CN111695040B - Fashion product recommendation method, system and device based on emotion label - Google Patents
Fashion product recommendation method, system and device based on emotion label Download PDFInfo
- Publication number
- CN111695040B CN111695040B CN202010537197.8A CN202010537197A CN111695040B CN 111695040 B CN111695040 B CN 111695040B CN 202010537197 A CN202010537197 A CN 202010537197A CN 111695040 B CN111695040 B CN 111695040B
- Authority
- CN
- China
- Prior art keywords
- fashion
- user
- score
- emotion
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention discloses a fashion product recommendation method, a fashion product recommendation system and a fashion product recommendation device based on emotion labels. Acquiring scoring information and emotion label information of a user; establishing a user emotion dictionary according to the emotion label information of the user; acquiring fashion information, and calculating a popularity score according to the life cycle of the fashion; recommending fashion products according to the fashion product recommendation scores of similar users; according to the method, the objective feedback of the user on the rating of the fashion is considered, the feedback of the user is supplemented through the emotional tag of the fashion, the preference of the user can be mastered more accurately, and the recommendation performance is improved; by predicting the life cycle of the fashion, the fashion which meets the preference of the user and the current fashion style can be recommended to the user according to the change of the fashion along with the time fashion.
Description
Technical Field
The invention relates to the field of recommendation systems in computer technology, in particular to a fashion recommendation method, system and device based on emotion labels.
Background
In the process of fashion recommendation, the most important consideration is how to recommend fashion which meets the current fashion style and the preference of the user. Fashion items have different life cycles, and once the fashion item is marketed, the popularity changes over time, and after the life cycle of the fashion item, the fashion item is eventually replaced with a new fashion item. The emotion label added to the fashion product reflects the emotional preference of the user on the fashion product to a certain extent. Therefore, the fashion recommendation method based on the emotion labels is used for recommending fashion products which accord with the current fashion style and meet the self preference for users according to the popularity of the fashion products and the score of the total weight of the fashion products.
Disclosure of Invention
In order to solve the problems, the invention provides a fashion product recommendation method, a fashion product recommendation system and a fashion product recommendation device based on emotion labels.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows: a fashion recommendation method based on emotion labels comprises the following steps:
s1, acquiring grading information of a fashion product purchased by a user and emotion scores of added labels of the fashion product; acquiring the emotion score of the added label for the fashion browsed by the user;
s2, establishing an emotion dictionary of the user;
s3, acquiring information of the fashion, wherein the information of the fashion at least comprises a predicted life cycle of the fashion, and calculating the fashion score of the fashion according to the life cycle of the fashion;
s4, calculating and sequencing the total weight scores of the fashion according to the grading information of the user to the fashion and the emotion scores of the labels in the S1 to obtain a ranking list of the total weight scores of the fashion; the fashion total weight score calculation process is as follows:
calculating a fashion weight score based on the scoring information;
calculating a fashion weight score based on emotion;
fashion total weight score = (1- α) × fashion total weight score based on scoring information + α × fashion weight score based on emotion;
s5, based on the fashion total weight score of each user obtained in the S4, calculating the average total weight score mu of each user by using the label total weight score of each user u u Then, calculating a Pearson correlation coefficient by utilizing a similarity principle to obtain a ranking list of similar users v of the user u;
s6, calculating and obtaining fashion recommendation scores and sorting the fashion recommendation scores according to the fashion weight score result of the user obtained in the S4 and the fashion popularity scores of the fashion obtained in the S3 to obtain a recommendation score sorting list;
fashion recommendation score = popularity score vs. total weight of fashion score
And recommending the fashion to the similar users from the fashion recommendation score list according to the similar user ranking list obtained in the step 5.
In S2, the emotion dictionary of the user records the emotion labels and emotion scores added by the user, and the user adds and deletes the emotion labels and modifies the emotion scores at any time.
In S3, the information of the fashion further includes an issue date, a brand, and a price.
In S3, fashion popularity score:
wherein: t is the predicted life cycle of the fashion product, T is the number of days after the fashion product is issued, the fashion product popularity score is lower along with the increase of the number of issued days, and F Score The minimum value is 0, and the popularity score of the fashion product of the classic style is constantly 1.
And S4, calculating the fashion weight score based on the scoring information:
wherein r is u,i Is the value of the user as a fashion item, r u,i (h) The normalized score value of the label h added by the user for the fashion i, the score of each user is vectorized and then normalized to a unit vector:
i is the total number of all fashion items scored by the user.
In S4, the weight fraction of the fashion based on the emotion is calculated as follows:
(1) Deleting the special characters contained in the label;
(2) Removing proper nouns in the tag;
(3) Calculating the emotion scores of the tags, calculating the emotion scores of the tags by using an emotion dictionary of the user, and if the tags exist in the emotion dictionary of the user, using the scores in the emotion dictionary as the emotion scores of the tags:
w e (h u,i )＝EmotionScore(h u,i )
wherein EmotionScore (h) u,i ) Is label h in emotion dictionary u,i If the label is contained in the emotion dictionary, the emotion score of the label is the emotion score in the emotion dictionary;
if a plurality of tags exist in the emotion dictionary of the user at the same time, calculating emotion scores according to the emotion values of the tags:
where set is a set composed of multiple tags, | set | is the number of all tags in the set, | set |, which is a set composed of multiple tags emotion And | is the number of emotion labels in the set.
In S5, the average total weight score mu of each user is calculated by using the total weight score of the label of each user u u ：
I u A set of serial numbers representing fashion items that have been evaluated by user u; pearson correlation coefficients may be used to measure the similarity Sim (u, v) of the scoring vector between user u and user v, and are defined as follows:
wherein I u ∩I v Is a set of label total weight scores known to both user u and user v.
A fashion recommendation system comprising: the information acquisition module is used for acquiring the grading information of the fashion product and the emotion value of the added label from the user, acquiring the emotion dictionary of the user and acquiring the information of the fashion product;
the data processing module is used for calculating and obtaining the following information based on the grading information of the fashion product and the emotion score of the added label of the user, the emotion dictionary of the user and the information of the fashion product: the method comprises the following steps of (1) obtaining a fashion weight score based on scoring information, a fashion weight score based on emotion, a total fashion weight score, a fashion popularity score, a fashion recommendation score and a fashion recommendation score list; calculating to obtain similar users by utilizing a similarity principle based on the total weight score of the fashion products by the users;
and the recommending module is used for recommending the fashion products to the similar users based on the fashion product recommending scores, the fashion product recommending score list and the similar users.
A fashion recommendation device comprises a processor, a memory, an information acquisition device and a recommendation result output device, wherein the processor is connected with the memory through an I/O interface, the information acquisition device is connected with the input end of the processor, and the recommendation result output device is connected with the output end of the processor; the memory stores an executable computer program, and the processor can execute the fashion recommendation method in the invention when executing the executable computer program and display the recommendation result through the recommendation result output device.
Compared with the prior art, the invention has at least the following beneficial effects: according to the method, the objective feedback of the user on the rating of the fashion is considered, the feedback of the user is supplemented through the emotional tag of the fashion, the preference of the user can be mastered more accurately, and the recommendation performance is improved; by predicting the life cycle of the fashion, the fashion which accords with the preference of the user and the current popular style can be recommended to the user according to the change of the fashion along with the time popularity; the emotion dictionary can be used for conveniently managing and maintaining the emotion labels added by the user, and the fashion to be recommended can be quickly adjusted according to the emotion preference change of the user.
Drawings
Fig. 1 is a flow chart of fashion recommendation based on emotion tags.
Detailed Description
The following describes an embodiment of the present invention with reference to fig. 1.
The fashion recommendation method based on the emotion label comprises the following specific steps:
step 1, acquiring grading information of a fashion product purchased by a user and emotion scores of added labels of the fashion product; acquiring the emotion score of the added label for the fashion browsed by the user; the range of the emotion score is-1 to 1, the negative emotion score represents that the user is a negative emotion, and the closer to-1, the deeper the negative emotion degree is; a positive emotion value indicates that the user has positive emotion, and the closer to 1, the more positive emotion is.
Step 2, establishing an emotion dictionary of the user; and recording the emotion labels and the emotion scores added by the user, adding and deleting the emotion labels at any time, and modifying the emotion scores.
Step 3, obtaining information of the fashion, wherein the information of the fashion comprises a predicted life cycle, a brand and a price of the fashion; if monthly fashion is released, the life cycle of the fashion is predicted to be 30 days; if a quarterly fashion new product is issued, the life cycle of the fashion product is predicted to be 90 days; if an annual fashion novelty is released, the life cycle of the fashion is predicted to be 365 days.
According to the life cycle of the fashion, calculating to obtain the popularity score of the fashion:
wherein: t is the predicted life cycle of the fashion, and T is the number of days after the fashion is released. Fashion products have a lower and lower prevalence score as the number of days of release increases, F Score The minimum value is 0; for classical fashion products, the popularity score is constantIs 1.
Step 4, calculating the total weight score of the fashion products and sequencing the total weight score according to the grading information of the user on the fashion products and the emotion scores of the added labels in the step 1;
the fashionable product total weight score calculation steps and the method are as follows:
1. calculating the weight score of the fashion based on the scoring information:
wherein r is u,i Is the value of the user's credit for fashion. r is u,i (h) The normalized score value of label h added by the user for fashion item i. If raw scores are used as label weights, deviations may occur because the range of scores given to fashion items varies from user to user. The scores for each user are vectorized and then normalized to a unit vector:
2. emotion-based fashion weight score calculation:
the fashion weight score based on the emotion is embodied by the emotion value of the label, and in order to obtain the emotion score, the following steps are carried out on each label:
(1) Deleting the special characters contained in the label;
(2) Remove the proper noun in the tag. Proper nouns cannot accurately reflect emotions, so the proper nouns are removed when the emotion scores are calculated;
(3) The sentiment score of the tag is calculated. Calculating the emotion scores of the tags by using the emotion dictionary of the user, and if the tags exist in the emotion dictionary of the user, using the scores in the emotion dictionary as the emotion scores of the tags:
w e (h u,i )＝EmotionScore(h u,i )
wherein EmotionScore (h) u,i ) Is a conditionSense label h in dictionary u,i If the label is contained in the emotion dictionary, the emotion score of the label is the emotion score in the emotion dictionary.
If a plurality of tags exist in the emotion dictionary of the user at the same time, calculating emotion scores according to the emotion values of the tags:
where set is a set composed of multiple tags, | set | is the number of all tags in the set, | set |, which is a set composed of multiple tags emotion And | is the number of emotion labels in the set.
If the label does not exist in the emotion dictionary, the label has an emotion value of 0, and the user can add the label to the emotion dictionary and set an emotion score for the computation of the emotion value of the label later.
And (3) calculating the total weight fraction of the fashion:
weight(h u,i )＝(1-α)*w(h u,i )+α*w e (h u,i )
where α is a parameter controlling the impact of the affective tag, the total weight is calculated using only the score-based fashion weight if the tag has no sentiment value, and using only the sentiment-based fashion weight if the fashion has no sentiment value.
Step 5, constructing an m multiplied by n label total weight score matrix R = [ w ] of the user and the fashion based on the fashion total weight scores obtained in the step 4 uj ]，w uj The total weight score of the fashion item of the user u to the fashion item j is calculated in the step 4;
calculating the average total weight score mu of each user by using the total weight score of the labels of each user u u ：
I u Order showing fashion items that have been evaluated by user (line) uA set of numbers; pearson correlation coefficients may be used to measure the similarity Sim (u, v) of the scoring vector between user u and user v, and are defined as follows:
wherein I u ∩I v Is a label total weight score set known by both user u and user v;
step 6, calculating the fashion scores of the fashion products corresponding to the current day, then calculating to obtain the fashion product recommendation scores, sorting according to the size of the fashion product recommendation scores to obtain a final fashion product recommendation score list, and recommending the fashion products to other similar users from the fashion product recommendation score list according to the ranking list of the fashion product total weight scores of the similar users and the similar users obtained in the step 5;
the fashion recommendation score calculating method comprises the following steps:
Rec Score ＝F Score *weight(h u,i )
the present invention also provides a fashion recommendation system, comprising: the information acquisition module is used for acquiring the grading information of the fashion product and the emotion value of the added label from the user, acquiring the emotion dictionary of the user and acquiring the information of the fashion product;
the data processing module is used for calculating and obtaining the following information based on the grading information of the fashion product and the emotion score of the added label of the user, the emotion dictionary of the user and the information of the fashion product: a fashion weight score based on the scoring information, a fashion weight score based on the sentiment, a fashion total weight score, a fashion popularity score, a fashion recommendation score and a list of fashion recommendation scores; calculating to obtain similar users by utilizing a similarity principle based on the total weight score of the fashion products by the users;
and the recommending module is used for recommending the fashion products to the similar users based on the fashion product recommending scores, the fashion product recommending score list and the similar users.
A fashion recommendation device comprises a processor, a memory, an information acquisition device and a recommendation result output device, wherein the processor is connected with the memory through an I/O interface, the information acquisition device is connected with the input end of the processor, and the recommendation result output device is connected with the output end of the processor; the memory stores an executable computer program, and the processor can execute the fashion recommendation method in the invention when executing the executable computer program and display the recommendation result through the recommendation result output device.
As a preferred embodiment, the information acquisition device and the recommendation result output device both adopt touch displays, and the touch displays are connected with the processor through an I/O interface.
When the fashion recommendation device executes the step 1 through executing the computer program, the fashion purchased by the user is acquired through the information acquisition device, and the grading information of the fashion and the emotion score of the added label of the user are acquired; acquiring the emotion score of the added label for the fashion browsed by the user; the range of the emotion score is-1 to 1, the negative emotion score represents that the user is a negative emotion, and the closer to-1, the deeper the negative emotion degree is; if the emotion value is positive, the user is positive emotion, and the closer to 1, the deeper the positive emotion degree is; and is stored in a memory in such a manner that,
when the fashion recommendation device executes the step 2 by executing the computer program, the information acquisition device records the emotion labels and the emotion scores added by the user, can add and delete the emotion labels at any time and modify the emotion scores, and stores the information to the memory through the processor;
the memory is also stored with an instruction set for automatically acquiring information, the processor is connected with the network transmitter, the processor can execute the instruction set for automatically acquiring information to acquire the information of the step 1 and the step 2 of the invention from the network, and when the fashion recommendation device executes the step 1 and the step 2 by executing the computer program, the fashion recommendation device can be acquired by executing the instruction set for acquiring information by the processor or can be used for inputting information manually by a user.
When the fashion recommendation device executes the step 3 through executing the computer program, the fashion recommendation device acquires information of the fashion, and stores the information into a memory through a processor; meanwhile, the processor calculates the popularity score of the fashion product according to the life cycle of the fashion piece, and sends the popularity score to the memory;
when the fashion recommendation device executes the step 4 through executing the computer program, the processor calculates the fashion weight score, the fashion weight score and the fashion total weight score based on the grading information, and sends the fashion weight score, the fashion weight score and the fashion total weight score to the memory;
when the fashion recommendation device executes the step 5 by executing a computer program, based on the fashion total weight score of each user obtained in the step 4, calculating the average total weight score of each user by using the label total weight score of each user, calculating a correlation coefficient by using a similarity principle to obtain a similar user list, and sending the obtained result to a memory for storage;
when the fashion recommendation device executes the step 6 by executing the computer program, the processor reads the fashion score of the fashion obtained by executing the step 3 and the weight score result of the fashion of the user obtained by the step 4 from the memory, and calculates the recommendation score of the fashion according to the recommendation score of the fashion = fashion score and the total weight score of the fashion and sorts the recommendation scores; simultaneously reading the data of the similar users obtained in the step 5, and recommending fashion products to the similar users from the fashion product recommendation score list; and displaying the recommendation result through a recommendation result output device.
Claims (6)
1. A fashion recommendation method based on emotion labels is characterized by comprising the following steps:
s1, acquiring grading information of a fashion product purchased by a user and emotion scores of added labels of the fashion product; acquiring the emotion score of the added label for the fashion browsed by the user;
s2, establishing an emotion dictionary of the user; the emotion dictionary of the user records the emotion labels and emotion scores added by the user, and the user adds and deletes the emotion labels and modifies the emotion scores at any time;
s3, acquiring information of the fashion, wherein the information of the fashion at least comprises a predicted life cycle of the fashion, and calculating the fashion score of the fashion according to the life cycle of the fashion; fashion popularity scores were calculated as follows:
wherein: t is the predicted life cycle of the fashion product, T is the number of days after the fashion product is issued, the fashion product popularity score is lower along with the increase of the number of issued days, and F Score The minimum value is 0, and the popularity score of the fashion product of the classic style is always 1;
s4, calculating and sequencing the total weight scores of the fashion according to the grading information of the user to the fashion and the emotion scores of the labels in the S1 to obtain a ranking list of the total weight scores of the fashion; the total weight score of the fashion is calculated as follows:
calculating a fashion weight score based on the scoring information;
calculating a fashion weight score based on emotion;
fashion total weight score = (1- α) × fashion total weight score based on scoring information + α × fashion weight score based on emotion;
s5, based on the fashion total weight score of each user obtained in the S4, calculating the average total weight score mu of each user by using the label total weight score of each user u u Then, calculating a Pearson correlation coefficient by utilizing a similarity principle to obtain a ranking list of similar users v of the user u; calculating the average total weight score mu of each user by using the total weight score of the labels of each user u u ：
I u A set of numbers representing fashion items that have been evaluated by user u; pearson correlationThe coefficient can be used to measure the similarity Sim (u, v) of the scoring vector between user u and user v, and the Pearson correlation coefficient between users u and v is defined as follows:
wherein I u ∩I v Is a label total weight score set known by both user u and user v;
s6, calculating and obtaining fashion recommendation scores and sorting the fashion recommendation scores according to the fashion weight score result of the user obtained in the S4 and the fashion popularity scores of the fashion obtained in the S3 to obtain a recommendation score sorting list;
fashion recommendation score = popularity score vs. total weight of fashion score
And recommending the fashion to the similar users from the fashion recommendation score list according to the similar user ranking list obtained in the step 5.
2. The emotion tag-based fashion recommendation method of claim 1, wherein in S3, the information of the fashion further includes a release date, a brand and a price.
3. The emotion tag-based fashion recommendation method of claim 1, wherein in S4, the fashion weight score based on the scoring information is calculated by:
wherein r is u,i Is the value of the user's score for fashion, r u,i (h) Vectorizing the score of each user for the normalized score value of the label h added by the user for the fashion item i, and then normalizing the score to be a unit vector:
i is the total number of all fashion items scored by the user.
4. The emotion-tag-based fashion recommendation method of claim 1, wherein, in S4, the emotion-based fashion weight score is calculated as follows:
(1) Deleting the special characters contained in the label;
(2) Removing proper nouns in the tag;
(3) Calculating the emotion score of the tag, calculating the emotion score of the tag by using an emotion dictionary of the user, and if the tag exists in the emotion dictionary of the user, using the score in the emotion dictionary as the emotion score of the tag:
w e (h u,i )＝EmotionScore(h u,i )
wherein EmotionScore (h) u,i ) Is label h in emotion dictionary u,i If the label is contained in the emotion dictionary, the emotion score of the label is the emotion score in the emotion dictionary;
if a plurality of tags exist in the emotion dictionary of the user at the same time, calculating an emotion score according to the emotion values of the tags:
where set is a set composed of multiple tags, | set | is the number of all tags in the set, | set |, which is a set composed of multiple tags emotion And | is the number of emotion labels in the set.
5. A fashion recommendation system, comprising: the information acquisition module is used for acquiring the grading information of the fashion product and the emotion score of the added label from the user, acquiring an emotion dictionary of the user and acquiring the information of the fashion product; the emotion dictionary of the user records the emotion labels and emotion scores added by the user, and the user adds and deletes the emotion labels and modifies the emotion scores at any time;
the data processing module is used for calculating and obtaining the following information based on the grading information of the fashion product and the emotion score of the added label of the user, the emotion dictionary of the user and the information of the fashion product: the method comprises the following steps of (1) obtaining a fashion weight score based on scoring information, a fashion weight score based on emotion, a total fashion weight score, a fashion popularity score, a fashion recommendation score and a fashion recommendation score list; fashion popularity scores were calculated as follows:
wherein: t is the predicted life cycle of the fashion product, T is the number of days after the fashion product is issued, the fashion product popularity score is lower along with the increase of the number of issued days, and F Score The minimum value is 0, and the popularity score of the fashion product of the classic style is always 1;
calculating to obtain similar users by utilizing a similarity principle based on the total weight score of the fashion products by the users; calculating the average total weight score mu of each user by using the total weight score of the labels of each user u u ：
I u A set of numbers representing fashion items that have been evaluated by user u; pearson correlation coefficients may be used to measure the similarity Sim (u, v) of the scoring vector between user u and user v, and are defined as follows:
wherein I u ∩I v Is a label total weight score set known by both user u and user v;
and the recommending module is used for recommending the fashion products to the similar users based on the fashion product recommending scores, the fashion product recommending score list and the similar users.
6. The fashion recommendation device is characterized by comprising a processor, a memory, an information acquisition device and a recommendation result output device, wherein the processor is connected with the memory through an I/O interface; the memory stores an executable computer program that, when executed, enables the processor to perform the fashion recommendation method of any one of claims 1-4 and present the recommendation via a recommendation output device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537197.8A CN111695040B (en) | 2020-06-12 | 2020-06-12 | Fashion product recommendation method, system and device based on emotion label |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537197.8A CN111695040B (en) | 2020-06-12 | 2020-06-12 | Fashion product recommendation method, system and device based on emotion label |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695040A CN111695040A (en) | 2020-09-22 |
| CN111695040B true CN111695040B (en) | 2023-03-24 |
Family
ID=72480787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010537197.8A Active CN111695040B (en) | 2020-06-12 | 2020-06-12 | Fashion product recommendation method, system and device based on emotion label |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695040B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8260787B2 (en) * | 2007-06-29 | 2012-09-04 | Amazon Technologies, Inc. | Recommendation system with multiple integrated recommenders |
| KR20140140309A (en) * | 2013-05-29 | 2014-12-09 | (주) 다이퀘스트 | Method for calculating simularity between users and item recommendation method using the same |
| CN109598586B (en) * | 2018-11-30 | 2022-11-15 | 哈尔滨工程大学 | Recommendation method based on attention model |
| CN109658210A (en) * | 2019-02-18 | 2019-04-19 | 苏州大学 | A kind of Method of Commodity Recommendation, device, equipment and storage medium |
| CN110427567A (en) * | 2019-07-24 | 2019-11-08 | 东北大学 | A kind of collaborative filtering recommending method based on user preference Similarity-Weighted |
-
2020
- 2020-06-12 CN CN202010537197.8A patent/CN111695040B/en active Active
Non-Patent Citations (4)
| Title |
|---|
| A Sentiment and Interest Based Approach for Product Recommendation;Vibhu Jawa etc.;《2015 17th UKSim-AMSS International Conference on Modelling and Simulation (UKSim)》;20160926;第75-79页 * |
| Recommender System Through Sentiment Analysis;Amel Ziani etc.;《2nd International Conference on Automatic Control,Telecommunications and Signals》;20171231;第1-6页 * |
| 基于流行性预测的推荐算法研究;刘冠君;《中国优秀硕士学位论文全文数据库（信息科技辑）》;20170215;第I138-4367页 * |
| 融合标签和评分的茶产品个性化推荐研究;许瑞瑞;《中国优秀硕士学位论文全文数据库（信息科技辑）》;20170315;第I138-5996页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695040A (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177569B (en) | Recommendation processing method, device and equipment based on artificial intelligence | |
| CN108536852B (en) | Question-answer interaction method and device, computer equipment and computer readable storage medium | |
| US20110258054A1 (en) | Automatic Generation of Bid Phrases for Online Advertising | |
| CN109064285B (en) | Commodity recommendation sequence and commodity recommendation method | |
| CN107590675A (en) | A kind of recognition methods of user's Shopping Behaviors, storage facilities and mobile terminal based on big data | |
| WO2020221022A1 (en) | Service object recommendation method | |
| CN110955750A (en) | Combined identification method and device for comment area and emotion polarity, and electronic equipment | |
| CN113946754A (en) | User portrait based rights and interests recommendation method, device, equipment and storage medium | |
| CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
| CN110852785A (en) | User grading method, device and computer readable storage medium | |
| US11501334B2 (en) | Methods and apparatuses for selecting advertisements using semantic matching | |
| CN115760202A (en) | Product operation management system and method based on artificial intelligence | |
| CN115147130A (en) | Problem prediction method, apparatus, storage medium, and program product | |
| CN113792134B (en) | User service method and system based on digital twin technology | |
| CN105760965A (en) | Pre-estimated model parameter training method, service quality pre-estimation method and corresponding devices | |
| CN115222433A (en) | Information recommendation method and device and storage medium | |
| CN111695040B (en) | Fashion product recommendation method, system and device based on emotion label | |
| CN117112775A (en) | Technique for automatically filling in an input form to generate a list | |
| CN112328918B (en) | Commodity sorting method, computing device and computer-readable storage medium | |
| US20240062264A1 (en) | Ai- backed e-commerce for all the top rated products on a single platform | |
| CN113254623B (en) | Data processing method, device, server, medium and product | |
| CN115439156A (en) | Method and device for recommending advertisement space, computer equipment and storage medium | |
| CN109146606A (en) | A kind of brand recommended method, electronic equipment, storage medium and system | |
| CN111639274B (en) | Online commodity intelligent sorting method, device, computer equipment and storage medium | |
| CN114971767A (en) | Information processing method, information processing device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |