Intelligent Recommendation Method, System and Medium for Maternal and Infant Products Based on Big Data Analysis

Abstract

The present invention discloses an intelligent recommendation method, system and medium for maternal and child products based on big data analysis; it relates to the technical field of intelligent recommendation; it improves the method on the basis of traditional product intelligent recommendation technology, divides multiple family roles based on the preprocessed basic data, and mines the decision-making product results of each family role regarding the target maternal and child products. According to the family role attribution and recommendation mode of the target account, combined with the decision-making product results, a recommendation strategy for the target maternal and child products is generated, which solves the deficiencies of the existing product intelligent recommendation system in dealing with the multi-role needs of families for maternal and child products, and can provide differentiated recommendation content for the needs of different family roles based on multi-role decision-making under the same target account, meeting the expectations of all parties.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent recommendation, and particularly to an intelligent recommendation method, system and medium for maternal and child products based on big data analysis. Background Art

[0002] With the rapid development of intelligent recommendation technology, personalized recommendation systems in the field of maternal and child products have gradually become an important tool for improving user experience and purchase efficiency. Traditional intelligent recommendation systems for maternal and child products mainly make recommendations based on the personalized needs of individual users. For example, by analyzing data such as the browsing history, purchase records, and preference tags of individual users, maternal and child products that meet their individual needs are recommended to them. This recommendation method meets the personalized needs of individual users to a certain extent and improves the accuracy of recommendations.

[0003] However, the purchase decisions of maternal and child products usually involve multiple family members, including mothers, fathers, grandparents, etc. Each role has different concerns and needs during the purchase process. For example, mothers may be more concerned about the safety, comfort, and practicality of products; fathers may pay more attention to the cost-effectiveness and functionality of products; while grandparents may be more concerned about the traditionality and durability of products. Traditional recommendation systems only make recommendations for individual users and cannot effectively balance and integrate the needs of different family members, resulting in the recommended content being difficult to meet the overall purchase decision needs of the family.

[0004] In addition, there may be conflicts or priority differences in the needs among family members. For example, mothers may tend to choose products of high-end brands, while fathers may be more inclined to choose economical and practical products. Traditional recommendation systems cannot effectively coordinate these differences, resulting in the recommended results being difficult to obtain the common recognition of family members, thereby reducing the practicality and user satisfaction of the recommendation system.

[0005] Therefore, the existing intelligent recommendation systems for maternal and child products have obvious deficiencies in dealing with the needs of multiple family roles, and there is an urgent need for an intelligent recommendation method that can comprehensively consider the needs of multiple family roles to improve the overall effect of the recommendation system and user experience. Summary of the Invention

[0006] The technical problem to be solved by the present invention is that the existing product intelligent recommendation system has obvious deficiencies in meeting the multi-role needs of families for maternal and child products. The purpose of the present invention is to provide an intelligent recommendation method, system and medium for maternal and child products based on big data analysis, which improves the method on the basis of traditional product intelligent recommendation technology, divides multi-family roles based on preprocessed basic data, and excavates the decision-making product results of each family role regarding target maternal and child products. According to the family role attribution and recommendation mode of the target account, combined with the decision-making product results, a recommendation strategy for target maternal and child products is generated, solving the deficiencies of the existing product intelligent recommendation system in meeting the multi-role needs of families for maternal and child products, and realizing multi-role decision-making based on the same target account, being able to provide differentiated recommended content for the needs of different family roles and meeting the expectations of all parties.

[0007] The present invention is realized through the following technical solutions:

[0008] This solution provides an intelligent recommendation method for maternal and child products based on big data analysis, including:

[0009] Obtain the basic data of target maternal and child products according to big data, and preprocess the basic data;

[0010] Based on the preprocessed basic data, conduct multi-family role division, and excavate the decision-making product results of each family role regarding target maternal and child products;

[0011] Obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for target maternal and child products in combination with all decision-making product results.

[0012] A further optimized solution is that the obtaining the basic data of target maternal and child products according to big data, and preprocessing the basic data; includes the method:

[0013] Obtain the basic data of target maternal and child products, and the basic data includes: user basic information, user behavior data, product information and family structure data;

[0014] Conduct data cleaning and integration on the basic data; the integration includes integrating the basic data from different data sources, constructing a unified user data table with users as the unit, and associating user behavior data, family structure data with product information in the user data table.

[0015] A further optimized solution is that the conducting multi-family role division based on the preprocessed basic data, and excavating the decision-making product results of each family role regarding target maternal and child products; includes the method:

[0016] Configure family roles including: mother users, father users, grandparent users and other family member users;

[0017] Based on the preprocessed basic data, the family roles are divided by combining the improved K-means clustering algorithm;

[0018] According to the family role division results, the original decision sets of each family role regarding the target mother and baby products are constructed, and the decision product sets are generated from the original decision sets.

[0019] The further optimization plan is that the family roles are divided by combining the improved K-means clustering algorithm based on the preprocessed basic data; the method includes:

[0020] Taking each family role as a cluster and respectively setting the centroids of each cluster; among them, the cluster of mother users takes the purchase frequency, browsing duration and age as the centroids; the cluster of father users takes the unit price of the customer and keyword search as the centroids; the cluster of grandparent users takes the commodity purchase records and age as the centroids; the cluster of other family member users takes the brand awareness and packaging as the centroids;

[0021] Based on the preprocessed basic data, clustering iteration is performed until each cluster converges and then each cluster and its centroid are output; the process of the clustering iteration includes:

[0022] Extract the general features and key features of each user from the preprocessed basic data, configure the first weight for the general features and the second weight for the key features; among them, the second weight is greater than the first weight;

[0023] Calculate the distance from the current user to the cluster centroid based on the general features and key features.

[0024] The further optimization plan is that the distance function of the clustering iteration is:

[0025]

[0026] Among them, D(x, c) represents the distance from the current user to the cluster centroid; x i represents the i-th general feature of the current user; x j represents the j-th key feature of the current user; β i represents the weight of the i-th general feature; β j represents the weight of the j-th key feature; n represents the total number of general features; m represents the total number of key features; c i represents the cluster centroid of the i-th general feature; c j represents the cluster centroid of the j-th key feature.

[0027] The further optimization plan is that the original decision sets of each family role regarding the target mother and baby products are constructed according to the family role division results, and the decision product sets are generated; the method includes:

[0028] Obtain the family roles of all users and the decision results; the decision results include purchase results and effective browsing results; the effective browsing results include that the browsing duration of the current product reaches a preset time threshold and the number of clicks on the current product during the browsing time reaches a preset number threshold.

[0029] Merge the decision results of all users with the same family role to form an original decision set.

[0030] After denoising the original decision set, a decision product set is obtained: count the occurrence frequency of the same decision product in the original decision set, and form the decision product set with the top N decision products with the larger occurrence frequency.

[0031] A further optimization plan is to obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for the target maternal and child products in combination with all decision product results; including methods:

[0032] Obtain the family role and recommendation mode of the target account. The recommendation mode includes an associated mode and a non-associated mode, and each recommendation mode contains 2 options: a single-role option or a multi-role option.

[0033] In combination with all decision product results, generate recommendation strategies for each option under different recommendation modes; in the associated mode, the recommendation strategy takes the decision product results corresponding to the family role of the target account as the main reference object and the decision product results corresponding to the single role or multi-role as the auxiliary reference object; in the non-associated mode, the recommendation strategy takes the decision product results corresponding to the single role or multi-role as the reference object.

[0034] A further optimization plan is that the method for generating the recommendation strategy includes:

[0035] Obtain all decision product results.

[0036] Regarding the single-role option in the non-associated mode, use the decision product of the decision product results corresponding to the current single-role option as the recommendation strategy.

[0037] Regarding the multi-role option in the non-associated mode, configure weights for the decision product results corresponding to each role option respectively, merge all the decision product results after configuring weights to obtain a combined result set, and use the top N combined results with larger weights in the combined result set as the recommendation strategy.

[0038] Regarding the single-role option in the associated mode, configure weight W1 for the decision product results corresponding to the current single-role option, configure weight W2 for the decision product results corresponding to the family role of the target account, merge all the decision product results after configuring weights to obtain a combined result set, and use the top N combined results with larger weights in the combined result set as the recommendation strategy; where W2 > W1.

[0039] Regarding the multi-role options in the association mode, weights Wi are configured for the decision product results corresponding to each role option i, and a weight W3 is configured for the decision product results corresponding to the family role of the target account. All the decision product results after weight configuration are combined to obtain a combined result set, and the top N combined results with larger weights in the combined result set are used as the recommendation strategy; where W3 > Wi.

[0040] This solution provides an intelligent recommendation system for maternal and child products based on big data analysis, which is used to implement the intelligent recommendation method for maternal and child products based on big data analysis described above; the system includes:

[0041] A preprocessing module, which is used to obtain the basic data of the target maternal and child products according to big data and preprocess the basic data;

[0042] A role decision module, which is used to perform multi-role division of families based on the preprocessed basic data and mine the decision product results of each family role regarding the target maternal and child products;

[0043] A strategy generation module, which is used to obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for the target maternal and child products in combination with all the decision product results.

[0044] This solution also provides a computer-readable medium, on which a computer program is stored. The computer program can be executed by a processor to implement the intelligent recommendation method for maternal and child products based on big data analysis described above; specifically, the following steps are executed:

[0045] Step 1: Obtain the basic data of the target maternal and child products according to big data and preprocess the basic data;

[0046] Step 2: Perform multi-role division of families based on the preprocessed basic data and mine the decision product results of each family role regarding the target maternal and child products;

[0047] Step 3: Obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for the target maternal and child products in combination with all the decision product results.

[0048] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0049] The intelligent recommendation method, system and medium for maternal and child products based on big data analysis provided by the present invention improve the method on the basis of traditional product intelligent recommendation technology. Based on the preprocessed basic data, the multi-roles of the family are divided, and the decision-making product results of each family role regarding the target maternal and child products are mined. According to the family role attribution and recommendation mode of the target account, combined with the decision-making product results, the recommendation strategy of the target maternal and child products is generated, which solves the deficiencies of the existing product intelligent recommendation system in dealing with the multi-role needs of the family for maternal and child products. Under the same target account, based on multi-role decision-making, it can provide differentiated recommended content according to the needs of different family roles, meeting the expectations of all parties. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings. In the drawings:

[0051] Figure 1 It is a schematic flow chart of the intelligent recommendation method for maternal and child products based on big data analysis;

[0052] Figure 2 It is a schematic structural diagram of the intelligent recommendation system for maternal and child products based on big data analysis. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] To make the purpose, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in combination with the embodiments and the drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0054] There are obvious deficiencies in the existing product intelligent recommendation system in dealing with the multi-role needs of the family for maternal and child products; there may be conflicts or priority differences in the needs among family members; for example, the mother may tend to choose products of high-end brands, while the father may be more inclined to choose products that are economical and practical; the traditional recommendation system cannot effectively coordinate these differences, resulting in the recommended results being difficult to be jointly recognized by family members, thus reducing the practicality and user satisfaction of the recommendation system. In view of this, the following embodiments are provided in this solution to solve the above technical problems:

[0055] Embodiment 1: This embodiment provides an intelligent recommendation method for maternal and child products based on big data analysis, as Figure 1 shown, including:

[0056] Step 1: Obtain the basic data of the target mother and baby products according to big data, and preprocess the basic data; the specific methods included in this step are as follows:

[0057] S11. Obtain the basic data of the target mother and baby products. The basic data includes: user basic information (such as age, gender, region, income, etc.), user behavior data (such as browsing data (such as browsing duration, browsing times), click data, purchase data (such as purchase results, purchase frequencies, etc.), comment data, etc.), product information (such as brand, price, model, function, evaluation, etc.), and family structure data (such as the number of family members, roles, etc.); discussions and user feedback on mother and baby products on social media (such as Weibo, Xiaohongshu, etc.); user behavior data of mother and baby apps (such as Babytree, QINBAOBAO, etc.); industry reports and user portrait data from third-party data providers (such as Nielsen, iResearch, etc.).

[0058] S12. Conduct data cleaning and integration on the basic data; the integration includes integrating the basic data from different data sources, constructing a unified user data table based on users, and associating user behavior data and family structure data with product information in the user data table. The following is Table 1 of the user data table given in this embodiment, and only some of the main basic data are shown in this table;

[0059] Table 1 User Data Table

[0060] ;

[0061] Step 2: Based on the preprocessed basic data, conduct multi-role division of families and mine the decision-making product results of each family role regarding the target mother and baby products; the specific methods included in this step are as follows:

[0062] S21. Configure family roles including: mother users, father users, grandparent users, and other family member users;

[0063] S22. Based on the preprocessed basic data, conduct family role division in combination with the improved K-means clustering algorithm; the specific methods included in this step are as follows:

[0064] S221. Take each family role as a cluster and set the centroid of each cluster respectively. Among them, the centroid of the cluster of mom users is the purchase frequency, browsing duration, and age; the centroid of the cluster of dad users is the unit price per customer and keyword search; the centroid of the cluster of grandparent users is the commodity purchase record and age; the centroid of the cluster of other family member users is the brand awareness and packaging. Specifically, it can be set as follows: the centroid of the cluster of mom users is set that the purchase frequency of essential mother and baby products > 5 times / month, and the age is set between 25 - 40 years old; the centroid of the cluster of dad users is set that the unit price per customer is higher than a certain unit price threshold; the centroid of the cluster of grandparent users is set as the purchase record of low-price commodities; the centroid of the cluster of other family member users is set that the brand awareness or packaging meets certain requirements.

[0065] S222. Conduct clustering iteration based on the preprocessed basic data until each cluster converges and then output each cluster and its centroid. The process of the clustering iteration includes:

[0066] S223. Extract the general features and key features of each user from the preprocessed basic data, configure the first weight for the general features, and configure the second weight for the key features. Among them, the second weight is greater than the first weight.

[0067] S224. Calculate the distance from the current user to the cluster centroid based on the general features and key features. The distance function for the clustering iteration is:

[0068] ;

[0069] Among them, D(x, c) represents the distance from the current user to the cluster centroid; x i represents the i-th general feature of the current user; x j represents the j-th key feature of the current user; β i represents the weight of the i-th general feature; β j represents the weight of the j-th key feature; n represents the total number of general features; m represents the total number of key features; c i represents the cluster centroid of the i-th general feature; c j represents the cluster centroid of the j-th key feature; The weights of the general features and the key features are dynamically adjusted according to the family role differences.

[0070] The above distance function is mainly used to calculate the distance from numerical features to the cluster centroid. For categorical features (such as gender), the Hamming distance can be used based on the K-prototype algorithm to better handle mixed-type data. This solution designs the above distance function for role differences to capture role differences. For example, mom users and grandparent users may have different price sensitivities, and different weights are set in the price dimension to reflect the differences between mom users and grandparent users.

[0071] When calculating the distance between the current user and the cluster centroid, different general features or key features can be set with the same weight, or different weights can be set according to the actual situation.

[0072] The number of family roles in this solution has been determined as four roles: mother, father, grandparents, and other family members. During the clustering process, the behavioral data between roles may overlap, resulting in inaccurate clustering. For example, fathers and grandparents may have similarities in purchasing behavior. At this time, the algorithm needs to be improved to distinguish these groups. In view of this, this solution introduces general features and key features, and sets higher weights for the key features of each role to emphasize the unique behavioral characteristics of the role. For example, the key features of mother users can include the frequency of purchasing baby necessities, browsing relevant parenting knowledge pages, and searching for related keywords. General features can be region, income, age, etc.; the key features of father users can include the products preferred for browsing and the related keywords searched; the key features of grandparent users include: browsing relevant product promotion and discount pages and price sensitivity;

[0073] When configuring weights for general features and key features, specifically, the weights can be assigned based on the importance of key features or general features through business experience or a random forest model. Compared with general features, higher weights are assigned to key features.

[0074] S23. Construct an original decision set for each family role regarding the target mother and baby products based on the family role division result, and generate a decision product set from the original decision set. This step specifically includes the following methods:

[0075] Obtain the family roles and decision results of all users; the decision results include purchase results and effective browsing results; the effective browsing results include that the browsing duration of the current product reaches a preset time threshold, and the number of clicks on the current product within the browsing time reaches a preset number threshold; the purchase results include actual purchase orders and recommendation results in social media;

[0076] Merge the decision results of all users with the same family role to form an original decision set;

[0077] Denoise the original decision set to obtain a decision product set: count the occurrence frequency of the same decision product in the original decision set, and form a decision product set with the top N decision products with the largest occurrence frequency.

[0078] Due to the different needs of family members, mom users usually pay more attention to the safety, practicality, and professionalism of products; dad users may pay more attention to the cost-effectiveness, technical content, and brand reputation of products; grandparent users may pay more attention to the price, durability, and ease of operation of products; other family members may pay more attention to the packaging and brand awareness of products; this solution can provide differentiated recommended content based on multi-role decision-making to meet the expectations of all parties according to the needs of different family roles.

[0079] Step 3: Obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for the target mother and baby products by combining all decision-making product results. This step specifically includes the following methods:

[0080] S31: Obtain the family role and recommendation mode of the target account. The recommendation mode includes an associated mode and a non-associated mode, and each recommendation mode contains 2 options: a single-role option or a multi-role option; the associated mode means that the generated recommendation strategy is associated with the family role of the target account (that is, the account user is the person himself, and his preferences can be considered more when making recommendations), and the non-associated mode means that the generated recommendation strategy is not associated with the family role of the target account (that is, the account user is not the person himself, and the preferences of the account user can be considered more when making recommendations);

[0081] S32: Combine all decision-making product results to generate recommendation strategies for each option under different recommendation modes respectively; under the associated mode, the recommendation strategy takes the decision-making product results corresponding to the family role of the target account as the main reference object, and the decision-making product results corresponding to the single-role or multi-role as the auxiliary reference object; under the non-associated mode, the recommendation strategy takes the decision-making product results corresponding to the single-role or multi-role as the reference object.

[0082] The method for generating the recommendation strategy includes:

[0083] Obtain all decision-making product results;

[0084] Regarding the single-role option under the non-associated mode, use the decision-making product corresponding to the current single-role option as the recommendation strategy;

[0085] Regarding the multi-role option under the non-associated mode, configure weights for the decision-making product results corresponding to each role option respectively, merge all the decision-making product results after weight configuration to obtain a combined result set, and use the top N combined results with larger weights in the combined result set as the recommendation strategy;

[0086] Regarding the single-role option in the association mode, configure the weight W1 for the decision product result corresponding to the current single-role option, and configure the weight W2 for the decision product result corresponding to the target account family role. Merge all the decision product results with configured weights to obtain a combined result set, and use the top N combined results with larger weights in the combined result set as the recommendation strategy; where W2 > W1.

[0087] Regarding the multi-role option in the association mode, configure the weight Wi for each decision product result corresponding to the role option i, and configure the weight W3 for the decision product result corresponding to the target account family role. Merge all the decision product results with configured weights to obtain a combined result set, and use the top N combined results with larger weights in the combined result set as the recommendation strategy; where W3 > Wi.

[0088] When merging all the decision product results with configured weights, some decision product results may correspond to different role options. Then, the same decision product result may have multiple weights. When merging, add up all the weights of the same decision product result. For example, product a of brand A appears as a decision product result in the decision product results of both mom users and grandparent users. Among them, the weight of the decision product result of mom users is 2.0, and the decision product result of grandparent users is 1.5. Then, the weight of product a of brand A in the combined result is 3.5.

[0089] The association mode in this solution means that the currently generated recommendation strategy needs to correspond to the family roles of the target account. For example, when a mother user purchases maternal and child products using her own account, the decision-making habits of the mother user should be the main consideration when generating the recommendation strategy, and then the decision-making habits of other family roles may or may not be considered. When considering the decision-making habits of multiple other family roles, it is a multi-role scenario. At this time, when generating the recommendation strategy, it is default that the decision-making weight of the target account's family role is large, and the decision-making weight of other roles is small, which is convenient for generating a decision-making strategy that satisfies the user of the target account. In addition, the decision-making weights of the target account and other roles can also be customized according to needs. When only considering the decision-making habits of the target account's family role, it is a single-role scenario. The non-association mode means that the currently generated recommendation strategy does not need to correspond to the family roles of the target account. For example, when multiple role users purchase maternal and child products using the mother user's account, the decision-making habits of the mother user do not need to be the main consideration when generating the recommendation strategy. Then, the decision-making habits of any one or more family roles can be selected. When considering the decision-making habits of multiple other family roles, it is a multi-role scenario. At this time, when generating the recommendation strategy, it is default that the decision-making weights of the target account's family role and other roles are equal, in order to generate a decision-making strategy that satisfies users of each role. At the same time, the decision-making weights of the target account and other roles can also be customized according to needs. When only considering the decision-making habits of one family role, it is a single-role scenario, and this single role can be the mother user or any other family role user.

[0090] Traditional recommendation systems usually take a single user as the unit and ignore the demand differences of different roles in the family (such as mothers, fathers, grandparents); this solution accurately identifies the roles and preferences of each family member through multi-role division of the family; generates personalized recommendation strategies for different roles to meet the diverse needs of multiple roles in the family. Traditional recommendation systems rely on a single data source (such as purchase records), with limited data dimensions and difficulty in comprehensively reflecting user needs; lack of in-depth mining of user behaviors (such as browsing, searching, commenting); this solution integrates multi-source data (purchase records, browsing behaviors, search keywords, comment sentiment, etc.) to build a comprehensive user profile. Through big data analysis, it mines the deep needs and preferences of users, improves the accuracy of recommendations, and can dynamically generate recommendation strategies according to the role attribution and recommendation mode of the target account to meet the needs of family collaborative decision-making.

[0091] Example 2

[0092] This example provides an intelligent recommendation system for maternal and child products based on big data analysis, as Figure 2 shown, for implementing the intelligent recommendation method for maternal and child products based on big data analysis described in Example 1; the system includes:

[0093] A preprocessing module, configured to obtain the basic data of the target mother and baby products according to big data and preprocess the basic data;

[0094] A role decision-making module, configured to perform multi-role division of the family based on the preprocessed basic data and mine the decision-making product results of each family role regarding the target mother and baby products;

[0095] A strategy generation module, configured to obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for the target mother and baby products in combination with all decision-making product results.

[0096] Embodiment 3

[0097] This embodiment provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, the intelligent recommendation method for mother and baby products based on big data analysis as described in Embodiment 1 can be implemented; specifically, it executes:

[0098] Step 1: Obtain the basic data of the target mother and baby products according to big data and preprocess the basic data;

[0099] Step 2: Perform multi-role division of the family based on the preprocessed basic data and mine the decision-making product results of each family role regarding the target mother and baby products;

[0100] Step 3: Obtain the family role attribution and recommendation mode of the target account, and generate a recommendation strategy for the target mother and baby products in combination with all decision-making product results.

[0101] The specific implementation manners described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only the specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent recommendation method for maternal and infant products based on big data analysis, characterized in that: include: Obtaining basic data of target maternal and infant products based on big data, and preprocessing the basic data; Based on the pre-processed basic data, the family is divided into multiple roles, and the decision-making product results of each family role regarding the target maternal and infant products are mined; Including methods: configuring family roles including: mother user, father user, grandparent user and other family member users; based on the pre-processed basic data, combined with the improved K-means clustering algorithm to divide the family roles; constructing the original decision set of each family role on the target maternal and child products according to the family role division results, and generating the decision product set from the original decision set; Obtain the family role attribution and recommendation model of the target account, and combine all decision-making product results to generate a recommendation strategy for the target maternal and infant products; including methods: Obtaining the family role and recommendation mode of the target account, wherein the recommendation mode includes an associated mode and an unassociated mode, and each recommendation mode includes two options: a single role option or a multi-role option; Combining all decision product results, recommendation strategies for each option under different recommendation modes are generated respectively; in the associated mode, the recommendation strategy uses the decision product results corresponding to the target account's family role as the main reference object, and the decision product results corresponding to a single role or multiple roles as the auxiliary reference object; in the unassociated mode, the recommendation strategy uses the decision product results corresponding to a single role or multiple roles as the reference object.

2. The method for intelligently recommending maternal and infant products based on big data analysis according to claim 1, characterized in that: The basic data of the target maternal and infant products are obtained according to the big data, and the basic data are preprocessed; Included methods: Obtaining basic data of target maternal and infant products, the basic data including: basic user information, user behavior data, product information and family structure data; The basic data is cleaned and integrated; the integration includes integrating the basic data from different data sources, constructing a unified user data table based on users, and associating user behavior data, family structure data and product information in the user data table.

3. The method for intelligently recommending maternal and infant products based on big data analysis according to claim 1, characterized in that: The method of dividing family roles based on the preprocessed basic data and combining the improved K-means clustering algorithm includes: Each family role is a cluster, and the centroid of each cluster is set separately. The centroid of the cluster of mother users is the purchase frequency, browsing time and age; the centroid of the cluster of father users is the customer unit price and keyword search; the centroid of the cluster of grandparent users is the product purchase record and age; the centroid of the cluster of other family members is the brand awareness and packaging; Perform clustering iteration based on the preprocessed basic data until each cluster converges and then outputs each cluster and centroid; the clustering iteration process includes: Extracting general features and key features of each user from the preprocessed basic data, assigning a first weight to the general features and a second weight to the key features; wherein the second weight is greater than the first weight; The distance from each user to the cluster centroid is calculated based on the general feature, the first weight, the key feature and the second weight.

4. The method for intelligently recommending maternal and infant products based on big data analysis according to claim 3, characterized in that: The calculation method of the distance D(x,c) from the current user to the cluster centroid includes: ； Among them, x i represents the i-th general feature of the current user; x j represents the jth key feature of the current user; β i represents the weight of the i-th general feature; β j represents the weight of the jth key feature; n represents the total number of general features; m represents the total number of key features; c i represents the cluster centroid of the i-th general feature; c j represents the cluster centroid of the jth key feature.

5. The method for intelligently recommending maternal and infant products based on big data analysis according to claim 4, characterized in that: The method constructs an original decision set of each family role on the target maternal and infant product according to the family role division result, and generates a decision product set from the original decision set; Included methods: Obtaining the family roles and decision results of all users; the decision results include purchase results and effective browsing results; the effective browsing results include that the browsing time of the current product reaches a preset time threshold, and the number of clicks on the current product during the browsing time reaches a preset number threshold; The decision results of all users with the same family role are combined to form the original decision set; After denoising the original decision set, the decision product set is obtained: the frequency of occurrence of the same decision product in the original decision set is counted, and the top N decision products with the largest occurrence frequency constitute the decision product set.

6. The method for intelligently recommending maternal and infant products based on big data analysis according to claim 1, characterized in that: The method for generating the recommendation strategy includes: Get all decision product results; For single-role options in non-association mode, the decision product in the decision product result corresponding to the current single-role option is used as the recommended strategy; For multi-role options in the non-association mode, weights are assigned to the decision product results corresponding to each role option, and all decision product results after weight assignment are merged to obtain a combined result set. The top N combined results with larger weights in the combined result set are used as the recommended strategies. For single-role options in association mode, weight W1 is configured for the decision product result corresponding to the current single-role option, and weight W2 is configured for the decision product result corresponding to the target account's family role. All decision product results after weight configuration are merged to obtain a combined result set, and the top N combined results with larger weights in the combined result set are used as the recommended strategy; where W2>W1; Regarding the multi-role options in the association mode, the weight Wi is configured for the decision product results corresponding to the role option i, and the weight W3 is configured for the decision product results corresponding to the target account family role. All decision product results after the weight configuration are merged to obtain a combined result set, and the top N combined results with larger weights in the combined result set are used as the recommended strategies; where W3>Wi.

7. Intelligent recommendation system for maternal and infant products based on big data analysis, characterized by: Used to implement the intelligent recommendation method for maternal and infant products based on big data analysis as described in any one of claims 1 to 6; the system comprises: A preprocessing module, used to obtain basic data of target maternal and infant products based on big data, and preprocess the basic data; The role decision module is used to divide the family into multiple roles based on the pre-processed basic data, and to mine the decision-making product results of each family role regarding the target maternal and child products; The strategy generation module is used to obtain the family role attribution and recommendation model of the target account, and combine the results of all decision-making products to generate a recommendation strategy for the target maternal and infant products.

8. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the intelligent recommendation method for maternal and infant products based on big data analysis as described in any one of claims 1 to 6.

Images