Financial service recommendation method and device, equipment, storage medium and program product

Abstract

The invention provides a financial service recommendation method and device, equipment, a storage medium and a program product, and relates to the field of financial science and technology. The method comprises the steps of obtaining a user portrait label, behavior preference data of a user and a product portrait label; processing the behavior preference data of the user to obtain keyword label data representing the type characteristics of the financial service and / or the financial product, scoring the keyword label data, determining label integral data, and determining a grade score of the keyword label data based on the label integral data; and performing matching on the basis of the user portrait label and the product portrait label every preset duration, determining a target financial service and / or a target financial product, performing evaluation on the target financial service and / or the target financial product on the basis of the grade score, and determining a to-be-recommended financial service and / or a to-be-recommended financial product. According to the method, the recommendation accuracy and efficiency can be improved, and the customer satisfaction can be improved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a financial service recommendation method, apparatus, device, storage medium, and program product. Background Technology

[0002] In the context of the digital age, new media operations have become an important channel for commercial banks to expand their business. As an early representative of new media, mini-programs have significant advantages in user reach and business conversion. Therefore, commercial banks commonly use mini-program accounts to conduct product recommendations and business operations, effectively expanding their user base and driving the development of their core businesses.

[0003] In related technologies, when financial institutions launch new wealth management products and other financial services, they typically use customer service personnel to proactively contact customers by phone to manually introduce product features and inquire about their purchase intentions. This method requires customer service personnel to communicate with each user individually, explaining the product details in detail and recording customer feedback.

[0004] However, the above methods are difficult to prioritize in identifying suitable or purchasing-capable target customer groups, resulting in a high degree of blindness in communication. This not only wastes human resources and time, but may also cause resentment by frequently disturbing non-target customers, thus reducing customer satisfaction. Summary of the Invention

[0005] This application provides a financial service recommendation method, apparatus, device, storage medium, and program product. Through automated data processing and intelligent matching mechanisms, it solves the technical problems faced by financial institutions in recommending financial services, such as wasted human resources and time costs, and decreased satisfaction due to frequent disturbances to non-target customers.

[0006] Firstly, this application provides a method for recommending financial services, the method comprising:

[0007] Obtain user profile tags and user behavior preference data, as well as product profile tags for at least one online financial service and / or financial product;

[0008] User behavior preference data is processed to obtain keyword tag data, which is used to characterize the type characteristics of financial services and / or financial products;

[0009] The keyword tag data is scored to determine the tag score data, and the level score of the keyword tag data is determined based on the tag score data.

[0010] At preset intervals, matching is performed based on user profile tags and product profile tags to determine target financial services and / or target financial products. The target financial services and / or target financial products are then evaluated based on rating scores to determine the financial services and / or financial products to be recommended.

[0011] Secondly, this application provides a financial service recommendation device, which includes:

[0012] The acquisition module is used to acquire user profile tags and user behavior preference data, as well as product profile tags for at least one online financial service and / or financial product.

[0013] The processing module is used to process user behavior preference data to obtain keyword tag data, which is used to characterize the type characteristics of financial services and / or financial products.

[0014] The determination module is used to score keyword tag data, determine tag score data, and determine the level score of keyword tag data based on the tag score data;

[0015] The matching module is used to match user profile tags and product profile tags at preset intervals to determine target financial services and / or target financial products, evaluate the target financial services and / or target financial products based on rating scores, and determine the financial services and / or financial products to be recommended.

[0016] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0017] The memory stores the instructions that the computer executes;

[0018] The processor executes computer-executable instructions stored in memory to implement the method as described in any of the first aspects.

[0019] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any of the first aspects.

[0020] Fifthly, this application provides a computer program product including a computer program that, when executed by a processor, implements the method as described in any of the first aspects.

[0021] In summary, this application provides a method, apparatus, device, storage medium, and program product for recommending financial services. By acquiring user profile tags, user behavioral preference data, and product profile tags for financial services and / or financial products, the user behavioral preference data is processed to extract keyword tag data representing the type characteristics of financial services and / or financial products. These keyword tag data are then scored and graded to obtain tag score data and determine grade values. Furthermore, target financial services and / or target financial products are initially screened based on the matching degree between user profile tags and product profile tags at regular intervals. A precise evaluation is then performed by combining the grade values ​​of the keyword tag data to determine the financial services and / or financial products to be recommended. Thus, this application, through a data-driven automated screening and evaluation mechanism, replaces traditional manual communication methods, effectively reducing interference with non-target customers, lowering labor and time costs, and improving not only the accuracy and efficiency of recommendations but also customer satisfaction. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0024] Figure 2 This is a schematic diagram of the structure of a smart management platform provided in an embodiment of this application;

[0025] Figure 3 This application provides a schematic diagram of the structure of a user information management module according to an embodiment of the present application.

[0026] Figure 4 A flowchart illustrating a financial service recommendation method provided in an embodiment of this application;

[0027] Figure 5 This is a schematic diagram of the structure of a financial service recommendation device provided in an embodiment of this application;

[0028] Figure 6 This is a schematic block diagram of an electronic device provided in an embodiment of this application.

[0029] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0030] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0031] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0032] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0033] It should be noted that the financial service recommendation methods, devices, equipment, storage media, and program products provided in this application can be used in the financial technology field, or in any field other than the financial technology field, such as the banking financial services field. This application does not limit the application field of the financial service recommendation methods, devices, equipment, storage media, and program products.

[0034] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0035] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0036] In related technologies, when financial institutions launch new financial products such as wealth management products, they mainly rely on customer service personnel to communicate with customers by telephone. Customer service personnel need to proactively contact customers, explain in detail the features, returns, and risks of the new products, and inquire about their purchase intentions.

[0037] However, the aforementioned manual communication methods struggle to accurately identify target customers who are genuinely interested in or have the purchasing power for new products, leading to highly indiscriminate communication and a low success rate. Secondly, manual communication is inefficient, consuming significant human and time resources, especially when dealing with a large customer base, making it difficult to achieve rapid and comprehensive coverage. Furthermore, repeatedly pushing products to non-target customers can easily cause customer resentment, reduce customer satisfaction and trust, and may even lead to customer churn. Therefore, there is an urgent need for a smart management platform for pushing banking financial services to achieve more precise and efficient financial service delivery.

[0038] To address the aforementioned issues, this application provides a method for recommending financial services. By acquiring user profile tags, user behavioral preference data, and product profile tags for financial services and / or financial products, the method processes the user behavioral preference data to extract keyword tag data representing the characteristics of the financial service and / or financial product types. These keyword tag data are then scored and graded to obtain tag score data and determine grade values. Furthermore, target financial services and / or target financial products are initially screened based on the matching degree between user profile tags and product profile tags on a regular basis. Finally, a precise evaluation is conducted by combining the grade values ​​of the keyword tag data to determine the financial services and / or financial products to be recommended. In this way, this application, through a data-driven automated screening and evaluation mechanism, replaces traditional manual communication methods, effectively reducing interference with non-target customers, lowering labor and time costs, improving not only the accuracy and efficiency of recommendations but also customer satisfaction.

[0039] For example, this application can be applied to a smart management platform for pushing banking financial services. Figure 1 This is a schematic diagram of an application scenario provided in an embodiment of this application, such as... Figure 1 As shown, the application scenario includes a user's terminal device 101 and a smart management platform 102. The terminal device 101 may have applications related to financial services and / or financial products installed, such as bank applications (APPs). The smart management platform 102 can add a push information management unit on the basis of the existing basic functions of the management platform. The push information management unit is used to promote the bank's financial products and / or financial services to the user's terminal device 101.

[0040] Optional, Figure 2 This is a schematic diagram of the structure of a smart management platform provided in an embodiment of this application, as shown below. Figure 2 As shown, the intelligent management platform 102 includes a push information management unit, which includes a user information management module, a financial product / financial service tag allocation module, a matching module, a timing module, and a push module. Figure 3 This is a schematic diagram of the structure of a user information management module provided in an embodiment of this application, such as... Figure 3 As shown, the user information management module includes a basic tag allocation module, a preference tag score calculation module, a preference tag activation module, and a tag storage module.

[0041] The basic tag allocation module is used to determine user profile tags based on user retention information and account information; the preference tag score calculation module is used to record users' daily behavior data on the platform, determine keyword tag data based on daily behavior data, and calculate the score for each keyword tag data; the preference tag activation module is used to judge the level of keyword tag data and assign different scores to different levels; and the tag storage module is used to store all user profile tags and keyword tag data.

[0042] The financial product / financial service tag allocation module is used to determine the product profile tags of financial services and / or financial products when they are launched; the matching module is used to match suitable financial services and / or financial products to users based on the user profile tags, product profile tags, and keyword tag data level scores; the timing module is used to set a countdown for matching updates, and the matching module is called when the countdown ends; the push module is used to push the matched financial services and / or financial products to users.

[0043] For example, the intelligent management platform 102 obtains basic attribute information and behavioral preference information such as user account information and daily behavior data from the bank's APP on the terminal device 101. Then, based on the user information management module, it tags the basic attribute information and behavioral preference information to determine user profile tags, keyword tag data, and the level score of the keyword tag data. Next, the matching module matches the user profile tags with the product profile tags of financial services and / or financial products determined by the financial product / financial service tag allocation module, and combines this with the level score of the keyword tag data to match the user with recommended financial products and / or financial products that have higher relevance and interest.

[0044] Optionally, the push module can push the recommended financial products and / or financial products to the user's terminal device 101 for the user to view, thereby achieving accurate push of financial products and / or financial products.

[0045] The terminal device can also be referred to as a user terminal, user equipment (UE), mobile station (MS), mobile terminal, or terminal. In practical applications, user terminals include, for example, desktop computers, laptops, personal digital assistants (PDAs), personal computers (PCs), smartphones, tablets, in-vehicle devices, wearable devices (such as smartwatches and smart bracelets), and smart home devices (such as smart display devices). This application does not specifically limit the types of devices mentioned.

[0046] It should be noted that the specific application scenarios of the financial service recommendation method in this application embodiment are not specifically limited. The above are just examples. For example, this application can be applied not only to financial institutions, such as banks, securities companies, and fund companies, but also to the precise display of financial products that different customers may be interested in to their message centers, advertising spaces, or push notifications in their mobile banking apps, mini-programs, and other digital channels. It can also be applied to the recommendation of relevant financial information.

[0047] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0048] Figure 4 This is a flowchart illustrating a financial service recommendation method provided in an embodiment of this application, such as... Figure 4 As shown, the entity implementing this financial service recommendation method can be... Figure 2 The intelligent management platform shown can also be a server. This application embodiment does not specifically limit the executing entity. The recommended method for financial services includes the following steps:

[0049] S401. Obtain user profile tags and user behavior preference data, as well as product profile tags for at least one online financial service and / or financial product.

[0050] In this embodiment of the application, user profile tags can refer to tags that describe attributes or characteristics of users such as behavior, occupation, and user value. These user profile tags can include occupation tags, industry tags, and user value tags. Occupation tags are used to represent the user's occupation, such as teacher, doctor, student, etc. Industry tags are used to represent the industry to which the user belongs, such as finance, education, catering, etc. User value tags are used to represent the user's purchasing power, such as level 1 user, level 2 user, level 3 user, etc., with different levels of users corresponding to different purchasing powers.

[0051] Behavioral preference data refers to aggregated data of users' dynamic operation sequences and interaction records on digital platforms such as apps, websites, and mini-programs. It is used to reflect users' interest in financial services and / or financial products, their operating habits, and their short-term intentions.

[0052] Financial services can refer to non-standard active activities or processes provided by financial institutions to users using their expertise and platforms, which are oriented towards achieving specific financial goals. These activities may involve multiple financial products or may not require specific products. This application does not specifically limit the type of financial services.

[0053] Financial products can refer to standardized, tradable financial contracts or wealth management products with clear value and usage rules. This application does not specifically limit the type of financial product. For example, financial products can be stocks, funds, insurance, etc.

[0054] Product profile tags are used to structurally describe the user-related characteristic tags corresponding to launched financial products and / or financial services. They are standardized definitions of the financial products and / or financial services themselves, matched with user profile tags. Specifically, when a financial product or / or financial service is launched, it is based on the industry, occupation, and value tags corresponding to the user's applicable industry, occupation, and value allocation, designed from the outset.

[0055] For example, the basic tag allocation module can determine the user profile tags based on the user's retained information and account information on the bank platform. The preference tag points calculation module can obtain the user's user behavior information on the bank platform, such as browsing history, purchase history, search history, etc., to extract the user's behavioral preference data based on the user behavior information. The financial product / service tag allocation module can determine the product profile tags based on the product information and preset tag information of the financial product / service launched.

[0056] S402. Process user behavior preference data to obtain keyword tag data, which is used to characterize the type characteristics of financial services and / or financial products.

[0057] In this embodiment of the application, keyword tag data may refer to user preference tags related to financial services and / or financial products, such as the types or characteristics of financial products that users prefer, such as keyword tags such as sports, health, sports, and environmental protection. This embodiment of the application does not limit the specific content corresponding to the keyword tag data.

[0058] Optionally, keyword tag data may include keyword tags corresponding to the financial services and / or financial products with the most user visits, the financial services and / or financial products with the longest user visit duration, the financial services and / or financial products with the most user purchases, and the financial services and / or financial products with the most user searches.

[0059] For example, the preference tag score calculation module can process user behavior preference data obtained from the bank platform to obtain keyword tag data.

[0060] S403. Score the keyword tag data, determine the tag score data, and determine the grade score of the keyword tag data based on the tag score data.

[0061] In this embodiment of the application, the importance of each keyword tag data can be evaluated by a preset scoring rule or algorithm model, and the importance can be converted into numerical points to obtain tag point data. Furthermore, the tag point data can be divided into levels according to the point range, and different levels correspond to different level scores.

[0062] For example, the preference tag activation module obtains the tag score data determined by the preference tag score calculation module and determines the level score corresponding to the tag score data.

[0063] S404. At preset intervals, match user profile tags and product profile tags to determine target financial services and / or target financial products, evaluate the target financial services and / or target financial products based on the rating score, and determine the financial services and / or financial products to be recommended.

[0064] In this embodiment, the preset duration is designed to update the matching process in real time. After the preset duration, the system will push financial services and / or financial products that the user is most interested in and that have higher interest in the banking platform based on the user's latest behavior. This embodiment does not specifically limit the setting of the preset duration; it can be one day or one week. Both the user and the financial institution can set the preset duration.

[0065] For example, the timing module calls the matching module at preset intervals so that the matching module matches user profile tags with product profile tags, filters out potential target financial services and / or target financial products, and then combines the level scores of keyword tag data to prioritize the matching results and determine the financial services and / or financial products to be recommended.

[0066] In this way, this application replaces the traditional method of relying on manual screening and recommendation with an automated data acquisition, processing, scoring, and matching process, significantly reducing the manpower and time consumption of financial institutions in customer insight and product recommendation. Furthermore, based on multi-dimensional user profile tags, behavioral preference data, and product profile tags, through systematic data processing and quantitative scoring, it can more objectively and accurately identify the correlation between users' real needs and financial services and / or financial products. This ensures that the recommended financial services and / or financial products highly match user needs, improving marketing conversion efficiency. Moreover, through regular automated precise matching and rating-based assessments, it ensures that suitable financial services and / or financial products are recommended to customers with corresponding needs at the appropriate time, greatly avoiding user resentment caused by blind recommendations or frequent disturbances to non-target customers, thereby protecting and improving overall customer experience and satisfaction.

[0067] Furthermore, this application, based on data and algorithms, eliminates the arbitrariness and uncertainty brought about by human subjective judgment, making the recommended financial services and / or financial products more accurate and enhancing the objectivity and scientific nature of financial service recommendations.

[0068] Optionally, behavioral preference data includes the number of visits to financial services and / or financial products, visit time, visit quantity, purchase history, and search history. Keyword tag data includes: a first set of keyword tags, a second set of keyword tags, a third set of keyword tags, and a fourth set of keyword tags. The user's behavioral preference data is processed to obtain keyword tag data, including:

[0069] User activity is determined based on the number of visits, and the first set of keyword tags corresponding to financial services and / or financial products is determined based on the activity.

[0070] The duration of a user's stay on financial services and / or financial products is determined based on the access time, and the set of second keyword tags corresponding to the financial services and / or financial products is determined based on the duration of stay.

[0071] The frequency of a user's access to financial services and / or financial products is determined based on the number of visits, the number of visits, and the purchase history. The set of third keyword tags corresponding to financial services and / or financial products is determined based on the access frequency.

[0072] Based on search history, determine the number of times a user searches for financial services and / or financial products, and based on the number of searches, determine the set of fourth keyword tags corresponding to financial services and / or financial products.

[0073] It should be noted that since financial services and / or financial products themselves have industry tags, occupation tags, and value tags, it is necessary to select more keywords than the basic number of tags. That is, in addition to determining industry tags, occupation tags, and value tags, keyword tag data also needs to be determined.

[0074] Optionally, user activity is determined based on the number of visits, and keyword tags corresponding to financial services and / or financial products with activity greater than a first threshold are selected to determine the first keyword tag set A. In this embodiment of the application, the size of the first threshold is not specifically limited, but it is used to represent high activity.

[0075] For example, activity level is calculated based on the following formula:

[0076]

[0077] Among them, c i,j The number of times user i accesses financial services and / or financial products j. The average number of times all users access financial services and / or financial products j.

[0078] Based on the above formula, the user activity set is determined as follows: Select the financial services and / or financial products with the most visits from the activity set, and extract the n keyword tags corresponding to the financial services and / or financial products with the most visits to obtain the first keyword tag set A, where n is an integer greater than 1, and optionally n = 10.

[0079] Optionally, the duration of a user's stay on financial services and / or financial products is determined based on the access time. Keyword tags corresponding to financial services and / or financial products with a stay duration greater than a second threshold are selected to determine the second keyword tag set B. In this embodiment of the application, the size of the second threshold is not specifically limited; it is sufficient to represent a longer stay duration.

[0080] For example, the duration of stay can be calculated based on the following formula:

[0081]

[0082] Where, d i,j d represents the total time user i accesses financial services and / or financial products j. i,j′ n is the total time that user i accesses financial services and / or financial products j′. i To enable users to access and view various financial services and / or financial products on the platform.

[0083] Based on the above formula, the set of user dwell times is determined as follows: Select the financial service and / or financial product with the longest stay from the set of stay durations, and extract the m keyword tags corresponding to the financial service and / or financial product with the longest stay duration to obtain the second keyword tag set B, where m is an integer greater than 1, and optionally m = 10.

[0084] Optionally, the frequency of a user's access to financial services and / or financial products is determined based on the number of accesses, the number of visits, and the purchase history. Keyword tags corresponding to financial services and / or financial products with access frequencies greater than a third threshold are selected to determine the third keyword tag set C. In this embodiment of the application, the size of the third threshold is not specifically limited; it is only used to characterize a high frequency of access.

[0085] For example, the access frequency of each keyword tag is calculated based on the following formula:

[0086]

[0087] Among them, w′ k1 w′ represents the number of times a single keyword appears in accessed financial products and / or financial services. k2 w′ represents the number of times a financial product and / or financial service appears in the purchased financial products and / or services. z1w′ represents the number of times financial products and / or financial services have been accessed. z2 The number of financial products and / or financial services purchased. k2 and w′ z2 This can be determined from the purchase history.

[0088] Based on the above formula, the set of user access frequencies is determined as follows: Select the financial services and / or financial products with the highest access frequency from the access frequency set, and extract the p keywords corresponding to the financial services and / or financial products with the highest access frequency to obtain the third keyword tag set C, where p is an integer greater than 1, and optionally p = 10.

[0089] Optionally, based on search records, the number of times a user searches for financial services and / or financial products is determined, and keyword tags corresponding to financial services and / or financial products with a search frequency greater than a fourth threshold are selected to determine the fourth keyword tag set F. In this embodiment of the application, the size of the fourth threshold is not specifically limited, but it is used to represent a large number of searches.

[0090] For example, the search count for each keyword tag is calculated based on the following formula:

[0091]

[0092] Among them, w′ k ′ represents the number of times the relevant keyword tags were searched, w′ z ′ represents the total number of searches for all involved keyword tags. The involved keyword tags are determined as follows: obtain the user's search keywords, match the search keywords with the stored tags in the database, and obtain all involved keywords. The stored tags in the database are the keyword tags stored in the tag storage module.

[0093] The search frequency array for the user's search keywords is determined based on the above formula. Obtain the financial services and / or financial products with the most searched times from the search count array, and extract the q keyword tags corresponding to the financial services and / or financial products with the most searched times to obtain the fourth keyword tag set F, where q is an integer greater than 1, and optionally q = 10.

[0094] In this way, by refining the analysis of multi-dimensional behavioral preference data, a more comprehensive keyword tag data can be constructed, avoiding the bias of a single data source. By establishing four sets of tags—activity level, dwell time, access frequency, and search frequency—to complement each other, the explicit and implicit needs of users can be captured more accurately, providing a more granular data foundation for subsequent rating and matching, and further improving the accuracy and personalization of recommendations.

[0095] Optionally, the keyword tag data can be scored to determine tag score data, including:

[0096] Obtain user behavior data in the current state, and determine the fifth keyword tag set based on the user behavior data;

[0097] Calculate the similarity between each keyword tag in the keyword tag data and the fifth keyword tag set to obtain a keyword similarity coefficient array;

[0098] Obtain the original score data and preset weight coefficient of each keyword tag in the keyword tag data for the previous preset time period. Based on the keyword similarity coefficient array, the original score data and the weight coefficient, update the score of each keyword tag in the keyword tag data to determine the tag score data.

[0099] In this embodiment of the application, user behavior data may refer to a user's browsing history, search history, or purchase history at the current moment or within a period of time close to the current moment. This embodiment of the application does not limit the specific content corresponding to user behavior data.

[0100] It should be noted that the preset weight coefficients are set based on the application scenario requirements. This application embodiment does not specifically limit the size of the weight coefficients, which can be modified manually. For the first keyword tag set, the second keyword tag set, the third keyword tag set, and the fourth keyword tag set, the weight coefficients for each keyword tag are different.

[0101] For example, after obtaining the first keyword tag set A, the second keyword tag set B, the third keyword tag set C, and the fourth keyword tag set F, the preference tag score calculation module can further obtain user behavior data in the user's current state, extract the keyword tags from this user behavior data, and obtain the fifth keyword tag set G. Furthermore, it calculates the Jaccard similarity between each keyword tag in the first keyword tag set A and the fifth keyword tag set G, obtaining the keyword similarity coefficient array A'.

[0102]

[0103] Furthermore, the keyword tag integral corresponding to the first keyword tag set A is determined using the following formula:

[0104] P g1 =P′ g1 +γ a ·(a k1 +h k1 )

[0105] in, ak1 ∈[0,1], A[k1] represents the k1-th keyword tag in the first keyword tag set A, P g ′1 represents the keyword tag corresponding to the previous preset duration P before calculating the integral. g1 The original integral data, γ a h is the preset weight coefficient in the first keyword tag set A. k1 To allow users to view the activity levels of financial services and / or financial products associated with corresponding keyword tags.

[0106] Accordingly, the Jaccard similarity between the second keyword tag set B and the fifth keyword tag set G is calculated to obtain the keyword similarity coefficient array B':

[0107] Furthermore, the keyword tag integral corresponding to the second keyword tag set B is determined using the following formula:

[0108] P g2 =P′ g2 +γ b ·(b k2 +t k2 )

[0109] in, b k2 ∈[0,1], B[k2] represents the k2th keyword in the second keyword tag set B, p′ g2 For keyword tags, the previous preset duration corresponds to P before calculating the integral. g2 The original integral data, γ b t represents the preset weight coefficient in the second keyword tag set B. k2 The duration of time users spend on financial services and / or financial products with corresponding keyword tags.

[0110] Accordingly, the Jaccard similarity between each keyword tag in the third keyword tag set C and the fifth keyword tag set G is calculated, resulting in the keyword similarity coefficient array E':

[0111]

[0112] Furthermore, the keyword tag integral corresponding to the third keyword tag set C is determined using the following formula:

[0113] P g3 =P′ g3 +γ e ·(e k3 +W′ k3 )

[0114] in, e k3∈[0,1], E[k3] represents the k3rd keyword in the third keyword tag set C, P′ g3 For keyword tags, the previous preset duration corresponds to P before calculating the integral. g3 The original integral data, γ e W is the preset weight coefficient in the third keyword tag set C. k ′3 represents the frequency of access to the corresponding keyword tags in the financial services and / or financial products that the user has visited and purchased.

[0115] Accordingly, the Jaccard similarity between each keyword tag in the fourth keyword tag set F and the fifth keyword tag set G is calculated, resulting in the keyword similarity coefficient array F':

[0116]

[0117] Furthermore, the keyword tag integral corresponding to the fourth keyword tag set F is determined using the following formula:

[0118]

[0119] in, f k4 ∈[0,1], F[k4] represents the k4th keyword in the fourth keyword tag set FF, P′ g4 For keyword tags, the previous preset duration corresponds to P before calculating the integral. g4 The original integral data, γ f W″ is the preset weight coefficient in the fourth keyword tag set F. k4 This represents the number of times the corresponding keyword tag appears in the user's search history.

[0120] Furthermore, the updated keyword tag scores corresponding to the first keyword tag set A, the second keyword tag set B, the third keyword tag set C, and the fourth keyword tag set F are summarized to obtain tag score data.

[0121] In this way, by introducing user behavior data in the current state, a fifth keyword tag set is generated in real time. Through the similarity calculation of the fifth keyword tag set, a dynamic score update mechanism is realized, so that the tag score data can reflect both the user's long-term preferences and capture short-term demand changes. In particular, in the process of calculating the tag score data, the original score data of the previous preset time period and the weight coefficient are combined, which can not only ensure the continuity and stability of the score update and avoid inaccuracy in recommending financial services and / or financial products, but also improve the timeliness and adaptability of the recommendations.

[0122] Optionally, the ranking score of keyword tag data can be determined based on tag score data, including:

[0123] The target label level range of the label score data is determined by matching the label score data with the preset label level range.

[0124] The grade score of keyword tag data is determined based on the target tag grade range; there is a mapping relationship between the target tag grade range and the grade score.

[0125] In this embodiment of the application, the tag level range is the level score range corresponding to different tag score data. The level score range is set to gradually increase. The purpose of setting the tag level range is to activate the corresponding preferred keyword tag. Activation indicates that the keyword tag is available.

[0126] Optionally, multiple different grade score ranges can be set, and each grade score range is mapped to a corresponding grade score. For example, [1, 20] corresponds to a grade score of 10, and [20, 40] corresponds to a grade score of 50. In this embodiment, the grade score mapped to each label grade range is not specifically limited. The above is just an example. Different mapping relationships can be set based on different application scenarios.

[0127] For example, the preference tag activation module can obtain the tag score data after the preference tag score calculation module updates the score corresponding to the preference keyword tag, and then determine in turn whether the score of each tag falls within the preset tag level range. After determining that it falls within the preset tag level range, that is, after reaching the preset activation threshold score, the keyword tag data can be judged for level score, that is, the level score corresponding to the tag level range can be obtained, thereby determining the level score of the keyword tag data.

[0128] In this way, by establishing a mapping mechanism between tag score data and grade score, the standardized evaluation and efficient application of keyword tag data are realized. This not only eliminates the subjectivity and arbitrariness of manually setting thresholds, but also makes the preference intensity of different keyword tag data comparable, providing a quantifiable decision basis for subsequent recommendation priority ranking, and improving the standardization of the evaluation process and the accuracy of the recommendation results.

[0129] Optionally, the target financial services and / or target financial products may be evaluated based on rating scores to determine the financial services and / or financial products to be recommended, including:

[0130] Calculate the tag score corresponding to the target financial service and / or target financial product based on the grade score of keyword tag data;

[0131] The target financial services and / or target financial products are sorted based on the tag scores to determine the financial services and / or financial products to be recommended.

[0132] In this embodiment of the application, the sorting process may refer to sorting by numerical value from largest to smallest or from smallest to largest. The sorting methods may be different, but the selected financial services and / or financial products to be recommended are the target financial services and / or target financial products with larger tag scores. For example, sorting from largest to smallest selects the target financial services and / or target financial products in the top N positions, and sorting from smallest to largest selects the target financial services and / or target financial products in the bottom N positions.

[0133] Optionally, in this application, instead of sorting, the target financial services and / or target financial products with tag scores greater than a preset threshold can be selected to determine the financial services and / or financial products to be recommended. Therefore, the embodiments of this application do not specifically limit the method of determining the financial services and / or financial products to be recommended, and they can also be selected randomly.

[0134] For example, the matching module can calculate the sum of the ranking scores of the keyword tag data for each target financial service and / or target financial product using the following formula:

[0135]

[0136] Among them, Y m′ (P′) represents the grade score corresponding to the tag score data P′ of the m′th keyword tag data of the target financial service and / or target financial product x.

[0137] Furthermore, the target financial services and / or target financial products are sorted in descending order based on the sum of the calculated grade scores, and the sorting results are stored in a reserve queue. Further, the top M data from the reserve queue are selected and stored in a recommendation queue. The data stored in the recommendation queue are the financial services and / or financial products to be recommended.

[0138] The number of items in the recommendation queue can be adjusted according to the actual situation, or according to user needs and application scenario requirements. This application embodiment does not impose specific limitations on this. M is an integer greater than 1, and optionally, M = 5.

[0139] It is understandable that by recording user behavior information on the platform, scoring and assigning values ​​to keywords that users are interested in, and then calculating the total score of the keyword tags of the filtered financial services and / or financial products, the platform can push financial services and / or financial products that users are more interested in to users.

[0140] In this way, through quantitative calculation and ranking mechanisms, multi-dimensional keyword tag data is transformed into a unified comparison standard, establishing a quantitative matching mechanism between user preferences and financial services and / or financial products. This achieves more accurate and intelligent recommendations for financial services and / or financial products. Furthermore, ranking based on tag scores ensures a positive correlation between the recommendation results and user preferences, significantly improving recommendation accuracy and user conversion rates.

[0141] Optionally, user profile tags include: the user's primary occupation tag, primary industry tag, and primary value tag; acquiring user profile tags and user behavioral preference data, as well as product profile tags for at least one online financial service and / or financial product, including:

[0142] Obtain user retention information and account information, and determine the user's primary occupation tag and primary industry tag based on the retention information;

[0143] Based on the user's account information, estimate the user's purchasing power level, and determine the first value tag based on the purchasing power level;

[0144] Extract user behavior preference data from user behavior information on at least one platform;

[0145] The preset keyword tags corresponding to at least one online financial service and / or financial product are matched with the stored tags in the database to determine product profile tags.

[0146] In this embodiment of the application, the retained information may refer to the user's pre-reserved identity information and other basic attributes related to the user's attributes on the platform. The account information may refer to the transaction information and credit limit of the user's opened account. Optionally, the account information includes annual cash outflows, total annual income, liquid deposits, total annual liabilities, total deposits, and the user's latest credit limit at the bank.

[0147] Optionally, the first occupation tag and the first industry tag can be determined and activated based on the user's retained information. That is, if the industry information is stored in advance, it can be activated. The first value tag can be determined and activated based on the user's financial changes within a preset time period, such as the most recent year. If there are financial changes in the most recent year, it can be activated.

[0148] For example, the basic tag allocation module obtains the user's pre-registered identity information on the bank platform to determine the user's occupation and industry, and then activates the user's corresponding first occupation tag and first industry tag; correspondingly, it obtains the user's account information, including the most recent year's transaction history (Lszc), the most recent year's total income (Srze), liquid deposits (Kldck), total annual liabilities (Nfzze), total deposits (Ckze), and the user's latest credit limit (E) at the bank. i The purchase value GMZ is calculated using the following formula:

[0149]

[0150] Wherein, E represents the bank's preset maximum credit limit. In this application embodiment, the size of E is not specifically limited. It is the maximum credit limit opened by the bank for the user, which can be set based on the user's identity information, historical transaction records, deposit amount, repayment status, etc.

[0151] Furthermore, based on the purchase value GMZ, the user's purchasing power level is determined. Different purchasing power levels correspond to different primary value tags. Optionally, the primary value tags include Level 1 users, Level 2 users, and Level 3 users.

[0152] Optionally, based on historical purchase data, three ranges can be set: no purchasing power, barely purchasing power, and purchasing power. Each range corresponds to a different numerical range. If a user's purchase value falls within the set no purchasing power range, the first value tag is activated, making them a level 3 user. If a user's purchase value falls within the set barely purchasing power range, the first value tag is activated, making them a level 2 user. If a user's purchase value falls within the set purchasing power range, the first value tag is activated, making them a level 1 user.

[0153] It should be noted that by activating user profile tags, an initial assessment of the user can be made. Even if the user is a new user of the platform, relevant financial services and / or financial products can be pushed to them. Furthermore, by classifying users by industry, occupation, and user value, user service needs can be well matched.

[0154] In this step, the financial product / financial service tag allocation module can also match the preset keyword tags corresponding to the online financial services and / or financial products with the stored tags in the database, and select the matching product profile tags. The stored tags are the preset keyword tags stored in the tag storage module.

[0155] The preset keyword tags are industry tags, occupation tags, and value tags that are applicable to the user's industry, profession, and value, as set at the beginning of the design of financial services and / or financial products when they are launched.

[0156] Optionally, the tag storage module can store all keyword tags, including user profile tags and keyword tag data. Since each user has one industry tag, one occupation tag, one value tag, and multiple keyword tag data by default, the corresponding keyword tag is activated based on the above trigger conditions; correspondingly, each financial service and / or financial product has multiple industry tags, multiple occupation tags, multiple value tags, and multiple keyword tag data by default, so matching is required.

[0157] Optionally, product profile tags include a second occupation tag, a second industry tag, and a second value tag that are compatible with financial services and / or financial products; matching based on user profile tags and product profile tags includes: matching the first occupation tag and the second occupation tag, matching the first industry tag and the second industry tag, and matching the first value tag and the second value tag, that is, matching one-to-one through the above user profile tags to filter out all financial services and / or financial products that match the user profile tags.

[0158] Among them, the first value tag and the second value tag are both user value tags.

[0159] In this way, by integrating retained information, account information, and cross-platform user behavior information to construct user profile tags, the comprehensiveness and accuracy of the tags are ensured. Value tags are derived based on account information, which significantly improves the targeting and effectiveness of financial service recommendations. By intelligently matching preset keyword tags with stored tags in the database, a standardized product profile tag generation mechanism is established to ensure the accuracy and consistency of product feature expression. This provides a high-quality and reliable data foundation for subsequent matching and recommendations, significantly improving recommendation reliability.

[0160] Understandably, by collecting users' retained information and account information, industry and occupational tags can be assigned to users based on the retained information, and user value can be assessed by calculating users' bank account information to determine user value tags. This allows for targeted push of personalized financial service information to users, filtering users with different needs, further improving customer satisfaction and loyalty, and making the pushed financial service information more accurate, thereby increasing the purchase rate of financial service products, reducing telephone communication time, and allowing customer service to communicate with customers in a targeted manner based on debt scores.

[0161] Optionally, the method also includes:

[0162] Set a countdown window based on the application scenario requirements, and determine the preset duration based on the countdown window.

[0163] In this embodiment of the application, the countdown window may refer to the business recommendation cycle. For example, a 7-day window may be set for weekly recommendation updates.

[0164] Optionally, different application scenarios may correspond to different countdown windows. These application scenario requirements may include marketing campaign cycles, product lifecycles, or the frequency of changes in user behavior, etc. This application embodiment does not specifically limit this.

[0165] For example, the timing module can set a countdown window according to the application scenario requirements, that is, match and update the countdown, and call the matching module to start working when the countdown ends.

[0166] Therefore, this application achieves intelligent management of data timeliness by introducing a countdown window mechanism. This means that time windows can be flexibly set according to the dynamic needs of different application scenarios, so that the recommendations of financial services and / or financial products can adapt to the timeliness requirements of different business scenarios, avoiding resource waste or recommendation lag caused by fixed cycles. Furthermore, the automated management and execution through the countdown mechanism can reduce manual intervention and ensure the continuity and timeliness of recommendation services.

[0167] Optionally, the method also includes:

[0168] Determine a predetermined number of first financial services and / or first financial products from the list of financial services and / or financial products to be recommended;

[0169] Obtain the push notification status of the first financial service and / or the first financial product, and based on the push notification status, filter out the second financial service and / or the second financial product that has not been pushed from a preset number of the first financial service and / or the first financial product;

[0170] If the quantity of the second financial service and / or the second financial product meets the preset conditions, the second financial service and / or the second financial product will be recommended to the user.

[0171] If the number of second financial services and / or second financial products does not meet the preset conditions, then the first financial service and / or first financial product will be determined again from the financial services and / or financial products to be recommended, until the number of second financial services and / or second financial products selected meets the preset conditions.

[0172] In this embodiment of the application, the preset condition may refer to the quantity that meets user preferences or user needs. Optionally, the preset condition may be a preset quantity or a redefined quantity. This embodiment of the application does not specifically limit this.

[0173] Optionally, a first financial service and / or first financial product may be determined again from the financial services and / or financial products to be recommended. Alternatively, a first financial service and / or first financial product may be determined from the financial services and / or financial products to be recommended, and then the selection and judgment may be carried out in sequence. Or, a preset number and multiple first financial services and / or first financial products may be determined again for selection and judgment.

[0174] For example, the push module can obtain the first X data items from the reserve queue and store them in the recommendation queue. It then iterates through the data in the recommendation queue and determines whether the first financial service and / or the first financial product has already been pushed. If it has been pushed, the first financial service and / or the first financial product is removed from the recommendation queue. The module then obtains the (X+1)th data item from the reserve queue and stores it in the recommendation queue. It continues to iterate through the recommendation queue until all the first financial services and / or the first financial products in the recommendation queue have not been pushed. Finally, the second financial service and / or the second financial product in the recommendation queue is pushed to the user's terminal device.

[0175] In this way, by introducing a push status check mechanism, the repeated recommendation of the same financial services and / or financial products to the same user can be effectively avoided, reducing user harassment and improving the experience; and this application ensures that each recommendation can deliver a sufficient amount of fresh financial services and / or financial products through a mechanism of dynamically supplementing the number of recommendations, thus guaranteeing the practicality of the recommendations and the integrity of the user experience.

[0176] Therefore, once the bank's platform is established, the aforementioned intelligent management platform will further strengthen communication and connection between the bank and its customers, thereby comprehensively enhancing the bank's brand image and awareness, and increasing customer trust. Furthermore, by promoting the bank's financial services and / or products to users through the platform, intelligent, smart, and precise services will be achieved, thereby improving customer satisfaction and loyalty, reducing customer churn, and saving customer acquisition costs. It is expected to drive growth in deposits, loans, wealth management, mobile banking, and third-party card binding services.

[0177] In the foregoing embodiments, the financial service recommendation method provided by the embodiments of this application has been described. To implement the functions of the methods provided by the embodiments of this application, the electronic device serving as the execution subject may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0178] For example, Figure 5 This is a schematic diagram of a financial service recommendation device provided in an embodiment of this application. The financial service recommendation device 500 includes:

[0179] The acquisition module 501 is used to acquire user profile tags and user behavior preference data, as well as product profile tags for at least one online financial service and / or financial product.

[0180] Processing module 502 is used to process user behavior preference data to obtain keyword tag data, which is used to characterize the type characteristics of financial services and / or financial products.

[0181] The determination module 503 is used to score the keyword tag data, determine the tag score data, and determine the grade score of the keyword tag data based on the tag score data;

[0182] The matching module 504 is used to match user profile tags and product profile tags at preset intervals to determine target financial services and / or target financial products, evaluate the target financial services and / or target financial products based on rating scores, and determine the financial services and / or financial products to be recommended.

[0183] Optionally, behavioral preference data includes the number of visits to financial services and / or financial products, visit time, visit quantity, purchase history, and search history; keyword tag data includes: a first set of keyword tags, a second set of keyword tags, a third set of keyword tags, and a fourth set of keyword tags; processing module 502 is specifically used for:

[0184] User activity is determined based on the number of visits, and the first set of keyword tags corresponding to financial services and / or financial products is determined based on the activity.

[0185] The duration of a user's stay on financial services and / or financial products is determined based on the access time, and the set of second keyword tags corresponding to the financial services and / or financial products is determined based on the duration of stay.

[0186] The frequency of a user's access to financial services and / or financial products is determined based on the number of visits, the number of visits, and the purchase history. The set of third keyword tags corresponding to financial services and / or financial products is determined based on the access frequency.

[0187] Based on search history, determine the number of times a user searches for financial services and / or financial products, and based on the number of searches, determine the set of fourth keyword tags corresponding to financial services and / or financial products.

[0188] Optionally, the determining module 503 includes a scoring unit and a determining unit, the scoring unit being used for:

[0189] Obtain user behavior data in the current state, and determine the fifth keyword tag set based on the user behavior data;

[0190] Calculate the similarity between each keyword tag in the keyword tag data and the fifth keyword tag set to obtain a keyword similarity coefficient array;

[0191] Obtain the original score data and preset weight coefficient of each keyword tag in the keyword tag data for the previous preset time period. Based on the keyword similarity coefficient array, the original score data and the weight coefficient, update the score of each keyword tag in the keyword tag data to determine the tag score data.

[0192] Optionally, the determining unit is used for:

[0193] The target label level range of the label score data is determined by matching the label score data with the preset label level range.

[0194] The grade score of keyword tag data is determined based on the target tag grade range; there is a mapping relationship between the target tag grade range and the grade score.

[0195] Optional, matching module 504, specifically used for:

[0196] Calculate the tag score corresponding to the target financial service and / or target financial product based on the grade score of keyword tag data;

[0197] The target financial services and / or target financial products are sorted based on the tag scores to determine the financial services and / or financial products to be recommended.

[0198] Optionally, user profile tags include: the user's primary occupation tag, primary industry tag, and primary value tag; acquisition module 501 is specifically used for:

[0199] Obtain user retention information and account information, and determine the user's primary occupation tag and primary industry tag based on the retention information;

[0200] Based on the user's account information, estimate the user's purchasing power level, and determine the first value tag based on the purchasing power level;

[0201] Extract user behavior preference data from user behavior information on at least one platform;

[0202] The preset keyword tags corresponding to at least one online financial service and / or financial product are matched with the stored tags in the database to determine product profile tags.

[0203] Optionally, the financial service recommendation device 500 also includes a timing module, which is used for:

[0204] Set a countdown window based on the application scenario requirements, and determine the preset duration based on the countdown window.

[0205] Optionally, the financial service recommendation device 500 also includes a recommendation module, which is used for:

[0206] Determine a predetermined number of first financial services and / or first financial products from the list of financial services and / or financial products to be recommended;

[0207] Obtain the push notification status of the first financial service and / or the first financial product, and based on the push notification status, filter out the second financial service and / or the second financial product that has not been pushed from a preset number of the first financial service and / or the first financial product;

[0208] If the quantity of the second financial service and / or the second financial product meets the preset conditions, the second financial service and / or the second financial product will be recommended to the user.

[0209] If the number of second financial services and / or second financial products does not meet the preset conditions, then the first financial service and / or first financial product will be determined again from the financial services and / or financial products to be recommended, until the number of second financial services and / or second financial products selected meets the preset conditions.

[0210] It should be noted that the specific implementation principle and effects of the above-mentioned financial service recommendation device 500 can be found in the relevant descriptions and effects of the above embodiments, and will not be elaborated further here.

[0211] This application also provides an electronic device. Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 6 As shown, the electronic device may include: a processor 601 and a memory 602 communicatively connected to the processor; the memory 602 stores a computer program; the processor 601 executes the computer program stored in the memory 602, causing the processor 601 to perform the method of any of the above embodiments.

[0212] The memory 602 and the processor 601 can be connected via a bus 603.

[0213] This application also provides a computer-readable storage medium storing computer program execution instructions, which, when executed by a processor, are used to implement the methods as described in any of the foregoing embodiments of this application.

[0214] This application also provides a chip for executing instructions, which is used to perform the methods executed by an electronic device as described in any of the foregoing embodiments of this application.

[0215] This application also provides a computer program product, which includes a computer program that, when executed by a processor, can implement the method performed by an electronic device as described in any of the foregoing embodiments of this application.

[0216] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0217] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0218] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0219] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods provided in the various embodiments of this application.

[0220] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor, a processor, or any conventional processor. The steps of the method disclosed in the application can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0221] The memory may include high-speed random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0222] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0223] The aforementioned storage media can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage media can be any available medium accessible to general-purpose or special-purpose computers.

[0224] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0225] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0226] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0227] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0228] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0229] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the claims.

Claims

1. A financial service recommendation method characterized by comprising: The method comprises: obtaining user portrait labels and behavior preference data of a user, and product portrait labels of at least one online financial service and / or financial product; processing the behavior preference data of the user to obtain keyword label data, the keyword label data being used to represent type characteristics of the financial service and / or financial product; scoring the keyword label data to determine label score data, and determining a grade score value of the keyword label data based on the label score data; every preset time length, matching the user portrait labels and the product portrait labels to determine target financial service and / or target financial product, and evaluating the target financial service and / or target financial product based on the grade score value to determine financial service to be recommended and / or financial product to be recommended.

2. The method of claim 1, wherein, The behavior preference data comprises access times, access times, access quantities, purchase history records and search records of the financial service and / or financial product, the keyword label data comprises a first keyword label set, a second keyword label set, a third keyword label set and a fourth keyword label set; the processing of the behavior preference data of the user to obtain keyword label data comprises: determining the activity of the user based on the access times, and determining the first keyword label set corresponding to the financial service and / or financial product based on the activity; determining the dwell time of the user on the financial service and / or financial product based on the access time, and determining the second keyword label set corresponding to the financial service and / or financial product based on the dwell time; determining the access frequency of the user on the financial service and / or financial product based on the access quantity, the access times and the purchase history records, and determining the third keyword label set corresponding to the financial service and / or financial product based on the access frequency; determining the search times of the user on the financial service and / or financial product based on the search records, and determining the fourth keyword label set corresponding to the financial service and / or financial product based on the search times.

3. The method of claim 1, wherein, The scoring of the keyword label data to determine label score data comprises: obtaining user behavior data of the user in the current state, and determining a fifth keyword label set based on the user behavior data; calculating the similarity of each keyword label in the keyword label data and the fifth keyword label set to obtain a keyword similarity coefficient array; obtaining original score data of each keyword label in the keyword label data in the last preset time length and a preset weight coefficient, and updating the score of each keyword label in the keyword label data based on the keyword similarity coefficient array, the original score data and the weight coefficient to determine label score data.

4. The method of claim 1, wherein, The determination of the grade score value of the keyword label data based on the label score data comprises: matching the label score data with a preset label grade interval to determine a target label grade interval of the label score data; Determine a grade score of the keyword label data based on the target label grade interval; and a mapping relationship exists between the target label grade interval and the grade score.

5. The method of claim 1, wherein, The evaluation of the target financial service and / or target financial product based on the grade score includes: Calculating a label score corresponding to the target financial service and / or target financial product based on the grade score of the keyword label data; Sorting the target financial service and / or target financial product based on the label score to determine the financial service to be recommended and / or the financial product to be recommended.

6. The method of claim 1, wherein, The user portrait label includes a first occupation label, a first industry label, and a first value label of the user; and the user portrait label and the behavior preference data of the user, and the product portrait label of at least one online financial service and / or financial product are obtained, including: Obtaining retention information and account information of the user, and determining the first occupation label and the first industry label of the user based on the retention information; Estimating a purchase ability level of the user based on the account information of the user, and determining the first value label based on the purchase ability level; Extracting the behavior preference data of the user from user behavior information of the user on at least one platform; Matching the preset keyword label corresponding to the at least one online financial service and / or financial product with a stored label in a database to determine the product portrait label.

7. The method of claim 1, wherein, The method further includes: Setting a countdown window based on application scenario requirements, and determining the preset time length based on the countdown window.

8. The method of claim 1, wherein, The method further includes: Determining a preset number of first financial services and / or first financial products from the financial services to be recommended and / or the financial products to be recommended; Obtaining a push situation of the first financial services and / or first financial products, and screening out second financial services and / or second financial products that have not been pushed from the preset number of first financial services and / or first financial products based on the push situation; If the number of the second financial services and / or second financial products meets a preset condition, recommending the second financial services and / or second financial products to the user; If the number of the second financial services and / or second financial products does not meet the preset condition, determining first financial services and / or first financial products again from the financial services to be recommended and / or the financial products to be recommended until the number of the second financial services and / or second financial products screened out meets the preset condition.

9. A financial service recommendation apparatus characterized by comprising: The device includes: An obtaining module configured to obtain a user portrait label and behavior preference data of a user, and a product portrait label of at least one online financial service and / or financial product; A processing module configured to process the behavior preference data of the user to obtain keyword label data, the keyword label data being used to represent type characteristics of the financial service and / or financial product; and The determining module is configured to score the keyword label data, determine label score data, and determine a grade score of the keyword label data based on the label score data; The matching module is configured to match the user portrait label and the product portrait label every preset time length, determine a target financial service and / or a target financial product, evaluate the target financial service and / or the target financial product based on the grade score, and determine a financial service to be recommended and / or a financial product to be recommended.

10. An electronic device, comprising: The method comprises: a processor, and a memory connected with the processor in communication; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

12. A computer program product, characterised in that, The computer program is executed by the processor to implement the method according to any one of claims 1 to 8.

Images