Insurance product recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an insurance product recommendation method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for the field of financial science and technology. The method comprises the following steps: acquiring original user behavior data, and performing activeness screening on the original user behavior data to obtain active user behavior data; obtaining target behavior data of the target object; performing user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data; performing user screening on the active user behavior data based on the target user similarity data to obtain target similar users; determining a target insurance product from the active user behavior data based on the target similar user; and performing product recommendation to the target object based on the target insurance product. According to the embodiment of the invention, recommendation errors caused by rare user behavior data can be effectively reduced, and the accuracy of insurance product recommendation is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, is applicable to the field of financial technology, and in particular, relates to an insurance product recommendation method and device, electronic equipment, and storage medium. Background Art

[0002] In the field of intelligent recommendation, corresponding content can be recommended based on the user's historical behavior, including recommended articles, videos, products, etc., which can be applied to multiple application scenarios. For example, in the financial technology scenario, financial products and insurance products can be recommended to users. However, in actual application scenarios, when the user's historical behavior data is relatively scarce, it is difficult to accurately capture and predict the user's preferences, which affects the accuracy of product recommendations.

[0003] Therefore, how to improve the accuracy of insurance product recommendations has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an insurance product recommendation method and device, an electronic device and a storage medium, aiming to improve the accuracy of insurance product recommendations.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes an insurance product recommendation method, the method comprising:

[0006] Acquire original user behavior data, and perform activity screening on the original user behavior data to obtain active user behavior data;

[0007] Obtain target behavior data of the target object;

[0008] Performing user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data;

[0009] Perform user screening on the active user behavior data based on the target user similarity data to obtain target similar users;

[0010] determining a target insurance product from the active user behavior data based on the target similar users;

[0011] Based on the target insurance product, a product recommendation is made to the target object.

[0012] In some embodiments, the user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data includes:

[0013] Matrix construction is performed on the active user behavior data to obtain an original user-product matrix;

[0014] Matrix the target behavior data to obtain a target user-product matrix;

[0015] User similarity calculation is performed based on the target user-product matrix and the original user-product matrix to obtain the target user similarity data.

[0016] In some embodiments, the performing user similarity calculation based on the target user-product matrix and the original user-product matrix to obtain the target user similarity data includes:

[0017] Extracting product data from the target user product matrix to obtain first insurance product data;

[0018] Extracting product data from the original user product matrix to obtain second insurance product data;

[0019] Performing intersection processing on the first insurance product data and the second insurance product data to obtain target insurance product data;

[0020] Performing user statistics on the original user-product matrix according to the target insurance product data to obtain the target number of interactive users;

[0021] Performing aggregation calculation based on the first insurance product data and the second insurance product data to obtain product active convergence data;

[0022] Performing aggregate calculation on the target number of interactive users to obtain user activity convergence data;

[0023] Aggregate the product active convergence data and the user active convergence data to obtain the target user similarity data.

[0024] In some embodiments, constructing a matrix of the active user behavior data to obtain an original user-product matrix includes:

[0025] Calculating the number of users based on the active user behavior data to obtain the number of active users;

[0026] Perform product statistics on the active user behavior data to obtain a list of active insurance products;

[0027] Initialize a matrix based on the number of active users and the list of active insurance products to obtain an initial user-product matrix;

[0028] The initial user-product matrix is ​​filled based on the active user behavior data to obtain the original user-product matrix.

[0029] In some embodiments, the performing user screening on the active user behavior data based on the target user similarity data to obtain target similar users includes:

[0030] Sorting the target user similarity data to obtain an original user similarity sequence;

[0031] Performing similarity screening on the original user similarity sequence to obtain a target user similarity sequence;

[0032] The target similar user is obtained by screening the active user behavior data based on the target user similarity sequence.

[0033] In some embodiments, determining a target insurance product from the active user behavior data based on the target similar user includes:

[0034] Extracting multiple candidate insurance products from the active user behavior data based on the target similar users;

[0035] Counting the number of interactions of each candidate insurance product to obtain the number of interactions of the candidate product;

[0036] Sorting the plurality of candidate insurance products based on the number of interactions of the candidate products to obtain a candidate recommended product sequence;

[0037] The candidate recommended product sequence is screened based on a preset product quantity threshold to obtain the target insurance product.

[0038] In some embodiments, the step of screening the original user behavior data for activity to obtain active user behavior data includes:

[0039] Calculating the active duration of the original user behavior data to obtain the original user active duration;

[0040] Calculating the number of active times of the original user behavior data to obtain the number of active times of the original user;

[0041] The original user behavior data is screened based on the original user active duration and the original user active times to obtain the active user behavior data.

[0042] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides an insurance product recommendation device, the device comprising:

[0043] An active user behavior data acquisition module is used to acquire original user behavior data, perform activity screening on the original user behavior data, and obtain active user behavior data;

[0044] A target user behavior data acquisition module is used to acquire target behavior data of a target object;

[0045] A user similarity calculation module, used to perform user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data;

[0046] A user screening module, configured to screen the active user behavior data based on the target user similarity data to obtain target similar users;

[0047] An insurance product determination module, configured to determine a target insurance product from the active user behavior data based on the target similar users;

[0048] A target product recommendation module is used to make product recommendations to the target object based on the target insurance product.

[0049] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0050] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0051] The insurance product recommendation method and device, electronic device and storage medium proposed in the present application obtain original user behavior data, and perform activity screening on the original user behavior data to obtain active user behavior data. By taking user activity as one of the consideration factors, it can ensure that the user group participating in the similarity calculation is more active and highly relevant, and then perform user similarity calculation based on the active user behavior data and the target behavior data of the target object to obtain target user similarity data; perform user screening on the active user behavior data based on the target user similarity data to obtain target similar users; determine the target insurance product from the active user behavior data based on the target similar users; and recommend products to the target object based on the target insurance product, thereby effectively reducing the recommendation error caused by the scarcity of user behavior data and improving the accuracy of insurance product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of the insurance product recommendation method provided in an embodiment of the present application;

[0053] Figure 2 yes Figure 1 Flow chart of step S101 in FIG.

[0054] Figure 3 yes Figure 1 Flow chart of step S103 in FIG.

[0055] Figure 4 yes Figure 3 Flow chart of step S301 in FIG.

[0056] Figure 5 yes Figure 3 Flow chart of step S303 in FIG.

[0057] Figure 6 yes Figure 1 Flow chart of step S104 in FIG.

[0058] Figure 7 yes Figure 1 Flow chart of step S105 in FIG.

[0059] Figure 8 is a schematic diagram of the structure of the insurance product recommendation device provided in an embodiment of the present application;

[0060] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0064] First, some nouns involved in this application are analyzed:

[0065] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0066] In the field of intelligent recommendation, corresponding content can be recommended based on the user's historical behavior, including recommended articles, videos, products, etc., which can be applied to multiple application scenarios. For example, in the financial technology scenario, financial products, insurance products, etc. can be recommended to users.

[0067] Currently, collaborative filtering algorithms are mainly used to implement product recommendations, such as user-based collaborative filtering (UserCF), which can generate a product list based on the similarities between users for product recommendation.

[0068] However, in actual application scenarios, when users' historical behavior data is relatively scarce, it is difficult to accurately capture and predict users' preferences, and it is also difficult to find similar users. There are sparsity problems and cold start problems, which affect the accuracy of product recommendations.

[0069] Based on this, the embodiments of the present application provide an insurance product recommendation method and device, an electronic device and a storage medium, aiming to improve the accuracy of insurance product recommendations.

[0070] The insurance product recommendation method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the insurance product recommendation method in the embodiments of the present application is described.

[0071] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0072] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0073] The insurance product recommendation method provided in the embodiment of the present application relates to the field of artificial intelligence technology and is applicable to the field of financial technology. The insurance product recommendation method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the insurance product recommendation method, etc., but is not limited to the above forms.

[0074] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0075] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0076] Figure 1 is an optional flow chart of the insurance product recommendation method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0077] Step S101, obtaining original user behavior data, screening the original user behavior data for activity, and obtaining active user behavior data;

[0078] Step S102, obtaining target behavior data of the target object;

[0079] Step S103, performing user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data;

[0080] Step S104, performing user screening on the active user behavior data based on the target user similarity data to obtain target similar users;

[0081] Step S105, determining a target insurance product from the active user behavior data based on the target similar users;

[0082] Step S106: recommending products to the target object based on the target insurance product.

[0083] Steps S101 to S106 shown in the embodiment of the present application obtain original user behavior data and perform activity screening on the original user behavior data to obtain active user behavior data. By taking user activity as one of the consideration factors, it is possible to ensure that the user group participating in the similarity calculation is more active and highly relevant, and then perform user similarity calculation based on the active user behavior data and the target behavior data of the target object to obtain target user similarity data; perform user screening on the active user behavior data based on the target user similarity data to obtain target similar users; determine target insurance products from the active user behavior data based on the target similar users; and make product recommendations to the target object based on the target insurance products, thereby effectively reducing recommendation errors caused by scarce user behavior data and improving the accuracy of insurance product recommendations.

[0084] In some embodiments, the original user behavior data is the embedded point data within a preset period obtained from the application in the insurance field, that is, the behavior data of all users in the application within the preset period. The original user behavior data includes but is not limited to: browsing insurance products, consulting insurance products, purchasing insurance products, etc., which is used to reflect the interaction between users and various insurance products; the preset period can be set according to the specific application scenario, such as one week, one month, one quarter, etc., but is not limited to this.

[0085] See also Figure 2 In some embodiments, step S101 may include but is not limited to steps S201 to S203:

[0086] Step S201, calculating the active duration of the original user behavior data to obtain the original user active duration;

[0087] Step S202, calculating the number of active times of the original user behavior data to obtain the number of active times of the original user;

[0088] Step S203 , performing user screening on the original user behavior data based on the original user active duration and the original user active times to obtain active user behavior data.

[0089] In steps S201 to S203 shown in the embodiment of the present application, the original user behavior data is subjected to active duration and active frequency calculation to obtain the original user active duration and the original user active frequency, and the original user behavior data is subjected to user screening based on the original user active duration and the original user active frequency to obtain active user behavior data, which can ensure that the user groups participating in subsequent analysis have higher activity and participation, thereby improving the representativeness and reliability of the data, facilitating a more accurate understanding of user preferences and behavior patterns, and effectively reducing the risk of analysis bias and inaccurate recommendations that may be caused by user inactivity or data sparsity.

[0090] In step S201 of some embodiments, the behavior record of each user is timestamped and parsed, and the total active time of each user in a preset time period is calculated to obtain the original user active time. By calculating the active time, a preliminary understanding of the user's activity level can be obtained.

[0091] In step S202 of some embodiments, the number of behaviors of each user in a preset time period is further calculated, that is, the original number of active users, which reflects the frequency of interaction between the user and the platform and is an important indicator for evaluating user activity. By calculating the number of active times, the user's behavior habits can be understood in more detail, such as whether the user tends to visit the platform frequently.

[0092] In step S203 of some embodiments, a reasonable screening threshold is set by comprehensively considering the original user's active duration and the original user's active times. Only users who meet both the active duration and active times thresholds are considered active users, and their behavior data is active user behavior data, which can remove a large amount of inactive or low-activity user data, ensuring that insurance product recommendations can be made based on a higher-quality and more representative user group in the future.

[0093] In step S102 of some embodiments, the target object needs to have certain behavior data, so the target object can be an active user or an inactive user.

[0094] Therefore, the target behavior data of the target object is obtained, and the target behavior data includes but is not limited to: browsing insurance products, consulting insurance products, purchasing insurance products, etc., which is used to reflect the interactive behavior between the target object and each insurance product; it is convenient to find other similar active users based on the target behavior data of the target object in the future to obtain a product recommendation sequence.

[0095] See also Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S303:

[0096] Step S301, constructing a matrix of active user behavior data to obtain an original user-product matrix;

[0097] Step S302, constructing a matrix for the target behavior data to obtain a target user-product matrix;

[0098] Step S303, performing user similarity calculation based on the target user-product matrix and the original user-product matrix to obtain target user similarity data.

[0099] In steps S301 to S303 shown in the embodiment of the present application, by respectively constructing matrices of active user behavior data and target behavior data, an original user-product matrix and a target user-product matrix are obtained, and user similarity calculation is performed based on the target user-product matrix and the original user-product matrix to obtain target user similarity data, which can more deeply mine the similarity information between user behavior data, thereby providing users with more personalized recommendation services.

[0100] See also Figure 4 In some embodiments, step S301 may include but is not limited to steps S401 to S404:

[0101] Step S401, calculating the number of users based on the active user behavior data to obtain the number of active users;

[0102] Step S402, performing product statistics on active user behavior data to obtain a list of active insurance products;

[0103] Step S403, initializing a matrix based on the number of active users and the list of active insurance products to obtain an initial user-product matrix;

[0104] Step S404: Fill the initial user-product matrix based on the active user behavior data to obtain an original user-product matrix.

[0105] In steps S401 to S404 shown in the embodiment of the present application, the number of active users is obtained by calculating the number of users based on the active user behavior data; product statistics are performed on the active user behavior data to obtain a list of active insurance products; a matrix is ​​initialized based on the number of active users and the list of active insurance products to obtain an initial user-product matrix; and then the initial user-product matrix is ​​filled based on the active user behavior data to obtain an original user-product matrix, which can intuitively display the association between active users and insurance products.

[0106] In some embodiments, the insurance products that active users have interacted with can be understood as active insurance products. Therefore, a list of active insurance products can be obtained by performing product statistics on the active user behavior data.

[0107] Further, a matrix is ​​initialized based on the number of active users and the list of active insurance products to obtain an initial user-product matrix, wherein the initial user-product matrix is ​​a two-dimensional matrix, and the rows in the initial user-product matrix may be users and the columns may be products; or the rows may be products and the columns may be users, and each element in the initial user-product matrix is ​​0;

[0108] Finally, the initial user-product matrix is ​​filled based on the active user behavior data. The corresponding element of each insurance product that the active user has interacted with is set to 1, indicating that the active user has interacted with the insurance product, thereby intuitively showing the association between active users and insurance products.

[0109] In some embodiments, step S302 may include but is not limited to the following steps:

[0110] Conduct product statistics on target user behavior data to obtain a list of target insurance products;

[0111] Initialize the matrix based on the target insurance product list and the active insurance product list to obtain the candidate user product matrix;

[0112] The candidate user-product matrix is ​​filled based on the target user behavior data to obtain the target user-product matrix.

[0113] It should be noted that the candidate user-product matrix is ​​a one-dimensional matrix, and each element in the candidate user-product matrix is ​​0; while in the target user-product matrix that is filled based on the target user behavior data, if the target object has interacted with a certain insurance product, its corresponding element is set to 1.

[0114] In step S303 of some embodiments, the user similarity between the target object and each active user is obtained by calculating the target user product matrix and the original user product matrix, thereby obtaining target user similarity data. Specifically, the user similarity calculation process is implemented by calculating each row / column in the target user product matrix and the original user product matrix.

[0115] See also Figure 5 In some embodiments, step S303 may include but is not limited to steps S501 to S507:

[0116] Step S501, extracting product data from the target user product matrix to obtain first insurance product data;

[0117] Step S502, extracting product data from the original user product matrix to obtain second insurance product data;

[0118] Step S503, performing intersection processing on the first insurance product data and the second insurance product data to obtain target insurance product data;

[0119] Step S504, performing user statistics on the original user product matrix according to the target insurance product data to obtain the target number of interactive users;

[0120] Step S505, performing aggregation calculation based on the first insurance product data and the second insurance product data to obtain product active convergence data;

[0121] Step S506, performing aggregate calculation on the number of target interactive users to obtain user activity convergence data;

[0122] Step S507: aggregate and calculate the product active convergence data and the user active convergence data to obtain target user similarity data.

[0123] Steps S501 to S507 shown in the embodiment of the present application are to extract product data from the target user product matrix to obtain first insurance product data, extract product data from the original user product matrix to obtain second insurance product data, perform intersection processing on the first insurance product data and the second insurance product data to obtain target insurance product data, perform user statistics on the original user product matrix based on the target insurance product data to obtain the target number of interactive users, perform aggregation calculation based on the first insurance product data and the second insurance product data to obtain product active convergence data, perform aggregation calculation on the target number of interactive users to obtain user active convergence data, and perform aggregation calculation on the product active convergence data and the user active convergence data to obtain target user similarity data, which can effectively reduce the situation where recommended products converge due to excessive user activity or excessive product activity, and improve the richness of product recommendations.

[0124] In step S501 of some embodiments, product data with which the target object has interacted is obtained from the target user product matrix to obtain first insurance product data;

[0125] In step S502 of some embodiments, product data with which each active user has interacted is obtained from the original user-product matrix to obtain second insurance product data for user similarity calculation with the target object.

[0126] In step S503 of some embodiments, the first insurance product data and the second insurance product data are intersected to obtain target insurance product data with which the target object has interacted with each active user; then, the number of users who have interacted with the target insurance product data is counted from the original user-product matrix to obtain the target number of interacting users.

[0127] Specifically, the specific process of calculating the user similarity between the target object and an active user is as follows:

[0128]

[0129] Among them, u1 represents the target object, u2 represents an active user, For the First Insurance product data, For the second insurance product data, is the number of insurance products that the target object has interacted with, that is, the number of first insurance product data. The number of insurance products that the active user has interacted with, that is, the number of second insurance product data; is the target insurance product data, i is an insurance product in the target insurance product data, U i The number of active users who have interacted with the insurance product, i.e. the target number of interactive users;

[0130] It is understandable that the more active the insurance product is, the greater the probability of being interacted with by different users, and the more active the user is, the more insurance products he or she has interacted with. Therefore, it is necessary to reduce the weights of active users and active insurance products, and use the first insurance product data, the second insurance product data, and the number of target interactive users as the denominator when calculating the similarity, so as to reduce the influence of insurance product activity and user activity on product recommendations, and to reduce the Matthew effect in the recommendation system to a certain extent.

[0131] In some embodiments, by repeating the above steps S501 to S506 , the user similarity between the target object and each active user is calculated to obtain a plurality of target user similarity data.

[0132] See also Figure 6 In some embodiments, step S104 may also include but is not limited to steps S601 to S603:

[0133] Step S601, sorting the target user similarity data to obtain an original user similarity sequence;

[0134] Step S602, performing similarity screening on the original user similarity sequence to obtain a target user similarity sequence;

[0135] Step S603: Filter target similar users from the active user behavior data based on the target user similarity sequence.

[0136] In steps S601 to S603 shown in the embodiment of the present application, the target user similarity data is sorted to obtain an original user similarity sequence; the original user similarity sequence is similarity screened to obtain a target user similarity sequence; and then the target similar user can be screened from the active user behavior data based on the target user similarity sequence, which not only improves the accuracy of similar user identification, but also ensures that the selected users are highly representative, thereby optimizing the accuracy and efficiency of insurance product recommendations.

[0137] In step S601 of some embodiments, the target user similarity data is sorted in descending order of similarity values ​​to form an original user similarity sequence, thereby ensuring that the active user most similar to the target user is at the front of the sequence, which facilitates subsequent screening.

[0138] In step S602 of some embodiments, considering the limitation of computing resources and time cost in practical applications, a quantity threshold or similarity threshold is set based on the original user similarity sequence. A preset number of user similarity data are selected to be retained in the sequence, or when the similarity value exceeds the similarity threshold, the user similarity data is retained in the sequence to obtain the target user similarity sequence, which can effectively filter out users with low similarity to the target user, reduce the complexity of subsequent analysis, and ensure that the screened users have high relevance.

[0139] For example: Filter out the top ten similarity data from the original user similarity sequence to obtain the target user similarity sequence;

[0140] Alternatively, similarity data with a similarity value greater than 0.85 (assuming that the similarity value is in the range of 0 to 1) is screened out from the original user similarity sequence to obtain the target user similarity sequence.

[0141] In step S603 of some embodiments, after obtaining the target user similarity sequence, a specific user is further determined from the active user behavior data as the final target similar user.

[0142] See also Figure 7 In some embodiments, step S105 includes but is not limited to steps S701 to S704:

[0143] Step S701, extracting multiple candidate insurance products from active user behavior data based on target similar users;

[0144] Step S702, counting the number of interactions of each candidate insurance product to obtain the number of interactions of the candidate product;

[0145] Step S703, sorting multiple candidate insurance products based on the number of candidate product interactions to obtain a candidate recommended product sequence;

[0146] Step S704: Screen the candidate recommended product sequence based on a preset product quantity threshold to obtain a target insurance product.

[0147] Steps S701 to S704 shown in the embodiment of the present application obtain candidate insurance products by extracting insurance products that have been interacted with by target-similar users from active user behavior data, and counting the number of times each candidate product has been interacted with by target-similar users for sorting and screening. This can accurately screen out insurance products that best meet the needs of the target object, effectively improve the pertinence and accuracy of insurance product recommendations, help avoid user selection difficulties caused by recommending too many products, and improve user experience and conversion rate.

[0148] In step S701 of some embodiments, insurance products that target similar users have interacted with are extracted from active user behavior data based on target similar users to obtain candidate insurance products, which can preliminarily reflect the insurance needs and preferences of the target object.

[0149] In step S702 of some embodiments, the number of views of each candidate insurance product is counted. It should be noted that the number of views is an important indicator for measuring the user's attention to the insurance product and can reflect the attractiveness of the insurance product to the target object.

[0150] In step S703 of some embodiments, multiple candidate insurance products are sorted from high to low based on the number of candidate product interactions to form a candidate recommended product sequence, which can ensure that the insurance product with the most views is at the front of the sequence, facilitating subsequent screening and improving data processing efficiency.

[0151] In step S704 of some embodiments, a preset product quantity threshold is first set according to the actual application scenario to perform product screening on the candidate recommended product sequence, and the top N insurance products with the highest number of views are screened out from the candidate recommended product sequence as target insurance products. This can ensure the accuracy of the recommendation while limiting the number of recommended results, thereby preventing the target object from being confused by too many choices.

[0152] For example, the candidate insurance products include 6 insurance products, namely, a first insurance product, a second insurance product, a third insurance product, a fourth insurance product, a fifth insurance product and a sixth insurance product;

[0153] Among them, the number of interactions between each insurance product and the candidate products are:

[0154] The number of candidate product interactions for the first insurance product was 8;

[0155] The number of candidate product interactions for the second insurance product is 5;

[0156] The number of candidate product interactions for the third insurance product is 4 times;

[0157] The candidate product interactions for the fourth insurance product were 7 times;

[0158] The candidate product interactions for the fifth insurance product were 6 times;

[0159] The number of candidate product interactions for the sixth insurance product is 1;

[0160] Then the candidate recommended product sequence is: the first insurance product, the fourth insurance product, the fifth insurance product, the second insurance product, the third insurance product, and the sixth insurance product;

[0161] Further, the first five insurance products are screened out from the candidate recommended product sequence to obtain target insurance products, which are the first insurance product, the fourth insurance product, the fifth insurance product, the second insurance product, and the third insurance product.

[0162] In some embodiments, step S106 may include but is not limited to the following steps:

[0163] Arrange the product pages of target insurance products based on the number of interactions with candidate products to obtain a target recommended product arrangement;

[0164] Arrange the target products in the application to display the products to the target audience.

[0165] See also Figure 8 The embodiment of the present application further provides an insurance product recommendation device, which can implement the above-mentioned insurance product recommendation method, and the device includes:

[0166] The active user behavior data acquisition module 801 is used to acquire original user behavior data, perform activity screening on the original user behavior data, and obtain active user behavior data;

[0167] The target user behavior data acquisition module 802 is used to acquire the target behavior data of the target object;

[0168] A user similarity calculation module 803 is used to calculate user similarity based on active user behavior data and target behavior data to obtain target user similarity data;

[0169] A user screening module 804 is used to screen the active user behavior data based on the target user similarity data to obtain target similar users;

[0170] An insurance product determination module 805, for determining a target insurance product from active user behavior data based on target similar users;

[0171] The target product recommendation module 806 is used to make product recommendations to the target object based on the target insurance product.

[0172] The specific implementation of the insurance product recommendation device is basically the same as the specific implementation of the above-mentioned insurance product recommendation method, and will not be repeated here.

[0173] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned insurance product recommendation method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0174] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0175] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0176] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the insurance product recommendation method of the embodiment of this application;

[0177] Input / output interface 903, used to implement information input and output;

[0178] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0179] A bus 905 that transmits information between the various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0180] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0181] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned insurance product recommendation method is implemented.

[0182] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.

[0183] The insurance product recommendation method and device, electronic device and storage medium provided in the embodiments of the present application obtain original user behavior data, perform activity screening on the original user behavior data, obtain active user behavior data, and take user activity as one of the consideration factors, thereby ensuring that the user group participating in the similarity calculation is more active and highly relevant, and then perform user similarity calculation based on the active user behavior data and the target behavior data of the target object to obtain target user similarity data; perform user screening on the active user behavior data based on the target user similarity data to obtain target similar users; determine the target insurance product from the active user behavior data based on the target similar users; and make product recommendations to the target object based on the target insurance product, thereby effectively reducing the recommendation error caused by the scarcity of user behavior data and improving the accuracy of insurance product recommendations.

[0184] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0185] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0186] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0187] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0188] The terms "first", "second", "third", "fourth", etc. (if any) in the specification 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.

[0189] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers 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, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0190] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0191] The units described above 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.

[0192] 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.

[0193] 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 is essentially 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 multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0194] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for recommending insurance products, characterized in that: The method comprises: Acquire original user behavior data, and perform activity screening on the original user behavior data to obtain active user behavior data; Obtain target behavior data of the target object; Performing user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data; Perform user screening on the active user behavior data based on the target user similarity data to obtain target similar users; determining a target insurance product from the active user behavior data based on the target similar users; Based on the target insurance product, a product recommendation is made to the target object.

2. The method according to claim 1, characterized in that The user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data includes: Matrix construction is performed on the active user behavior data to obtain an original user-product matrix; Matrix the target behavior data to obtain a target user-product matrix; User similarity calculation is performed based on the target user-product matrix and the original user-product matrix to obtain the target user similarity data.

3. The method according to claim 2, characterized in that The user similarity calculation is performed based on the target user-product matrix and the original user-product matrix to obtain the target user similarity data, including: Extracting product data from the target user product matrix to obtain first insurance product data; Extracting product data from the original user product matrix to obtain second insurance product data; Performing intersection processing on the first insurance product data and the second insurance product data to obtain target insurance product data; Performing user statistics on the original user-product matrix according to the target insurance product data to obtain the target number of interactive users; Performing aggregation calculation based on the first insurance product data and the second insurance product data to obtain product active convergence data; Performing aggregate calculation on the target number of interactive users to obtain user activity convergence data; Aggregate the product active convergence data and the user active convergence data to obtain the target user similarity data.

4. The method according to claim 2, characterized in that: The matrix construction of the active user behavior data to obtain the original user product matrix includes: Calculating the number of users based on the active user behavior data to obtain the number of active users; Perform product statistics on the active user behavior data to obtain a list of active insurance products; Initialize a matrix based on the number of active users and the list of active insurance products to obtain an initial user-product matrix; The initial user-product matrix is ​​filled based on the active user behavior data to obtain the original user-product matrix.

5. The method according to any one of claims 1 to 4, characterized in that: The performing user screening on the active user behavior data based on the target user similarity data to obtain target similar users includes: Sorting the target user similarity data to obtain an original user similarity sequence; Performing similarity screening on the original user similarity sequence to obtain a target user similarity sequence; The target similar user is obtained by screening the active user behavior data based on the target user similarity sequence.

6. The method according to any one of claims 1 to 4, characterized in that: The determining a target insurance product from the active user behavior data based on the target similar user includes: Extracting a plurality of candidate insurance products from the active user behavior data based on the target similar users; Counting the number of interactions of each candidate insurance product to obtain the number of interactions of the candidate product; Sorting the plurality of candidate insurance products based on the number of interactions of the candidate products to obtain a candidate recommended product sequence; The candidate recommended product sequence is screened based on a preset product quantity threshold to obtain the target insurance product.

7. The method according to any one of claims 1 to 4, characterized in that: The step of screening the original user behavior data for activity to obtain active user behavior data includes: Calculating the active duration of the original user behavior data to obtain the original user active duration; Calculating the number of active times of the original user behavior data to obtain the number of active times of the original user; The original user behavior data is screened based on the original user active duration and the original user active times to obtain the active user behavior data.

8. An insurance product recommendation device, characterized in that: The device comprises: An active user behavior data acquisition module is used to acquire original user behavior data, perform activity screening on the original user behavior data, and obtain active user behavior data; A target user behavior data acquisition module is used to acquire target behavior data of a target object; A user similarity calculation module, used to perform user similarity calculation based on the active user behavior data and the target behavior data to obtain target user similarity data; A user screening module, configured to screen the active user behavior data based on the target user similarity data to obtain target similar users; An insurance product determination module, configured to determine a target insurance product from the active user behavior data based on the target similar users; A target product recommendation module is used to make product recommendations to the target object based on the target insurance product.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images