Product recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a 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 target user information and original bill information of a target object; performing source priority division on the original bill information to obtain original sub-bills with bill priority levels; determining target family relationship information of the target object according to the original sub-bills; performing network construction based on the bill priority level, the target user information and the target family relationship information to obtain a target family relationship network; and determining a target recommended product according to the target family relationship network. According to the embodiment of the invention, the target family relationship network of the target object can be accurately constructed, and the products more suitable for the target object and family members thereof are determined based on the target family relationship network, so that personalized and efficient product recommendation is realized, and the accuracy of 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 particularly relates to a product recommendation method and device, electronic equipment, and storage medium. Background Art

[0002] In the field of intelligent recommendation, corresponding content can be recommended to users based on their preferences, including recommended articles, videos, products, etc. For example, in financial scenarios, business personnel can recommend financial products based on customers' personal preferences. However, in actual application scenarios, it is impossible to accurately understand customers' needs based solely on their personal preferences, which affects the accuracy of product recommendations.

[0003] Therefore, how to improve the accuracy of 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 a product recommendation method and device, an electronic device and a storage medium, aiming to improve the accuracy of product recommendations.

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

[0006] Obtain the target user information and original billing information of the target object;

[0007] The original bill information is divided into source priorities to obtain original sub-bills with bill priority levels;

[0008] Determining target family relationship information of the target object according to the original sub-bill;

[0009] Based on the bill priority level, the target user information and the target family relationship information, a network is constructed to obtain a target family relationship network;

[0010] Determine target recommended products based on the target family relationship network.

[0011] In some embodiments, determining the target family relationship information of the target object according to the original sub-bill includes:

[0012] Determining the family relationship type according to a preset family relationship information table; wherein the family relationship information table records at least two preset family relationship types;

[0013] Filtering the original sub-bills according to the family relationship type to obtain current query bill information;

[0014] Extracting user information from the current queried bill information to obtain original household user information;

[0015] The original family user information is screened to obtain the target family relationship information.

[0016] In some embodiments, the target family relationship information includes at least a plurality of sub-family relationship information including a time attribute, each sub-family relationship information corresponds to one of the family relationship types; and the network construction based on the bill priority level, the target user information and the target family relationship information to obtain the target family relationship network includes:

[0017] Combining family relationships based on the sub-family relationship information and the target user information to obtain an original family relationship network;

[0018] Performing weighted calculation on the original family relationship network based on the preset family relationship weight, the time attribute and the bill priority level to obtain weighted data of the family relationship network;

[0019] Based on the weighted data of the family relationship network, data with the largest weight value is screened out from the original family relationship network to obtain the target family relationship network.

[0020] In some embodiments, the filtering of the original family user information to obtain the target family relationship information includes:

[0021] If the family relationship type is a spousal relationship, obtaining the spouse identity information from the original family user information;

[0022] Acquire target object gender information from the target user information;

[0023] Determine the gender of the target spouse based on the gender information of the target object;

[0024] Calculate the spouse's age based on the spouse's identity information to obtain original spouse's age data;

[0025] The original family user information is screened based on the target spouse's gender and the original spouse's age data to obtain target spouse information, and the target spouse information is used as the target family relationship information.

[0026] In some embodiments, the filtering of the original family user information to obtain the target family relationship information includes:

[0027] If the family relationship type is a parent relationship, obtaining parent identity information from the original family user information;

[0028] Acquire target object identity information from the target user information;

[0029] Calculate the parents' age based on the parents' identity information to obtain original parents' age data;

[0030] Performing compliance verification on the original parent age data based on a preset childbearing age threshold and the target object identity information to obtain parent identity compliance verification data;

[0031] The original family user information is screened based on the parent identity compliance verification data to obtain target parent information, and the target parent information is used as the target family relationship information.

[0032] In some embodiments, the filtering of the original family user information to obtain the target family relationship information further includes:

[0033] If the family relationship type is a child relationship, obtaining the child identity information from the original family user information;

[0034] Calculate the age of the child based on the child's identity information to obtain the child's age data;

[0035] Performing compliance verification on the child age data based on the childbearing age threshold and the target object identity information to obtain child age compliance verification data;

[0036] The original family user information is screened based on the child age compliance verification data to obtain target child information, and the target child information is used as the target family relationship information.

[0037] In some embodiments, the original bill information includes a plurality of original sub-bills, and the step of dividing the original bill information by source priority to obtain original sub-bills with bill priority levels includes:

[0038] Perform source analysis on each of the original sub-bills to obtain the source information of the original sub-bill;

[0039] The original sub-bills are prioritized based on a preset source priority mapping table and the original sub-bill source information to obtain the bill priority level.

[0040] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a product recommendation device, the device comprising:

[0041] User information acquisition module, used to obtain target user information and original billing information of the target object;

[0042] A priority classification module, used to classify the source priority of the original bill information to obtain an original sub-bill with a bill priority level;

[0043] A family relationship determination module, configured to determine target family relationship information of the target object according to the original sub-bill;

[0044] A network construction module, configured to construct a network based on the bill priority level, the target user information and the target family relationship information to obtain a target family relationship network;

[0045] The target recommendation module is used to determine the target recommended products according to the target family relationship network.

[0046] 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.

[0047] 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.

[0048] The product recommendation method and device, electronic device and storage medium proposed in the present application obtain the target user information and original bill information of the target object, and classify the source priority of the original bill information to obtain the original sub-bill with the bill priority level, so as to determine the target family relationship information of the target object according to the original sub-bill; construct a network based on the bill priority level, target user information and target family relationship information to obtain the target family relationship network, thereby improving the efficiency and accuracy of family relationship network construction; and then can determine the products that are more suitable for the target object and its family members according to the target family relationship network, thereby realizing personalized and efficient product recommendations and improving the accuracy of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of a product recommendation method provided in an embodiment of the present application;

[0050] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0051] Figure 3 yes Figure 1 Flow chart of step S103 in FIG.

[0052] Figure 4 yes Figure 3 A flowchart of step S304 in FIG.

[0053] Figure 5 yes Figure 3Another flowchart of step S304 in;

[0054] Figure 6 yes Figure 3 Another flowchart of step S304 in;

[0055] Figure 7 yes Figure 1 Flow chart of step S104 in FIG.

[0056] Figure 8 is a schematic diagram of the structure of a product recommendation device provided in an embodiment of the present application;

[0057] 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

[0058] 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.

[0059] 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.

[0060] 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.

[0061] First, some nouns involved in this application are analyzed:

[0062] 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.

[0063] Family relationship network refers to a series of interrelated and interactive social connections between members of a family unit based on marriage, blood, adoption or legal relationship. This network not only covers the close relationship between direct relatives, such as the relationship between parents and children, and between husband and wife, but also includes the relationship between collateral relatives and other family members who join through legal means such as marriage.

[0064] In the field of intelligent recommendation, corresponding content can be recommended to users based on their preferences, including recommended articles, videos, products, etc. For example, in financial scenarios, business personnel can recommend financial products based on customers' personal preferences.

[0065] However, in actual application scenarios, it is impossible to accurately understand the customer's needs based solely on the customer's personal preferences. In addition to personal needs, there may also be needs of family members. Therefore, it is impossible to accurately recommend suitable products to customers, which affects the accuracy of product recommendations.

[0066] Based on this, the embodiments of the present application provide a product recommendation method and device, an electronic device and a storage medium, aiming to improve the accuracy of product recommendations.

[0067] The 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 product recommendation method in the embodiments of the present application is described.

[0068] 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.

[0069] 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.

[0070] The product recommendation method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The product recommendation method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the 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 it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as 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 product recommendation method, etc., but is not limited to the above forms.

[0071] 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.

[0072] 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.

[0073] Figure 1 is an optional flowchart of the 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 S105.

[0074] Step S101, obtaining target user information and original billing information of the target object;

[0075] Step S102, dividing the original bill information into source priorities to obtain original sub-bills with bill priority levels;

[0076] Step S103, determining the target family relationship information of the target object according to the original sub-bill;

[0077] Step S104, constructing a network based on the bill priority level, target user information and target family relationship information to obtain a target family relationship network;

[0078] Step S105, determining target recommended products according to the target family relationship network.

[0079] In steps S101 to S105 shown in the embodiment of the present application, the target user information and original bill information of the target object are obtained, and the original bill information is divided into source priority levels to obtain the original sub-bill with a bill priority level, thereby determining the target family relationship information of the target object according to the original sub-bill; a network is constructed based on the bill priority level, the target user information and the target family relationship information to obtain a target family relationship network, thereby improving the efficiency and accuracy of family relationship network construction; and more products suitable for the target object and its family members can be recommended based on the target family relationship network, thereby achieving personalized and efficient product recommendations and improving the accuracy of product recommendations.

[0080] In step S101 of some embodiments, the target user information is the personal information of the target object, which may include but is not limited to: the target object's name information, the target object's gender information, the target object's identity information, etc., which needs to be set according to the actual application scenario and is not limited thereto.

[0081] The original bill information is the bill paid by the target object, which includes multiple original sub-bills.

[0082] For example:

[0083] The target's bill for the accident insurance product he / she purchased for himself / herself;

[0084] The target is the bill for the accident insurance product purchased for the spouse;

[0085] The target is the bill for the vehicle insurance product purchased by the spouse;

[0086] The target's bills for health insurance products purchased for their children;

[0087] The target audience is the bills for health insurance products purchased by parents;

[0088] The target audience is the bills for annuity insurance products purchased by parents;

[0089] These bills can be used to obtain relevant information about the target's family members and family relationships, so that an accurate target family relationship network can be constructed.

[0090] See also Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S202:

[0091] Step S201, performing source analysis on each original sub-bill to obtain the original sub-bill source information;

[0092] Step S202: Prioritize the original sub-bills based on the preset source priority mapping table and the original sub-bill source information to obtain a bill priority level.

[0093] In steps S201 to S202 shown in the embodiment of the present application, the bill information of family members is obtained according to the bill priority level by performing source parsing on each original sub-bill in the original bill information and prioritizing these sub-bills based on a preset source priority mapping table, thereby ensuring the accuracy of constructing the family relationship network and providing accurate data support for subsequent product recommendations based on the family relationship network.

[0094] In step S201 of some embodiments, each original sub-bill has its corresponding source, for example:

[0095] The target object is the bill for the accident insurance product purchased by the spouse, which comes from the accident insurance product platform;

[0096] The target object is the bill for the vehicle insurance product purchased by the spouse, which comes from the vehicle insurance product platform;

[0097] The target object is the bill for purchasing health insurance products for children, which comes from the health insurance product platform.

[0098] In step S202 of some embodiments, the preset source priority mapping table is pre-calibrated by technical personnel / business personnel according to actual application scenarios, and is used to assign different bill priority levels to bills from different sources. For example:

[0099] For bills from the health insurance product platform, the priority level can be set to the first bill priority level;

[0100] For bills from the accident insurance product platform, the priority level can be set to the second bill priority level;

[0101] For bills from the vehicle insurance product platform, the priority level can be set to the third bill priority level;

[0102] Among them, the priority order is: the first bill priority level is higher than the second bill priority level, and the second bill priority level is higher than the third bill priority level.

[0103] See also Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S304:

[0104] Step S301, determining a family relationship type according to a preset family relationship information table; wherein the family relationship information table records at least two preset family relationship types;

[0105] Step S302, filtering the original sub-bills according to the family relationship type to obtain the current queried bill information;

[0106] Step S303, extracting user information from the current queried bill information to obtain original household user information;

[0107] Step S304, screening the original family user information to obtain target family relationship information.

[0108] In steps S301 to S304 shown in the embodiment of the present application, the current query bill information, i.e., the relevant bills corresponding to the family relationship type, are obtained by filtering from the original sub-bill according to the family relationship type recorded in the preset family relationship information table, user information is extracted from the current query bill information to obtain the original family user information, and finally the original family user information is filtered to obtain the target family relationship information. This can efficiently and accurately extract the information corresponding to each family relationship type, which is conducive to improving the accuracy of constructing the family relationship network.

[0109] In step S301 of some embodiments, the preset family relationship information table is pre-calibrated by technical personnel / business personnel according to the actual application scenario, and is used to filter out different family relationship information. Specifically, the family relationship information table may include but is not limited to: spouse relationship, parent relationship, child relationship, collateral blood relationship, etc., but is not limited thereto.

[0110] It is understandable that, since it is uncertain which family relationship types are included in the original sub-bill in the original bill information, it is necessary to filter the original sub-bill according to each family relationship type in the family relationship information table in order to accurately extract the family relationship information.

[0111] In step S302 of some embodiments, the current queried bill information is obtained by filtering from the original sub-bills according to the family relationship type, thereby narrowing the scope of information data processing and improving the efficiency of family relationship extraction.

[0112] In some embodiments, if the target object is a male and the family relationship type is a spousal relationship, it is necessary to filter out the relevant bills of women from the original sub-bill to obtain the current query bill information;

[0113] If the family relationship type is a child relationship, you need to filter out the relevant bills whose age is younger than the target object from the original sub-bill to obtain the current query bill information;

[0114] If the family relationship type is parent-child relationship, it is necessary to filter out the relevant bills whose age is greater than the target object's age from the original sub-bill to obtain the current query bill information;

[0115] In step S303 of some embodiments, user-related information is extracted from the current queried bill information to obtain original household user information. Specifically, the original household user information may include, but is not limited to: gender information, identity identification information, consumed financial products, etc., and needs to be set in combination with the actual application scenario, but is not limited to this.

[0116] It should be noted that the number of original family user information can be zero (no relevant family relationship information is found), one or more.

[0117] See also Figure 4 In some embodiments, step S304 may include but is not limited to steps S401 to S405:

[0118] Step S401, if the family relationship type is a spouse relationship, obtain spouse identity information from the original family user information;

[0119] Step S402, obtaining target object gender information from target user information;

[0120] Step S403, determining the gender of the target spouse based on the gender information of the target object;

[0121] Step S404, calculating the spouse's age based on the spouse's identity information to obtain original spouse's age data;

[0122] Step S405, filtering the original family user information based on the target spouse's gender and the original spouse's age data to obtain the target spouse information, and using the target spouse information as the target family relationship information.

[0123] In steps S401 to S405 shown in the embodiment of the present application, if the family relationship type is a spouse relationship, the spouse identity information is obtained from the original family user information, and the original spouse age data is calculated based on the spouse identity information, and the target spouse gender is determined based on the target user information. This allows the target spouse information that is in a spouse relationship with the target object to be accurately screened out from the original family user information based on the target spouse gender and the original spouse age data, which helps to improve the accuracy of constructing the family relationship network and provides accurate data support for subsequent product recommendations based on the family relationship network.

[0124] In step S401 of some embodiments, if the family relationship type is a spouse relationship and the number of original family user information is not zero, the spouse identity information is obtained from the original family user information, wherein the spouse identity information is used to identify the identity of the spouse, and may be an ID number or a registered date of birth, etc., but is not limited thereto.

[0125] At the same time, the target object's gender information, that is, the target object's gender information, is obtained from the target user information, and the target spouse's gender is determined based on the target object's gender information;

[0126] For example: in the case of a spouse of the opposite sex, if the target object is male, the target spouse is female; if the target object is female, the target spouse is male.

[0127] In step S404 of some embodiments, the current time is obtained, and the age is calculated based on the current time and the spouse's identity information to obtain the original spouse's age data.

[0128] In some embodiments, step S405 may include but is not limited to the following steps:

[0129] Based on the gender of the target spouse, the original family user information is screened by gender to obtain initial spouse information;

[0130] The initial spouse information is screened based on a preset first age threshold and the original spouse age data to obtain target spouse information, and the target spouse information is used as target family relationship information.

[0131] Among them, the preset first age threshold is used to determine whether one is an adult. If one is a minor, he or she cannot become a spouse.

[0132] See also Figure 5 In some embodiments, step S304 may also include but is not limited to steps S501 to S505:

[0133] Step S501, if the family relationship type is a parent relationship, obtain the parent identity information from the original family user information;

[0134] Step S502, obtaining target object identity information from target user information;

[0135] Step S503, calculating the parents' ages based on the parents' identity identification information to obtain original parents' age data;

[0136] Step S504, performing compliance verification on the original parent age data based on the preset childbearing age threshold and the target object identity identification information to obtain parent identity compliance verification data;

[0137] Step S505, screening the original family user information based on the parent identity compliance verification data, obtaining the target parent information, and using the target parent information as the target family relationship information.

[0138] In steps S501 to S505 shown in the embodiment of the present application, if the family relationship type is a parent-child relationship, the parent identity information is obtained from the original family user information, and the original parent age data is calculated based on the parent identity information; the original parent age data is verified for compliance based on a preset childbearing age threshold and the target object identity information to obtain parent identity compliance verification data, and then the original family user information is screened based on the parent identity compliance verification data to obtain the target parent information, which helps to improve the accuracy of constructing the family relationship network and provides accurate data support for subsequent product recommendations based on the family relationship network.

[0139] In step S501 of some embodiments, if the family relationship type is a parent-child relationship and the number of original family user information is not zero, the parent identification information is obtained from the original family user information, wherein the parent identification information is used to identify the identity of the parents, and may be an ID number or a registered date of birth, etc., but is not limited thereto.

[0140] In step S502 of some embodiments, the target object identity information is used to identify the identity of the target object, and may be the target object's ID number or registered date of birth, etc., but is not limited thereto.

[0141] In step S503 of some embodiments, the current time is obtained, and the age is calculated based on the current time and the parent identification information to obtain the original parent age data.

[0142] It should be noted that the preset childbearing age threshold is used to determine whether childbearing occurs within the preset age. If childbearing occurs within the preset age, it is not considered that a parental relationship exists.

[0143] In some embodiments, step S504 may include but is not limited to the following steps:

[0144] Calculate the age of the target object based on the identity information of the target object to obtain the age data of the target object;

[0145] Aggregate and calculate the original parents' age data and the target object's age data to obtain the first age difference data;

[0146] The preset childbearing age threshold is compared with the first age difference data to obtain parental identity compliance verification data.

[0147] Specifically,

[0148] If the parent identity compliance verification data indicates that the parent identity is not compliant, the corresponding situation is: the birth age threshold is set to be greater than the first age difference data, which means that it does not belong to the parent relationship;

[0149] If the parent identity compliance verification data indicates that the parent identity is compliant, the corresponding situation is: the birth age threshold is set to be less than or equal to the first age difference data, which means that it is a parent relationship;

[0150] Therefore, the original family user information can be screened based on the parent identity compliance verification data to obtain the target parent information, and the target parent information can be used as the target family relationship information.

[0151] See also Figure 6 In some embodiments, step S304 may also include but is not limited to steps S601 to S604:

[0152] Step S601, if the family relationship type is a child relationship, obtain the child identity information from the original family user information;

[0153] Step S602, calculating the age of the child based on the child's identity information to obtain the child's age data;

[0154] Step S603, verifying the compliance of the child's age data based on the childbearing age threshold and the target object's identity information, and obtaining the child's age compliance verification data;

[0155] Step S604, screening the original family user information based on the children's age compliance verification data to obtain target children's information, and using the target children's information as target family relationship information.

[0156] In steps S601 to S604 shown in the embodiment of the present application, if the family relationship type is a child relationship, the child identity information is obtained from the original family user information, and the child age data is calculated based on the child identity information; the age of the child identity information is calculated to obtain the child age data; the original family user information is screened based on the child age compliance verification data to obtain the target child information, which helps to improve the accuracy of the construction of the family relationship network and provides accurate data support for subsequent product recommendations based on the family relationship network.

[0157] In step S601 of some embodiments, if the family relationship type is a child relationship and the number of original family user information is not zero, the child identity information is obtained from the original family user information, wherein the child identity information is used to identify the identity of the child, and may be an ID number or a registered date of birth, etc., but is not limited thereto.

[0158] In step S602 of some embodiments, the current time is obtained, and the age is calculated based on the current time and the child's identity information to obtain the child's age data.

[0159] In some embodiments, step S603 may include but is not limited to the following steps:

[0160] Calculate the age of the target object based on the identity information of the target object to obtain the age data of the target object;

[0161] Aggregate and calculate the children's age data and the target object's age data to obtain the second age difference data;

[0162] The preset childbearing age threshold is compared with the second age difference data to obtain the child's age compliance verification data.

[0163] Specifically,

[0164] If the child age compliance verification data indicates that the child identity is not compliant, the corresponding situation is: the set birth age threshold is greater than the second age difference data, which means that it does not belong to the child relationship;

[0165] If the child age compliance verification data indicates that the child identity is compliant, the corresponding situation is: the set birth age threshold is less than or equal to the second age difference data, which means that it is a child relationship;

[0166] Therefore, the original family user information can be screened based on the children's age compliance verification data to obtain the target child information, and the target child information can be used as the target family relationship information.

[0167] In some embodiments, step S304 may also include but is not limited to the following steps:

[0168] If the family relationship type is a collateral relative relationship, obtain the relative identity information from the original family user information;

[0169] Calculate the age based on the relative identification information to obtain the original relative age data;

[0170] Based on the preset childbearing age threshold and the original parents' age data, the original relative age data is verified for compliance to obtain the relative identity compliance verification data;

[0171] The original family user information is screened based on the relative identity compliance verification data to obtain the target relative information, and the target relative information is used as the target family relationship information.

[0172] Specifically, the step of "verifying the compliance of the original relative age data based on the preset childbearing age threshold and the original parent age data to obtain the relative identity compliance verification data" may include but is not limited to the following steps:

[0173] Aggregate the original parents' age data and the original relatives' age data to obtain the third age difference data;

[0174] Compare the preset childbearing age threshold with the third age difference data to obtain the relative identity compliance verification data.

[0175] If the kinship compliance verification data indicates that the kinship is not compliant, the corresponding situation is: the birth age threshold is greater than the third age difference data, which means that it is not a collateral relative relationship;

[0176] If the kinship compliance verification data indicates that the kinship is compliant, the corresponding situation is: the birth age threshold is less than or equal to the third age difference data, which means that it is a collateral relative relationship;

[0177] Therefore, the original family user information can be screened based on the relative identity compliance verification data to obtain the target relative information, and the target relative information can be used as the target family relationship information.

[0178] It should be noted that the target family relationship information includes at least a plurality of sub-family relationship information containing time attributes, and each sub-family relationship information corresponds to a family relationship type;

[0179] It should be noted that the time attribute of the sub-family relationship information corresponds to the time attribute of the original sub-bill.

[0180] See also Figure 7 In some embodiments, step S104 may include but is not limited to steps S701 to S703:

[0181] Step S701, combining family relationships based on the sub-family relationship information and the target user information to obtain an original family relationship network;

[0182] Step S702, performing weighted calculation on the original family relationship network based on preset family relationship weights, time attributes and bill priority levels to obtain weighted family relationship network data;

[0183] Step S703, based on the weighted data of the family relationship network, the data with the largest weight value is screened out from the original family relationship network to obtain the target family relationship network.

[0184] Steps S701 to S703 shown in the embodiment of the present application are to obtain weighted data of the family relationship network by combining the sub-family relationship information and the target user information, and performing weighted calculation on the original family relationship network based on the preset family relationship weights, time attributes and bill priority levels. Finally, based on the weighted data of the family relationship network, the data with the largest weight value is screened out from the original family relationship network to obtain the target family relationship network, which helps to improve the accuracy of the construction of the family relationship network and provides accurate data support for subsequent product recommendations based on the family relationship network.

[0185] It can be understood that the target family relationship information includes at least one sub-family relationship information corresponding to the family relationship type, namely, the target spouse information, the target parent information, the target child information and the target relative information, and each sub-family relationship information may contain multiple data. Therefore, the family relationship combination based on the sub-family relationship information and the target user information can be performed to obtain at least one original family relationship network;

[0186] For each original family network, each original family relationship network can be sorted by weighted calculation to screen out the target family relationship network.

[0187] In one embodiment, the preset family relationship weights may include bill priority weights, spouse age difference weights, relative age difference weights, and bill generation time weights, and the bill generation time weights of the family relationship information correspond to the bill generation time weights of the original sub-bill.

[0188] For example:

[0189] For bill priority weights:

[0190] If the bill priority is the first bill priority, the bill priority weight is set to A1;

[0191] If the bill priority level is the second bill priority level, the bill priority level weight is set to A2;

[0192] If the bill priority level is the third bill priority level, the bill priority level weight is set to A3;

[0193] Weight for spouse age difference:

[0194] If the age difference between the target and the spouse is within 10 years, the weight of the spouse age difference is set to B1;

[0195] If the age difference between the target and the spouse is 10 to 20 years, the weight of the spouse age difference is set to B2;

[0196] If the age difference between the target and the spouse is greater than 20 years, the spouse age difference weight is set to B3;

[0197] For the relative age difference weight:

[0198] If the age difference between the target subject and the collateral relative is within 10 years, the relative age difference weight is set to C1;

[0199] If the age difference between the target subject and the collateral relative is 10 to 20 years, the relative age difference weight is set to C2;

[0200] If the age difference between the target subject and the collateral relative is greater than 20 years, the relative age difference weight is set to C3;

[0201] Weight for bill generation time:

[0202] If the time attribute shows that the bill was generated within the past three months, the weight of the bill generation time is set to D1;

[0203] If the bill generation time is within the last 3 to 6 months, the weight of the bill generation time is set to D2;

[0204] If the bill generation time is more than 6 months based on the time attribute, the bill generation time weight is set to D3;

[0205] Finally, the weight ratios of the bill priority level weight, the spouse age difference weight, the relative age difference weight, and the bill generation time weight are set to preset ratios, such as 40%, 15%, 15%, and 30%, and then weighted calculations are performed to obtain weighted data of the family relationship network, namely:

[0206] Weighted data of family relationship network = 40%*weight of bill priority level + 15%*weight of spouse's age difference + 15%*weight of relative's age difference + 30%*weight of bill generation time;

[0207] In step S703 of some embodiments, data with the largest weight value is screened out from the weighted data of the family relationship network, and a corresponding network is acquired from the original family relationship network to obtain a target family relationship network.

[0208] In step S105 of some embodiments, suitable products are screened out from a preset product database for each family member based on the family members recorded in the target family relationship network, and finally highly targeted target recommended products are formed, wherein the target recommended products include at least one product.

[0209] Specifically, the preset product database needs to be set up in combination with the application scenario and includes various types of products. For example, in the financial field, the product database includes but is not limited to accident insurance products, vehicle insurance products, health insurance products, annuity insurance products, etc.

[0210] After step S105 in some embodiments, the product recommendation method may further include but is not limited to the following steps:

[0211] Recommend products based on goals Make product recommendations to target objects.

[0212] Among them, product recommendations can be achieved through intelligent outbound calls, manual outbound calls, SMS push, etc., but are not limited to these.

[0213] The product recommendation method and device, electronic device and storage medium provided in the embodiments of the present application can, after generating a target family relationship network, perform customer analysis based on the target family relationship network to achieve accurate customer marketing, so that enterprises can better understand the customer's family member relationships, family member preferences, consumption preferences, consumption habits and consumption behaviors, and truly provide customers with the products and services they need, reduce disturbances to customers, and better improve marketing effectiveness, enhance customer stickiness, reduce corporate marketing costs, and enhance the company's brand image and reputation.

[0214] See also Figure 8 The embodiment of the present application also provides a product recommendation device, which can implement the above-mentioned product recommendation method, and the device includes:

[0215] User information acquisition module 801, used to acquire target user information and original billing information of the target object;

[0216] The priority classification module 802 is used to classify the source priority of the original bill information to obtain the original sub-bill with the bill priority level;

[0217] A family relationship determination module 803, used to determine the target family relationship information of the target object according to the original sub-bill;

[0218] A network construction module 804 is used to construct a network based on the bill priority level, the target user information and the target family relationship information to obtain a target family relationship network;

[0219] The target recommendation module 805 is used to determine target recommended products according to the target family relationship network.

[0220] The specific implementation of the product recommendation device is basically the same as the specific implementation of the above-mentioned product recommendation method, and will not be repeated here.

[0221] 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 product recommendation method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0222] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0223] 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;

[0224] 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 applications. 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 product recommendation method of the embodiment of this application;

[0225] Input / output interface 903, used to implement information input and output;

[0226] 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.);

[0227] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0228] 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 .

[0229] 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 product recommendation method is implemented.

[0230] 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.

[0231] The product recommendation method and device, electronic device and storage medium provided in the embodiments of the present application obtain the target user information and original bill information of the target object, and classify the source priority of the original bill information to obtain the original sub-bill with the bill priority level, so as to determine the target family relationship information of the target object according to the original sub-bill; construct a network based on the bill priority level, the target user information and the target family relationship information to obtain the target family relationship network, thereby improving the efficiency and accuracy of the family relationship network construction; and then can recommend products that are more suitable for the target object and its family members according to the target family relationship network, thereby realizing personalized and efficient product recommendations and improving the accuracy of product recommendations.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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, 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.

[0242] 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 product recommendation method, characterized in that: The method comprises: Obtain the target user information and original billing information of the target object; The original bill information is divided into source priorities to obtain original sub-bills with bill priority levels; Determining target family relationship information of the target object according to the original sub-bill; Based on the bill priority level, the target user information and the target family relationship information, a network is constructed to obtain a target family relationship network; Determine target recommended products based on the target family relationship network.

2. The method according to claim 1, characterized in that: The step of determining the target family relationship information of the target object according to the original sub-bill includes: Determining the family relationship type according to a preset family relationship information table; wherein the family relationship information table records at least two preset family relationship types; Filtering the original sub-bills according to the family relationship type to obtain current query bill information; Extracting user information from the current queried bill information to obtain original household user information; The original family user information is screened to obtain the target family relationship information.

3. The method according to claim 2, characterized in that The target family relationship information includes at least a plurality of sub-family relationship information containing a time attribute, each of the sub-family relationship information corresponds to one of the family relationship types; The network construction based on the bill priority level, the target user information and the target family relationship information to obtain the target family relationship network includes: Combining family relationships based on the sub-family relationship information and the target user information to obtain an original family relationship network; Performing weighted calculation on the original family relationship network based on the preset family relationship weight, the time attribute and the bill priority level to obtain weighted data of the family relationship network; Based on the weighted data of the family relationship network, data with the largest weight value is screened out from the original family relationship network to obtain the target family relationship network.

4. The method according to claim 2, characterized in that: The filtering of the original family user information to obtain the target family relationship information includes: If the family relationship type is a spousal relationship, obtaining the spouse identity information from the original family user information; Acquire target object gender information from the target user information; Determine the gender of the target spouse based on the gender information of the target object; Calculate the spouse's age based on the spouse's identity information to obtain original spouse's age data; The original family user information is screened based on the target spouse's gender and the original spouse's age data to obtain the target spouse information, and the target spouse information is used as the target family relationship information.

5. The method according to claim 2, characterized in that: The filtering of the original family user information to obtain the target family relationship information includes: If the family relationship type is a parent relationship, obtaining parent identity information from the original family user information; Acquire target object identity information from the target user information; Calculate the parents' age based on the parents' identity information to obtain original parents' age data; Performing compliance verification on the original parent age data based on a preset childbearing age threshold and the target object identity information to obtain parent identity compliance verification data; The original family user information is screened based on the parent identity compliance verification data to obtain target parent information, and the target parent information is used as the target family relationship information.

6. The method according to claim 5, characterized in that The screening of the original family user information to obtain the target family relationship information further includes: If the family relationship type is a child relationship, obtaining the child identity information from the original family user information; Calculate the age of the child based on the child's identity information to obtain the child's age data; Performing compliance verification on the child age data based on the childbearing age threshold and the target object identity information to obtain child age compliance verification data; The original family user information is screened based on the child age compliance verification data to obtain target child information, and the target child information is used as the target family relationship information.

7. The method according to any one of claims 1 to 6, characterized in that: The original bill information includes a plurality of original sub-bills, and the original bill information is divided into source priorities to obtain original sub-bills with bill priority levels, including: Perform source analysis on each of the original sub-bills to obtain the source information of the original sub-bill; The original sub-bills are prioritized based on a preset source priority mapping table and the original sub-bill source information to obtain the bill priority level.

8. A product recommendation device, characterized in that: The device comprises: User information acquisition module, used to obtain target user information and original billing information of the target object; A priority classification module, used to classify the source priority of the original bill information to obtain an original sub-bill with a bill priority level; A family relationship determination module, configured to determine target family relationship information of the target object according to the original sub-bill; A network construction module, configured to construct a network based on the bill priority level, the target user information and the target family relationship information to obtain a target family relationship network; The target recommendation module is used to determine the target recommended products according to the target family relationship network.

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