchased. Product transaction amount coverage: the proportion of the amount of financial product transactions that the customer has made to his potential total investment amount. Product transaction frequency coverage: the proportion of the frequency of financial product transactions conducted by the customer to his potential transaction frequency.

[0064] Compare the calculated financial product coverage with the preset coverage threshold. If the coverage is less than or equal to the coverage threshold, it indicates that there are gaps or deficiencies in the customer's use of financial products, and it is a good time to recommend new financial products. For customers whose coverage is below the threshold, recommend suitable target financial products based on the types of products they have purchased, trading preferences, financial status and other information. Recommendation strategies can include providing customers with complementary financial products to fill gaps in their product portfolios. Recommend financial products that meet their needs based on their risk preferences and financial status. Send recommendation information to the recommended customers through email, text messages, phone calls or face-to-face communication with account managers. At the same time, record recommendation results and customer feedback for subsequent strategy optimization.

[0065] By analyzing the products and transaction information that customers have purchased, this embodiment enables financial institutions to more accurately identify customers' financial product needs and provide more personalized recommendations. It avoids recommending products that customers already have or are not interested in, and reduces customer dissatisfaction caused by irrelevant or repeated recommendations. The calculation of financial product coverage helps financial institutions identify the best time to make recommendations and avoid making invalid recommendations when customers have fully covered their financial product needs.

[0066] Optionally, in the method for determining the recommended customer group provided in an embodiment of the present application, determining the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customers to be recommended includes: determining the purchase amount of the purchased financial products from the product information, and determining the investment amount of the target customers within the target period from the transaction information; calculating the ratio of the purchase amount to the investment amount to obtain the financial product coverage rate.

[0067] In some examples, detailed information on financial products purchased by the recommended customer is obtained, especially the purchase amount of each product. All investment amounts of the target customer in the target period (such as the most recent year, the most recent quarter) are extracted from the transaction records of the financial institution, including investment in financial products, other forms of investment, etc. The purchase amounts of the purchased financial products are summarized to obtain the total purchase amount of the target customer on financial products. All investment amounts of the target customer in the target period are summarized to obtain their total investment amount. Financial product coverage rate = purchase amount of financial products / total investment amount. This ratio reflects the proportion of financial products purchased by the customer through financial institutions in the target period in their total investment amount.

[0068] By calculating the financial product coverage rate in this embodiment, financial institutions can understand customers' utilization of their products and services in more detail, thus providing a basis for personalized services.

[0069] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0070] Example 2

[0071] The embodiment of the present application also provides a device for determining a recommended customer group. It should be noted that the device for determining a recommended customer group in the embodiment of the present application can be used to execute the method for determining a recommended customer group provided in the embodiment of the present application. The device for determining a recommended customer group provided in the embodiment of the present application is introduced below.

[0072] According to an embodiment of the present application, a device for implementing the above-mentioned method for determining a recommended customer group is also provided. Figure 3is a schematic diagram of a device for determining a recommended customer group according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0073] The acquisition unit 301 is used to acquire transaction information of a financial institution, and extract target customers who have conducted transactions with historical customers from the transaction information, wherein historical customers are customers who have purchased financial products from a financial institution, and target customers are new customers who have not purchased financial products from a financial institution;

[0074] An input unit 302 is used to obtain customer information of a target customer, input the customer information into a target model, and obtain a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple sets of training samples, each set of training samples includes historical customer information and historical recommendation intention evaluation values;

[0075] The first determining unit 303 is configured to determine the target customer as a customer to be recommended when the recommendation intention evaluation value is greater than or equal to an evaluation value threshold, and determine a recommended customer group based on the customer to be recommended.

[0076] The device for determining the recommended customer group provided in the embodiment of the present application obtains the transaction information of the financial institution through the acquisition unit 301, and extracts the target customers who have conducted transactions with the historical customers from the transaction information, wherein the historical customers are customers who have purchased financial products at the financial institution, and the target customers are new customers who have not purchased financial products at the financial institution; the input unit 302 obtains the customer information of the target customer, inputs the customer information into the target model, and obtains the recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; the first determination unit 303 determines the target customer as a customer to be recommended when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, and determines the recommended customer group based on the customer to be recommended, by mining the customer to be recommended from the target customers who have conducted transactions with the historical customers, obtaining the customer information of the target customer and determining the recommendation intention evaluation value, and then determining the customer to be recommended based on the recommendation intention evaluation value, thereby achieving the purpose of efficiently mining the customer to be recommended, thereby achieving the technical effect of improving the customer acquisition efficiency of the financial institution's new customers, and thus solving the technical problem of low efficiency in acquiring customers to be recommended for financial products.

[0077] Optionally, in the device for determining the recommended customer group provided in the embodiment of the present application, the device also includes: an extraction unit, used to obtain the historical evaluation records of the financial institution on the customers, and extract the historical customer information and historical recommendation intention evaluation values ​​of each customer from the historical evaluation records; a second determination unit, used to determine the historical customer information and historical recommendation intention evaluation values ​​of each customer as a group of training samples, to obtain multiple groups of training samples; a training unit, used to train the machine learning model based on the multiple groups of training samples to obtain a target model.

[0078] Optionally, in the device for determining the recommended customer group provided in the embodiment of the present application, the extraction unit includes: a first determination module, used to determine the historical customer information of each customer from the historical evaluation records, and for each customer, extracting at least one of the following from the customer's historical customer information: enterprise registration information, business information, transaction information and credit information; a second determination module, used to determine the customer's investment capacity assessment value based on the transaction information, determine the customer's enterprise scale assessment value based on the enterprise registration information, determine the customer's capital income and expenditure assessment value based on the business information, and determine the customer's stability assessment value based on the credit information; a third determination module, used to determine the customer's historical recommendation intention assessment value based on at least one of the following: investment capacity assessment value, enterprise scale assessment value, capital income and expenditure assessment value and stability assessment value.

[0079] Optionally, in the device for determining the recommended customer group provided in the embodiment of the present application, the device also includes: a third determination unit, used to determine the target transaction between the target customer and the historical customer, and judge whether the target transaction affects the financial status of the target customer within a preset period; a first execution unit, used to execute the step of determining the target customer as a customer to be recommended when the target transaction does not affect the financial status of the target customer within the preset period; a marking unit, used to mark the target customer as a non-intended customer within the preset period when the target transaction affects the financial status of the target customer within the preset period; a first updating unit, used to update the customer information of the target customer after the preset period, and execute the step of inputting the customer information into the target model based on the updated customer information to obtain the recommendation intention evaluation value of the target customer.

[0080] Optionally, in the device for determining the recommended customer group provided in the embodiment of the present application, the device also includes: a detection unit, which is used to detect change information of the target customer when the recommendation intention evaluation value is less than the evaluation value threshold, wherein the change information includes at least one of the following: business change information, bidding information and tender information; a second updating unit, which is used to update the customer information of the target customer based on the change information when the change information of the target customer is detected; a fourth determination unit, which is used to determine an updated recommendation intention evaluation value based on the updated customer information, and determine the target customer as a customer to be recommended when the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold; a second execution unit, which is used to repeatedly execute the step of detecting change information of the target customer when the updated recommendation intention evaluation value is less than the evaluation value threshold, until the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, or the detection duration is greater than or equal to the detection duration threshold.

[0081] Optionally, in the device for determining the recommended customer group provided in the embodiment of the present application, the device also includes: a fifth determination unit, used to determine, for each customer to be recommended in the recommended customer group, the financial products purchased by the customer to be recommended; a sixth determination unit, used to determine the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customer to be recommended; and a recommendation unit, used to recommend the target financial product to the customer to be recommended when the financial product coverage rate is less than or equal to a coverage rate threshold.

[0082] Optionally, in the device for determining the recommended customer group provided in the embodiment of the present application, the sixth determination unit includes: a fourth determination module, used to determine the purchase amount of the purchased financial products from the product information, and determine the investment amount of the target customers within the target period from the transaction information; a calculation module, used to calculate the ratio of the purchase amount and the investment amount to obtain the financial product coverage rate.

[0083] It should be noted that the acquisition unit 301, the input unit 302 and the first determination unit 303 correspond to steps S201 to S203 in Example 1, and the three units and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules or units can also be part of the device and can be run in the computer terminal 10 provided in Example 1.

[0084] Example 3

[0085] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 402, memory 404, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0086] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0087] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain transaction information of the financial institution, extract target customers who have conducted transactions with historical customers from the transaction information, wherein historical customers are customers who have purchased financial products at the financial institution, and target customers are new customers who have not purchased financial products at the financial institution; obtain customer information of the target customer, input the customer information into the target model, and obtain a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, the target customer is determined as a customer to be recommended, and a recommended customer group is determined based on the customer to be recommended.

[0088] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the financial institution's historical evaluation records of customers, and extract each customer's historical customer information and historical recommendation intention evaluation values ​​from the historical evaluation records; determine each customer's historical customer information and historical recommendation intention evaluation values ​​as a set of training samples to obtain multiple sets of training samples; train the machine learning model based on the multiple sets of training samples to obtain a target model.

[0089] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the historical customer information of each customer from the historical evaluation records, and for each customer, extract at least one of the following from the customer's historical customer information: enterprise registration information, business information, transaction information and credit information; determine the customer's investment capacity assessment value based on the transaction information, determine the customer's enterprise scale assessment value based on the enterprise registration information, determine the customer's capital income and expenditure assessment value based on the business information, and determine the customer's stability assessment value based on the credit information; determine the customer's historical recommendation intention assessment value based on at least one of the following: investment capacity assessment value, enterprise scale assessment value, capital income and expenditure assessment value and stability assessment value.

[0090] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the target transaction between the target customer and the historical customer, and judge whether the target transaction affects the financial status of the target customer within a preset period; if the target transaction does not affect the financial status of the target customer within the preset period, execute the step of determining the target customer as a customer to be recommended; if the target transaction affects the financial status of the target customer within the preset period, mark the target customer as a non-intended customer within the preset period; update the customer information of the target customer after the preset period, and based on the updated customer information, execute the step of inputting the customer information into the target model to obtain the recommendation intention evaluation value of the target customer.

[0091] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: when the recommendation intention evaluation value is less than the evaluation value threshold, detect the change information of the target customer, wherein the change information includes at least one of the following: business change information, bidding information and tender information; when the change information of the target customer is detected, update the customer information of the target customer based on the change information; determine an updated recommendation intention evaluation value based on the updated customer information, and when the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, determine the target customer as a customer to be recommended; when the updated recommendation intention evaluation value is less than the evaluation value threshold, repeat the step of detecting the change information of the target customer until the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, or the detection duration is greater than or equal to the detection duration threshold.

[0092] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each customer to be recommended in the recommended customer group, determine the financial products that the customer to be recommended has purchased; determine the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customer to be recommended; when the financial product coverage rate is less than or equal to the coverage rate threshold, recommend the target financial product to the customer to be recommended.

[0093] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the purchase amount of the purchased financial products from the product information, and determine the investment amount of the target customer within the target period from the transaction information; calculate the ratio of the purchase amount and the investment amount to obtain the financial product coverage rate.

[0094] By adopting the embodiment of the present application, a method is provided for obtaining transaction information of a financial institution, extracting target customers who have conducted transactions with historical customers from the transaction information, wherein historical customers are customers who have purchased financial products at a financial institution, and target customers are new customers who have not purchased financial products at a financial institution; obtaining customer information of the target customer, inputting the customer information into a target model, and obtaining a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical customer information and historical recommendation intention evaluation values; when the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, the target customer is determined as a customer to be recommended, and a solution for determining a recommended customer group based on the customer to be recommended is provided. By mining the customer to be recommended from the target customers who have conducted transactions with historical customers, obtaining the customer information of the target customer and determining the recommendation intention evaluation value, and then determining the customer to be recommended based on the recommendation intention evaluation value, the purpose of efficiently mining the customer to be recommended is achieved, thereby achieving the technical effect of improving the customer acquisition efficiency of new customers of financial institutions, and thereby solving the technical problem of low efficiency in acquiring customers to be recommended for financial products.

[0095] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone, a tablet computer, a PDA, a mobile Internet device (MID), a PAD or other terminal device. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0096] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0097] Example 4

[0098] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for determining the recommended customer group provided in the first embodiment.

[0099] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0100] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the method for determining a recommended customer group.

[0101] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0102] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0107] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a recommended customer group, characterized in that: include: Acquire transaction information of a financial institution, and extract target customers who have conducted transactions with historical customers from the transaction information, wherein the historical customers are customers who have purchased financial products from the financial institution, and the target customers are new customers who have not purchased financial products from the financial institution; Acquire customer information of the target customer, input the customer information into a target model, and obtain a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple sets of training samples, each set of training samples includes historical customer information and historical recommendation intention evaluation values; In the case that the recommendation intention evaluation value is greater than or equal to the evaluation value threshold, the target customer is determined as a customer to be recommended, and a recommended customer group is determined based on the customer to be recommended.

2. The method according to claim 1, characterized in that The target model is obtained by: Obtaining the financial institution's historical evaluation records of the customer, and extracting each customer's historical customer information and historical recommendation intention evaluation value from the historical evaluation records; Determine each customer's historical customer information and historical recommendation intention evaluation value as a set of training samples, and obtain multiple sets of training samples; A machine learning model is trained based on the multiple groups of training samples to obtain the target model.

3. The method according to claim 2, characterized in that Extracting historical customer information and historical recommendation intention evaluation values ​​of each customer from the historical evaluation records includes: Determining historical customer information of each customer from the historical evaluation records, and for each customer, extracting at least one of the following from the historical customer information of the customer: business registration information, business information, transaction information, and credit information; Determine the investment capacity assessment value of the customer based on the transaction information, determine the enterprise scale assessment value of the customer based on the enterprise registration information, determine the capital income and expenditure assessment value of the customer based on the operating information, and determine the stability assessment value of the customer based on the credit information; The historical recommendation intention evaluation value of the client is determined based on at least one of: the investment capacity evaluation value, the enterprise scale evaluation value, the capital income and expenditure evaluation value, and the stability evaluation value.

4. The method according to claim 1, characterized in that Before determining the target customer as the customer to be recommended, the method further includes: Determine a target transaction between the target customer and the historical customer, and judge whether the target transaction affects the capital status of the target customer within a preset period; In the case where the target transaction does not affect the financial status of the target customer within a preset period, executing the step of determining the target customer as a customer to be recommended; In the case where the target transaction affects the financial status of the target customer within a preset period, marking the target customer as a non-intended customer within the preset period; The customer information of the target customer is updated after the preset period, and based on the updated customer information, the step of inputting the customer information into a target model is performed to obtain a recommendation intention evaluation value of the target customer.

5. The method according to claim 1, characterized in that After obtaining the recommendation intention evaluation value of the target customer, the method further includes: In the case where the recommendation intention evaluation value is less than the evaluation value threshold, detecting change information of the target customer, wherein the change information includes at least one of the following: business change information, bidding information, and tender information; When the change information of the target customer is detected, updating the customer information of the target customer based on the change information; Determine an updated recommendation intention evaluation value based on the updated customer information, and determine the target customer as a customer to be recommended when the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold; When the updated recommendation intention evaluation value is less than the evaluation value threshold, the step of detecting the change information of the target customer is repeated until the updated recommendation intention evaluation value is greater than or equal to the evaluation value threshold, or the detection duration is greater than or equal to the detection duration threshold.

6. The method according to claim 1, characterized in that After determining the recommended customer group based on the customers to be recommended, the method further includes: For each customer to be recommended in the recommended customer group, determining the financial products that the customer to be recommended has purchased; Determining the financial product coverage rate based on the product information of the purchased financial products and the transaction information of the customers to be recommended; When the financial product coverage rate is less than or equal to a coverage rate threshold, the target financial product is recommended to the customer to be recommended.

7. The method according to claim 6, characterized in that Determining the financial product coverage rate based on the product information of the purchased financial product and the transaction information of the customer to be recommended includes: Determine the purchase amount of the purchased financial product from the product information, and determine the investment amount of the target customer in the target period from the transaction information; The ratio of the purchase amount to the investment amount is calculated to obtain the financial product coverage rate.

8. A device for determining a recommended customer group, characterized in that: include: An acquisition unit, used to acquire transaction information of a financial institution, and extract target customers who have conducted transactions with historical customers from the transaction information, wherein the historical customers are customers who have purchased financial products from the financial institution, and the target customers are new customers who have not purchased financial products from the financial institution; An input unit, used to obtain customer information of the target customer, input the customer information into a target model, and obtain a recommendation intention evaluation value of the target customer, wherein the target model is trained by multiple groups of training samples, each group of training samples includes historical customer information and historical recommendation intention evaluation values; The first determining unit is configured to determine the target customer as a customer to be recommended if the recommendation intention evaluation value is greater than or equal to an evaluation value threshold, and determine a recommended customer group based on the customer to be recommended.

9. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the method for determining the recommended customer group described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method for determining the recommended customer group described in any one of claims 1 to 7 are implemented.

Images