Gift recommendation method, device, apparatus, and storage medium

Abstract

The application provides a gift recommendation method, device and equipment and a storage medium; the method in the application comprises the following steps: receiving a gift recommendation request, extracting a target user corresponding to the gift recommendation request and user attribute characteristics of the target user; extracting historical user comments of the target user according to the user attribute characteristics, and performing sentiment tendency analysis on the historical user comments to obtain positive user comments; obtaining evaluation commodities corresponding to the positive user comments and target gift categories corresponding to the evaluation commodities, obtaining candidate gifts corresponding to the target gift categories in a preset gift database; obtaining historical gift comments of the candidate gifts, determining target gifts to be recommended according to the historical gift comments and the positive user comments, and recommending the target gifts to the target user. The target gifts that the target user is interested in are determined according to the historical user comments of the target user, and the recommendation accuracy of credit card gifts is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and specifically to a gift recommendation method, apparatus, device, and storage medium. Background Technology

[0002] Currently, with the development of the financial and other industries, different banks have launched credit cards with varying benefits. During the application and usage stages, the card issuer will recommend different physical or virtual gifts based on the user's card usage. The user can choose any one from the gift recommendation list as a reward. However, the card issuer cannot accurately determine whether the listed gifts are what the user wants, which may result in the list of gifts not containing the user's desired gifts, making it impossible to accurately recommend credit card gifts that the user is interested in or wants. Summary of the Invention

[0003] This application provides a gift recommendation method, apparatus, device, and storage medium, aiming to solve the technical problem of poor accuracy in gift recommendations in the prior art.

[0004] On one hand, embodiments of this application provide a gift recommendation method, which includes the following steps:

[0005] Receive a gift recommendation request, extract the target user corresponding to the gift recommendation request, and the user attribute characteristics of the target user;

[0006] Based on the user attribute features, historical user comments of the target user are extracted, and sentiment analysis is performed on the historical user comments to obtain positive user comments;

[0007] Obtain the rated product corresponding to the positive user review, and the target gift category corresponding to the rated product; obtain the candidate gift corresponding to the target gift category from the preset gift database.

[0008] Obtain historical gift reviews of the candidate gifts, determine the target gifts to be recommended based on the historical gift reviews and the positive user reviews, and recommend the target gifts to the target users.

[0009] In one possible implementation of this application, the step of extracting historical user reviews of the target user based on the user attribute features and performing sentiment analysis on the historical user reviews to obtain positive user reviews includes:

[0010] Obtain the user identifier from the user attribute features, and crawl the target user's historical user comments based on the user identifier;

[0011] The historical user comments and preset sentiment tendency data are used to calculate the point mutual information to obtain the sentiment mutual information of the historical user comments;

[0012] Historical user comments whose emotional mutual information is greater than a preset emotional tendency threshold are set as positive user comments.

[0013] In one possible implementation of this application, obtaining the rated product corresponding to the positive user review and the target gift category corresponding to the rated product, and obtaining candidate gifts corresponding to the target gift category from a preset gift database, includes:

[0014] The positive user reviews are segmented into words to obtain the product-related words within the positive user reviews;

[0015] Identify the rated products corresponding to the product segmentation and obtain the target gift category corresponding to the rated products;

[0016] Query the preset gift database to obtain the candidate products corresponding to the target gift category.

[0017] In one possible implementation of this application, obtaining historical gift reviews of the candidate gifts, determining the target gift to be recommended based on the historical gift reviews and the positive user reviews, and recommending the target gift to the target user includes:

[0018] Obtain historical gift reviews for the candidate gifts, and obtain the sentiment data corresponding to the historical gift reviews;

[0019] Calculate the first score of the candidate gifts based on the historical gift reviews and the sentiment data;

[0020] Obtain the sentiment mutual information of positive user comments corresponding to the candidate gifts, and determine the second rating of the positive user comments based on the sentiment mutual information;

[0021] The recommended score of the candidate gift is determined based on the first score and the second score, and the target gift to be recommended is determined based on the recommended score.

[0022] In one possible implementation of this application, determining the recommendation score of the candidate gift based on the first score and the second score, and determining the target gift to be recommended based on the recommendation score, includes:

[0023] Obtain the target user's browsing history;

[0024] The historical browsing records are clustered to obtain the historical browsing categories of the target user and the browsing percentage corresponding to each historical browsing category.

[0025] The second score is weighted according to the historical browsing category and the browsing percentage to obtain the second weighted score;

[0026] The recommended score of the candidate gift is determined based on the first score and the second weighted score, and the target gift to be recommended is determined based on the recommended score.

[0027] In one possible implementation of this application, determining the recommendation score of the candidate gift based on the first score and the second score, and determining the target gift to be recommended based on the recommendation score, includes:

[0028] Calculate the popularity data of the candidate gifts, and determine the recommendation weight of the candidate gifts based on the popularity data and a preset popularity weight strategy;

[0029] The first score of the candidate gift is weighted according to the recommendation weight to obtain the first weighted score;

[0030] The recommended score of the candidate gift is calculated based on the first weighted score and the second score, and the target gift to be recommended is determined based on the recommended score.

[0031] In one possible implementation of this application, recommending the target gift to the target user includes:

[0032] The recommended scores of the candidate gifts are compared with a preset recommended score threshold, and the candidate gifts whose recommended scores exceed the preset recommended score threshold are determined as target gifts;

[0033] The target gifts are compiled, a recommended gift list is generated, and the recommended gift list is transmitted to the target user to perform the gift recommendation operation.

[0034] On the other hand, this application provides a gift recommendation device, the gift recommendation device comprising:

[0035] The acquisition module is configured to receive gift recommendation requests, extract the target user corresponding to the gift recommendation request, and the user attribute features of the target user;

[0036] The sentiment analysis module is configured to extract historical user comments of the target user based on the user attribute characteristics, and perform sentiment tendency analysis on the historical user comments to obtain positive user comments;

[0037] The gift acquisition module is configured to acquire the rated product corresponding to the positive user review, the target gift category corresponding to the rated product, and acquire candidate gifts corresponding to the target gift category from a preset gift database;

[0038] The gift recommendation module is configured to retrieve historical gift reviews of the candidate gifts, determine target gifts to be recommended based on the historical gift reviews and the positive user reviews, and recommend the target gifts to the target users.

[0039] On the other hand, this application also provides a gift recommendation device, the gift recommendation device comprising:

[0040] One or more processors;

[0041] Memory; and

[0042] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the gift recommendation method.

[0043] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the gift recommendation method.

[0044] This application receives a gift recommendation request, extracts the target user corresponding to the request, and the user attribute characteristics of the target user; extracts the target user's historical user reviews based on the user attribute characteristics, and performs sentiment analysis on the historical user reviews to obtain positive user reviews; obtains the rated products corresponding to the positive user reviews and the target gift categories corresponding to the rated products, and obtains candidate gifts corresponding to the target gift categories from a preset gift database; obtains historical gift reviews of the candidate gifts, determines the target gift to be recommended based on the historical gift reviews and the positive user reviews, and recommends the target gift to the target user, thereby improving the accuracy of credit card gift recommendations by determining the target gifts that the user is interested in based on the target user's historical user reviews. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram illustrating a scenario of the gift recommendation method in an embodiment of this application;

[0047] Figure 2 This is a flowchart illustrating one embodiment of the gift recommendation method in this application.

[0048] Figure 3A flowchart illustrating one embodiment of the gift recommendation method provided in this application for calculating the recommendation score of candidate gifts;

[0049] Figure 4 A flowchart illustrating another embodiment of the gift recommendation method provided in this application for calculating the recommendation score of candidate gifts;

[0050] Figure 5 This is a schematic diagram of one embodiment of the gift recommendation device in this application;

[0051] Figure 6 This is a schematic diagram of one embodiment of the gift recommendation device provided in this application. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0054] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0055] Currently, with the development of the financial and other industries, different banks have launched credit cards with varying benefits. During the application and usage stages, the card issuer will recommend different physical or virtual gifts based on the user's card usage. The user can choose any one from the gift recommendation list as a reward. However, the card issuer cannot accurately determine whether the listed gifts are what the user wants, which may result in the list of gifts not containing the user's desired gifts, thus failing to achieve the intended incentive effect.

[0056] Based on this, this application proposes a gift recommendation method, apparatus, device, and computer-readable storage medium to solve the technical problem that the accuracy of gift recommendations in the prior art is poor and cannot achieve the corresponding gift incentive effect.

[0057] The gift recommendation method in this embodiment of the invention is applied to a gift recommendation device, which is disposed in a gift recommendation equipment. The gift recommendation equipment is provided with one or more processors, a memory, and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the gift recommendation method. The gift recommendation equipment can be a smart terminal, such as a mobile phone, tablet computer, smart TV, network device, and smart computer. Optionally, the gift recommendation equipment can also be a server or a service cluster composed of multiple servers.

[0058] like Figure 1 As shown, Figure 1 This is a schematic diagram of a scenario for a gift recommendation method according to an embodiment of this application. In this embodiment of the invention, the gift recommendation scenario includes multiple gift recommendation devices 100 (each gift recommendation device 100 integrates a gift recommendation apparatus). Each gift recommendation device 100 is equipped with a computer-readable storage medium corresponding to the gift recommendation method to execute the steps of the gift recommendation method.

[0059] Understandable Figure 1The gift recommendation device in the gift recommendation method scenario shown, or the device included in the gift recommendation device, does not constitute a limitation on the embodiments of the present invention. That is, the number or type of the gift recommendation device included in the gift recommendation method scenario, or the number or type of devices included in each device, does not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0060] In this embodiment of the invention, the gift recommendation device 100 is mainly used for: receiving a gift recommendation request; extracting the target user corresponding to the gift recommendation request and the user attribute features of the target user; extracting the historical user reviews of the target user based on the user attribute features, and performing sentiment analysis on the historical user reviews to obtain positive user reviews; obtaining the rated product corresponding to the positive user review and the target gift category corresponding to the rated product, and obtaining candidate gifts corresponding to the target gift category in a preset gift database; obtaining historical gift reviews of the candidate gifts, determining the target gift to be recommended based on the historical gift reviews and the positive user reviews, and recommending the target gift to the target user.

[0061] In this embodiment of the invention, the gift recommendation device 100 can be multiple independent gift recommendation devices, such as mobile phones, tablets, smart TVs, network devices, servers, and smart computers, or a gift recommendation network or gift recommendation cluster composed of multiple gift recommendation devices.

[0062] This application provides a gift recommendation method, apparatus, device, and computer-readable storage medium, which will be described in detail below.

[0063] It will be understood by those skilled in the art that Figure 1 The application environment shown is only one application scenario related to the solution of this application and does not constitute a limitation on the application scenario of this application. Other application environments may include more than one application scenario. Figure 1 The number of more or fewer gift recommendation devices shown, or gift recommendation network connections, for example Figure 1 Only one gift recommendation device is shown in the document. It is understood that the scenario of this gift recommendation method may also include one or more gift recommendation devices, which is not limited here. The gift recommendation device may also include a memory for storing user review data and other data.

[0064] It should be noted that, Figure 1The illustrated scenario of the gift recommendation method is merely an example. The scenarios of the gift recommendation method described in this embodiment of the invention are intended to more clearly illustrate the technical solutions of this embodiment and do not constitute a limitation on the technical solutions provided by this embodiment of the invention.

[0065] Based on the scenarios described above for gift recommendation methods, various embodiments of the gift recommendation method disclosed in this invention are proposed.

[0066] like Figure 2 As shown, Figure 2 This is a flowchart illustrating one embodiment of the gift recommendation method in this application. The image processing method includes the following steps 201-204:

[0067] 201. Receive a gift recommendation request, extract the target user corresponding to the gift recommendation request, and the user attribute characteristics of the target user;

[0068] The gift recommendation method in this embodiment is applied to a gift recommendation device. The type and quantity of the gift recommendation device are not specifically limited. That is, the gift recommendation device can be one or more smart terminals. In a specific embodiment, the gift recommendation device is a smart computer.

[0069] Specifically, the gift recommendation device is configured to receive gift recommendation requests, obtain the gifts that the target user is interested in corresponding to the request, and recommend those gifts. The gift recommendation request is an instruction from the credit card issuer to gift a specific gift to the target user when the user meets certain credit card benefits requirements or other marketing scenarios.

[0070] Specifically, during operation, the gift recommendation device receives gift recommendation requests. The triggering method for these requests is not specifically limited here; that is, the request can be proactively triggered by banking or financial industry personnel. For example, when a personnel determine that a target user has fulfilled specific credit card benefits requirements and a specific credit card gift needs to be given to that user, they can proactively trigger the gift recommendation by clicking the gift recommendation button on the device. Alternatively, gift recommendations can also be triggered automatically by the device. For instance, the device may be pre-programmed with an automatic push process, recommending gifts to target users according to a preset gift push strategy.

[0071] Specifically, after receiving the gift recommendation request, the gift recommendation device parses the request and determines the user attribute characteristics of the target user. These user attribute characteristics include user identifiers, user age characteristics, and credit card usage characteristics, which are feature data representing user identity information and credit card usage.

[0072] After acquiring the user attribute characteristics of the target user, the gift recommendation device also retrieves the user's historical user reviews based on these characteristics, and determines the credit card gifts the user is interested in based on these historical user reviews. Optionally, the credit card gifts can include physical gifts and virtual gifts.

[0073] Optionally, after obtaining the user attribute characteristics of the target user, the gift recommendation device further determines preset candidate gifts that match the target user based on the credit card usage characteristics and user age characteristics within those user attribute characteristics. Optionally, different credit card usage characteristics correspond to different preset candidate gifts. After determining the preset candidate gifts in the gift database corresponding to the credit card usage characteristics, the gift recommendation device also compares the user's age characteristics with the age range of the preset candidate gifts to determine the preset candidate gifts corresponding to the age range that matches the user's age characteristics.

[0074] 202. Extract the target user's historical user comments based on the user attribute features, and perform sentiment analysis on the historical user comments to obtain positive user comments;

[0075] Specifically, after obtaining user attribute features from a gift recommendation request, the gift recommendation device obtains the user identifier from those attributes and crawls historical user reviews of the target user across various social media or shopping applications based on that identifier. Optionally, these historical user reviews can be dynamic sharing comments about items or historical shopping reviews from the target user. The gift recommendation device performs sentiment analysis on the obtained historical user reviews to identify positive user reviews with a positive sentiment bias.

[0076] Specifically, the gift recommendation device is pre-set with a sentiment analysis model. This model includes several positive sentiment data points, which are used to calculate the sentiment mutual information between the target user's historical user reviews and this positive sentiment data, thereby obtaining the sentiment mutual information of the user's online reviews. The positive sentiment data consists of samples of positive tag words with a positive sentiment orientation.

[0077] Specifically, the gift recommendation device inputs the historical user review into the sentiment analysis model, encodes the target online review using the model, obtains the online review code, and calculates the sentiment mutual information between this online review code and the pre-set positive sentiment data code, thus obtaining the sentiment mutual information of the historical user review. Here, sentiment mutual information is a parameter that measures the frequency of word collocations; the higher the sentiment mutual information, the more consistent the sentiment of the text.

[0078] After calculating the sentiment mutual information of the historical user comments and positive sentiment data, the gift recommendation device further determines whether the sentiment tendency of the historical user comments is positive sentiment based on the sentiment mutual information.

[0079] Specifically, after calculating the sentiment mutual information of historical user reviews and positive sentiment data, the gift recommendation device compares the sentiment mutual information with a preset sentiment tendency threshold to determine the sentiment tendency of the historical user review. The preset sentiment tendency threshold is the sentiment mutual information value that determines the sentiment mutual information has the same sentiment tendency.

[0080] Optionally, the gift recommendation device compares the sentiment mutual information with a preset sentiment tendency threshold. If the sentiment mutual information is less than the preset sentiment tendency threshold, it determines that the sentiment tendency of the historical user comment is inconsistent with that of the positive sentiment data.

[0081] Optionally, the gift recommendation device compares the emotional mutual information with a preset emotional tendency threshold. If the emotional tendency mutual information is greater than or equal to the preset emotional tendency threshold, it determines that the historical user comments corresponding to the emotional mutual information are consistent with the emotional tendency of the positive sentiment data, that is, the emotional tendency of the historical user comments is a positive sentiment tendency, and sets the historical user comments corresponding to the positive sentiment tendency as positive user comments.

[0082] The gift recommendation device identifies the sentiment of all historical user comments of the target user, thereby obtaining positive user comments from the target user's historical user comments.

[0083] 203. Obtain the rated product corresponding to the positive user review, and the target gift category corresponding to the rated product, and obtain the candidate gift corresponding to the target gift category in the preset gift database;

[0084] After identifying the sentiment of historical user reviews and obtaining positive user reviews, the gift recommendation device further identifies the product category based on the positive user reviews to obtain the target gift category corresponding to the positive user reviews, thereby obtaining candidate gifts from the target gift category in the preset gift database.

[0085] Specifically, the gift recommendation device performs word segmentation on the acquired positive user reviews and extracts the product word segments from the saturated user reviews. The device then inputs these product word segments into a pre-defined product recognition model for product identification, thereby identifying the rated product corresponding to the product word segment, obtaining the product category of the rated product, and determining that this product type is the target gift category corresponding to the positive user review.

[0086] Specifically, after determining the target gift category corresponding to the positive user review, the gift recommendation device queries the preset gift database for the corresponding candidate products under the target gift category and obtains the candidate products corresponding to the target gift category as candidate gifts.

[0087] 204. Obtain historical gift reviews of the candidate gifts, determine the target gifts to be recommended based on the historical gift reviews and the positive user reviews, and recommend the target gifts to the target users.

[0088] After obtaining candidate products corresponding to the target gift category with positive user reviews based on positive user comments, the gift recommendation device obtains the historical gift reviews of the candidate products, determines the target gift to be recommended based on the historical gift reviews and the positive user reviews, and recommends the target gift to the target user as a target gift for credit card benefits.

[0089] Specifically, the gift recommendation device acquires historical gift reviews for the candidate gift and obtains the corresponding sentiment data. Optionally, this sentiment data can be determined based on the historical product ratings corresponding to the historical gift reviews. That is, the gift recommendation device presets product rating ranges to characterize the sentiment of the historical gift reviews for the candidate gift. Different product rating ranges characterize different sentiment data. The gift recommendation device determines the historical product ratings for the candidate gift, determines the product rating ranges, and thus determines the sentiment data corresponding to the historical gift reviews. A first rating for the candidate gift is then calculated using the preset historical gift reviews and the sentiment data.

[0090] Optionally, the gift recommendation device can also calculate the sentiment mutual information of the historical gift reviews, use the sentiment mutual information as the sentiment data of the historical gift reviews, and input the historical gift reviews and the sentiment data into a preset recommendation scoring model to calculate the first score of the candidate gifts.

[0091] Specifically, the gift recommendation device obtains positive user reviews corresponding to the candidate gift, as well as the sentiment mutual information corresponding to the positive user reviews, and inputs the sentiment mutual information into the preset recommendation scoring model to calculate the second score.

[0092] The gift recommendation device determines a recommendation score for each candidate gift based on a first score and a second score. It then compares this recommendation score with a preset recommendation score threshold, identifying candidate gifts whose scores exceed the threshold as target gifts. The device compiles these target gifts, generates a recommended gift list, and transmits this list to the target user to perform the gift recommendation operation. The recommendation score represents the degree of interest or liking a candidate gift has towards the target user.

[0093] In this embodiment, the gift recommendation device receives a gift recommendation request, extracts the target user corresponding to the request, and the user attribute features of the target user; extracts the target user's historical user reviews based on the user attribute features, and performs sentiment analysis on the historical user reviews to obtain positive user reviews; obtains the rated products corresponding to the positive user reviews and the target gift categories corresponding to the rated products, and obtains candidate gifts corresponding to the target gift categories from a preset gift database; obtains historical gift reviews of the candidate gifts, determines the target gift to be recommended based on the historical gift reviews and the positive user reviews, and recommends the target gift to the target user, thereby improving the accuracy of credit card gift recommendations by determining the target gifts that the user is interested in based on the target user's historical user reviews.

[0094] like Figure 3 As shown, Figure 3 A flowchart illustrating an embodiment of the gift recommendation method for calculating the recommendation score of candidate gifts provided in this application, specifically including steps 301-304:

[0095] 301. Obtain the target user's browsing history;

[0096] 302. Perform category clustering on the historical browsing records to obtain the historical browsing categories of the target user and the browsing percentage corresponding to the historical browsing categories;

[0097] 303. The second score is weighted according to the historical browsing category and the browsing percentage to obtain the second weighted score;

[0098] 304. Determine the recommended score of the candidate gift based on the first score and the second weighted score, and determine the target gift to be recommended based on the recommended score.

[0099] Based on the above embodiments, in this embodiment, the gift recommendation device further determines the target user's historical browsing records and the importance of the target user's positive user comments through these historical browsing records, thereby weighting the second score and calculating the recommendation score of the candidate gift based on the weighted second score, thus improving the accuracy of the recommendation score.

[0100] Specifically, the gift recommendation device obtains the target user's historical browsing records and performs category clustering on these records to obtain the target user's historical browsing categories and the browsing percentage corresponding to each category. These historical browsing categories can be application categories or product categories browsed by the user.

[0101] After obtaining the historical browsing categories and browsing percentages, the gift recommendation device determines the weight corresponding to the browsing percentage. Specifically, the gift recommendation device presets several browsing percentage ranges related to the weights. Different browsing percentage ranges correspond to different weights. After determining the browsing percentage range corresponding to the browsing percentage, the gift recommendation device determines the weight corresponding to the browsing percentage as the weight corresponding to the browsing percentage range and sets this weight as the first weight corresponding to the historical browsing category.

[0102] After obtaining the first weight of the historical browsing category, the gift recommendation device further determines the historical browsing category to which the positive user review corresponding to the candidate gift belongs, and obtains the corresponding first weight. Based on the first weight, the second score of the positive user review is weighted to obtain the second weighted score.

[0103] The gift recommendation device determines the recommendation score for each candidate gift based on the first and second weighted scores obtained from historical gift reviews. It then compares the recommendation score of each candidate gift with a preset recommendation score threshold, and identifies candidate gifts whose recommendation scores exceed the preset threshold as target gifts. The device then compiles these target gifts, generates a recommended gift list, and transmits the recommended gift list to the target user to perform the gift recommendation operation.

[0104] In this embodiment, the gift recommendation device acquires the target user's historical browsing records; performs category clustering on the historical browsing records to obtain the target user's historical browsing categories and the browsing percentage corresponding to each historical browsing category; weights the second score based on the historical browsing categories and the browsing percentage to obtain a second weighted score; determines the recommendation score for the candidate gifts based on the first score and the second weighted score; and determines the target gift to be recommended based on the recommendation score. This achieves the goal of weighting the second score based on the user's historical browsing records, thereby improving the accuracy of the recommendation score.

[0105] like Figure 4 As shown, Figure 4 A flowchart illustrating another embodiment of the gift recommendation method provided in this application for calculating the recommendation score of candidate gifts, specifically including steps 401-403:

[0106] 401. Calculate the popularity data of the candidate gifts, and determine the recommendation weight of the candidate gifts based on the popularity data and the preset popularity weight strategy;

[0107] 402. The first score of the candidate gift is weighted according to the recommendation weight to obtain the first weighted score;

[0108] 403. Calculate the recommendation score of the candidate gift based on the first weighted score and the second score, and determine the target gift to be recommended based on the recommendation score.

[0109] Based on the above embodiments, in this embodiment, after calculating the first score of the candidate gift, the gift recommendation device further obtains the popularity data of the candidate gift, and determines the recommendation weight of the candidate gift according to the popularity data and the preset popularity weight strategy, and uses the recommendation weight to weight the first score of the candidate gift.

[0110] Specifically, the gift recommendation device obtains the historical sales volume of the candidate gift and calculates the popularity data of the candidate gift based on the historical sales volume. The gift recommendation device converts the historical sales volume into the sales popularity of the candidate gift according to the preset popularity conversion strategy, and obtains the sum of the sales popularity and the preset initial popularity. The device then subtracts the time decay popularity from the sum of the sales popularity and the preset initial popularity to obtain the popularity data of the candidate gift. The time decay popularity is a preset value that represents the popularity data of the candidate gift as time goes by.

[0111] After acquiring the popularity data, the gift recommendation device determines the recommendation weight of the candidate gift based on the popularity data and a preset popularity weight strategy. Specifically, the preset popularity weight strategy sets several popularity intervals, with different popularity intervals corresponding to different recommendation weights. The gift recommendation device determines the popularity interval corresponding to the popularity data, thereby determining the recommendation weight of the candidate gift.

[0112] After obtaining the recommendation weight of the candidate gift, the gift recommendation device weights the first score of the candidate gift according to the recommendation weight, thereby obtaining the first weighted score.

[0113] The gift recommendation device determines the recommendation score for each candidate gift based on the first weighted score and the second weighted score obtained from the historical gift reviews of the candidate gifts. It then compares the recommendation score of the candidate gift with a preset recommendation score threshold and determines the candidate gifts whose recommendation scores exceed the preset recommendation score threshold as target gifts. The device then summarizes the target gifts, generates a list of recommended gifts, and transmits the list of recommended gifts to the target user to perform the gift recommendation operation.

[0114] In this embodiment, the gift recommendation device calculates the popularity data of the candidate gifts, determines the recommendation weight of the candidate gifts based on the popularity data and a preset popularity weighting strategy, weights the first score of the candidate gifts according to the recommendation weight to obtain a first weighted score, calculates the recommendation score of the candidate gifts based on the first weighted score and a second score, and determines the target gift to be recommended based on the recommendation score. This achieves the goal of obtaining the popularity of the candidate gifts, weighting the first score based on the popularity, and calculating the recommendation score based on the popularity, thereby improving the accuracy of target gift recommendations by calculating the recommendation score based on multiple dimensions.

[0115] To better implement the gift recommendation method in the embodiments of this application, a gift recommendation device is also provided in the embodiments of this application, such as... Figure 5 As shown, Figure 5 This is a schematic diagram of one embodiment of the gift recommendation device in this application. The gift recommendation device 500 includes:

[0116] The acquisition module is configured to receive gift recommendation requests, extract the target user corresponding to the gift recommendation request, and the user attribute features of the target user;

[0117] The sentiment analysis module is configured to extract historical user comments of the target user based on the user attribute characteristics, and perform sentiment tendency analysis on the historical user comments to obtain positive user comments;

[0118] The gift acquisition module is configured to acquire the rated product corresponding to the positive user review, the target gift category corresponding to the rated product, and acquire candidate gifts corresponding to the target gift category from a preset gift database;

[0119] The gift recommendation module is configured to retrieve historical gift reviews of the candidate gifts, determine target gifts to be recommended based on the historical gift reviews and the positive user reviews, and recommend the target gifts to the target users.

[0120] In some embodiments of this application, the gift recommendation device 500 extracts historical user reviews of the target user based on the user attribute characteristics, and performs sentiment analysis on the historical user reviews to obtain positive user reviews, including:

[0121] Obtain the user identifier from the user attribute features, and crawl the target user's historical user comments based on the user identifier;

[0122] The historical user comments and preset sentiment tendency data are used to calculate the point mutual information to obtain the sentiment mutual information of the historical user comments;

[0123] Historical user comments whose emotional mutual information is greater than a preset emotional tendency threshold are set as positive user comments.

[0124] In some embodiments of this application, the gift recommendation device 500 obtains the rated product corresponding to the positive user review and the target gift category corresponding to the rated product, and obtains candidate gifts corresponding to the target gift category from a preset gift database, including:

[0125] The positive user reviews are segmented into words to obtain the product-related words within the positive user reviews;

[0126] Identify the rated products corresponding to the product segmentation and obtain the target gift category corresponding to the rated products;

[0127] Query the preset gift database to obtain the candidate products corresponding to the target gift category.

[0128] In some embodiments of this application, the gift recommendation device 500 acquires historical gift reviews of the candidate gifts, determines target gifts to be recommended based on the historical gift reviews and the positive user reviews, and recommends the target gifts to the target users, including:

[0129] Obtain historical gift reviews for the candidate gifts, and obtain the sentiment data corresponding to the historical gift reviews;

[0130] Calculate the first score of the candidate gifts based on the historical gift reviews and the sentiment data;

[0131] Obtain the sentiment mutual information of positive user comments corresponding to the candidate gifts, and determine the second rating of the positive user comments based on the sentiment mutual information;

[0132] The recommended score of the candidate gift is determined based on the first score and the second score, and the target gift to be recommended is determined based on the recommended score.

[0133] In some embodiments of this application, the gift recommendation device 500 determines a recommendation score for the candidate gifts based on the first and second scores, and determines a target gift to be recommended based on the recommendation score, including:

[0134] Obtain the target user's browsing history;

[0135] The historical browsing records are clustered to obtain the historical browsing categories of the target user and the browsing percentage corresponding to each historical browsing category.

[0136] The second score is weighted according to the historical browsing category and the browsing percentage to obtain the second weighted score;

[0137] The recommended score of the candidate gift is determined based on the first score and the second weighted score, and the target gift to be recommended is determined based on the recommended score.

[0138] In some embodiments of this application, the gift recommendation device 500 determines a recommendation score for the candidate gifts based on the first and second scores, and determines a target gift to be recommended based on the recommendation score, including:

[0139] Calculate the popularity data of the candidate gifts, and determine the recommendation weight of the candidate gifts based on the popularity data and a preset popularity weight strategy;

[0140] The first score of the candidate gift is weighted according to the recommendation weight to obtain the first weighted score;

[0141] The recommended score of the candidate gift is calculated based on the first weighted score and the second score, and the target gift to be recommended is determined based on the recommended score.

[0142] In some embodiments of this application, the gift recommendation device 500 recommends the target gift to the target user, including:

[0143] The recommended scores of the candidate gifts are compared with a preset recommended score threshold, and the candidate gifts whose recommended scores exceed the preset recommended score threshold are determined as target gifts;

[0144] The target gifts are compiled, a recommended gift list is generated, and the recommended gift list is transmitted to the target user to perform the gift recommendation operation.

[0145] In this embodiment, the gift recommendation device receives a gift recommendation request, extracts the target user corresponding to the request and the user attribute features of the target user; extracts the target user's historical user reviews based on the user attribute features, and performs sentiment analysis on the historical user reviews to obtain positive user reviews; obtains the rated products corresponding to the positive user reviews and the target gift categories corresponding to the rated products, and obtains candidate gifts corresponding to the target gift categories from a preset gift database; obtains historical gift reviews of the candidate gifts, determines the target gift to be recommended based on the historical gift reviews and the positive user reviews, and recommends the target gift to the target user, thereby improving the accuracy of credit card gift recommendations by determining the target gifts that the user is interested in based on the target user's historical user reviews.

[0146] This invention also provides a gift recommendation device, such as... Figure 6 As shown, Figure 6 This is a schematic diagram of one embodiment of the gift recommendation device provided in this application.

[0147] The gift recommendation device integrates any of the gift recommendation apparatuses provided in the embodiments of the present invention, and the gift recommendation device includes:

[0148] One or more processors;

[0149] Memory; and

[0150] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor from the steps of the gift recommendation method described in any of the above embodiments of the gift recommendation method.

[0151] Specifically, the gift recommendation device may include components such as a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will understand that... Figure 6 The gift recommendation device structure shown does not constitute a limitation on the gift recommendation device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0152] The processor 601 is the control center of the gift recommendation device. It connects various parts of the device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, thereby providing overall monitoring of the gift recommendation device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601.

[0153] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the gift recommendation device, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0154] The gift recommendation device also includes a power supply 603 that supplies power to various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0155] The gift recommendation device may also include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0156] Although not shown, the gift recommendation device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 601 in the gift recommendation device loads the executable files corresponding to the processes of one or more applications into the memory 602 according to the following instructions, and the processor 601 runs the applications stored in the memory 602 to realize various functions, as follows:

[0157] Receive a gift recommendation request, extract the target user corresponding to the gift recommendation request, and the user attribute characteristics of the target user;

[0158] Based on the user attribute features, historical user comments of the target user are extracted, and sentiment analysis is performed on the historical user comments to obtain positive user comments;

[0159] Obtain the rated product corresponding to the positive user review, and the target gift category corresponding to the rated product; obtain the candidate gift corresponding to the target gift category from the preset gift database.

[0160] Obtain historical gift reviews of the candidate gifts, determine the target gifts to be recommended based on the historical gift reviews and the positive user reviews, and recommend the target gifts to the target users.

[0161] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0162] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0163] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0164] The above provides a detailed description of a gift recommendation method provided by the embodiments of this application. Specific embodiments have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A gift recommendation method, characterized in that, The gift recommendation method includes: Receive a gift recommendation request, extract the target user corresponding to the gift recommendation request, and the user attribute characteristics of the target user; Based on the user attribute features, historical user comments of the target user are extracted, and sentiment analysis is performed on the historical user comments to obtain positive user comments; Obtain the rated product corresponding to the positive user review, and the target gift category corresponding to the rated product; obtain the candidate gift corresponding to the target gift category from the preset gift database. The process of obtaining historical gift reviews for candidate gifts, determining target gifts to be recommended based on the historical gift reviews and positive user reviews, and recommending the target gifts to the target users includes: obtaining historical gift reviews for candidate gifts and obtaining sentiment trend data corresponding to the historical gift reviews; calculating a first rating for the candidate gifts based on the historical gift reviews and the sentiment trend data; obtaining sentiment trend mutual information of positive user reviews corresponding to the candidate gifts, and determining a second rating for the positive user reviews based on the sentiment trend mutual information; determining a recommendation score for the candidate gifts based on the first and second ratings, and determining the target gifts to be recommended based on the recommendation score.

2. The gift recommendation method as described in claim 1, characterized in that, The step of extracting historical user reviews of the target user based on the user attribute features, and performing sentiment analysis on the historical user reviews to obtain positive user reviews, includes: Obtain the user identifier from the user attribute features, and crawl the target user's historical user comments based on the user identifier; The historical user comments and preset sentiment tendency data are used to calculate the point mutual information to obtain the sentiment mutual information of the historical user comments; Historical user comments whose emotional mutual information is greater than a preset emotional tendency threshold are set as positive user comments.

3. The gift recommendation method as described in claim 1, characterized in that, The step of obtaining the rated product corresponding to the positive user review, and the target gift category corresponding to the rated product, and obtaining candidate gifts corresponding to the target gift category from a preset gift database, includes: The positive user reviews are segmented into words to obtain the product-related words within the positive user reviews; Identify the rated products corresponding to the product segmentation and obtain the target gift category corresponding to the rated products; Query the preset gift database to obtain the candidate products corresponding to the target gift category.

4. The gift recommendation method as described in claim 1, characterized in that, The step of determining the recommendation score of the candidate gift based on the first score and the second score, and determining the target gift to be recommended based on the recommendation score, includes: Obtain the target user's browsing history; The historical browsing records are clustered to obtain the historical browsing categories of the target user and the browsing percentage corresponding to each historical browsing category. The second score is weighted according to the historical browsing category and the browsing percentage to obtain the second weighted score; The recommended score of the candidate gift is determined based on the first score and the second weighted score, and the target gift to be recommended is determined based on the recommended score.

5. The gift recommendation method as described in claim 1, characterized in that, The step of determining the recommendation score of the candidate gift based on the first score and the second score, and determining the target gift to be recommended based on the recommendation score, includes: Calculate the popularity data of the candidate gifts, and determine the recommendation weight of the candidate gifts based on the popularity data and a preset popularity weight strategy; The first score of the candidate gift is weighted according to the recommendation weight to obtain the first weighted score; The recommended score of the candidate gift is calculated based on the first weighted score and the second score, and the target gift to be recommended is determined based on the recommended score.

6. The gift recommendation method as described in claim 1, characterized in that, Recommending the target gift to the target user includes: The recommended scores of the candidate gifts are compared with a preset recommended score threshold, and the candidate gifts whose recommended scores exceed the preset recommended score threshold are determined as target gifts; The target gifts are compiled, a recommended gift list is generated, and the recommended gift list is transmitted to the target user to perform the gift recommendation operation.

7. A gift recommendation device, characterized in that, The gift recommendation device includes: The acquisition module is configured to receive gift recommendation requests, extract the target user corresponding to the gift recommendation request, and the user attribute features of the target user; The sentiment analysis module is configured to extract historical user comments of the target user based on the user attribute characteristics, and perform sentiment tendency analysis on the historical user comments to obtain positive user comments; The gift acquisition module is configured to acquire the rated product corresponding to the positive user review, the target gift category corresponding to the rated product, and acquire candidate gifts corresponding to the target gift category from a preset gift database; The gift recommendation module is configured to obtain historical gift reviews of the candidate gifts, determine target gifts to be recommended based on the historical gift reviews and positive user reviews, and recommend the target gifts to the target users. This includes: obtaining historical gift reviews of the candidate gifts and obtaining sentiment data corresponding to the historical gift reviews; calculating a first rating for the candidate gifts based on the historical gift reviews and the sentiment data; obtaining sentiment mutual information of positive user reviews corresponding to the candidate gifts and determining a second rating for the positive user reviews based on the sentiment mutual information; determining a recommendation score for the candidate gifts based on the first and second ratings; and determining the target gifts to be recommended based on the recommendation score.

8. A gift recommendation device, characterized in that, The gift recommendation device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the gift recommendation method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to perform the steps of the gift recommendation method according to any one of claims 1 to 6.

Images