CN107203622B - Network user influence assessment system with accurate assessment - Google Patents
Network user influence assessment system with accurate assessment Download PDFInfo
- Publication number
- CN107203622B CN107203622B CN201710381405.8A CN201710381405A CN107203622B CN 107203622 B CN107203622 B CN 107203622B CN 201710381405 A CN201710381405 A CN 201710381405A CN 107203622 B CN107203622 B CN 107203622B
- Authority
- CN
- China
- Prior art keywords
- influence
- user
- network
- evaluation index
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a network user influence evaluation system with accurate evaluation, which comprises a user information acquisition module, an influence calculation module, an influence authenticity coefficient calculation module, a final influence calculation module and a user screening module, wherein the user information acquisition module is used for acquiring user information; the user information acquisition module is used for acquiring network user information, and the influence calculation module is used for calculating the influence of the network user; the influence authenticity coefficient calculation module is used for calculating the influence authenticity coefficient of the network user according to the influence of the network user; the final influence calculation module is used for calculating the final influence of the network user according to the influence authenticity coefficient of the network user; and the user screening module is used for screening the network users according to the final influence of the network users. The invention has the beneficial effects that: and the accurate evaluation of the influence of the network user is realized.
Description
Technical Field
The invention relates to the technical field of influence evaluation, in particular to a network user influence evaluation system with accurate evaluation.
Background
The development of internet technology greatly changes the working and living modes of people, so that the communication between people becomes rapid and various.
The Internet community question-answering service provides a very convenient channel for people to find help and exchange viewpoints on line. In the internet community, people search and obtain existing information on one hand, and on the other hand, the other hand shares own experience and knowledge in an area polar manner, so that high-quality content is contributed to the community. Originally, the technical core point of the traditional information retrieval type question-answering service lies in how to search answers and information related to query requirements for users. Now, the technology core point of the novel community question-answering system is changed. Due to the participation of the real users, the required knowledge can be searched in the existing knowledge base and can also be asked for help from the online users. At this point, the core task of the system is transformed into how to search for potential users that can provide high-quality knowledge to the system, either directly or indirectly. The attention of researchers is no longer limited to content retrieval, but extends to the mining of particular users.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a network user influence assessment system for accurate assessment.
The purpose of the invention is realized by adopting the following technical scheme:
the system comprises a user information acquisition module, an influence calculation module, an influence authenticity coefficient calculation module, a final influence calculation module and a user screening module;
the user information acquisition module is used for acquiring network user information,
the influence calculation module is used for calculating the influence of the network user;
the influence authenticity coefficient calculation module is used for calculating the influence authenticity coefficient of the network user according to the influence of the network user;
the final influence calculation module is used for calculating the final influence of the network user according to the influence authenticity coefficient of the network user;
and the user screening module is used for screening the network users according to the final influence of the network users.
The invention has the beneficial effects that: and the accurate evaluation of the influence of the network user is realized.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a schematic structural view of the present invention;
reference numerals:
the system comprises a user information acquisition module 1, an influence calculation module 2, an influence authenticity coefficient calculation module 3, a final influence calculation module 4 and a user screening module 5.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the network user influence evaluation system for accurately evaluating the influence of the present embodiment includes a user information acquisition module 1, an influence calculation module 2, an influence authenticity coefficient calculation module 3, a final influence calculation module 4, and a user screening module 5;
the user information collecting module 1 is used for collecting network user information,
the influence calculation module 2 is used for calculating the influence of the network user;
the influence authenticity coefficient calculation module 3 is used for calculating the influence authenticity coefficient of the network user according to the influence of the network user;
the final influence calculation module 4 is used for calculating the final influence of the network user according to the influence authenticity coefficient of the network user;
and the user screening module 5 is used for screening the network users according to the final influence of the network users.
The embodiment realizes accurate evaluation of the influence of the network user.
Preferably, the influence authenticity coefficient calculation module 3 includes an influence ranking calculation unit and an influence authenticity coefficient calculation unit, the influence ranking calculation unit is configured to calculate an influence ranking of the network user according to the influence of the network user, the influence authenticity coefficient calculation unit is configured to calculate an influence authenticity coefficient of the network user according to the influence ranking of the network user, wherein the influence authenticity coefficient of the network user is 1, and is subtracted from the square of the influence ranking of the network user divided by the number of the network users, and is formulated as:
the influence authenticity coefficient obtained by the preferred embodiment is more in line with the actual situation.
Preferably, the influence calculation module 2 includes a first influence calculation unit, a second influence calculation unit, a third influence calculation unit, and a comprehensive influence calculation unit, where the first influence calculation unit is configured to evaluate a contribution of a user to knowledge in a network and obtain a content evaluation index, the second influence calculation unit is configured to evaluate an activity level of the user in the network and obtain an activity evaluation index, the third influence calculation unit is configured to evaluate a direct influence of the user in the network and obtain an influence evaluation index, and the comprehensive influence calculation unit is configured to obtain an influence of the network user according to the content evaluation index, the activity evaluation index, and the influence evaluation index.
The contribution of the user to the knowledge in the network is measured by adopting a content evaluation index, and the content evaluation index is calculated by adopting the following formula:
in the formula, A (u)j) Representing user ujContent evaluation index, NR(uj) Representing user ujNumber of questions to answer, NQ(uj) Representing user ujNumber of questions posed, NDR(uj) Representing other users to user ujAnd replying the number of praise questions, wherein the larger the content evaluation index is, the larger the contribution of the user to the knowledge in the network is.
The preferred embodiment introduces content evaluation indexes to evaluate the contribution of the user network knowledge, comprehensively considers the influence of the number of questions asked by the user, the number of reply questions and the recognition degree of other users on the contribution of the knowledge, and obtains more accurate evaluation results.
Preferably, the activity level of the user in the network is measured by using an activity level evaluation index, and the activity level evaluation index is calculated by using the following formula:
in the formula, B (u)j) Representing user ujActivity evaluation index, ND(uj) Representing user ujFor the praise number of other users for replying the questions, the larger the activity evaluation index is, the more active the users are in the network.
The activity evaluation indexes are introduced to evaluate the activity degree of the user in the network, various behaviors of the user in the network are comprehensively considered, and the obtained evaluation result is more accurate.
Preferably, the direct influence of the user in the network is measured by an influence evaluation index, and the influence evaluation index is obtained through the following steps:
a. by focusing on relationshipsInterconnecting users into a social relationship network (U, G), where U represents the set of all users, G represents the set of all concerns, and G has an element G (U) in iti,uj) Representing users u in a social relationship networkiUser u of interestjU since social relationship network connections are directionaliIs called ujVermicelli of (u)jIs called uiA friend of (2);
b. calculating an influence evaluation index by using the following formula:
in the formula, C (u)j) Representing user ujIndex for evaluation of influence, NH(uj) Representing user ujNumber of friends, NF(uj) Representing user ujNumber of vermicelli, Ei(uj) Representing user ujFor user ujThe value of the trust of (a) is,
where F is a constant value representing the overall trust value for each user, XiRepresenting user ujThe larger the influence evaluation index is, the larger the direct influence of the user in the network is.
The method and the device introduce an influence evaluation index to evaluate the direct influence of the user in the network, the obtained evaluation result is more accurate, specifically, the index considers both the concerned person and the concerned person, the concerned relation can influence the behaviors of other people from the perspective of the concerned person, the more the owned fan users are, the wider the direct influence of the fan users can be radiated, the larger the generated direct influence is, the concerned relation is a trust voting behavior from the perspective of the concerned person, the total trust value of the concerned person to all the concerned users is a fixed value, and each concerned user can be classified into one part of the total trust value.
Preferably, the influence of the network user is calculated by the following formula:
in the formula, D (u)j) Representing user ujIn the formula (2), D (u)j) Representing user ujThe influence of (c);
the final influence of the network user is equal to the product of the influence of the network user and the influence authenticity coefficient of the network user.
In the preferred embodiment, the comprehensive influence computing unit is introduced to compute the influence of the user, specifically, the influence of the user is quantified from three aspects of the content evaluation index, the activity evaluation index and the influence evaluation index, so that the comprehensive and reliable influence of the user is obtained, and the comprehensive and reliable influence computing unit has strong applicability to subsequent user screening.
The network user influence evaluation system with accurate evaluation of the invention is adopted to evaluate the users, when the number of the users takes different values, the evaluation accuracy and the evaluation efficiency are counted, and compared with the system without the invention, the beneficial effects are shown in the following table:
| number of users | Assessing efficiency improvements | Assessment accuracy improvement |
| 500 | 10％ | 18％ |
| 600 | 15％ | 23％ |
| 700 | 20％ | 25％ |
| 800 | 24％ | 28％ |
| 900 | 31％ | 32％ |
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (1)
1. A network user influence evaluation system with accurate evaluation is characterized by comprising a user information acquisition module, an influence calculation module, an influence authenticity coefficient calculation module, a final influence calculation module and a user screening module;
the user information acquisition module is used for acquiring network user information,
the influence calculation module is used for calculating the influence of the network user;
the influence authenticity coefficient calculation module is used for calculating the influence authenticity coefficient of the network user according to the influence of the network user;
the final influence calculation module is used for calculating the final influence of the network user according to the influence authenticity coefficient of the network user;
the user screening module is used for screening the network users according to the final influence of the network users;
the influence reality coefficient calculation module comprises an influence ranking calculation unit and an influence reality coefficient calculation unit, wherein the influence ranking calculation unit is used for calculating the influence ranking of the network users according to the influence of the network users, the influence reality coefficient calculation unit is used for calculating the influence reality coefficient of the network users according to the influence ranking of the network users, the influence reality coefficient of the network users is 1, the influence ranking of the network users is divided by the number of the network users, and the influence reality coefficient is represented by the formula:
the influence calculation module comprises a first influence calculation unit, a second influence calculation unit, a third influence calculation unit and a comprehensive influence calculation unit, wherein the first influence calculation unit is used for evaluating the contribution of a user to knowledge in a network and acquiring a content evaluation index, the second influence calculation unit is used for evaluating the activity degree of the user in the network and acquiring an activity evaluation index, the third influence calculation unit is used for evaluating the direct influence of the user in the network and acquiring an influence evaluation index, and the comprehensive influence calculation unit is used for calculating the influence of the network user according to the content evaluation index, the activity evaluation index and the influence evaluation index;
the contribution of the user to the knowledge in the network is measured by adopting a content evaluation index, and the content evaluation index is calculated by adopting the following formula:
in the formula, a (uj) represents a user uj content evaluation index, nr (uj) represents the number of questions answered by the user uj, nq (uj) represents the number of questions posed by the user uj, ndr (uj) represents the number of questions answered by other users for the user uj, and the larger the content evaluation index is, the larger the contribution of the user to knowledge in the network is;
the activity degree of the user in the network is measured by adopting an activity degree evaluation index, and the activity degree evaluation index is calculated by adopting the following formula:
in the formula, B (uj) represents an activity evaluation index of the user uj, ND (uj) represents the number of prawns of the user uj for replying questions to other users, and the higher the activity evaluation index is, the more active the user is in the network;
the direct influence of the user in the network is measured by adopting an influence evaluation index, and the influence evaluation index is obtained through the following steps:
a. interconnecting users into a social relationship network (U, G) through attention relationships, wherein U represents all user sets, G represents all attention relationships sets, elements G (ui, uj) in G represent behaviors of users ui paying attention to users uj in the social relationship network, ui is called fan of uj, and uj is called friend of ui because the social relationship network is connected with directionality;
b. calculating an influence evaluation index by using the following formula:
in the formula, C (uj) represents an influence evaluation index of the user uj, NH (uj) represents the number of friends of the user uj, NF (uj) represents the number of fans of the user uj, Ei (uj) represents the trust value of the ith fan of the user uj on the user uj,
f is a fixed value and represents the total trust value of each user, Xi represents the friend number of the ith fan of the uj of the user, and the larger the evaluation index of the influence is, the larger the direct influence of the user in the network is;
the influence of the network user is calculated by the following formula:
in the formula, d (uj) represents the influence of the user uj;
the final influence of the network user is equal to the product of the influence of the network user and the influence authenticity coefficient of the network user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710381405.8A CN107203622B (en) | 2017-05-25 | 2017-05-25 | Network user influence assessment system with accurate assessment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710381405.8A CN107203622B (en) | 2017-05-25 | 2017-05-25 | Network user influence assessment system with accurate assessment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107203622A CN107203622A (en) | 2017-09-26 |
| CN107203622B true CN107203622B (en) | 2020-11-06 |
Family
ID=59905968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710381405.8A Active CN107203622B (en) | 2017-05-25 | 2017-05-25 | Network user influence assessment system with accurate assessment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107203622B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358625A (en) * | 2022-09-06 | 2022-11-18 | 重庆新致金服信息技术有限公司 | User value evaluation method and device for question-answer community, electronic equipment and storage medium |
| CN116628385B (en) * | 2023-06-19 | 2025-09-23 | 国家计算机网络与信息安全管理中心 | Highly sensitive account evaluation method based on multi-dimensional model weighting |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617279A (en) * | 2013-12-09 | 2014-03-05 | 南京邮电大学 | Method for achieving microblog information spreading influence assessment model on basis of Pagerank method |
| CN105260474A (en) * | 2015-10-29 | 2016-01-20 | 俞定国 | Microblog user influence computing method based on information interaction network |
| CN106354733A (en) * | 2015-07-17 | 2017-01-25 | 中移(苏州)软件技术有限公司 | Calculating method and device for influence of microblog user |
| CN106570763A (en) * | 2016-11-09 | 2017-04-19 | 福建中金在线信息科技有限公司 | User influence evaluation method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9542451B2 (en) * | 2014-09-05 | 2017-01-10 | Google Inc. | Mobile application search ranking |
-
2017
- 2017-05-25 CN CN201710381405.8A patent/CN107203622B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617279A (en) * | 2013-12-09 | 2014-03-05 | 南京邮电大学 | Method for achieving microblog information spreading influence assessment model on basis of Pagerank method |
| CN106354733A (en) * | 2015-07-17 | 2017-01-25 | 中移(苏州)软件技术有限公司 | Calculating method and device for influence of microblog user |
| CN105260474A (en) * | 2015-10-29 | 2016-01-20 | 俞定国 | Microblog user influence computing method based on information interaction network |
| CN106570763A (en) * | 2016-11-09 | 2017-04-19 | 福建中金在线信息科技有限公司 | User influence evaluation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107203622A (en) | 2017-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106781785B (en) | A Big Data-Based Question Difficulty Construction Method, Device, and Service Equipment | |
| US11935137B2 (en) | Method for distributing equity reward for federated learning based on equity theory | |
| CN105225149B (en) | A kind of reference scoring determines method and device | |
| US20130004933A1 (en) | Increasing confidence in responses to electronic surveys | |
| CN104573017B (en) | Identify the method and system of network navy group | |
| CN100521611C (en) | A method and system for recommending friends in SNS community | |
| US11250369B2 (en) | Computerized system for detecting the exposure and impact of an entity within virtual networking platforms | |
| CN103353920A (en) | Method and device for recommending games based on SNS | |
| CN116739794B (en) | User personalized scheme recommendation method and system based on big data and machine learning | |
| CN107203622B (en) | Network user influence assessment system with accurate assessment | |
| KR20150135584A (en) | A Difficulty Level Based Question Posing Study System Which Self-renews The Difficulty Level of Questions Based on Standard Average Hit Rate and Standard Average Solving Time of Students | |
| Van Oest | A new coefficient of interrater agreement: The challenge of highly unequal category proportions. | |
| CN110472943A (en) | A kind of online Course Arrangement | |
| US20140297399A1 (en) | System and method for providing social media marketing performance and feedback | |
| CN112836137B (en) | Character network support degree computing system and method, terminal, equipment and storage medium | |
| Uy et al. | Social Media adoption for agricultural development: Insights from smallholders in central Vietnam | |
| CN112488743A (en) | Satisfaction degree prediction method, network equipment and storage medium | |
| CN114782224A (en) | Webpage evaluation cheating monitoring method and device based on user characteristics and electronic equipment | |
| Asamer et al. | Quality assessment for register-based statistics-Results for the Austrian census 2011 | |
| CN102509186A (en) | Self-learning based bidding evaluation system and method | |
| CN117808368A (en) | Method and device for generating user evaluation report based on evaluation data and electronic equipment | |
| CN118134285A (en) | Questionnaire analysis method, device, equipment and storage medium | |
| CN110136001A (en) | A kind of data processing method, calculates equipment and storage medium at device | |
| CN109472454B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| KR101357804B1 (en) | Q & A system and method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201015 Address after: Room 801, No.3, Huaqiang Road, Tianhe District, Guangzhou City, Guangdong Province Applicant after: Guangzhou Xihang Information Technology Co., Ltd Address before: 518000 West Tower 1708, Nanshan Software Park, Nanshan Digital Culture Industry Base, 10128 Shennan Avenue, Nanshan Street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN CHUANGYI INDUSTRIAL TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |