CN106709076B - Social network recommendation device and method based on collaborative filtering - Google Patents
Social network recommendation device and method based on collaborative filtering Download PDFInfo
- Publication number
- CN106709076B CN106709076B CN201710106305.4A CN201710106305A CN106709076B CN 106709076 B CN106709076 B CN 106709076B CN 201710106305 A CN201710106305 A CN 201710106305A CN 106709076 B CN106709076 B CN 106709076B
- Authority
- CN
- China
- Prior art keywords
- user
- social network
- recommendation
- users
- attribute
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000006399 behavior Effects 0.000 claims description 48
- 239000013598 vector Substances 0.000 claims description 27
- 238000012216 screening Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 230000000977 initiatory effect Effects 0.000 claims description 4
- 230000008447 perception Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013549 information retrieval technique Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a social network recommendation device and a social network recommendation method based on collaborative filtering. Compared with the traditional recommendation device based on demographics and content, the recommendation device emphasizes the difference among users, can continuously learn and innovate a recommendation engine aiming at the historical data of the users, and has stronger robustness. Moreover, by utilizing the collaborative filtering idea, the method is more in line with the friend making scene of the user in the real social scene, and the recommended result tends to be accurate.
Description
Technical Field
The invention relates to the technical field of information recommendation, in particular to a social network recommendation device and method based on collaborative filtering.
Background
Summary the rapid growth of internet information creates a vast amount of data, and users often consume a great deal of time and effort to find information of interest to themselves. Inefficient internet information retrieval techniques have become a bottleneck that prevents users from efficiently utilizing information, and recommended techniques have been developed in such a context. The recommendation technology can effectively solve the problem of information overload, and retrieves content helpful to the user from mass data. Current recommendation techniques generally recommend to a single user at the same time, but in real-world applications, recommendation to a certain group may often be required, such as a tourist group to travel destination, a party dining place, and a family movie viewing plan. The interests and hobbies among the group members have great diversity, so the traditional recommendation technology is difficult to meet the requirements of group recommendation, and the research on the group recommendation technology based on the social network has important practical significance.
The research of the recommending device and the social network group recommending device relates to the technical fields of personal recommending devices, social networks, group decisions and the like. Most existing recommending devices are personal recommending devices, i.e. recommending behaviors intended to serve a single user, and the most commonly used recommending algorithms are collaborative filtering recommending algorithms and content-based recommending algorithms; the collaborative filtering algorithm recommends by referring to the behaviors of users with similar interests to the recommended users, the content-based recommendation algorithm analyzes the historical content accessed by the recommended users, and recommends by utilizing the similarity degree of different contents.
Disclosure of Invention
A first object of the present invention is to solve the above-mentioned drawbacks of the prior art, and to provide a social network recommendation device based on collaborative filtering.
Another object of the present invention is to solve the above-mentioned drawbacks of the prior art, and to provide a social network recommendation method based on collaborative filtering.
The first object of the present invention can be achieved by adopting the following technical scheme:
the social network recommending device based on collaborative filtering comprises a starting module, a filtering module, a recommending module and a sequencing module which are connected in sequence,
the starting module is used for initializing and defining behavior data and personal attributes of the recommended social network users, classifying the behaviors of the users, setting the conditions of an initial search engine, initiating a recommendation request to the recommendation engine, and sending an initialized data set to the recommendation engine;
the filtering module filters users which do not meet the requirements through basic search conditions set in the social network by a basic search engine to form a recommended candidate set A;
the recommendation module screens the recommendable candidate set A according to the historical behaviors and data of the users to obtain a basic user interest set, and obtains a recommendable result set B of each user based on the collaborative filtering thought of the users;
and the ordering module divides the behavior data and the personal attribute of the social network user according to the recommendable result set B, and orders the interested set of the social network user to obtain a preliminary recommendation list C.
Further, the initial personal attribute of the user is filled in by the user when registering, and the recommendation engine can conduct feature division for the initial user according to the personal attribute value filled in by the user.
Further, when the number of people in the recommended candidate set a after filtering and screening is less than the minimum calculated number of people, the recommendation engine in the starting module sends an instruction, and the social network enlarges the screening range or increases the screening number of people.
The other object of the invention can be achieved by adopting the following technical scheme:
a social network recommendation method based on collaborative filtering, the recommendation method comprising the steps of:
s1, a starting module carries out initialization definition on behavior data and personal attributes of a recommended social network user through a service party, classifies the behavior data of the user, sets conditions of an initial search engine, initiates a recommendation request to the recommendation engine after initialization setting and recommendation engine access are completed, and sends an initialized data set to the recommendation engine;
s2, the filtering module gathers data meeting the search conditions through a recommendation engine according to the conditions of an initial search engine of a service party to form a primary recommended candidate set, the primary recommended candidate set is judged to obtain a similar user set through similarity, and data screening is carried out based on collaborative filtering ideas of users to obtain a recommended candidate set A;
s3, screening the recommendable candidate set A according to historical behaviors and data of the recommended social network users by a recommendation module to obtain a basic user interest set, and obtaining a recommendable result set B of each recommended social network user based on collaborative filtering thought of the user;
and S4, dividing the characteristic values of the personal attributes according to the personal attributes of the recommended social network users, obtaining the weight of each attribute characteristic value in the user of the recommended result set B according to the proportion of each characteristic value in the user 'S interest set, obtaining the attribute with the most sensitive perception of the user according to each most obvious characteristic set, and sequencing the user' S interest set according to different reference weights of the attribute with the most sensitive perception to obtain the preliminary recommendation list C.
Further, the specific process of step S2 is as follows:
s201, the social network sets an initial screening condition for the user, and the user selects or directly sets according to the historical behaviors of the user.
And S202, the social network sends the initial screening conditions and the initialized data set to a recommendation engine, and the recommendation engine screens according to the conditions to form a recommendable candidate set A.
Further, the specific process of step S3 is as follows:
s301, dividing the behavior of the user into T 1 ～T K K classes are added, and weights are assigned to the K classes of behaviors respectively 1 ～w k The method comprises the steps of dividing the user behavior into positive, negative, high, medium and low dimensions according to different user behaviors, wherein the value of an assignment vector w is w= [ 2, -1,0,1,2,3 ];
s302, acquiring a behavior operation accumulated value of a user on a social network user to obtain a preference H= Σwof the user on the social network user;
s303, utilizing Euclidean distance according to favorites H of different users on each social network user
And calculating to obtain the similarity between users:
when the similarity sim (x, y) > k between two users is determined by the service party, that is, the two users are considered to be similar, so as to obtain a similar user set, and based on the collaborative filtering thought of the users, a recommended result set B of each user is obtained.
Further, the specific process of step S4 is as follows:
s401, dividing the personal attribute and the characteristic value of the recommended social network user according to the recommended result set B, and setting the personal attribute vector of the recommended social network user as:
attribute S i The eigenvalue vectors of (a) are:
s402, constructing an attribute feature matrix through the distinguishing degree vector of each personal attribute and the candidate recommendation set;
for user A, candidate recommendation set Q T Personal attribute S of a certain social network user i Characteristic value v of (2) k At the position ofThe proportion is->Then at candidate recommendation set Q T Setting the characteristic value v of the personal attribute of the social network user k The weight is as follows:
in addition, when(i, k take any value)
Then consider the personal attribute S x The degree of distinction is the strongest; discrimination of each attribute is taken:
therefore, when Q is given A Then, a desirability discrimination vector can be obtained:
obtaining Q T Then, the attribute feature matrix of the social network user can be obtained:
s403, according to the attribute feature matrix and the attribute distinguishing degree vector, a candidate recommendation set Q can be obtained T Is a recommendation score vector for each social network user:
s404, determining a preliminary recommendation list C according to the obtained recommendation score vector and the sequence of the recommendable result set B.
Further, the personal attribute and the characteristic value of the recommended social network user are defined in a manner of [ attribute-value ] key value pairs.
Further, when the user's preference for social network users, H >3, then the user is considered interested in the item.
Compared with the prior art, the invention has the following advantages and effects:
compared with the traditional recommendation device based on demographics and content, the social network recommendation device emphasizes the difference among users, can continuously learn and innovate a recommendation engine according to the historical data of the users, and has stronger robustness. Moreover, by utilizing the collaborative filtering idea, the method is more in line with the friend making scene of the user in the real social scene, and the recommended result tends to be accurate.
Drawings
FIG. 1 is a block diagram of a collaborative filtering-based social network recommender in accordance with the present disclosure;
FIG. 2 is a flow chart of a collaborative filtering-based social network recommendation method disclosed herein.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
As shown in fig. 1, this embodiment discloses a social network recommendation device based on coordinated filtering, which designs a set of recommendation engines for making friends on a social network by referring to collaborative filtering ideas and content-based recommendation ideas.
The social network recommending device specifically comprises a starting module, a filtering module, a recommending module and a sequencing module which are connected in sequence,
the starting module is used for initializing and defining behavior data and personal attributes of the recommended social network users, classifying the behaviors of the users, setting the conditions of an initial search engine, initiating a recommendation request to the recommendation engine, and sending an initialized data set to the recommendation engine;
in a specific embodiment, the working process of the starting module is as follows:
the service party performs initialization definition on behavior data and personal attributes of the recommended social network users, classifies the behaviors of the users, sets conditions of an initial search engine, initiates a recommendation request to the recommendation engine after initialization setting and recommendation engine access are completed, and sends an initialized data set to the recommendation engine.
In a specific application, the initial personal attribute of the user is filled in by the user during registration, and the recommendation engine can perform feature division for the initial user according to the personal attribute value filled in by the user.
The filtering module filters out users which do not meet the requirements through basic search conditions set in the social network by a basic search engine to form a recommended candidate set A, and the purpose of simplifying the calculation amount of the recommending device is achieved.
The main working principle is as follows:
1) The social network sets an initial screening condition for the user, and the user selects or directly sets the initial screening condition according to the historical behavior of the user.
2) The social network sends the initial screening conditions and the initialized data set to a recommendation engine, and the recommendation engine screens according to the conditions to form a recommendable candidate set A.
3) When the number of the screened people is less than the minimum calculated number of people, the recommendation engine sends an instruction, and the social network enlarges the screening range or increases the number of the screened people.
The recommendation module screens the recommendable candidate set A according to the historical behaviors and data of the users to obtain a basic user interest set, and obtains a recommendable result set B of each user based on the collaborative filtering thought of the users.
The module is a core module of the recommending device, and is mainly used for further screening the screened users according to the historical behaviors and data of the users to obtain a basic user interest set.
The main working principle is as follows:
1) Classifying the behaviors of the user, and respectively carrying out weight assignment on the classified behaviors.
2) The recommendation module obtains the accumulated value of the behavior operation of the user on friend making, and considers that the user is interested in the social network user when the preference of the user on the social network user is greater than a certain value;
3) Calculating favorites of different users on other social network users, calculating the similarity between the users by using Euclidean distance according to the favorites of the different users, considering that the two users are similar to obtain a similar user set when the similarity between the two users is larger than a certain value, and obtaining a recommended result set B of each user based on the collaborative filtering thought of the users.
The ranking module divides the behavior data and the personal attributes of the social network users according to the recommendable result set B, and ranks the interested sets of the social network users to obtain a preliminary recommendation list C.
The main working principle is as follows:
1) Dividing the characteristic values of the personal attributes according to the personal attributes of the social network users, obtaining the weight of each attribute characteristic value of the users in the recommended candidate set A according to the proportion of each characteristic value in the interesting set of the social network users, and obtaining the attribute with the most sensitive perception of the users according to each most obvious characteristic set, thereby obtaining different reference weights of each attribute.
2) And obtaining a score vector of the candidate recommendation set through the distinguishing degree vector of each attribute and the attribute feature matrix of the candidate recommendation set, and obtaining a preliminary recommendation list C according to the sorting of the recommendable result set B by the score vector, namely a final recommendation result.
Example two
As shown in fig. 2, this embodiment discloses a social network recommendation method based on coordinated filtering, which designs a set of recommendation engines for making friends on a social network by referring to collaborative filtering ideas and content-based recommendation ideas.
The social network recommendation method specifically comprises the following steps:
s1, initializing and defining behavior data and personal attributes of recommended social network users by a starting module through a service party, wherein the mode of definition is a key value pair of attribute-value, such as height-170 CM; classifying behavior data of a user, setting conditions of an initial search engine, initiating a recommendation request to the recommendation engine after initialization setting and recommendation engine access are completed, and sending an initialized data set to the recommendation engine.
In a specific application, the initial attribute of the user is filled in by the user during registration, and the recommendation engine can perform feature division for the initial user according to the attribute value filled in by the user.
S2, the filtering module gathers data meeting the search conditions through a recommendation engine according to the conditions of an initial search engine of a service party to form a primary recommended candidate set, the primary recommended candidate set is judged to obtain a similar user set through similarity, and data screening is carried out based on collaborative filtering ideas of users to obtain a recommended candidate set A; and if the number of the recommended candidate set A does not meet the minimum recommended number requirement, requesting the business party to expand the search condition.
The specific process of the method comprises the following steps:
s201, the social network sets an initial screening condition for the user, and the user selects or directly sets according to the historical behaviors of the user.
And S202, the social network sends the initial screening conditions and the initialized data set to a recommendation engine, and the recommendation engine screens according to the conditions to form a recommendable candidate set A.
And S3, screening the recommendable candidate set A according to the historical behavior and data of the recommended social network user to obtain a basic user interest set, and obtaining a recommendable result set B of each user based on the collaborative filtering thought of the user.
The specific process of the step S3 is as follows:
s301, dividing the behavior of the user into T 1 ～T K K classes are added, and weights are assigned to the K classes of behaviors respectively 1 ～w k Differentiated into positive and negative according to different user behaviorsAnd the value of the assignment vector w is w= [ 2, -1,0,1,2,3 ] in six dimensions of high, medium and low;
in a specific application, the characteristics of different behaviors are defined according to behavior data of a user on a line.
S302, acquiring a behavior operation accumulated value of a user on a social network user to obtain a preference H= Σwof the user on the social network user, and considering that the user is interested in the social network user when H > 3;
s303, utilizing Euclidean distance according to favorites H of different users on each social network user
And calculating to obtain the similarity between users:
when the similarity sim (x, y) > k between two users is determined by the service party, that is, the two users are considered to be similar, so as to obtain a similar user set, and based on the collaborative filtering thought of the users, a recommended result set B of each user is obtained.
And S4, dividing the characteristic values of the personal attributes according to the personal attributes of the recommended social network users, obtaining the weight of each attribute characteristic value in the user of the recommended result set B according to the proportion of each characteristic value in the user 'S interest set, obtaining the attribute with the most sensitive perception of the user according to each most obvious characteristic set, and sequencing the user' S interest set according to different reference weights of the attribute with the most sensitive perception to obtain the preliminary recommendation list C.
The specific process of the method comprises the following steps:
s401, dividing the personal attribute and the characteristic value of the recommended social network user according to the recommended result set B, and setting the personal attribute vector of the recommended social network user as:
attribute S i The eigenvalue vectors of (a) are:
s402, constructing an attribute feature matrix through the distinguishing degree vector of each personal attribute and the candidate recommendation set;
for user A, candidate recommendation set Q T Personal attribute S of a certain social network user i Characteristic value v of (2) k At the position ofThe proportion is->Then at candidate recommendation set Q T Setting the characteristic value v of the personal attribute of the social network user k The weight is as follows:
in addition, when(i, k take any value)
Then consider the personal attribute S x The degree of distinction is the strongest; discrimination of each attribute is taken:
therefore, when Q is given A Then, a desirability discrimination vector can be obtained:
obtaining Q T After that, social contact is availableAttribute feature matrix of network users:
s403, according to the attribute feature matrix and the attribute distinguishing degree vector, a candidate recommendation set Q can be obtained T Is a recommendation score vector for each social network user:
s404, determining a preliminary recommendation list C according to the obtained recommendation score vector and the sequence of the recommendable result set B.
The above examples are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above examples, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principle of the present invention should be made in the equivalent manner, and the embodiments are included in the protection scope of the present invention.
Claims (6)
1. A social network recommending device based on collaborative filtering is characterized in that the recommending device comprises a starting module, a filtering module, a recommending module and a sequencing module which are connected in sequence,
the starting module is used for initializing and defining behavior data and personal attributes of the recommended social network users, classifying the behaviors of the users, setting the conditions of an initial search engine, initiating a recommendation request to the recommendation engine, and sending an initialized data set to the recommendation engine;
the filtering module filters users which do not meet the requirements through basic search conditions set in the social network by a basic search engine to form a recommended candidate set A;
the recommendation module screens the recommendable candidate set A according to the historical behaviors and data of the users to obtain a basic user interest set, and obtains a recommendable result set B of each user based on the collaborative filtering thought of the users;
the ordering module divides the behavior data and the personal attribute of the social network user according to the recommendable result set B, and orders the interested set of the social network user to obtain a preliminary recommendation list C;
the recommendation method based on the social network recommendation device comprises the following steps:
s1, a starting module carries out initialization definition on behavior data and personal attributes of a recommended social network user through a service party, classifies the behavior data of the user, sets conditions of an initial search engine, initiates a recommendation request to the recommendation engine after initialization setting and recommendation engine access are completed, and sends an initialized data set to the recommendation engine;
s2, the filtering module gathers data meeting the search conditions through a recommendation engine according to the conditions of an initial search engine of a service party to form a primary recommended candidate set, the primary recommended candidate set is judged to obtain a similar user set through similarity, and data screening is carried out based on collaborative filtering ideas of users to obtain a recommended candidate set A;
s3, screening the recommendable candidate set A according to historical behaviors and data of the recommended social network users by a recommendation module to obtain a basic user interest set, and obtaining a recommendable result set B of each recommended social network user based on collaborative filtering thought of the user;
the specific process of the step S3 is as follows:
s301, dividing the behavior of the user into T 1 ～T K K classes are added, and weights are assigned to the K classes of behaviors respectively 1 ～w k The method comprises the steps of dividing the user behavior into positive, negative, high, medium and low dimensions according to different user behaviors, wherein the value of an assignment vector w is w= [ 2, -1,0,1,2,3 ];
s302, acquiring a behavior operation accumulated value of a user on a social network user to obtain a preference H= Σwof the user on the social network user;
s303, utilizing Euclidean distance according to favorites H of different users on each social network user
And calculating to obtain the similarity between users:
when the similarity sim (x, y) between two users is greater than k, wherein k is determined by a service party, namely, the two users are considered to be similar to obtain a similar user set, and based on the collaborative filtering thought of the users, a recommended result set B of each user is obtained;
s4, dividing the characteristic values of the personal attributes according to the personal attributes of the recommended social network users, obtaining the weight of each attribute characteristic value in the user of the recommended result set B according to the proportion of each characteristic value in the user 'S interest set, obtaining the attribute of the user which is perceived to be most sensitive according to each most obvious characteristic set, and sorting the user' S interest set according to different reference weights of the attribute which is perceived to be most sensitive to obtain a preliminary recommendation list C;
the specific process of the step S4 is as follows:
s401, dividing the personal attribute and the characteristic value of the recommended social network user according to the recommended result set B, and setting the personal attribute vector of the recommended social network user as:
attribute S i The eigenvalue vectors of (a) are:
s402, constructing an attribute feature matrix through the distinguishing degree vector of each personal attribute and the candidate recommendation set;
for user A, candidate recommendation set Q T Personal attribute S of a certain social network user i Characteristic value v of (2) k At the position ofThe proportion is->Then at candidate recommendation set Q T Setting the characteristic value v of the personal attribute of the social network user k The weight is as follows:
in addition, wheni, k takes any value which can be taken,
then consider the personal attribute S x The degree of distinction is the strongest; discrimination of each attribute is taken:
therefore, when Q is given A Then, a desirability discrimination vector can be obtained:
obtaining Q T Then, the attribute feature matrix of the social network user can be obtained:
s403, obtaining a candidate recommendation set Q according to the attribute feature matrix and the attribute distinguishing degree vector T Is a recommendation score vector for each social network user:
s404, determining a preliminary recommendation list C according to the obtained recommendation score vector and the sequence of the recommendable result set B.
2. The collaborative filtering-based social network recommender of claim 1, wherein the initial personal attributes of the user are filled in by the user at registration, and the recommendation engine is operable to profile the initial user based on the user-filled personal attribute values.
3. The collaborative filtering-based social network recommender as set forth in claim 1, wherein the recommendation engine in the start module sends an instruction to expand the filtering range or increase the number of filtered people from the social network when the number of filtered recommended candidate set a is less than the minimum calculated number.
4. The social network recommending apparatus based on collaborative filtering according to claim 1, wherein the specific procedure of step S2 is as follows:
s201, the social network sets an initial screening condition for the user, and the user selects or directly sets according to the historical behaviors of the user.
And S202, the social network sends the initial screening conditions and the initialized data set to a recommendation engine, and the recommendation engine screens according to the conditions to form a recommendable candidate set A.
5. The collaborative filtering-based social network recommender of claim 1, wherein personal attributes and eigenvalues of the recommending social network users are defined in the manner of [ attribute-value ] key value pairs.
6. The collaborative filtering-based general item recommendation device of claim 4,
when the user's preference for social network users, H >3, then the user is considered interested in the item.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710106305.4A CN106709076B (en) | 2017-02-27 | 2017-02-27 | Social network recommendation device and method based on collaborative filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710106305.4A CN106709076B (en) | 2017-02-27 | 2017-02-27 | Social network recommendation device and method based on collaborative filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106709076A CN106709076A (en) | 2017-05-24 |
| CN106709076B true CN106709076B (en) | 2023-09-29 |
Family
ID=58917560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710106305.4A Active CN106709076B (en) | 2017-02-27 | 2017-02-27 | Social network recommendation device and method based on collaborative filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106709076B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020099A (en) * | 2017-08-21 | 2019-07-16 | 武汉斗鱼网络科技有限公司 | A kind of the user's recommended method and device of video friend-making |
| CN108090801A (en) * | 2017-11-29 | 2018-05-29 | 维沃移动通信有限公司 | Method of Commodity Recommendation, mobile terminal and server |
| CN108763314B (en) * | 2018-04-26 | 2021-01-19 | 深圳市腾讯计算机系统有限公司 | Interest recommendation method, device, server and storage medium |
| CN109739768B (en) * | 2018-12-29 | 2021-03-30 | 深圳Tcl新技术有限公司 | Search engine evaluation method, device, equipment and readable storage medium |
| US11429682B2 (en) * | 2019-06-25 | 2022-08-30 | Sap Portals Israel Ltd. | Artificial crowd intelligence via networking recommendation engines |
| CN111797309B (en) * | 2020-06-19 | 2024-04-16 | 一汽奔腾轿车有限公司 | Vehicle-mounted intelligent recommendation device and method based on travel mode |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011101527A1 (en) * | 2010-02-19 | 2011-08-25 | Osumus Recommendations Oy | Method for providing a recommendation to a user |
| CN103927347A (en) * | 2014-04-01 | 2014-07-16 | 复旦大学 | Collaborative filtering recommendation algorithm based on user behavior models and ant colony clustering |
| CN104317900A (en) * | 2014-10-24 | 2015-01-28 | 重庆邮电大学 | Multiattribute collaborative filtering recommendation method oriented to social network |
| KR101516329B1 (en) * | 2013-12-27 | 2015-05-06 | 충북대학교 산학협력단 | System and method for recommending group in social network environments |
| CN105095267A (en) * | 2014-05-09 | 2015-11-25 | 阿里巴巴集团控股有限公司 | User involving project recommendation method and apparatus |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090164929A1 (en) * | 2007-12-20 | 2009-06-25 | Microsoft Corporation | Customizing Search Results |
| US20150286650A1 (en) * | 2014-04-03 | 2015-10-08 | Kurt Stump | Decision Making and Activity Recommendations Engine via Online Persona |
-
2017
- 2017-02-27 CN CN201710106305.4A patent/CN106709076B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011101527A1 (en) * | 2010-02-19 | 2011-08-25 | Osumus Recommendations Oy | Method for providing a recommendation to a user |
| KR101516329B1 (en) * | 2013-12-27 | 2015-05-06 | 충북대학교 산학협력단 | System and method for recommending group in social network environments |
| CN103927347A (en) * | 2014-04-01 | 2014-07-16 | 复旦大学 | Collaborative filtering recommendation algorithm based on user behavior models and ant colony clustering |
| CN105095267A (en) * | 2014-05-09 | 2015-11-25 | 阿里巴巴集团控股有限公司 | User involving project recommendation method and apparatus |
| CN104317900A (en) * | 2014-10-24 | 2015-01-28 | 重庆邮电大学 | Multiattribute collaborative filtering recommendation method oriented to social network |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 基于产品属性及用户偏好的个性化产品推荐方法;鲁辉;张太华;何二宝;徐卫平;;贵州师范大学学报(自然科学版)(第01期);87-92 * |
| 基于双边兴趣的社交网好友推荐方法研究;何静等;《计算机工程与应用》;20151231(第06期);108-113页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106709076A (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709076B (en) | Social network recommendation device and method based on collaborative filtering | |
| Yin et al. | Social influence-based group representation learning for group recommendation | |
| CN107729444B (en) | Knowledge graph-based personalized tourist attraction recommendation method | |
| CN110598130B (en) | Movie recommendation method integrating heterogeneous information network and deep learning | |
| CN104462292B (en) | Socially collaborative filtering | |
| CN106952130B (en) | General article recommendation method based on collaborative filtering | |
| US20160259857A1 (en) | User recommendation using a multi-view deep learning framework | |
| US20160171036A1 (en) | Item recommendation method and apparatus | |
| US20220147523A1 (en) | Self-organizing maps for adaptive individualized user preference determination for recommendation systems | |
| CN109947987B (en) | Cross collaborative filtering recommendation method | |
| CN112948625B (en) | Film recommendation method based on attribute heterogeneous information network embedding | |
| CN108171535B (en) | Personalized restaurant recommendation algorithm based on multiple features | |
| CN111310046B (en) | Object recommendation method and device | |
| CN107145541B (en) | Social network recommendation model construction method based on hypergraph structure | |
| Feng et al. | Improving group recommendations via detecting comprehensive correlative information | |
| Modani et al. | Like-minded communities: bringing the familiarity and similarity together | |
| Liu et al. | Evolving graph construction for successive recommendation in event-based social networks | |
| CN107346333B (en) | Online social network friend recommendation method and system based on link prediction | |
| CN106649733B (en) | Online video recommendation method based on wireless access point context classification and perception | |
| CN113221015B (en) | Homologous user determination and homologous network construction method, system and storage medium | |
| Liu et al. | Short video recommendation algorithm incorporating temporal contextual information and user context | |
| CN104954873B (en) | A kind of smart television video method for customizing and system | |
| CN108848152B (en) | Object recommendation method and server | |
| US11947616B2 (en) | Systems and methods for implementing session cookies for content selection | |
| CN106101839A (en) | A kind of method identifying that television user gathers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |