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

Abstract

The invention provides an insurance policy recommendation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining first portrait data of a target user and second portrait data of a candidate user; determining a first similar user of the target user from the candidate users according to the first portrait data and the second portrait data; determining a second similar user who purchases the candidate insurance policy in the first similar users according to the insurance policy purchase information of the first similar users; and determining a target insurance policy from the candidate insurance policies according to the first similarity between the target user and the second similar user, and recommending the target insurance policy to the target user. Therefore, the insurance policy to be recommended is determined from the candidate insurance policies according to the similarity between the similar users who have purchased the candidate insurance policies and the target user, so that the recommended insurance policy better meets the potential requirements of the target user, and the recommendation accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular, to a method and device for recommending an insurance policy, an electronic device, and a storage medium. BACKGROUND

[0002] With the development of insurance business, more and more people have the awareness of preventing risks, and more and more people start to purchase insurance. With the rapid development of the insurance industry, there are more and more types of insurance products (i.e., insurance policies), and the types of insurance policies are numerous and the clauses are complex, which increases the difficulty for users to select.

[0003] In the related art, a series of fixed recommendation rules can be formulated in advance by insurance experts according to business experience and insurance product characteristics, and insurance policies are recommended to users according to the recommendation rules. However, this method of recommending insurance policies is difficult to cover complex and variable user needs, and the recommendation accuracy is low. SUMMARY

[0004] The present application aims to at least partially solve one of the technical problems in the related art.

[0005] To this end, a first object of the present application is to provide a method for recommending an insurance policy.

[0006] A second object of the present application is to provide a device for recommending an insurance policy.

[0007] A third object of the present application is to provide an electronic device.

[0008] A fourth object of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objects, a first aspect of the present application provides a method for recommending an insurance policy, comprising: obtaining first portrait data of a target user and second portrait data of a candidate user; determining a first similar user of the target user from the candidate users according to the first portrait data and the second portrait data; determining a second similar user who has purchased the candidate insurance policy from the first similar users according to insurance purchase information of the first similar users; determining a target insurance policy from the candidate insurance policies according to a first similarity between the target user and the second similar user, and recommending the target insurance policy to the target user.

[0011] To achieve the above objects, a second aspect of the present application provides a device for recommending an insurance policy, comprising: obtain first portrait data of a target user and second portrait data of a candidate user; determine, according to the first portrait data and the second portrait data, a first similar user of the target user from the candidate user; determine, according to the first similar user, a second similar user of the target user from the candidate user; recommend, according to a first similarity between the target user and the second similar user, a target insurance policy from the candidate insurance policy, and recommend the target insurance policy to the target user.

[0012] To achieve the above object, a third aspect of the present application provides an electronic device, comprising: comprising a processor and a memory connected with the processor in communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method according to the first aspect of the present application.

[0013] To achieve the above object, a fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method according to the first aspect of the present application.

[0014] To achieve the above object, a fifth aspect of the present application provides a computer program product, comprising a computer program, which is executed by a processor to implement the method according to the first aspect of the present application.

[0015] The insurance policy recommendation method and device, electronic device and storage medium provided by the present application can determine a first similar user of a target user from candidate users according to the first portrait data of the target user and the portrait data of the candidate users, and determine a second similar user of the target user from the candidate users according to the purchase information of the first similar user, and determine a target insurance policy from the candidate insurance policies according to the similarity between the target user and the second similar user, and recommend the target insurance policy to the target user. Therefore, the first similar user of the target user can be determined according to the portrait data between the target user and the candidate users, which can improve the accuracy of the similar user, and the second similar user who has purchased the candidate insurance policy can be further selected from the first similar user according to the purchase information of the first similar user, and the insurance policy to be recommended can be determined from the candidate insurance policies according to the similarity between the second similar user and the target user, so that the recommended insurance policy is more in line with the potential needs of the target user, and the accuracy of the recommendation is greatly improved.

[0016] Additional aspects and advantages of the present application will be made apparent by the following description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings. Figure 1 A flowchart of a policy recommendation method provided by an embodiment of the present application is shown in FIG. 1. Figure 2 A flowchart of another policy recommendation method provided by an embodiment of the present application is shown in FIG. 2. Figure 3 A flowchart of another policy recommendation method provided by an embodiment of the present application is shown in FIG. 3. Figure 4 A structural diagram of a policy recommendation device provided by an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0018] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which the same or similar components have the same or similar designations and functions throughout. The embodiments described below are examples in which the present application is applied. The embodiments described below are intended to explain the present application, and are not to be understood as limiting the present application.

[0019] In the technical solutions of the present application, data acquisition, transmission, storage, use, processing, etc. comply with the provisions of national laws and regulations.

[0020] A policy recommendation method, device, electronic equipment and storage medium of an embodiment of the present application are described below with reference to the accompanying drawings.

[0021] Figure 1 A flowchart of a policy recommendation method provided by an embodiment of the present application is shown in FIG. 1.

[0022] As shown in FIG. 1, the policy recommendation method includes the following steps: Figure 1 Step 101, obtaining first portrait data of a target user and second portrait data of a candidate user.

[0023] The first portrait data can include but is not limited to user feature data of the target user, policy-related behavior data, etc., and the second portrait data can include but is not limited to user feature data of the candidate user, policy-related behavior data, etc. The candidate user can be multiple.

[0024] ​Exemplarily, the user feature data can include but is not limited to basic information (such as age, gender, occupation preference, etc.), risk assessment data, and the like. The risk assessment data can be obtained by assessing the risk procedure ability of the user through a questionnaire or an algorithm.

[0025] Exemplarily, the policy-related behavior data can include but is not limited to browsing behavior data (insured product pages browsed, time spent, etc.), interaction behavior data (insured products collected, shared, consulted, etc.), and purchase behavior data (historical insurance application records, amount of insurance products purchased, frequency, etc.).

[0026] In step 102, a first similar user of the target user is determined from the candidate users according to the first portrait data and the second portrait data.

[0027] In the present application, for each candidate user, the first portrait data and the second portrait data can be vectorized to obtain a first vector and a second vector, and the similarity between the target user and the candidate user is calculated according to the first vector and the second vector, and the first similar user is determined from the candidate users according to the similarity.

[0028] Exemplarily, the candidate users can be sorted in order of similarity from small to large to obtain a sorting result, and the first similar user of the target user is determined from the first preset number of candidate users in the sorting result.

[0029] Exemplarily, the candidate user whose similarity is greater than a preset threshold can also be determined as the first similar user of the target user.

[0030] It should be noted that the first similar user can be one or more, which is not limited in the present application.

[0031] In step 103, a second similar user who has purchased a candidate policy among the first similar users is determined according to the policy purchase information of the first similar user.

[0032] The policy purchase information can include but is not limited to identification information of the policy, purchase time, amount, frequency, and the like.

[0033] In the present application, for each candidate policy, the identification information of the candidate policy can be matched with the identification information of the policy purchased by the first similar user in the policy purchase information of the first similar user to determine the second similar user who has purchased the candidate policy among the first similar users.

[0034] It should be noted that the second similar user corresponding to different candidate policies can be the same or different, and the number of the second similar users corresponding to different candidate policies can be the same or different, which is not limited.

[0035] Step 104: Based on the first similarity between the target user and the second similar user, determine the target policy from the candidate policies and recommend the target policy to the target user.

[0036] In this application, for each candidate policy, the policy score of the candidate policy can be determined based on the first similarity between the target user and the second similar user corresponding to the candidate policy. Based on the policy score, the target policy is determined from the candidate policies and then recommended to the target user.

[0037] For example, a policy score can be determined based on the first similarity score and the discount information of the candidate policies. For instance, the policy score can be obtained by weighting the average of the first similarity scores and the discount amount of the candidate policies. The discount amount can be equal to the ratio of the discount amount to the original policy amount.

[0038] It should be noted that there can be one or more target policies, and this application does not limit this. For example, if there are multiple target policies, multiple target policies can be recommended to the target user for the user to choose from.

[0039] In this embodiment, by using the first profile data of the target user and the profile data of candidate users, a first similar user similar to the target user is identified from the candidate users. Then, based on the purchase information of the first similar user, a second similar user who has purchased a candidate policy is identified from among the first similar users. Finally, based on the similarity between the target user and the second similar user, a target policy is determined from the candidate policies and recommended to the target user. Therefore, identifying the first similar user based on the profile data between the target user and candidate users improves the accuracy of similar users. Furthermore, by further filtering the purchase information of the first similar user to identify the second similar user who has purchased a candidate policy, and then determining the recommended policy from the candidate policies based on the similarity between the second similar user and the target user, the recommended policy better meets the potential needs of the target user, significantly improving the accuracy of the recommendation.

[0040] Figure 2 This is a flowchart illustrating another policy recommendation method provided in an embodiment of this application.

[0041] like Figure 2 As shown, this policy recommendation method may include the following steps: Step 201: Obtain the first profile data of the target user and the second profile data of the candidate user.

[0042] Step 202: Based on the first profile data and the second profile data, determine the first similar user of the target user from the candidate users.

[0043] Step 203, determining a second similar user who has purchased the candidate insurance policy from the first similar users according to the insurance policy purchase information of the first similar users.

[0044] In the present application, steps 201-203 can adopt any of the implementation manners of the embodiments of the present application, and thus will not be described here again.

[0045] Step 204, determining a matching degree between the candidate insurance policy and the target attribute of the target user.

[0046] The target attribute can include but is not limited to the insured age, family attribute, protection demand, budget, etc. The family attribute is used to describe the family member situation, such as being married and having a minor child, etc. In the present application, the insurance policy features of the candidate insurance policy can be matched with the target attribute, and the matching degree between the candidate insurance policy and the target attribute can be determined according to whether the insurance policy features and the target attribute are consistent. The insurance policy features can include but are not limited to the insured age, requirement for family members, protection range, amount, etc.

[0047] For example, according to the consistency of each target attribute, a preset matching score can be obtained, and the total matching score is taken as the matching degree.

[0048] For example, if the preset matching score is 1 point, if the insured age of the candidate insurance policy is consistent with the insured age of the target user, 1 point is obtained, if the requirement for family members of the candidate insurance policy is consistent with the family attribute of the target user, 1 point is obtained, if the protection range of the candidate insurance policy is consistent with the protection demand of the target user (such as critical illness protection, etc.), 1 point is obtained, and if the amount of the candidate insurance policy is consistent with the budget of the target user, 1 point is obtained.

[0049] Step 205, determining an insurance policy score of the candidate insurance policy according to the first similarity and the matching degree.

[0050] The insurance policy score can be used to represent the recommendation degree of the candidate insurance policy to the target user, and the higher the insurance policy score is, the higher the recommendation degree to the target user is.

[0051] In some embodiments, the average value of the first similarity can be determined according to the number of the second similar users and the first similarity, and the average value and the matching degree are weighted to obtain the insurance policy score.

[0052] For example, the first similarities between the target user and the second similar users can be added to obtain a similarity sum, and the average value of the first similarity can be determined according to the ratio between the similarity sum and the number of the second similar users.

[0053] For example, the insurance policy score of the candidate insurance policy can be calculated by using the following formula (1): (1) in, This represents the policy score of candidate policy P; and These are weighting coefficients. ; This represents the similarity weight of the second most similar user who has purchased candidate policy P, where... , It is the first similarity between the target user (target) and the second most similar user (j). This indicates the number of users who are the second most similar to the first. Represents the set of second-most similar users; This indicates the degree of matching between the candidate policy P and the target attributes of the target user.

[0054] Therefore, by using the average similarity between the target user and the second most similar user and the weighted sum of the matching degree, the policy score is obtained, which improves the accuracy of the policy score. Step 206: Determine the target policy from the candidate policies based on the policy score.

[0055] In this application, candidate policies can be sorted according to their policy scores from highest to lowest to obtain a sorting result, and the second preset number of candidate policies at the top of the sorting result can be determined as the target policies.

[0056] The number can be one or more, and there is no limit to this.

[0057] Step 207: Recommend the target policy to the target user.

[0058] In this application, step 207 can be implemented in any of the embodiments of this application, so it will not be described in detail here.

[0059] In this embodiment, by determining the matching degree between candidate policies and target attributes of the target user, and based on the similarity between the target user and similar users who have purchased candidate policies, and this matching degree, the policy score of the candidate policy is determined. Then, based on the policy score, the target policy is determined from the candidate policies. Therefore, by combining the similarity between the target user and similar users who have purchased candidate policies with the matching degree between the candidate policy and the target user's needs, policies to be recommended are filtered out, avoiding the recommendation of policies that do not meet the user's needs, thus improving the accuracy and personalization of policy recommendations.

[0060] Figure 3 This is a flowchart illustrating another policy recommendation method provided in an embodiment of this application.

[0061] like Figure 3 As shown, this policy recommendation method may include the following steps: At step 301, first portrait data of a target user and second portrait data of a candidate user are obtained.

[0062] In this application, step 301 can adopt any of the implementation manners of the embodiments of this application, and thus will not be described here.

[0063] At step 302, a second similarity between the policy-related behavior of the target user and the policy-related behavior of the candidate user is determined according to the policy-related behavior data of the target user in the first portrait data and the policy-related behavior data of the candidate user in the second portrait data.

[0064] In this application, the policy-related behavior data of the target user is included in the first portrait data, and the policy-related behavior data of the candidate user is included in the second portrait data. The policy-related behavior data of the target user and the policy-related behavior data of the candidate user can be respectively vectorized to obtain a policy behavior vector of the target user and a policy behavior vector of the candidate user. The second similarity between the policy-related behavior of the target user and the policy-related behavior of the candidate user is calculated according to the policy behavior vector of the target user and the policy behavior vector of the candidate user.

[0065] The second similarity can be used to represent the similarity between the policy-related behavior of the target user and the policy-related behavior of the candidate user.

[0066] For example, the policy behavior vector of the target user can be constructed according to the browsing times, the stay time, whether to collect, whether to consult, and the like of the target user. Similarly, the policy behavior vector of the candidate user can be constructed according to the browsing times, the stay time, whether to collect, whether to consult, and the like of the candidate user.

[0067] At step 303, a first similar user is determined from the candidate users according to the second similarity.

[0068] In some embodiments, the candidate users can be sorted in descending order of the second similarity, and the first similar user can be determined as the candidate users in the first preset number of the sorting results.

[0069] In some embodiments, the candidate user whose second similarity is greater than a preset threshold can be determined as the first similar user.

[0070] Since the information of age, occupation, etc. of the user can also affect the selection of the insurance policy, in some embodiments, according to the user feature data of the target user in the first portrait data and the user feature data of the candidate user in the second portrait data, a third similarity between the user basic features of the target user and the user basic features of the candidate user is determined, and according to the second similarity and the third similarity, a comprehensive similarity between the target user and the candidate user is determined, and then according to the comprehensive similarity, the first similar user is determined from the candidate user.

[0071] The third similarity can be used to represent the degree of similarity between the user basic features of the target user and the user basic features of the candidate user.

[0072] For example, the user feature data of the target user and the user feature data of the candidate user can be respectively vectorized to obtain the basic feature vector of the target user and the basic feature vector of the candidate user, and the third similarity can be calculated according to the basic feature vector of the target user and the basic feature vector of the candidate user.

[0073] For example, the user feature data can be vectorized by the following method: for the numerical features in the user feature data, standardization processing is performed, and for the gender, occupation, etc. in the user feature data, encoding processing is performed, and then all the features are combined into a feature vector, i.e. the basic feature vector, to represent the basic features of the user.

[0074] For example, the second similarity and the third similarity can be weighted to obtain the comprehensive similarity.

[0075] For example, the comprehensive similarity can be calculated by the following formula (2): (2) Wherein, represents the comprehensive similarity between the user and the user , the second similarity between the user and the user , and the third similarity between the user and the user . is a weight coefficient. . .

[0076] ​The fusion of the multi-dimensional data such as the policy-related behavior data and the user feature data can more comprehensively and deeply depict the user portrait, capture the potential needs and personalized features of the user, the policy-related behavior data reflects the insurance preferences and needs of the user, the user feature data provides the basic attributes and risk attitudes of the user, and the multiple data complement each other to provide rich information support for the accurate recommendation, and significantly improve the pertinence and effectiveness of the recommendation. In addition, the similarity between users is measured from two dimensions of user behavior and user features, which can more comprehensively and accurately capture the association relationship between users, the behavior similarity focuses on the actual interaction behavior of the user, the feature similarity focuses on the inherent attributes of the user, the weighted fusion of the two can give full play to their respective advantages, improve the accuracy and stability of the similarity calculation, and provide a reliable basis for the policy recommendation, and thus improve the quality and effect of the recommendation.

[0077] In step 304, a second similar user who has purchased the candidate policy is determined from the first similar users according to the policy purchase information of the first similar users.

[0078] In step 305, a target policy is determined from the candidate policies according to the first similarity between the target user and the second similar user, and the target policy is recommended to the target user.

[0079] In the present application, steps 304-305 can adopt any of the implementation manners of the embodiments of the present application, and thus will not be described herein.

[0080] In the embodiments of the present application, the second similarity between the policy-related behavior of the target user and the policy-related behavior of the candidate user is determined according to the policy-related behavior data of the target user in the first portrait data and the policy-related behavior data of the candidate user in the second portrait data, and the similar user similar to the target user is determined from the candidate users according to the second similarity. Thus, the policy-related behavior data reflects the insurance preferences and needs of the user, and the behavior data related to the policy of the target user and the candidate user can be used to filter the users similar to the target user in terms of policy needs, which can improve the filtering accuracy of the similar users, and then based on the filtered similar users, the policy recommendation can be made to the target user, which can improve the accuracy of the policy recommendation. In order to facilitate the user to understand and select the policy, in an embodiment of the present application, an interpretable recommendation reason can also be generated for the target policy, so as to be visually displayed to the target user together with the target policy.

[0081] For example, the recommendation explanation information can be generated according to one or more of the following: the user feature data of the third similar user who has purchased the target policy; the matching relationship between the user feature data of the target user and the applicable conditions of the target policy; and the matching between the risk tolerance of the target user and the risk level of the target policy.

[0082] The recommendation explanation information can include one or more of the following: a recommendation reason, a targeted explanation, and a matching explanation.

[0083] As an example, the user characteristics of a third similar user who has purchased the target policy among the first similar users of the target user can be analyzed, and common characteristics can be extracted as the recommendation reason.

[0084] As an example, the matching relationship between the user characteristic data of the target user, such as age, occupation, family status, and the applicable conditions of the target policy can be analyzed to generate a targeted explanation.

[0085] As an example, a matching explanation can be generated according to the matching between the risk tolerance of the target user and the risk level of the policy.

[0086] In the embodiments of the present application, one or more of the following can be used to generate the recommendation explanation information of the target policy: the user characteristic data of the similar user who has purchased the target policy, the matching relationship between the user characteristic data of the target user and the applicable conditions of the target policy, and the matching between the risk tolerance of the target user and the risk level of the target policy. The target policy can be displayed together with the target policy, which can provide a basis for the user to select a policy and improve the policy recommendation experience.

[0087] To achieve the above-mentioned embodiments, the present application further provides a policy recommendation device.

[0088] Figure 4 A structural schematic diagram of a policy recommendation device provided in the embodiments of the present application.

[0089] As shown in Figure 4 The policy recommendation device 400 includes: An acquisition module 410 is configured to acquire first portrait data of a target user and second portrait data of a candidate user. A first determination module 420 is configured to determine, according to the first portrait data and the second portrait data, a first similar user of the target user from the candidate user. A second determination module 430 is configured to determine, according to policy purchase information of the first similar user, a second similar user who has purchased the candidate policy among the first similar users. A recommendation module 440 is configured to determine a target policy from the candidate policy according to a first similarity between the target user and the second similar user, and recommend the target policy to the target user.

[0090] Further, in a possible implementation manner of the embodiments of the present application, the recommendation module 440 is configured to: determine a matching degree between the candidate policy and a target attribute of the target user. determine a policy score of the candidate policy according to the first similarity and the matching degree; determine the target policy from the candidate policies according to the policy score.

[0091] Further, in a possible implementation manner of the embodiment of the present application, the recommendation module 440 is configured to: determine an average value of the first similarity according to the number of the first similar users and the first similarity; weight the average value and the matching degree to obtain the policy score.

[0092] Further, in a possible implementation manner of the embodiment of the present application, the first determination module 420 is configured to: determine a second similarity between the policy-related behaviors of the target user and the policy-related behaviors of the candidate user according to the policy-related behavior data of the target user in the first portrait data and the policy-related behavior data of the candidate user in the second portrait data; determine the first similar user from the candidate users according to the second similarity.

[0093] Further, in a possible implementation manner of the embodiment of the present application, the first determination module 420 is configured to: determine a third similarity between the user basic features of the target user and the user basic features of the candidate user according to the user feature data in the first portrait data and the user feature data in the second portrait data; determine a comprehensive similarity between the target user and the candidate user according to the second similarity and the third similarity; determine the first similar user from the candidate users according to the comprehensive similarity.

[0094] Further, in a possible implementation manner of the embodiment of the present application, the device can further include: a generation module configured to generate recommendation explanation information of the target policy according to one or more of the following: user feature data of a third similar user who has purchased the target policy; a matching relationship between the user feature data of the target user and applicable conditions of the target policy; a matching situation between a risk bearing capacity of the target user and a risk level of the target policy.

[0095] It should be noted that the foregoing explanation and description of the policy recommendation method embodiment are also applicable to the policy recommendation device of the embodiment, which will not be described here again.

[0096] In the embodiments of the present application, the first similar user similar to the target user is determined from the candidate users according to the first portrait data of the target user and the portrait data of the candidate users, and the second similar user who has purchased the candidate insurance policy is determined from the first similar user according to the purchase information of the first similar user, and the target insurance policy is determined from the candidate insurance policy according to the similarity between the target user and the second similar user, and the target insurance policy is recommended to the target user. Thus, the first similar user of the target user is determined according to the portrait data between the target user and the candidate user, which can improve the accuracy of the similar user. On the basis of the first similar user, the second similar user who has purchased the candidate insurance policy is further screened out according to the purchase information of the first similar user, and the insurance policy to be recommended is determined from the candidate insurance policy according to the similarity between the second similar user and the target user, so that the recommended insurance policy is more in line with the potential needs of the target user, and the accuracy of the recommendation is greatly improved.

[0097] In order to realize the above-mentioned embodiments, the present application further provides an electronic device, comprising: a processor and a memory connected with the processor in communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to realize the method provided by the foregoing embodiments. In order to realize the above-mentioned embodiments, the present application further provides a computer readable storage medium, the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to realize the method provided by the foregoing embodiments.

[0098] In order to realize the above-mentioned embodiments, the present application further provides a computer program product, comprising a computer program, which is executed by the processor to realize the method provided by the foregoing embodiments.

[0099] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the present application comply with relevant laws and regulations and do not violate public order and good customs.

[0100] It should be noted that the personal information from the user should be collected for legal and reasonable purposes, and should not be shared or sold outside these legal uses. In addition, such collection / sharing should be carried out after the user's informed consent, including but not limited to informing the user to read the user agreement / user notice before the user uses the function, and signing the agreement / authorization including authorization of relevant user information. In addition, any necessary steps should be taken to protect and ensure access to such personal information data, and to ensure that other people with access to personal information data comply with their privacy policy and processes.

[0101] The present application contemplates an implementation that provides users with the ability to selectively opt in or opt out of permitting the collection and / or use of their personal information data. That is, the present disclosure contemplates providing users with the ability to prevent or limit the collection and / or use of their personal information data. For example, the present disclosure contemplates providing users with the ability to prevent or limit the collection and / or use of their personal information data by, for example, blocking or deleting cookies. In addition, the present disclosure contemplates providing users with the ability to determine whether and how to interact with the present disclosure by, for example, blocking web beacons. Further, the present disclosure contemplates providing users with the ability to access and / or edit their personal information data when such data is collected by the present disclosure. In addition, the present disclosure contemplates that the collection and / or use of personal information data can be limited to only those users who expressly consent or give permission to the collection and / or use of their personal information data.

[0102] In the foregoing detailed description, the description used with respect to the terms "one embodiment", "some embodiments”, "an example”, "a specific example” or "some examples” etc. means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. Illustrative appearances of the above terms in the description are not necessarily referred to the same embodiment or example. Moreover, the particular features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. Furthermore, in non-contradictory cases, those skilled in the art can combine and combine the features described in different embodiments or examples and the features of different embodiments or examples in the present application.

[0103] In addition, the terms "first", "second", etc. are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically limited.

[0104] Any process or method descriptions or descriptions of the flow diagrams in the present application can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions (or steps) in the process, and the preferred embodiments of the present application include additional implementations in which the order of the steps can be different, including the steps can be performed in substantially simultaneous with one another, or in reverse order, depending upon the functionality involved. Such descriptions and representations are used by those skilled in the art of software manufacture to most effectively convey the substance of their work to others skilled in the art.

[0105] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination thereof. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer readable medium can specifically include the following, which are non-exhaustive list: electrical connection (electrical device), portable computer diskette (magnetic device), Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM or Flash memory), optical fiber device, and portable compact disc read-only memory (CDROM). Additionally, the computer readable medium can even be paper or other suitable medium upon which the program is printed, as the program can be electronically captured, for example, by optically scanning the paper or other suitable medium, then electronically converted into a form that can be further processed by a computer based system into an electronically accessible form in computer memory.

[0106] It should be understood that portions of the present application can be realized by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if realized by hardware, as in another embodiment, any one or a combination of the following technologies known in the art can be used: discrete logic circuit having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0107] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing relevant hardware, and the programs can be stored in a computer readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0108] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0109] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for recommending insurance policies, characterized in that, include: Obtain the first profile data of the target user and the second profile data of the candidate user; Based on the first profile data and the second profile data, determine the first similar user of the target user from the candidate users; Based on the policy purchase information of the first similar user, a second similar user who has purchased the candidate policy is identified among the first similar users; Based on the first similarity between the target user and the second similar user, a target policy is determined from the candidate policies and recommended to the target user.

2. The method according to claim 1, characterized in that, The step of determining the target policy from the candidate policies based on the first similarity between the target user and the second similar user includes: Determine the degree of matching between the candidate insurance policy and the target attributes of the target user; The policy score of the candidate policy is determined based on the first similarity and the matching degree. The target policy is determined from the candidate policies based on the policy score.

3. The method according to claim 2, characterized in that, The step of determining the policy score of the candidate policy based on the first similarity and the matching degree includes: Based on the number of the second similar users and the first similarity, determine the average value of the first similarity; The policy score is obtained by weighting the average value and the matching degree.

4. The method according to claim 1, characterized in that, The step of determining the first similar user of the target user from the candidate users based on the first profile data and the second profile data includes: Based on the policy-related behavior data of the target user in the first profile data and the policy-related behavior data of the candidate user in the second profile data, a second similarity between the policy-related behavior of the target user and the policy-related behavior of the candidate user is determined. The first similar user is determined from the candidate users based on the second similarity.

5. The method according to claim 4, characterized in that, The step of determining the first similar user from the candidate users based on the second similarity includes: Based on the user feature data in the first profile data and the user feature data in the second profile data, a third similarity between the basic user features of the target user and the user feature-based similarity of the candidate user is determined. Based on the second similarity and the third similarity, a comprehensive similarity between the target user and the candidate user is determined; Based on the comprehensive similarity, the first similar user is determined from the candidate users.

6. The method according to any one of claims 1-5, characterized in that, Also includes: Generate recommended explanation information for the target policy based on one or more of the following: User characteristic data of a third similar user who has purchased the target policy; The matching relationship between the user characteristic data of the target user and the applicable conditions of the target insurance policy; The matching between the target user's risk tolerance and the risk level of the target policy.

7. A policy recommendation device, characterized in that, include: The acquisition module is used to acquire the first profile data of the target user and the second profile data of the candidate user. The first determining module is used to determine a first similar user of the target user from the candidate users based on the first profile data and the second profile data; The second determining module is used to determine, based on the policy purchase information of the first similar user, a second similar user who has purchased the candidate policy among the first similar users; The recommendation module is used to determine a target insurance policy from the candidate policies based on the first similarity between the target user and the second similar user, and recommend the target insurance policy to the target user.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images