Financial service recommendation method and device, electronic equipment and computer program product

Abstract

The invention discloses a financial service recommendation method and device, electronic equipment and a computer program product. The method comprises the steps of determining an intentional customer group of a to-be-recommended service, and recommending the to-be-recommended service to the intentional customer group in a first recommendation mode; a feedback result of each customer in the intention customer group on the first recommendation mode is received, a contact portrait of the customer is constructed through the feedback result, and the feedback result comprises a feedback feature of the customer; and determining a second recommendation mode based on the contact portrait of the customer, and recommending the to-be-recommended service to the customer through the second recommendation mode, the second recommendation mode being a mode of recommending the service to the customer through a preset second contact strategy, and the second contact strategy being a strategy of which the degree of disturbing the customer is higher than that of the first contact strategy. Through application of the method and the device, the problem of relatively low customer satisfaction caused by inaccurate recommendation modes adopted when financial services are recommended to intentional customers in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the fields of big data and artificial intelligence, and specifically, to a financial service recommendation method, device, electronic device and computer program product. Background Art

[0002] In order to recommend activities or products to users in order to expand the customer base and increase transaction volume, the related technologies use methods such as advertising, information, or intelligent outbound calls. However, different customer groups may have different attitudes towards different recommendation methods. Some customer groups can accept all forms of recommendation interruptions, but some customer groups may be disgusted by these recommendation methods. Therefore, the promotion methods for activities or products in the related technologies are simple and crude, which sometimes cause disgust among customers, reduce user experience, and lead to customer loss.

[0003] Currently, no effective solution has been proposed to address the problem in related technologies of low customer satisfaction due to inaccurate recommendation methods used when recommending financial services to potential customers. Summary of the invention

[0004] The main purpose of this application is to provide a financial service recommendation method, device, electronic device and computer program product to solve the problem in the related art that the recommendation method used when recommending financial services to potential customers is inaccurate, resulting in low customer satisfaction.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for recommending financial services is provided. The method includes: determining a potential customer group for the service to be recommended, recommending the service to be recommended to the potential customer group through a first recommendation method, wherein the first recommendation method is a method of recommending services to customers through a preset first contact strategy; receiving feedback results from each customer in the potential customer group on the first recommendation method, and constructing a contact profile of the customer through the feedback results, wherein the feedback results include the feedback characteristics of the customer; determining a second recommendation method based on the contact profile of the customer, and recommending the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy.

[0006] Optionally, recommending the service to be recommended to the intended customer group through the first recommendation method includes: obtaining customer information of each customer in the intended customer group, wherein the customer information includes at least one of the following: transaction data, social behavior data and identity information data; inputting the customer information into the target model to obtain the customer's contact strategy preference evaluation value, wherein the target model is trained by multiple groups of first training samples, and each group of first training samples includes historical customer information and historical contact strategy preference evaluation values; determining a target preference evaluation range to which the contact strategy preference evaluation value belongs, and determining a target contact strategy from a contact strategy mapping relationship table based on the target preference evaluation range, wherein the contact strategy mapping relationship table contains multiple groups of mapping relationships, and each group of mapping relationships represents a correspondence between a contact strategy and a preference evaluation range; determining the first recommendation method for the customer to communicate with the customer through the target contact strategy in order to recommend the service, and recommending the service to the customer through the first recommendation method.

[0007] Optionally, after obtaining the customer's contact strategy preference evaluation value, the method also includes: determining whether the contact strategy preference evaluation value is greater than or equal to a first evaluation value threshold; when the contact strategy preference evaluation value is less than the first evaluation value threshold, executing the step of determining a target preference evaluation range to which the contact strategy preference evaluation value belongs; when the contact strategy preference evaluation value is greater than or equal to the first evaluation value threshold, obtaining a second recommendation method; and recommending the service to be recommended to the customer through the second recommendation method.

[0008] Optionally, constructing a customer's contact profile through feedback results includes: extracting the customer's feedback features from the feedback results, wherein the feedback features include at least one of the following: response interval, response duration, response attitude, response discourse, and recommendation results; inputting the feedback features into a contact profile construction model to obtain the customer's contact profile, wherein the contact profile construction model is trained by multiple groups of second training samples, and each group of second training samples includes historical feedback features and historical contact profiles.

[0009] Optionally, determining the second recommendation method based on the customer's contact profile includes: determining the customer's handling intention evaluation value for the recommended service through the contact profile; judging whether the handling intention evaluation value is greater than or equal to a second evaluation value threshold; when the handling intention evaluation value is greater than or equal to the second evaluation value threshold, communicating with the customer through the first preset contact strategy to recommend the service is determined as the second recommendation method; when the handling intention evaluation value is less than the second evaluation value threshold, communicating with the customer through the second preset contact strategy to recommend the service is determined as the second recommendation method.

[0010] Optionally, after recommending the service to be recommended to the customer through the second recommendation method, the method also includes: receiving the customer's handling intention result for the recommended service; when the handling intention result indicates that the customer has the handling intention for the recommended service, determining a target contact cycle, and recommending the service to be recommended to the customer every target contact cycle; when the handling intention result indicates that the customer has no handling intention for the recommended service, adding a target tag to the customer, wherein the target tag is used to indicate that the customer has no handling intention for the recommended service.

[0011] Optionally, determining the intended customer group for the service to be recommended includes: obtaining target features of the service to be recommended, and calculating the similarity between the service to be recommended and historically recommended services based on the target features; determining historically recommended services whose similarity is greater than or equal to a similarity threshold, and obtaining multiple customers who have handled the historically recommended services; and defining the set of multiple customers as the intended customer group for the service to be recommended.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a financial service recommendation device is provided. The device includes: a first determination unit, which is used to determine the intended customer group of the service to be recommended, and recommend the service to be recommended to the intended customer group through a first recommendation method, wherein the first recommendation method is a method of recommending services to customers through a preset first contact strategy; a receiving unit, which is used to receive the feedback results of each customer in the intended customer group on the first recommendation method, and build a contact profile of the customer through the feedback results, wherein the feedback results include the feedback characteristics of the customer; a second determination unit, which is used to determine a second recommendation method based on the contact profile of the customer, and recommend the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy.

[0013] In an embodiment of the present application, a potential customer group for a service to be recommended is determined, and the service to be recommended is recommended to the potential customer group through a first recommendation method, wherein the first recommendation method is a method of recommending services to customers through a preset first contact strategy; feedback results of each customer in the potential customer group on the first recommendation method are received, and a contact profile of the customer is constructed through the feedback results, wherein the feedback results include feedback characteristics of the customer; a second recommendation method is determined based on the contact profile of the customer, and the service to be recommended is recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy, by first recommending financial services to the potential customer group through the first recommendation method, then collecting feedback results from the customer, constructing a contact profile of the customer based on the feedback results, determining a second recommendation method with a higher degree of disturbance from the contact profile, and then recommending financial services to the customer through the second recommendation method, the purpose of recommending financial services to customers through a more accurate recommendation method is achieved, thereby achieving the technical effect of improving the accuracy of the recommendation method for selecting financial services, and further solving the technical problem of low customer satisfaction due to inaccurate recommendation methods used when recommending financial services to potential customers. 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 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a financial service recommendation method is shown;

[0016] Figure 2 is a flowchart of a financial service recommendation method provided according to an embodiment of the present application;

[0017] Figure 3 is a schematic diagram of a financial service recommendation device provided 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 of financial service recommendation 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 financial service recommendation method. Figure 1As 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 financial service recommendation method 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, to implement the above-mentioned financial service recommendation method. 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 recommending financial services. Figure 2 is a flowchart of a financial service recommendation method provided according to an embodiment of the present application, such as Figure 2 As shown, the method includes:

[0030] Step S201, determining a potential customer group for the service to be recommended, and recommending the service to be recommended to the potential customer group through a first recommendation method, wherein the first recommendation method is a method of recommending the service to the customer through a preset first contact strategy.

[0031] In step S201, the service to be recommended may be a financial product promotion or a financial service promotion, such as precious metals, financial funds, account opening preferential service plans, financial management treasures, etc. The financial product categories may include new customer account opening and expansion, or deposit collection, financial management sales, and customer quality improvement, etc.

[0032] The first recommendation method can be to recommend services by adopting a weak-interruption contact strategy (also known as the first contact strategy), that is, to recommend services in a gentle way that does not directly interrupt the user's current activities, so as to reduce user disgust and maintain a good user experience. For example, sending text messages, emails, pushing non-intrusive sidebar ads or information notifications, etc. The first recommendation method can also be combined with the user's emotional and social attributes, such as sending text messages according to the user's active time period, or pushing relevant service information when the user is reading an email, to ensure that the information is delivered at the time when the user is most likely to pay attention.

[0033] Through the first recommendation method, it is possible to initially contact and attract the user's attention without causing significant discomfort to the user. Subsequently, based on the user's feedback on the weak interruption method, the user's interest in the service and his or her acceptance of the subsequent possible strong interruption method can be judged, so as to more accurately adjust the subsequent service recommendation strategy and improve the success rate of service recommendation.

[0034] For example, if a user quickly replies to a text message or clicks on a link in an email and shows a positive attitude towards inquiry, it means that the user is interested in the recommended service and may be more inclined to accept further communication through strong interruptions such as telephone consultation or advertising on the home screen. On the contrary, if the user reacts coldly or has no feedback to the initial weak interruption, a gentler approach can be used to follow up to avoid premature strong interruptions that may cause user disgust.

[0035] Step S202, receiving feedback results of each customer in the intended customer group on the first recommendation method, and constructing a contact profile of the customer through the feedback results, wherein the feedback results include feedback features of the customer.

[0036] In step S202, the first recommendation method is a weakly disturbing recommendation method for customers, which aims to preliminarily understand the customer's attitude and interest in the recommended service. The feedback result may include multiple feedback characteristics of the customer, for example, the response interval: the time from the customer receiving the recommendation information to the time of responding, which can measure the customer's immediate interest and response speed. Response attitude: the tone and wording of the customer's feedback, which helps to understand the customer's interest status. Response time: the time the customer spends in giving feedback can indirectly reflect the degree of his or her in-depth attention to the recommended service. Response words: the customer's direct feedback content, including the depth of the inquiry, the focus of attention, etc., providing clues to specific points of interest. Whether to listen but not respond: whether the customer does not make any response, indicating that he or she is not interested or disgusted with the interruption method. Whether there is communication inquiry: whether the customer actively asks questions or expresses the desire to learn more, reflecting his or her potential needs. Whether to continue communication in the future: whether the customer is willing to conduct follow-up communication, such as making an appointment for telephone consultation, subscribing to more information, etc., to measure his or her continued interest. Recommendation result: whether the final customer accepts the recommended service and successfully converts it into a transaction.

[0037] Based on the above feedback characteristics, a contact profile of each customer can be constructed. This profile can include the customer's basic information and feedback characteristics, which is used to reflect the customer's preference and acceptance of different recommendation methods, as well as their interest in the recommended service. Through contact profiles, recommendation strategies can be adjusted more personalized. For customers who show high interest and positive feedback, more direct strong interruption methods can be used for further communication. For customers who respond coldly or dislike, the frequency and depth of weak interruptions should be maintained or increased to avoid customer loss caused by excessive interruptions.

[0038] For example, customers who quickly respond to text messages and ask detailed inquiries can be marked as "highly interested" and direct communication through telephone consultation can be considered; while customers who only open the email but do not respond can be marked as "potentially interested" and more information can be provided through emails or non-intrusive advertisements to stimulate their interest.

[0039] Step S203, determining a second recommendation method based on the customer's contact profile, and recommending the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to the customer through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy.

[0040] In step S203, the second recommendation method is a recommendation method that strongly disturbs the customer. Strong or weak disturbance is a relative concept. The second contact strategy is a notification method that interrupts the customer's behavior after intervention. For example, telephone recommendation, playing advertisements on the main screen of the application, etc. In this method, the customer must terminate his behavior and be forced to accept the treatment.

[0041] Conduct in-depth analysis of customer contact profiles to identify customer groups that respond positively to the first recommended method, have a high interest, or have a clear willingness to communicate. These characteristics may include but are not limited to quick response, proactive inquiry, and an open attitude to continue communication. Based on customer preferences and contact profiles, determine the second contact strategy, and interact directly with customers through the second contact strategy to provide more detailed service information or answer their questions.

[0042] When determining the second recommendation method, you can weigh the relationship between the degree of intrusion and customer acceptance. Although a more intrusive method can provide a more direct communication opportunity, it may also cause customer disgust. Therefore, the degree of intrusion should be adjusted appropriately according to the customer's specific feedback characteristics and portrait information to avoid excessive intrusion. For customers marked as "highly interested", one-to-one communication can be carried out through telephone recommendations, and customized service introductions and solutions can be provided based on their previous feedback characteristics to increase the success rate of transactions. For customers with "potential interest" or "moderate interest", you can consider using home screen pop-up ads or personalized web page push. Although these methods are more intrusive than emails or text messages, they can provide instant and intuitive service information when users are surfing the Internet or using applications to stimulate their interest.

[0043] After implementing the second recommendation method, continue to collect customer feedback, including their attitude towards receiving services, communication effects, etc., and constantly adjust and optimize the second contact strategy to find the most effective recommendation method. For example, for a customer who expressed interest in precious metal investment through email feedback in the first stage, you can choose to make a telephone recommendation in the second stage, talk directly with the customer, understand their specific investment needs and risk preferences, provide personalized investment plans, and answer any questions the customer may have, thereby increasing the possibility of the customer accepting the service.

[0044] It should be noted that, in some embodiments, a correspondence between a first recommendation mode of weak disturbance and a second recommendation mode of strong disturbance may be set, a second recommendation mode that may follow the first recommendation mode may be set, and a condition for selecting the second recommendation mode subsequently may be set.

[0045] The financial service recommendation method provided in the embodiment of the present application determines the intended customer group for the service to be recommended, and recommends the service to be recommended to the intended customer group through a first recommendation method, wherein the first recommendation method is a method of recommending services to customers through a preset first contact strategy; receives feedback results of each customer in the intended customer group on the first recommendation method, and builds a contact profile of the customer through the feedback results, wherein the feedback results include feedback characteristics of the customer; determines a second recommendation method based on the contact profile of the customer, and recommends the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy, by first recommending financial services to the intended customer group in the first recommendation method, then collecting feedback results from the customer, building a contact profile of the customer based on the feedback results, determining a second recommendation method with a higher degree of disturbance from the contact profile, and then recommending financial services to the customer in the second recommendation method, thereby achieving the purpose of recommending financial services to customers in a more accurate recommendation method, thereby achieving the technical effect of improving the accuracy of the recommendation method for selecting financial services, and further solving the technical problem of low customer satisfaction due to inaccurate recommendation methods used when recommending financial services to intended customers.

[0046] After determining the intended customer group for the service to be recommended, first recommend the service to be recommended to the customer in a first recommendation manner. Optionally, in the financial service recommendation method provided in the embodiment of the present application, recommending the service to be recommended to the intended customer group in the first recommendation manner includes: obtaining customer information of each customer in the intended customer group, wherein the customer information includes at least one of the following: transaction data, social behavior data and identity information data; inputting the customer information into a target model to obtain a contact strategy preference evaluation value of the customer, wherein the target model is trained by multiple groups of first training samples, and each group of first training samples includes historical customer information and historical contact strategy preference evaluation values; determining a target preference evaluation range to which the contact strategy preference evaluation value belongs, and determining a target contact strategy from a contact strategy mapping relationship table based on the target preference evaluation range, wherein the contact strategy mapping relationship table contains multiple groups of mapping relationships, and each group of mapping relationships represents a corresponding relationship between a contact strategy and a preference evaluation range; determining the first recommendation method for the customer to communicate with the customer in order to recommend the service through the target contact strategy, and recommending the service to the customer to the customer through the first recommendation method.

[0047] In some examples, customers with different preferences have different preferences for the intensity of interruptions when receiving recommended financial services. The contact strategy preference evaluation value can be evaluated through the user's customer information such as transaction data of shopping websites, historical product recommendation data feedback, social group type, job occupation, mobile phone call time, call length, Internet usage habits and other data to determine the customer's first recommendation method.

[0048] Collect customer information of each customer in the intended customer group from various data sources, which includes at least transaction data, social behavior data and identity information data. Transaction data can be past purchase records, investment preferences, consumption frequency, etc.; social behavior data can include interaction habits, participation, points of interest, etc. on social media and shopping websites; identity information data refers to basic information such as age, gender, occupation, etc., which together constitute a multi-dimensional portrait of the customer.

[0049] The target model is a machine learning model trained by multiple groups of first training samples, where each group of first training samples contains historical customer information and corresponding historical contact strategy preference evaluation values. By learning from these historical data, the model can predict the current customer's preference for different contact strategies. The collected customer information is input into the target model, and the model outputs the customer's contact strategy preference evaluation value, which reflects the customer's acceptance and preference for the recommended method. The contact strategy preference evaluation value will fall within a continuous interval, and according to the size of the evaluation value, it can be classified into different preference evaluation ranges. For example, the evaluation value may be divided into three ranges: "high preference", "medium preference" and "low preference", each range representing a different degree of customer acceptance of the interruption method.

[0050] The contact strategy mapping relationship table records the correspondence between contact strategies and preference evaluation ranges. According to the preference evaluation range to which the customer contact strategy preference evaluation value belongs, the target contact strategy is queried and determined from the mapping relationship table. For example, customers with preference evaluation values ​​in the "high preference" range are more suitable for recommendation methods such as home screen pop-ups; while customers in the "low preference" range should be recommended by sending emails or text messages.

[0051] This embodiment evaluates the contact strategy preference evaluation value through customer information, thereby accurately locating the customer's contact strategy preference from a data-driven perspective, and then implementing a personalized and layered recommendation method, which not only improves the effect of service recommendation, but also maintains a good user experience and avoids possible blindness and excessive interruptions in the recommendation method.

[0052] If the customer's contact strategy preference evaluation value is high, financial services can be directly recommended to the customer in a second recommendation manner. Optionally, in the financial service recommendation method provided in the embodiment of the present application, after obtaining the customer's contact strategy preference evaluation value, the method also includes: determining whether the contact strategy preference evaluation value is greater than or equal to a first evaluation value threshold; if the contact strategy preference evaluation value is less than the first evaluation value threshold, executing the step of determining a target preference evaluation range to which the contact strategy preference evaluation value belongs; if the contact strategy preference evaluation value is greater than or equal to the first evaluation value threshold, obtaining a second recommendation manner; and recommending the service to be recommended to the customer through the second recommendation manner.

[0053] In some examples, the first evaluation value threshold is a pre-set standard value used to distinguish whether the customer is suitable for accepting the second recommended method (strong interruption method). If the contact strategy preference evaluation value is lower than this threshold, it means that the customer may prefer the weak interruption method and is not very receptive to the strong interruption method; on the contrary, if the evaluation value reaches or exceeds the threshold, it means that the customer may be more willing to accept the strong interruption method and may respond more positively to this type of recommendation method.

[0054] When the contact strategy preference evaluation value is less than the first evaluation value threshold, the strong interruption method is not directly used. According to the customer's preference evaluation range, select the appropriate weak interruption recommendation method, such as email, SMS or non-intrusive advertising push, to avoid excessive interruption and maintain a good user experience. When the contact strategy preference evaluation value is greater than or equal to the first evaluation value threshold, it indicates that the customer has a high degree of acceptance of the strong interruption recommendation method. The second recommendation method can be used for this customer, and the recommended service can be recommended to the customer through the second recommendation method, in order to obtain a higher conversion rate and transaction success rate.

[0055] Through this hierarchical decision-making process, this embodiment can intelligently select the most suitable recommendation method based on the personalized preferences of each customer, thereby avoiding excessive disturbance to uninterested customers and effectively establishing deeper connections with potential high-value customers, thereby improving the service recommendation effect while ensuring good user experience and customer satisfaction.

[0056] In order to further determine a second recommendation method that is more suitable for the customer, it is necessary to construct a contact profile of the customer based on the feedback results. Optionally, in the financial service recommendation method provided in the embodiment of the present application, constructing the contact profile of the customer through the feedback results includes: extracting the customer's feedback features from the feedback results, wherein the feedback features include at least one of the following: response interval, response time, response attitude, response words and recommendation results; inputting the feedback features into a contact profile construction model to obtain the customer's contact profile, wherein the contact profile construction model is trained by multiple groups of second training samples, and each group of second training samples includes historical feedback features and historical contact profiles.

[0057] In some examples, after customers receive recommended services, their feedback results are analyzed in depth to extract feedback features. These features should include at least one of the following: response interval, response time, response attitude, response words, and recommendation results. For example, the response interval reveals the customer's immediate response speed to the recommended service; the response time and response attitude can reflect the customer's preference for the depth of communication; the response words can provide clues to the customer's specific interests; and the recommendation results directly measure the success rate of the recommendation strategy.

[0058] The contact profile construction model is trained based on multiple sets of second training samples, which include historical feedback features and corresponding historical contact profiles. By learning from historical data, the model can understand the correlation between different feedback features and specific contact profiles, thereby predicting the current customer's contact preferences and behavior patterns. The extracted feedback features are input into the contact profile construction model, and the model will output the customer's contact profile based on these features. The contact profile includes a comprehensive evaluation of customer preferences, acceptance, and the effectiveness of the recommendation strategy, and is an important basis for the subsequent selection of recommendation methods.

[0059] Based on the customer contact profile, it is possible to more accurately judge the customer's reaction to different recommendation methods, so as to customize the selection or adjustment of recommendation methods. For example, for customers whose feedback characteristics show that they have a positive response to strong interruption methods, you can consider increasing the frequency of telephone recommendations; while for customers whose feedback characteristics show that they prefer weak interruption methods, you should continue to use gentler methods such as email or non-intrusive advertising push to communicate.

[0060] By constructing a contact customer portrait, this embodiment can continuously optimize and adjust the customer contact strategy based on the user's feedback results on the first recommendation method, improve the recommendation success rate, and maintain a good user experience.

[0061] After determining the customer's contact profile, the customer's handling intention can be determined through the contact profile, and then a second recommendation method for the customer can be determined. Optionally, in the financial service recommendation method provided in the embodiment of the present application, determining the second recommendation method based on the customer's contact profile includes: determining the customer's handling intention evaluation value for the recommended service through the contact profile; judging whether the handling intention evaluation value is greater than or equal to a second evaluation value threshold; when the handling intention evaluation value is greater than or equal to the second evaluation value threshold, communicating with the customer through the first preset contact strategy to recommend the service is determined as the second recommendation method; when the handling intention evaluation value is less than the second evaluation value threshold, communicating with the customer through the second preset contact strategy to recommend the service is determined as the second recommendation method.

[0062] In some examples, the customer's intention to handle the recommended service is analyzed and calculated from the customer contact profile. This evaluation value combines the customer's basic information, historical transaction behavior, social attributes, and feedback on previous recommendations, reflecting the customer's interest in a specific service and the likelihood of handling it. For example, a score is assigned to each feature in the customer's contact profile, and the handling intention evaluation value is calculated by combining the scores of all features.

[0063] A second evaluation value threshold is set, which is used to distinguish whether the customer has a high handling intention. When the handling intention evaluation value is greater than or equal to the second evaluation value threshold, it means that the customer may have a strong interest in the recommended service and is willing to learn more or handle it; conversely, when the evaluation value is lower than the threshold, it means that the customer is less interested or needs more time to consider.

[0064] If the customer has a high interest in the service and has a high intention to handle the service, a more direct and intrusive communication method can be adopted to improve the speed and efficiency of the service handling. The communication with the customer through the first preset contact strategy (such as telephone communication, instant message push, etc.) to recommend the service is determined as the second recommendation method to directly promote transactions or service handling.

[0065] If the customer's handling intention evaluation value is lower than the set threshold, it means that the customer may need more information or time to consider. At this time, a more gentle and non-intrusive way will be adopted to continue communicating with the customer to avoid possible disgust or loss. The second recommended method is to communicate with the customer through the second preset contact strategy (such as non-intrusive advertising, etc.) to recommend services, continue to provide information and observe customer reactions, and gradually guide them to increase their handling intention.

[0066] This embodiment dynamically adjusts the recommendation strategy according to the customer's true intentions and preferences for recommended services, which not only improves the conversion rate of service recommendations, but also maintains good customer relationships, avoids excessive interruptions or ineffective communication, and achieves a balance between recommendation efficiency and customer experience.

[0067] In order to improve the success rate of the recommended service, the service cycle can be determined or a label of no handling intention can be added based on the customer's handling intention result. Optionally, in the financial service recommendation method provided in the embodiment of the present application, after recommending the recommended service to the customer through the second recommendation method, the method also includes: receiving the customer's handling intention result for the recommended service; when the handling intention result indicates that the customer has the handling intention for the recommended service, determining the target contact cycle, and recommending the recommended service to the customer every target contact cycle; when the handling intention result indicates that the customer has no handling intention for the recommended service, adding a target tag to the customer, wherein the target tag is used to indicate that the customer has no handling intention for the recommended service.

[0068] In some examples, after a customer receives the recommended service information, the customer's intention to handle the recommended service is collected through various communication channels (such as telephone feedback, email replies, online surveys, etc.). This result directly reflects whether the customer is interested in the recommended service and whether he is willing to learn more about or handle it. If the handling intention result indicates that the customer has the intention to handle the recommended service, that is, the customer expresses interest in the service, is willing to learn more about it, or is ready to handle it, then this customer is marked as an "intentional customer." If the handling intention result indicates that the customer has no intention to handle the recommended service, that is, the customer clearly expresses that he is not interested or has no current needs, then this customer is marked as an "unintentional customer."

[0069] A target contact cycle will be determined for "potential customers". The target contact cycle refers to re-recommending services to customers at regular intervals after the customer expresses interest, in order to maintain the enthusiasm of communication, provide the latest information or resolve any concerns the customer may have. The setting of this cycle can take into account customer preferences, service characteristics and market dynamics, so as not to cause customer disgust too frequently, nor to alienate customers too much to lose the recommendation opportunity. "Uninterested customers" will be added with a target tag based on their handling intention results. This tag is used to indicate that the customer currently has no intention of handling the recommended service. In subsequent recommendation activities, avoid making repeated or unnecessary service recommendations to these customers, thereby reducing disturbance to customers and maintaining good customer relationships.

[0070] This embodiment dynamically adjusts the recommendation strategy according to the customer's real needs and preferences, and can also effectively manage customer relationships, avoid waste of resources, and improve the overall efficiency and success rate of service recommendations.

[0071] Before recommending a service to be recommended to a customer, it is necessary to first determine the intended customer group for the service to be recommended. Optionally, in the financial service recommendation method provided in the embodiment of the present application, determining the intended customer group for the service to be recommended includes: obtaining target features of the service to be recommended, and calculating the similarity between the service to be recommended and historically recommended services based on the target features; determining historically recommended services whose similarity is greater than or equal to a similarity threshold, and obtaining multiple customers who have handled the historically recommended services; and defining a set of multiple customers as the intended customer group for the service to be recommended.

[0072] In some examples, first, it is necessary to collect and define the target features of the service to be recommended, which may include but are not limited to service type, service content, service price, service period, service effect, target customer group attributes, etc. Based on the target features of the service to be recommended, a pre-set algorithm is used to calculate its similarity with the historical recommended service. The similarity can be calculated in a variety of ways, such as cosine similarity based on feature vectors, association rule analysis based on historical feedback, and prediction models based on machine learning. The similarity reflects the degree of similarity between services in terms of potential demand satisfaction, customer preference matching, etc.

[0073] A similarity threshold is set to filter out historically recommended services that are highly similar to the service to be recommended. The setting of the similarity threshold can take into account the characteristics of the service type, market environment, and customer group to ensure that the filtered services can truly represent the interests and needs of the target customers of the service to be recommended. Similarity calculations are performed on all historically recommended services to determine those services whose similarity is greater than or equal to the similarity threshold. The customer groups of these highly similar services, that is, customers who have shown interest in or have handled these services, can be regarded as potential customers who may be interested in the service to be recommended.

[0074] The set of multiple customers who have applied for highly similar historical recommendation services is defined as the intended customer group for the recommended service. Based on historical data and behavior analysis, this customer group has a high probability of being interested in the new service and becoming a potential target customer for the new service.

[0075] This embodiment mines potential customer interests from historical data to construct a potential customer group for the service to be recommended, which not only improves the targeted nature of service recommendations, but also can predict the customer's possible response to new services based on his or her historical behavior, thereby formulating a more personalized recommendation strategy and improving the effectiveness of service promotion and customer satisfaction.

[0076] 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.

[0077] Example 2

[0078] The embodiment of the present application also provides a financial service recommendation device. It should be noted that the financial service recommendation device of the embodiment of the present application can be used to execute the financial service recommendation method provided in the embodiment of the present application. The financial service recommendation device provided in the embodiment of the present application is introduced below.

[0079] According to an embodiment of the present application, a device for implementing the above-mentioned financial service recommendation method is also provided. Figure 3 is a schematic diagram of a financial service recommendation device provided according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0080] The first determining unit 301 is used to determine the intended customer group of the service to be recommended, and recommend the service to be recommended to the intended customer group through a first recommendation method, wherein the first recommendation method is a method of recommending the service to the customer through a preset first contact strategy;

[0081] The receiving unit 302 is used to receive the feedback result of each customer in the intended customer group on the first recommendation method, and construct a contact profile of the customer through the feedback result, wherein the feedback result includes the feedback feature of the customer;

[0082] The second determination unit 303 is used to determine a second recommendation method based on the customer's contact profile, and recommend the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to the customer through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy.

[0083] The financial service recommendation device provided in the embodiment of the present application determines the intended customer group for the service to be recommended through a first determination unit 301, and recommends the service to be recommended to the intended customer group through a first recommendation method, wherein the first recommendation method is a method of recommending services to customers through a preset first contact strategy; a receiving unit 302 receives feedback results of each customer in the intended customer group on the first recommendation method, and builds a contact profile of the customer through the feedback results, wherein the feedback results include the feedback characteristics of the customer; a second determination unit 303 determines a second recommendation method based on the contact profile of the customer, and recommends the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, The first contact strategy is a way of recommending services to customers. The second contact strategy is a strategy that disturbs customers more than the first contact strategy. Financial services are first recommended to potential customers in the first recommendation method, and then customer feedback is collected. A contact profile of the customer is constructed based on the feedback results. The second recommendation method with a higher degree of disturbance is determined by the contact profile, and then financial services are recommended to customers in the second recommendation method. The purpose of recommending financial services to customers in a more accurate recommendation method is achieved, thereby realizing the technical effect of improving the accuracy of the recommendation method for selecting financial services, and further solving the technical problem of low customer satisfaction due to inaccurate recommendation method used when recommending financial services to intended customers.

[0084] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the first determination unit 301 includes: a first acquisition module, used to obtain customer information of each customer in the intended customer group, wherein the customer information includes at least one of the following: transaction data, social behavior data and identity information data; a first input module, used to input the customer information into the target model to obtain the customer's contact strategy preference evaluation value, wherein the target model is trained by multiple groups of first training samples, and each group of first training samples includes historical customer information and historical contact strategy preference evaluation values; a first determination module, used to determine the target preference evaluation range to which the contact strategy preference evaluation value belongs, and determine the target contact strategy from the contact strategy mapping relationship table based on the target preference evaluation range, wherein the contact strategy mapping relationship table contains multiple groups of mapping relationships, and each group of mapping relationships represents the correspondence between a contact strategy and a preference evaluation range; a second determination module, used to determine the method of communicating with the customer through the target contact strategy to recommend a service as the first recommendation method for the customer, and recommend the service to be recommended to the customer through the first recommendation method.

[0085] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the first determination unit 301 also includes: a first judgment module, used to judge whether the contact policy preference evaluation value is greater than or equal to a first evaluation value threshold; an execution module, used to execute the step of determining the target preference evaluation range to which the contact policy preference evaluation value belongs when the contact policy preference evaluation value is less than the first evaluation value threshold; a second acquisition module, used to acquire a second recommendation method when the contact policy preference evaluation value is greater than or equal to the first evaluation value threshold; and a recommendation module, used to recommend the service to be recommended to the customer through the second recommendation method.

[0086] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the receiving unit 302 includes: an extraction module, used to extract customer feedback features from the feedback results, wherein the feedback features include at least one of the following: response interval, response duration, response attitude, response words and recommendation results; a second input module, used to input the feedback features into a contact portrait construction model to obtain the customer's contact portrait, wherein the contact portrait construction model is trained by multiple groups of second training samples, and each group of second training samples includes historical feedback features and historical contact portraits.

[0087] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the second determination unit 303 includes: a third determination module, used to determine the customer's handling intention evaluation value for the recommended service through the contact portrait; a second judgment module, used to judge whether the handling intention evaluation value is greater than or equal to the second evaluation value threshold; a fourth determination module, used to determine the second recommendation method of communicating with the customer through the first preset contact strategy to recommend the service when the handling intention evaluation value is greater than or equal to the second evaluation value threshold; a fifth determination module, used to determine the second recommendation method of communicating with the customer through the second preset contact strategy to recommend the service when the handling intention evaluation value is less than the second evaluation value threshold.

[0088] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the device also includes: a processing intention receiving unit, used to receive the customer's processing intention result for the recommended service; a third determination unit, used to determine the target contact cycle when the processing intention result indicates that the customer has the processing intention for the recommended service, and recommend the recommended service to the customer every target contact cycle; an adding unit, used to add a target tag to the customer when the processing intention result indicates that the customer has no processing intention for the recommended service, wherein the target tag is used to indicate that the customer has no processing intention for the recommended service.

[0089] Optionally, in the financial service recommendation device provided in the embodiment of the present application, the first determination unit 301 includes: a third acquisition module, used to obtain target features of the service to be recommended, and calculate the similarity between the service to be recommended and the historical recommended service based on the target features; a sixth determination module, used to determine the historical recommended service whose similarity is greater than or equal to a similarity threshold, and obtain multiple customers who have handled the historical recommended services; a definition module, used to define a set of multiple customers as a potential customer group for the service to be recommended.

[0090] It should be noted that the first determining unit 301, the receiving unit 302, and the second determining 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 may 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 may also be part of a device and may be run in the computer terminal 10 provided in Example 1.

[0091] Example 3

[0092] 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.

[0093] 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.

[0094] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: determine the intended customer group for the service to be recommended, and recommend the service to be recommended to the intended customer group through a first recommendation method, wherein the first recommendation method is a method of recommending services to customers through a preset first contact strategy; receive feedback results from each customer in the intended customer group on the first recommendation method, and build a contact profile of the customer through the feedback results, wherein the feedback results include the customer's feedback characteristics; determine a second recommendation method based on the customer's contact profile, and recommend the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, and the second contact strategy is a strategy that disturbs the customer more than the first contact strategy.

[0095] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain customer information of each customer in the intended customer group, wherein the customer information includes at least one of the following: transaction data, social behavior data and identity information data; input the customer information into the target model to obtain the customer's contact strategy preference evaluation value, wherein the target model is trained by multiple groups of first training samples, and each group of first training samples includes historical customer information and historical contact strategy preference evaluation values; determine the target preference evaluation range to which the contact strategy preference evaluation value belongs, and determine the target contact strategy from the contact strategy mapping relationship table based on the target preference evaluation range, wherein the contact strategy mapping relationship table contains multiple groups of mapping relationships, and each group of mapping relationships represents the correspondence between a contact strategy and a preference evaluation range; determine the first recommendation method for the customer to communicate with the customer through the target contact strategy in order to recommend the service, and recommend the service to be recommended to the customer through the first recommendation method.

[0096] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: determine whether the contact policy preference evaluation value is greater than or equal to the first evaluation value threshold; when the contact policy preference evaluation value is less than the first evaluation value threshold, execute the step of determining the target preference evaluation range to which the contact policy preference evaluation value belongs; when the contact policy preference evaluation value is greater than or equal to the first evaluation value threshold, obtain a second recommendation method; and recommend the service to be recommended to the customer through the second recommendation method.

[0097] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: extract the customer's feedback features from the feedback results, wherein the feedback features include at least one of the following: response interval, response duration, response attitude, response words and recommendation results; input the feedback features into the contact portrait construction model to obtain the customer's contact portrait, wherein the contact portrait construction model is trained by multiple groups of second training samples, and each group of second training samples includes historical feedback features and historical contact portraits.

[0098] 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 customer's handling intention evaluation value for the recommended service through the contact portrait; determine whether the handling intention evaluation value is greater than or equal to the second evaluation value threshold; when the handling intention evaluation value is greater than or equal to the second evaluation value threshold, communicate with the customer through the first preset contact strategy to recommend the service as the second recommendation method; when the handling intention evaluation value is less than the second evaluation value threshold, communicate with the customer through the second preset contact strategy to recommend the service as the second recommendation method.

[0099] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: receiving the customer's intention to handle the recommended service; when the intention to handle result indicates that the customer has the intention to handle the recommended service, determining the target contact cycle, and recommending the recommended service to the customer every target contact cycle; when the intention to handle result indicates that the customer has no intention to handle the recommended service, adding a target tag to the customer, wherein the target tag is used to indicate that the customer has no intention to handle the recommended service.

[0100] 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 target features of the service to be recommended, and calculate the similarity between the service to be recommended and the historically recommended service based on the target features; determine the historically recommended service whose similarity is greater than or equal to the similarity threshold, and obtain multiple customers who have handled the historically recommended service; define the set of multiple customers as the intended customer group for the service to be recommended.

[0101] By adopting the embodiment of the present application, a method is provided for determining the intended customer group for the service to be recommended, recommending the service to be recommended to the intended customer group through a first recommendation method, wherein the first recommendation method is a method of recommending the service to the customer through a preset first contact strategy; receiving the feedback result of each customer in the intended customer group on the first recommendation method, building the contact profile of the customer through the feedback result, wherein the feedback result includes the feedback characteristics of the customer; determining the second recommendation method based on the contact profile of the customer, and recommending the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending the service to the customer through a preset second contact strategy, and the second contact strategy is a strategy scheme with a higher degree of disturbance to the customer than the first contact strategy. By first recommending financial services to the intended customer group in the first recommendation method, then collecting the feedback results of the customer, building the contact profile of the customer based on the feedback results, determining the second recommendation method with a higher degree of disturbance from the contact profile, and then recommending the financial services to the customer in the second recommendation method, the purpose of recommending financial services to the customer in a more accurate recommendation method is achieved, thereby achieving the technical effect of improving the accuracy of the recommendation method for selecting financial services, and then solving the technical problem of low customer satisfaction due to inaccurate recommendation methods used when recommending financial services to intended customers.

[0102] 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 4More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0103] 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.

[0104] Example 4

[0105] 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 financial service recommendation method provided in the first embodiment.

[0106] 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.

[0107] 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 financial service recommendation method.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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 recommending financial services, characterized in that: include: Determine a potential customer group for the service to be recommended, and recommend the service to be recommended to the potential customer group through a first recommendation method, wherein the first recommendation method is a method of recommending the service to the customer through a preset first contact strategy; receiving feedback results of each customer in the intended customer group on the first recommendation method, and constructing a contact profile of the customer based on the feedback results, wherein the feedback results include feedback features of the customer; A second recommendation method is determined based on the customer's contact profile, and the service to be recommended is recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to customers through a preset second contact strategy, and the second contact strategy is a strategy that causes a higher degree of disturbance to the customer than the first contact strategy.

2. The method according to claim 1, characterized in that Recommending the service to be recommended to the intended customer group by the first recommendation method includes: Acquire customer information of each customer in the intended customer group, wherein the customer information includes at least one of the following: transaction data, social behavior data, and identity information data; Inputting the customer information into a target model to obtain a contact strategy preference evaluation value of the customer, wherein the target model is trained by multiple groups of first training samples, each group of first training samples including historical customer information and historical contact strategy preference evaluation values; Determine a target preference evaluation range to which the contact strategy preference evaluation value belongs, and determine a target contact strategy from a contact strategy mapping relationship table based on the target preference evaluation range, wherein the contact strategy mapping relationship table includes multiple groups of mapping relationships, each group of mapping relationships representing a corresponding relationship between a contact strategy and a preference evaluation range; The method of communicating with the customer through the target contact strategy to recommend a service is determined as a first recommendation method for the customer, and the service to be recommended is recommended to the customer through the first recommendation method.

3. The method according to claim 2, characterized in that After obtaining the contact strategy preference evaluation value of the customer, the method further includes: Determining whether the contact strategy preference evaluation value is greater than or equal to a first evaluation value threshold; In the case where the contact strategy preference evaluation value is less than the first evaluation value threshold, performing the step of determining a target preference evaluation range to which the contact strategy preference evaluation value belongs; When the contact strategy preference evaluation value is greater than or equal to the first evaluation value threshold, obtaining a second recommendation method; The service to be recommended is recommended to the customer through the second recommendation method.

4. The method according to claim 1, characterized in that: Constructing the contact profile of the customer through the feedback results includes: Extracting the feedback features of the customer from the feedback results, wherein the feedback features include at least one of the following: response interval, response duration, response attitude, response words, and recommendation results; The feedback features are input into a contact profile construction model to obtain a contact profile of the customer, wherein the contact profile construction model is trained by multiple groups of second training samples, and each group of second training samples includes historical feedback features and historical contact profiles.

5. The method according to claim 1, characterized in that The second recommendation method based on the customer's contact profile includes: Determining the evaluation value of the customer's handling intention for the recommended service through the contact profile; Determine whether the processing intention evaluation value is greater than or equal to a second evaluation value threshold; In the case where the handling intention evaluation value is greater than or equal to the second evaluation value threshold, communicating with the customer through the first preset contact strategy to recommend services is determined as the second recommendation method; When the handling intention evaluation value is less than the second evaluation value threshold, communicating with the customer through a second preset contact strategy to recommend services is determined as the second recommendation method.

6. The method according to claim 1, characterized in that After recommending the service to be recommended to the customer by using the second recommendation method, the method further includes: Receiving the result of the customer's intention to handle the service to be recommended; If the handling intention result indicates that the customer has handling intention for the service to be recommended, determining a target contact period, and recommending the service to be recommended to the customer every target contact period; In the case where the handling intention result indicates that the customer has no handling intention for the service to be recommended, a target mark is added to the customer, wherein the target mark is used to indicate that the customer has no handling intention for the service to be recommended.

7. The method according to claim 1, characterized in that The potential customer groups for recommended services include: Acquire the target feature of the service to be recommended, and calculate the similarity between the service to be recommended and the historical recommended service based on the target feature; Determine a historical recommendation service whose similarity is greater than or equal to a similarity threshold, and obtain a plurality of customers who have applied for the historical recommendation service; The set of the multiple customers is defined as the potential customer group for the service to be recommended.

8. A financial service recommendation device, characterized in that: include: A first determining unit, configured to determine a potential customer group for a service to be recommended, and recommend the service to be recommended to the potential customer group through a first recommendation method, wherein the first recommendation method is a method of recommending a service to a customer through a preset first contact strategy; a receiving unit, configured to receive feedback results of each customer in the intended customer group on the first recommendation method, and construct a contact profile of the customer through the feedback results, wherein the feedback results include feedback features of the customer; A second determination unit is used to determine a second recommendation method based on the customer's contact profile, and recommend the service to be recommended to the customer through the second recommendation method, wherein the second recommendation method is a method of recommending services to the customer through a preset second contact strategy, and the second contact strategy is a strategy that causes a higher degree of disturbance to the customer than the first contact strategy.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the financial service recommendation method according to any one of claims 1 to 7.

10. 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 financial service recommendation method described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the financial service recommendation method described in any one of claims 1 to 7 are implemented.

Images