CN111026966A - Search recommendation ranking method based on user, product portrait and correlation degree of user and product portrait - Google Patents
Search recommendation ranking method based on user, product portrait and correlation degree of user and product portrait Download PDFInfo
- Publication number
- CN111026966A CN111026966A CN201911242968.4A CN201911242968A CN111026966A CN 111026966 A CN111026966 A CN 111026966A CN 201911242968 A CN201911242968 A CN 201911242968A CN 111026966 A CN111026966 A CN 111026966A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- similarity
- product
- hidden
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 230000006399 behavior Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
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]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a search recommendation ranking method based on user and product portrait and correlation degree of the user and the product portrait, which comprises the following steps: generating features in the user representation relating to the content of the product using a conventional recommendation system, such as an item-based recommendation model; using a commonly used user behavior matrix concept in a collaborative filtering recommendation system, regarding all users who purchased a certain commodity or consulted a single content as an implicit user of the content, and generating a behavior matrix of the implicit user in a product portrait; generating new characteristics to describe the similarity between the search user and the search target; the similarity between a search user and a search target is described in multiple angles, and the importance degree of each training data set characteristic is judged by using an LTR algorithm. The invention fully considers the ordering mode of the user personality, so that the ordering is more targeted, thereby improving the ordering effect and the user satisfaction.
Description
Technical Field
The patent application belongs to the technical field of in-station search systems, and particularly relates to a search recommendation sorting method based on user and product portrait and correlation degree of the user and the product portrait.
Background
Most of the existing in-site search engines use models such as VSM and BM25 to sort search sentences and commodity descriptions based on semantic similarity when performing search sorting, or sort search results according to commodity heat and content heat. This sort does not take into account the personality of the searcher. Even if the system considers the personality of the searcher, the user image of the searcher and the product/content image of the search result are not related when generating the characteristics, or the similarity degree of the two images is considered, so the existing in-site search engine is not enough for improving the accuracy of sequencing and providing personalized and targeted services for the user.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a search recommendation sorting method based on the user, the product portrait and the correlation degree of the user and the product portrait, which can improve the sorting accuracy and provide personalized and targeted services for the user.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a search recommendation sorting method based on user and product portrait and correlation degree of the user and the product portrait comprises the following steps:
s1, generating the comprehensive commodity characteristics of the user related to the product content in the original user portrait according to the attributes of all commodities purchased or consulted by a certain user;
s2, generating hidden user characteristics of the commodity related to the user content in the original product portrait according to the behavior characteristics of all users who have bought or consulted a certain commodity;
s3, carrying out multiple similarity calculation on the comprehensive commodity characteristics of the user in the S1 and the attribute characteristics of the corresponding commodities in the sample to generate multiple commodity similarity results; meanwhile, carrying out multiple similarity calculation on the hidden user characteristics of the commodity in the S2 and the behavior characteristics of the corresponding user in the sample to obtain multiple user similarity results;
s4, judging a plurality of commodity similarity results and a plurality of user similarity results in the S3, and calculating the importance degree of each similarity result through a learning sequencing model;
and S5, outputting the similarity result with the highest importance degree, namely outputting the commodity similarity result with the highest importance degree and the user similarity result, so as to predict and recommend the purchasing behavior.
The technical scheme of the invention is further improved as follows: at S1, a user' S comprehensive merchandise features are generated in the original user representation using a conventional recommendation system.
The technical scheme of the invention is further improved as follows: the traditional recommendation system is an item-based recommendation model or a user-based recommendation model.
The technical scheme of the invention is further improved as follows: in S2, a hidden user characteristic of the commodity is generated in the original product portrait by using a user behavior matrix algorithm in the collaborative filtering recommendation system.
The technical scheme of the invention is further improved as follows: in S3, the similarity calculation includes vector similarity, cross-phase, singular value decomposition SVD, where:
s31, calculating cosine similarity according to the cosine similarity calculation formula:
a is the comprehensive commodity characteristics of the user or the hidden user characteristics of the commodity, and B is the attribute characteristics of the corresponding commodity in the sample or the behavior characteristics of the corresponding user in the sample; a, B, wherein bold and non-bold have different meanings, bold represents a vector, non-bold represents an element in the vector, and the specific number i is combined with the subscript i;
s32, cross phase: generating cross items for the comprehensive commodity characteristics of the user and the attribute characteristics of the corresponding commodities in the sample, and generating cross items for the hidden user characteristics of the commodities and the behavior characteristics of the corresponding users in the sample;
s33 behavior characteristics for all users and all quotientsThe hidden user characteristic of the product is taken as SVD and is recorded as M ═ U ∑ VTThe matrix M is a matrix formed by behavior characteristics of all users or a matrix formed by hidden user characteristics of all commodities, and the matrix U obtained after SVD enables similar users and commodities with similar hidden users to be mapped to closer positions in a final characteristic space.
The technical scheme of the invention is further improved as follows: in S4, the learning ranking model is LTR algorithm.
Due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. combining with a traditional recommendation algorithm, fusing evaluation indexes based on the traditional algorithm into the characteristics of an LTR (learning Toank) model;
2. describing the similarity between the user and the product from different angles by using a plurality of similarity calculation modes, and learning the importance of various similarities by using a model;
3. the dimension increasing mode enables the similarity between the user and the content to be displayed in the characteristics, so that the basic enhancement of the learning effect of the model is realized;
4. the problem of cold start of new products and new contents can be effectively solved when only the comprehensive commodity characteristics of the user are used;
5. the sorting mode fully considering the user personality can lead the sorting to be more targeted, and improve the sorting effect and the user satisfaction.
Drawings
FIG. 1 is a schematic process diagram of the present invention;
FIG. 2 is a schematic diagram of the class A feature principle of the embodiment of the present invention;
fig. 3 is a schematic diagram of the principle of class B features according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples.
As shown in FIGS. 1 to 3, the invention discloses a search recommendation ranking method based on user and product portraits and their association degree, the process is:
s1, according to the attributes of all commodities purchased or consulted by a certain user, generating the comprehensive commodity characteristics of the user related to the product content by using the traditional recommendation system in the original user portrait and performing summary calculation; the summary calculation manner in S1 includes one or more of weighted average, logical and, logical or. The weighted average, logical and, logic or operations performed on all the commodities purchased by the user exist different summary calculation methods because the commodity characteristics include different data types such as numerical type and discrete type, and the weighted average is used for the numerical type, and the logical and, logical or is used for the discrete type.
S2, according to the behavior characteristics of all users who bought or consult a certain commodity, generating hidden user characteristics of the commodity relevant to the user content after summarizing and calculating the user behavior matrix concept in the collaborative filtering recommendation system used in the original product portrait; the aggregate calculation in S1 is collaborative filtering and weighted averaging.
S3, carrying out multiple similarity calculation on the comprehensive commodity characteristics of the user in the S1 and the attribute characteristics of the corresponding commodities in the sample to generate multiple commodity similarity results; meanwhile, carrying out multiple similarity calculation on the hidden user characteristics of the commodity in the S2 and the behavior characteristics of the corresponding user in the sample to obtain multiple user similarity results;
s4, judging a plurality of commodity similarity results and a plurality of user similarity results in the S3, and calculating the importance degree of each similarity result through a learning sequencing model; the Learning ranking model is LTR algorithm (Learning to Rank).
S5, outputting the similarity result with the highest importance degree, namely outputting the commodity similarity result with the highest importance degree and the user similarity result, so as to predict and recommend purchasing behavior;
in S1, a traditional recommendation system is used to generate a comprehensive commodity feature of the user in the original user portrait, such as an item-based recommendation model or a user-based recommendation model.
In S2, a hidden user characteristic of the commodity is generated in the original product portrait by using a user behavior matrix algorithm in the collaborative filtering recommendation system.
In S3, the similarity calculation includes vector similarity, cross-phase, singular value decomposition SVD, where:
s31, calculating cosine similarity according to the cosine similarity calculation formula:
a is the comprehensive commodity characteristics of the user or the hidden user characteristics of the commodity, and B is the attribute characteristics of the corresponding commodity in the sample or the behavior characteristics of the corresponding user in the sample; a, B, wherein bold and non-bold have different meanings, bold represents a vector, non-bold represents an element in the vector, and the specific number i is combined with the subscript i;
s32, cross phase: generating cross items for the comprehensive commodity characteristics of the user and the attribute characteristics of the corresponding commodities in the sample, and generating cross items for the hidden user characteristics of the commodities and the behavior characteristics of the corresponding users in the sample;
s33, taking SVD of the behavior characteristics of all users and the hidden user characteristics of all commodities, and recording as M ═ U ∑ VTThe matrix M is a matrix formed by behavior characteristics of all users or a matrix formed by hidden user characteristics of all commodities, and the matrix U obtained after SVD enables similar users and commodities with similar hidden users to be mapped to closer positions in a final characteristic space.
SVD also decomposes matrices, but unlike eigen decomposition, SVD does not require that the matrix to be decomposed be a square matrix. Assuming that our matrix A is an m × n m × n matrix, we define the SVD of matrix A as: u- Σ VT
Where U is an m x m matrix, Σ is an m x n matrix, all 0's except for the elements on the main diagonal, each element on the main diagonal is called a singular value, and V is an n x n matrix. Both U and V are unitary matrices, i.e. satisfy UTU＝I，VTV＝I。
The following examples are given for illustration purposes:
1) generating characteristics related to product contents in a user portrait by using a traditional recommendation system such as an item-based recommendation model, wherein the partial characteristics are referred to as class A characteristics, similarity can be directly calculated with the characteristics related to the product contents in the product portrait, such as attributes of commodities P1, P2, P3 and the like purchased by a user U1, and the class A characteristics of the user U1 are formed;
2) the method comprises the steps that a common user behavior matrix concept in a collaborative filtering recommendation system is used, all users who buy a certain commodity or look up a single content are regarded as an 'implicit user' of the content, a behavior matrix of the 'implicit user' is generated in a product image, the partial characteristics are called as B-type characteristics in the following, and the similarity can be directly calculated with behavior information in the user image; such as user U1, user U2, user U3, etc., who had purchased P1, form a class B feature of item P1.
3) And generating new characteristics to describe the similarity degree between the A-type characteristics and the B-type characteristics by using the following methods respectively:
(1) respectively calculating the similarity of the two types of features by using a vector similarity calculation formula, such as cosine similarity;
(2) generating cross-phase for the two kinds of characteristics;
(3) and performing SVD (singular value decomposition) on the user behavior characteristics and the commodity B characteristics.
Here, these similarity calculation methods can be used simultaneously, and the results are passed into the LTR model as features. The similarity here is used to describe the similarity between the user and the user group who purchased the product before. The higher the degree of similarity theoretically, the more likely the user is to purchase the item.
4) And describing the similarity between the search user and the search target from multiple angles, and judging the importance degree of the input features of each training data set by using an LTR (Learning ToRank) algorithm, thereby carrying out more effective search recommendation and improving the sequencing effect and the user satisfaction.
Claims (6)
1. A search recommendation ranking method based on user and product portrait and correlation degree of the user and the product portrait is characterized by comprising the following steps:
s1, generating the comprehensive commodity characteristics of the user related to the product content in the original user portrait according to the attributes of all commodities purchased or consulted by a certain user;
s2, generating hidden user characteristics of the commodity related to the user content in the original product portrait according to the behavior characteristics of all users who have bought or consulted a certain commodity;
s3, carrying out multiple similarity calculation on the comprehensive commodity characteristics of the user in the S1 and the attribute characteristics of the corresponding commodities in the sample to generate multiple commodity similarity results; meanwhile, carrying out multiple similarity calculation on the hidden user characteristics of the commodity in the S2 and the behavior characteristics of the corresponding user in the sample to obtain multiple user similarity results;
s4, judging a plurality of commodity similarity results and a plurality of user similarity results in the S3, and calculating the importance degree of each similarity result through a learning sequencing model;
and S5, outputting the most important similarity result, and predicting and recommending purchasing behavior.
2. The method of claim 1, wherein the search recommendation ranking method is based on user and product portraits and their association degrees, and further comprising: at S1, a user' S comprehensive merchandise features are generated in the original user representation using a conventional recommendation system.
3. The method of claim 2, wherein the search recommendation ranking method is based on user and product portraits and their association degrees, and further comprising: the traditional recommendation system is an item-based recommendation model or a user-based recommendation model.
4. The method of claim 1, wherein the search recommendation ranking method is based on user and product portraits and their association degrees, and further comprising: in S2, a hidden user characteristic of the commodity is generated in the original product portrait by using a user behavior matrix algorithm in the collaborative filtering recommendation system.
5. The method of claim 1, wherein the search recommendation ranking method is based on user and product portraits and their association degrees, and further comprising: in S3, the similarity calculation includes vector similarity, cross-phase, singular value decomposition SVD, where:
s31, calculating cosine similarity according to the cosine similarity calculation formula:
a is the comprehensive commodity characteristics of the user or the hidden user characteristics of the commodity, and B is the attribute characteristics of the corresponding commodity in the sample or the behavior characteristics of the corresponding user in the sample; a, B, wherein bold and non-bold have different meanings, bold represents a vector, non-bold represents an element in the vector, and the specific number i is combined with the subscript i;
s32, cross phase: generating cross items for the comprehensive commodity characteristics of the user and the attribute characteristics of the corresponding commodities in the sample, and generating cross items for the hidden user characteristics of the commodities and the behavior characteristics of the corresponding users in the sample;
s33, taking SVD of the behavior characteristics of all users and the hidden user characteristics of all commodities, and recording as M ═ U ∑ VTThe matrix M is a matrix formed by behavior characteristics of all users or a matrix formed by hidden user characteristics of all commodities, and the matrix U obtained after SVD enables similar users and commodities with similar hidden users to be mapped to closer positions in a final characteristic space.
6. The method of claim 1, wherein the search recommendation ranking method is based on user and product portraits and their association degrees, and further comprising: in S4, the learning ranking model is LTR algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911242968.4A CN111026966B (en) | 2019-12-06 | 2019-12-06 | Search recommendation ordering method based on user and product portrait and association degree of user and product portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911242968.4A CN111026966B (en) | 2019-12-06 | 2019-12-06 | Search recommendation ordering method based on user and product portrait and association degree of user and product portrait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111026966A true CN111026966A (en) | 2020-04-17 |
| CN111026966B CN111026966B (en) | 2023-12-22 |
Family
ID=70207466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911242968.4A Active CN111026966B (en) | 2019-12-06 | 2019-12-06 | Search recommendation ordering method based on user and product portrait and association degree of user and product portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026966B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418956A (en) * | 2020-12-16 | 2021-02-26 | 国网雄安金融科技集团有限公司 | Financial product recommendation method and device |
| CN114943573A (en) * | 2022-03-30 | 2022-08-26 | 爱友智信息科技(苏州)有限公司 | Retail SaaS platform-based user portrait construction method, system and storage medium |
| CN114996589A (en) * | 2022-08-02 | 2022-09-02 | 八爪鱼人工智能科技(常熟)有限公司 | Online information pushing method and system based on epidemic prevention big data |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000079453A2 (en) * | 1999-06-18 | 2000-12-28 | I2 Technologies, Inc. | Product substitution search method |
| JP2010092432A (en) * | 2008-10-10 | 2010-04-22 | Nec Corp | Data similarity calculation system, method, and program |
| JP2012027757A (en) * | 2010-07-26 | 2012-02-09 | Dainippon Printing Co Ltd | Commodity recommendation device, commodity recommendation system, commodity recommendation method, and program |
| CN103093376A (en) * | 2013-01-16 | 2013-05-08 | 北京邮电大学 | Clustering collaborative filtering recommendation system based on singular value decomposition algorithm |
| US20150379609A1 (en) * | 2014-06-30 | 2015-12-31 | Kobo Incorporated | Generating recommendations for unfamiliar users by utilizing social side information |
| CN106327227A (en) * | 2015-06-19 | 2017-01-11 | 北京航天在线网络科技有限公司 | Information recommendation system and information recommendation method |
| CN107301592A (en) * | 2017-07-19 | 2017-10-27 | 北京京东尚科信息技术有限公司 | The method and device excavated for commodity substitute |
| US20180107685A1 (en) * | 2016-10-16 | 2018-04-19 | Ebay Inc. | Intelligent online personal assistant with offline visual search database |
| CN108647996A (en) * | 2018-04-11 | 2018-10-12 | 中山大学 | A kind of personalized recommendation method and system based on Spark |
| CN109191240A (en) * | 2018-08-14 | 2019-01-11 | 北京九狐时代智能科技有限公司 | A kind of method and apparatus carrying out commercial product recommending |
| CN109783738A (en) * | 2019-01-22 | 2019-05-21 | 东华大学 | A kind of double extreme learning machine mixing collaborative filtering recommending methods based on more similarities |
-
2019
- 2019-12-06 CN CN201911242968.4A patent/CN111026966B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000079453A2 (en) * | 1999-06-18 | 2000-12-28 | I2 Technologies, Inc. | Product substitution search method |
| JP2010092432A (en) * | 2008-10-10 | 2010-04-22 | Nec Corp | Data similarity calculation system, method, and program |
| JP2012027757A (en) * | 2010-07-26 | 2012-02-09 | Dainippon Printing Co Ltd | Commodity recommendation device, commodity recommendation system, commodity recommendation method, and program |
| CN103093376A (en) * | 2013-01-16 | 2013-05-08 | 北京邮电大学 | Clustering collaborative filtering recommendation system based on singular value decomposition algorithm |
| US20150379609A1 (en) * | 2014-06-30 | 2015-12-31 | Kobo Incorporated | Generating recommendations for unfamiliar users by utilizing social side information |
| CN106327227A (en) * | 2015-06-19 | 2017-01-11 | 北京航天在线网络科技有限公司 | Information recommendation system and information recommendation method |
| US20180107685A1 (en) * | 2016-10-16 | 2018-04-19 | Ebay Inc. | Intelligent online personal assistant with offline visual search database |
| CN107301592A (en) * | 2017-07-19 | 2017-10-27 | 北京京东尚科信息技术有限公司 | The method and device excavated for commodity substitute |
| CN108647996A (en) * | 2018-04-11 | 2018-10-12 | 中山大学 | A kind of personalized recommendation method and system based on Spark |
| CN109191240A (en) * | 2018-08-14 | 2019-01-11 | 北京九狐时代智能科技有限公司 | A kind of method and apparatus carrying out commercial product recommending |
| CN109783738A (en) * | 2019-01-22 | 2019-05-21 | 东华大学 | A kind of double extreme learning machine mixing collaborative filtering recommending methods based on more similarities |
Non-Patent Citations (3)
| Title |
|---|
| J.M. KELLER等: "LevenshteinOWA operators for gene product similarity, clustering, and knowledge discovery", 《NAFIPS 2005 - 2005 ANNUAL MEETING OF THE NORTH AMERICAN FUZZY INFORMATION PROCESSING SOCIETY》, pages 233 - 234 * |
| 廖列法等: "隐式反馈场景中结合信任与相似度的排序推荐", 《计算机应用研究》, vol. 35, no. 12, pages 3614 - 3617 * |
| 鲁辉等: "基于产品属性及用户偏好的个性化产品推荐方法", 《贵州师范大学学报》, vol. 35, no. 1, pages 87 - 92 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418956A (en) * | 2020-12-16 | 2021-02-26 | 国网雄安金融科技集团有限公司 | Financial product recommendation method and device |
| CN114943573A (en) * | 2022-03-30 | 2022-08-26 | 爱友智信息科技(苏州)有限公司 | Retail SaaS platform-based user portrait construction method, system and storage medium |
| CN114996589A (en) * | 2022-08-02 | 2022-09-02 | 八爪鱼人工智能科技(常熟)有限公司 | Online information pushing method and system based on epidemic prevention big data |
| CN114996589B (en) * | 2022-08-02 | 2022-10-21 | 八爪鱼人工智能科技(常熟)有限公司 | Online information pushing method and system based on epidemic prevention big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111026966B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Archak et al. | Show me the money! Deriving the pricing power of product features by mining consumer reviews | |
| Chen et al. | Developing recommender systems with the consideration of product profitability for sellers | |
| US8903811B2 (en) | System and method for personalized search | |
| Zhang et al. | An improved hybrid collaborative filtering algorithm based on tags and time factor | |
| TWI505212B (en) | A method and system for bidding on advertisements | |
| Cheng et al. | Video ecommerce++: Toward large scale online video advertising | |
| CN111026966B (en) | Search recommendation ordering method based on user and product portrait and association degree of user and product portrait | |
| Li et al. | Grocery shopping recommendations based on basket-sensitive random walk | |
| Chen et al. | A novel collaborative filtering approach for recommending ranked items | |
| CN107330727A (en) | A kind of personalized recommendation method based on hidden semantic model | |
| Chen et al. | Common pitfalls in training and evaluating recommender systems | |
| CN109858770A (en) | Object quality appraisal procedure and device | |
| Ahamed et al. | A recommender system based on deep neural network and matrix factorization for collaborative filtering | |
| Li et al. | A survey of researches on personalized bundle recommendation techniques | |
| CN110968675A (en) | Recommendation method and system based on multi-field semantic fusion | |
| Garfinkel et al. | Empirical analysis of the business value of recommender systems | |
| Knotzer | Product recommendations in e-commerce retailing applications | |
| Hooda et al. | A study of recommender systems on social networks and content-based web systems | |
| Driskill et al. | Recommender systems for e-commerce: Challenges and opportunities | |
| Padti et al. | Hybrid Movie Recommender System | |
| Wan et al. | A classification of product comparison agents | |
| Bao et al. | Collaborative filtering with user ratings and tags | |
| Sonkusare et al. | E-commerce Shopping System with Semantic Search and Recommender System | |
| Gao et al. | E‐Commerce Personalized Recommendation Model Based on Semantic Sentiment | |
| Racherla | Graph Neural Network for Service Recommender System in Digital Service Marketplace |
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 |