CN112948697A - Scientific article recommendation algorithm based on bipartite graph - Google Patents
Scientific article recommendation algorithm based on bipartite graph Download PDFInfo
- Publication number
- CN112948697A CN112948697A CN202110356572.3A CN202110356572A CN112948697A CN 112948697 A CN112948697 A CN 112948697A CN 202110356572 A CN202110356572 A CN 202110356572A CN 112948697 A CN112948697 A CN 112948697A
- Authority
- CN
- China
- Prior art keywords
- user
- bipartite graph
- recommendation algorithm
- carried out
- pushing
- 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.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000011273 social behavior Effects 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a scientific article recommendation algorithm based on bipartite graph, comprising the following steps: when a new user enters the software for the first time, judging whether the user logs in through registration or not; if the user logs in through registration, personal information is filled in and whether the user fills in personal preferences is judged preferentially, targeted pushing is carried out according to the personal preferences of the user, then selective pushing can be carried out according to the filled personal information, such as information of sex, age, occupation, location and the like, if the user does not register to log in through the identity of a tourist, pushing is carried out on the user according to current comprehensive big data.
Description
Technical Field
The invention relates to the technical field of personalized intelligent recommendation, in particular to a scientific article recommendation algorithm based on a bipartite graph.
Background
The exponential growth of the internet and world wide web has exposed people to an overload of information, too much data for users to find out what is most relevant to them. The personalized recommendation algorithm is a method capable of effectively filtering information overload at present, and can recommend interested information for a user according to the preference of the user. Bipartite graph network recommendation is a hotspot of personalized recommendation research in recent years. In the bipartite graph network, two types of nodes are included, which are respectively represented by two sets of X and Y, and only two nodes in different sets are allowed to be connected. Many systems can be modeled naturally using bipartite networks, such as sex-relationship bipartite networks, metabolic chemical and chemical reaction bipartite networks, and so forth. Due to its particular significance in social, economic and information systems, two types of bipartite graph networks are important. One type is the so-called cooperative network, which is generally defined as network actors connect through common cooperative behavior. For example, scientists join together through a joint scientific paper, and so on. Another type is called "opinion networks," where each node in a user set is associated with an object in a set of objects.
The bipartite graph algorithm needs a user to provide personal preference, calculates all objects which are not collected by the user before according to the personal preference to generate a ranking in a descending order, and recommends the top L objects to the user, but the user cannot calculate the ranking by using the bipartite graph algorithm if the user does not provide the personal preference, and provides a scientific article recommendation algorithm based on the bipartite graph to solve the problems.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides a scientific article recommendation algorithm based on a bipartite graph.
The invention provides a scientific article recommendation algorithm based on bipartite graphs, which comprises the following steps:
(1) when a new user enters the software for the first time, judging whether the user logs in through registration or not;
(2) if the user logs in through registration, personal information is filled in and whether the user fills in personal preferences is judged preferentially, targeted pushing is carried out according to the personal preferences of the user, then selective pushing can be carried out according to the filled personal information, such as information of sex, age, occupation, location and the like, and if the user does not register to log in through the identity of a tourist, pushing is carried out on the user according to current comprehensive big data;
(3) after the user logs in for a long time, the user preference can be obtained by comprehensive calculation according to the click times and the browsing duration of the user, and targeted pushing is carried out;
(4) generating a descending rank for all objects which are not collected by the user before according to the calculated association degree of the preference by using a bipartite graph recommendation algorithm, and sequentially recommending X objects positioned at the top to the user according to the rank;
(5) and synthesizing the preference of all the users to generate a comprehensive descending ranking again, and sequentially recommending the top Y objects to the new user according to the ranking.
Further, X and Y in steps (4) and (5) are the length of the recommendation list.
Further, the time that the user watches is multiplied by the number of times that the user watches to obtain a result, and the preference degree of the user can be calculated according to the result.
Further, the ratio of the number of viewing times of the user is greater than the viewing time of the user.
The invention has the beneficial effects that: the ranking is generated according to the personal preference selected by the user through the bipartite graph algorithm in a descending order for all objects which are not collected by the user before, the top L objects are recommended to the user, the user preference can be recalculated for the user logged in by the tourist according to the user clicking times and watching duration, and the ranking is pushed according to the user preference.
Drawings
Fig. 1 is a block diagram of a bipartite graph-based scientific article recommendation algorithm according to an embodiment of the present invention.
Detailed Description
The present invention will be further illustrated with reference to the following specific examples.
Example one
As shown in fig. 1, a scientific article recommendation algorithm based on bipartite graph includes the steps of:
(1) when a new user enters the software for the first time, judging whether the user logs in through registration or not;
(2) if the user logs in through registration, personal information is filled in and whether the user fills in personal preferences is judged preferentially, targeted pushing is carried out according to the personal preferences of the user, then selective pushing can be carried out according to the filled personal information, such as information of sex, age, occupation, location and the like, and if the user does not register to log in through the identity of a tourist, pushing is carried out on the user according to current comprehensive big data;
(3) after the user logs in for a long time, the user preference can be obtained by comprehensive calculation according to the click times and the browsing duration of the user, and targeted pushing is carried out;
(4) generating a descending rank for all objects which are not collected by the user before according to the calculated association degree of the preference by using a bipartite graph recommendation algorithm, and sequentially recommending X objects positioned at the top to the user according to the rank;
(5) and synthesizing the preference of all the users to generate a comprehensive descending ranking again, and sequentially recommending the top Y objects to the new user according to the ranking.
Assuming that U represents a user and P represents the number of logins, an individual user may be denoted as UP;
assuming that N represents the number of clicks and T represents the browsing duration, the total browsing duration can be expressed as NT;
assuming that O represents a browsing object, selecting two push objects can be respectively represented as ON1T1And ON2T2；
1. Judging the nature of the user:
when P is 1 and N is 0, judging the user as a new user;
when P is greater than 1 and N is 0, the user is still judged to be a new user;
and when P is greater than 1 and N is greater than 0, judging the user to be a common user.
2. Push sequence of common users:
when N is present1>N2When the object is preferentially pushed to be ON1T1；
When N is present1＝N2、N1T1>N2T2When it is, push firstIs sent to the object as ON1T1；
When N is present1＝N2、N1T1<N2T2When the object is preferentially pushed to be ON2T2；
When N is present1<N2When the object is preferentially pushed to be ON2T2。
In the present invention, X and Y in steps (4) and (5) are the length of the recommendation list.
In the invention, the time of the user watching is multiplied by the number of times of the user watching to obtain a result, and the preference degree of the user can be calculated according to the result.
In the invention, the watching times of the user is larger than the watching time of the user.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (4)
1. A scientific article recommendation algorithm based on bipartite graph is characterized by comprising the following steps:
(1) when a new user enters the software for the first time, judging whether the user logs in through registration or not;
(2) if the user logs in through registration, personal information is filled in and whether the user fills in personal preferences is judged preferentially, targeted pushing is carried out according to the personal preferences of the user, then selective pushing can be carried out according to the filled personal information, such as information of sex, age, occupation, location and the like, and if the user does not register to log in through the identity of a tourist, pushing is carried out on the user according to current comprehensive big data;
(3) after the user logs in for a long time, the user preference can be obtained by comprehensive calculation according to the click times and the browsing duration of the user, and targeted pushing is carried out;
(4) generating a descending rank for all objects which are not collected by the user before according to the calculated association degree of the preference by using a bipartite graph recommendation algorithm, and sequentially recommending X objects positioned at the top to the user according to the rank;
(5) and synthesizing the preference of all the users to generate a comprehensive descending ranking again, and sequentially recommending the top Y objects to the new user according to the ranking.
2. A bipartite graph-based scientific article recommendation algorithm according to claim 1, wherein X and Y in steps (4) and (5) are the length of the recommendation list.
3. A bipartite graph-based scientific article recommendation algorithm as claimed in claim 1, wherein the time a user watches is multiplied by the number of times the user watches to obtain a result, from which the user's preference can be calculated.
4. A bipartite graph-based scientific article recommendation algorithm as claimed in claim 1, wherein the ratio of the number of user views is greater than the user's viewing time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356572.3A CN112948697A (en) | 2021-04-01 | 2021-04-01 | Scientific article recommendation algorithm based on bipartite graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356572.3A CN112948697A (en) | 2021-04-01 | 2021-04-01 | Scientific article recommendation algorithm based on bipartite graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112948697A true CN112948697A (en) | 2021-06-11 |
Family
ID=76232076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110356572.3A Pending CN112948697A (en) | 2021-04-01 | 2021-04-01 | Scientific article recommendation algorithm based on bipartite graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112948697A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520878A (en) * | 2009-04-03 | 2009-09-02 | 华为技术有限公司 | Method, device and system for pushing advertisements to users |
| CN103440329A (en) * | 2013-09-04 | 2013-12-11 | 北京邮电大学 | Authoritative author and high-quality paper recommending system and recommending method |
| CN105260460A (en) * | 2015-10-16 | 2016-01-20 | 桂林电子科技大学 | Diversity-oriented recommendation method |
| CN105893585A (en) * | 2016-04-05 | 2016-08-24 | 电子科技大学 | Label data-based bipartite graph model academic paper recommendation method |
| CN107807958A (en) * | 2017-09-30 | 2018-03-16 | 广东南都全媒体网络科技有限公司 | A kind of article list personalized recommendation method, electronic equipment and storage medium |
| CN108920624A (en) * | 2018-06-29 | 2018-11-30 | 西安电子科技大学 | Recommended method based on evolution multi-objective Algorithm extraction system key user |
| CN110162704A (en) * | 2019-05-21 | 2019-08-23 | 西安电子科技大学 | More scale key user extracting methods based on multiple-factor inheritance algorithm |
| CN110727856A (en) * | 2019-09-04 | 2020-01-24 | 福州智永信息科技有限公司 | Optimized collaborative recommendation method and system based on low-age users |
| CN112307312A (en) * | 2019-07-30 | 2021-02-02 | 北京三好互动教育科技有限公司 | Article recommendation method and device |
-
2021
- 2021-04-01 CN CN202110356572.3A patent/CN112948697A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520878A (en) * | 2009-04-03 | 2009-09-02 | 华为技术有限公司 | Method, device and system for pushing advertisements to users |
| CN103440329A (en) * | 2013-09-04 | 2013-12-11 | 北京邮电大学 | Authoritative author and high-quality paper recommending system and recommending method |
| CN105260460A (en) * | 2015-10-16 | 2016-01-20 | 桂林电子科技大学 | Diversity-oriented recommendation method |
| CN105893585A (en) * | 2016-04-05 | 2016-08-24 | 电子科技大学 | Label data-based bipartite graph model academic paper recommendation method |
| CN107807958A (en) * | 2017-09-30 | 2018-03-16 | 广东南都全媒体网络科技有限公司 | A kind of article list personalized recommendation method, electronic equipment and storage medium |
| CN108920624A (en) * | 2018-06-29 | 2018-11-30 | 西安电子科技大学 | Recommended method based on evolution multi-objective Algorithm extraction system key user |
| CN110162704A (en) * | 2019-05-21 | 2019-08-23 | 西安电子科技大学 | More scale key user extracting methods based on multiple-factor inheritance algorithm |
| CN112307312A (en) * | 2019-07-30 | 2021-02-02 | 北京三好互动教育科技有限公司 | Article recommendation method and device |
| CN110727856A (en) * | 2019-09-04 | 2020-01-24 | 福州智永信息科技有限公司 | Optimized collaborative recommendation method and system based on low-age users |
Non-Patent Citations (2)
| Title |
|---|
| 李镇东: "基于二部图网络结构的个性化推荐***研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 郑欣欣: "基于二部图的推荐算法研究", 《内蒙古科技与经济》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10902462B2 (en) | System and method of providing a platform for managing data content campaign on social networks | |
| JP6250768B2 (en) | Facilitating interactions between users of social networks | |
| Kim et al. | Viscors: A visual-content recommender for the mobile web | |
| US8943053B2 (en) | Social data ranking and processing | |
| US8843463B2 (en) | Providing content by using a social network | |
| CN105809554B (en) | Prediction method for user participating in hot topics in social network | |
| TW201248534A (en) | Method and system of recommending items | |
| CN102165441A (en) | Method, system, and apparatus for ranking media sharing channels | |
| US20170351769A1 (en) | System and Method for a Platform to Identify and Connect Like-Minded Individuals Based on Interaction | |
| Rana et al. | Enriching and simplifying communication by social prioritization | |
| CN107346333B (en) | Online social network friend recommendation method and system based on link prediction | |
| JP5849952B2 (en) | Communication support device, communication support method, and program | |
| CN111159570A (en) | Information recommendation method and server | |
| CN114282077A (en) | Session recommendation method and system based on session data | |
| Ullah et al. | Identification of influential nodes based on temporal-aware modeling of multi-hop neighbor interactions for influence spread maximization | |
| CN113326425A (en) | Session recommendation method and system based on structure and semantic attention stacking | |
| CN112905887A (en) | Conversation recommendation method based on multi-interest short-term priority model | |
| JP5849953B2 (en) | Communication support device, communication support method, and program | |
| CN108401005B (en) | Expression recommendation method and device | |
| Wang et al. | Self-avoiding pruning random walk on signed network | |
| CN108810089A (en) | A kind of information-pushing method, device and storage medium | |
| Cui et al. | Emergence of scale-free close-knit friendship structure in online social networks | |
| CN112948697A (en) | Scientific article recommendation algorithm based on bipartite graph | |
| Kalaï et al. | User's Social Profile--Based Web Services Discovery | |
| Xiao et al. | A novel trust evaluation mechanism for collaborative filtering recommender systems |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210611 |