CN112446795A - System and method for measuring and calculating individual influence in tissue - Google Patents
System and method for measuring and calculating individual influence in tissue Download PDFInfo
- Publication number
- CN112446795A CN112446795A CN201910752829.XA CN201910752829A CN112446795A CN 112446795 A CN112446795 A CN 112446795A CN 201910752829 A CN201910752829 A CN 201910752829A CN 112446795 A CN112446795 A CN 112446795A
- Authority
- CN
- China
- Prior art keywords
- module
- measuring
- influence
- individual
- relation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000005259 measurement Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 230000008520 organization Effects 0.000 abstract description 27
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
Images
Classifications
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a system and a method for measuring and calculating individual influence in an organization, wherein the system comprises a user and project creation module, a processing module, a relation term processing module, a semantic calculation module and an identification network node module which are sequentially connected, the user and project creation module receives information of a user and a project, and characters of core nodes are presented after being processed by the identification network node module. The method defines the possible forms of the informal social network and classifies the forms, so that the collection of the early-stage organization information is effectively guided; through automatic calculation and analysis of individual social network nodes, key individuals with large influence in the organization can be found, so that the enterprise decision is guided to be executed, and the problem of quantitative measurement and calculation of individual influence is solved.
Description
Technical Field
The invention relates to the technical field of computer network node analysis, in particular to a system and a method for measuring and calculating individual influence in an organization.
Background
The existing method for measuring and calculating the influence of individuals in an organization is mainly offline and qualitative, is not combined with information technology, has individual influence network analysis based on user interaction compared with social websites such as microblogs, facebooks and the like, but is not suitable for being used in enterprises, and is mainly caused by the fact that the interaction of individuals in the enterprises is difficult to record and the online and offline interaction behaviors of the individuals are possibly greatly different. Meanwhile, the traditional evaluation mode focuses on organization structure and reporting relation, and ignores the influence of informal social network influence on the organization. Therefore, improvements in the prior art are needed.
Disclosure of Invention
In order to overcome the defects of the prior art, a system and a method for measuring and calculating the individual influence in an organization are provided, wherein the computer technology is used for measuring and calculating the nodes of a formal report network and an informal social network, so that the influence value of each individual in the organization is obtained, and the execution of enterprise decision is guided.
In order to achieve the purpose, the invention provides a system for measuring and calculating individual influence in an organization, which comprises a user and project creation module, a processing module, a relation word processing module, a semantic calculation module and an identification network node module which are sequentially connected, wherein the user and project creation module receives information of users and projects, and characters corresponding to core nodes are presented after being processed by the identification network node module.
In the system for measuring and calculating the individual influence in the organization, the relation word processing module comprises a relation word selecting module and a relation word calculating module which are connected with each other.
The processing module comprises a learning generalization module and a relation establishment word module which are connected with each other, the learning generalization module is connected with the user and the project establishment module, and the relation establishment word module is connected with the relation selection word module.
The invention also provides a method for measuring and calculating individual influence in tissues, which comprises the following steps:
s1, learning and generalizing from the training corpus to obtain cooperative relation word extraction rules, and selecting one or more description candidate items from the relation examples by using the rules;
s2: establishing common phrase dictionaries of various cooperative relation words, extracting specific cooperative relation words, calculating and processing the relation words to obtain corresponding semantic codes;
s3: calculating the semantic similarity between semantic codes;
s4: and identifying the influence indexes of the network nodes, finding out the core nodes, and finding out characters of the core nodes through relational clustering.
In the method for measuring and calculating the influence of individuals in the organization, the cooperative relation words comprise cooperative items, interest groups and individual contact.
In the method for measuring and calculating individual influence in organization, in steps S2 and S3, when extracting the specific cooperative relation words, semantic similarity of words and phrases in the candidate items and the dictionary is calculated, the word or the phrase with the highest similarity is selected as description information, the overall idea of semantic similarity calculation between word collections and semantic similarity calculation between word groups is mapped to a semantic space, and corresponding semantic codes are obtained, so that the semantic similarity calculation between semantic codes can be performed.
In the method for measuring and calculating the influence of individuals in an organization, in S3, a few connections existing between human networks should be the necessary paths for communication traffic during communication between human networks. If some form of communication in the network is considered and the edge with the highest traffic is found, the edge should be the path connecting the different communities, and removing such an edge may result in the most natural breakdown of the network.
In the method for measuring and calculating individual influence in an organization, in S4, 3 measurement nodes are selected as parameters for measuring core nodes of a network, the contact degree reflects the activity degree of the nodes in the network, the central degree measures the degree of the nodes located between other nodes, the closeness measures the distance between one node and other nodes, and the larger the contact degree, the central degree and the closeness of the nodes are, the more likely the nodes are the core of the network.
The system and the method for measuring and calculating the individual influence in the organization combine the management theory of informal organization influence and the computer node algorithm, measure and calculate the individual influence in the organization, and have the following improvement points and corresponding beneficial effects:
1) the problem of quantitative measurement and calculation of individual influence is solved;
2) the forms of the informal social network are defined and classified, so that the collection of the early-stage organization information is effectively guided;
3) through automatic calculation and analysis of individual social network nodes, key individuals with large influence in the organization can be found, and therefore execution of enterprise decision making is guided.
Drawings
FIG. 1 is a schematic block diagram of a system for measuring an individual's influence on tissue according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for measuring the influence of an individual on a tissue according to a second embodiment of the present invention.
Corresponding reference numerals in the description are as follows:
the system comprises a user and project creating module 1, a processing module 2, a relation word processing module 3, a semantic calculation module 4 and an identification network node module 5.
Detailed Description
In order to make the technical means, the inventive features, the objectives and the effects of the invention easy to understand, the invention will be further described with reference to the specific drawings.
The first embodiment of the invention discloses a system for measuring and calculating individual influence in organization, which comprises a user and project creation module 1, a processing module 2, a relation word processing module 3, a semantic calculation module 4 and an identification network node module 5 which are connected in sequence as shown in figure 1, wherein the user and project creation module 1 receives information of users and projects, and characters corresponding to core nodes are displayed after being processed by the identification network node module 5. In addition, the relation word processing module 3 comprises a relation word selecting module and a relation word calculating module which are connected with each other, the processing module 2 comprises a learning generalization module and a relation word establishing module which are connected with each other, the learning generalization module is connected with the user and the project creating module 1, and the relation word establishing module is connected with the relation word selecting module 3.
The second embodiment of the invention discloses a method for measuring and calculating individual influence in organization, as shown in figure 2, the first stage is extraction, because different cooperative relation words have different semantics and weights, the extraction adopts the combination of rules and semantics (the cooperative relation words comprise cooperative items, interest groups and individual contact), and the extraction process is carried out by the following two steps of (1) learning generalization from training corpus to obtain the extraction rules of the cooperative relation words, and selecting one or more description candidates from the relation examples by using the rules; (2) a common phrase dictionary of various collaborative relationship words is established. When extracting specific cooperative relation words, calculating semantic similarity of words and phrases in a candidate item and a dictionary, selecting the word or phrase with the highest similarity as description information, calculating the semantic similarity between words and phrases, and mapping the words and phrases to a semantic space to obtain corresponding semantic codes, so as to calculate the semantic similarity between semantic codes, wherein the following table 1 is an example for extracting the cooperative relation words, and interpersonal relation categories can be extracted and found through machine learning and semantic extraction of interview text input of questionnaires.
TABLE 1
| Raw input (interview based on questionnaire) | Extraction dictionary | Relationship classes |
| Having past project cooperation | Item | Collaborative projects |
| Together make an action plan | Scheme(s) | Collaborative projects |
| Organizing the activities of vehicle friends | Vehicle friend meeting | Interest group |
| Badminton for off-duty playing | Shuttlecock | Interest group |
| Hobby photography | Photography | Interest group |
| Tea room chatting | Tea room | Subject contact |
| Is his sister | Jie Fu | Subject contact |
The second stage is: and (3) calculating, wherein the algorithm of the interpersonal network is based on the following ideas: if some form of communication in the network is considered and the edge with the highest communication traffic is found, the edge should be the path connecting the different communities, and removing such edges allows the most natural breakdown of the network. As shown in Table 2, each project may be assigned a specific weight number along with the company's internal subject matter expert.
TABLE 2
Then the third stage: identifying the influence index of the network node, finding out the core node, selecting 3 measurement nodes as parameters for measuring the network core node: the contact degree reflects the activity degree of the node in the network; the centrality is used for measuring the degree of the nodes between other nodes; compactness, the distance between a node and other nodes is measured. The greater the contact, centrality and closeness of the nodes, the more likely they are to be the core of the network, as shown by way of example in table 3:
TABLE 3
| Character | Number of interpersonal connections | Degree of contact | Degree of centrality | Compactness of |
| 1 | 12 | 3.12 | 7.24 | 4.33 |
| 2 | 7 | 2.45 | 5.34 | 3.32 |
| 3 | 2 | 1.01 | 2.15 | 1.00 |
| 4 | 1 | 1.01 | 0.05 | 0.92 |
And the last stage is presentation, wherein a connected graph is extracted on the basis of the existing relationship, a network graph is obtained through a community discovery algorithm, and the characters corresponding to the core nodes are found through relationship clustering.
The specific use steps can be described by the following cases: a500-strength enterprise in a world needs to drive a CRM system to be on line, and the organization behavior of 2000 sales users can be influenced. The company is expected to identify 50 opinion leaders that can be influenced first by measuring the magnitude of individual influence in the organization, and to promote the project by receiving approval of the 50 opinion leaders.
The first step is as follows: collecting text data
Interviewing HR to obtain organizational structure and reporting relationship;
interviewing 2000 sales, obtaining interpersonal relationship text data for each sale (e.g., collaborate with whom to have a project, have lunch with whom to go to work, and who to kick a ball after going to work, etc.);
the second step is that: classifying by extracting semantics of text data
Dividing interpersonal relationships among 2000 sales into four categories of organizational structure, collaborative projects, interest groups, and individual exposure;
the third step: setting weight, and calculating interpersonal relationship data;
determining the weight values of different interpersonal relationship classifications from three dimensions of the strength, the range and the persistence of the influence through interviewing with an enterprise internal theme expert, and calculating the times and the value (times weight) of interpersonal relationships
The fourth step: calculating network centrality data (including contact degree, centrality and closeness) of different nodes (sales);
and fifthly, generating a human network map, identifying 50 core opinion leaders and visually presenting the core opinion leaders.
The system and the method for measuring and calculating the individual influence in the organization define the possible existing forms of the informal social network and classify, thereby effectively guiding the collection of the early-stage organization information; through automatic calculation and analysis of individual social network nodes, key individuals with large influence in the organization can be found, so that the enterprise decision is guided to be executed, and the problem of quantitative measurement and calculation of individual influence is solved.
Specific embodiments of the invention have been described above. It is to be understood that the invention is not limited to the particular embodiments described above, in that devices and structures not described in detail are understood to be implemented in a manner common in the art; various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention.
Claims (8)
1. A system for measuring the impact of an individual on a tissue, comprising: the system comprises a user and project creation module, a processing module, a relation word processing module, a semantic calculation module and an identification network node module which are sequentially connected, wherein the user and project creation module receives information of the user and a project, and characters corresponding to core nodes are displayed after being processed by the identification network node module.
2. The system for measuring influence of an individual on a tissue according to claim 1, wherein: the relation word processing module comprises a relation word selecting module and a relation word calculating module which are connected with each other.
3. The system for measuring influence of an individual on a tissue according to claim 2, wherein: the processing module comprises a learning generalization module and a relation word establishing module which are connected with each other, the learning generalization module is connected with the user and the project establishing module, and the relation word establishing module is connected with the relation word selecting module.
4. A method for measuring the influence of an individual in a tissue, comprising the steps of:
s1, learning and generalizing from the training corpus to obtain cooperative relation word extraction rules, and selecting one or more description candidate items from the relation examples by using the rules;
s2: establishing common phrase dictionaries of various cooperative relation words, extracting specific cooperative relation words, calculating and processing the relation words to obtain corresponding semantic codes;
s3: calculating the semantic similarity between semantic codes;
s4: and identifying the influence indexes of the network nodes, finding out the core nodes, and finding out characters of the core nodes through relational clustering.
5. The method for measuring individual influence in a tissue according to claim 4, wherein: the term of cooperative relationship includes organizational structures, collaborative projects, interest groups, and individual contacts.
6. The method for measuring individual influence in a tissue according to claim 4, wherein: in steps S2 and S3, when extracting the specific cooperative relation word, calculating semantic similarity of the word and the phrase in the candidate and the dictionary, selecting the word or the phrase with the highest similarity as description information, mapping the word to a semantic space to obtain corresponding semantic codes, thereby performing semantic similarity calculation between the semantic codes.
7. The method for measuring individual influence in a tissue according to claim 4, wherein: if some form of communication in the network is considered and the edge with the highest communication traffic is found, the edge should be the path connecting different communities, and such edges are removed to obtain the most natural breakdown of the network.
8. The method for measuring individual influence in a tissue according to claim 4, wherein: in S4, 3 measurement nodes are selected as parameters for measuring the core node of the network, the contact degree reflects the activity degree of the node in the network, the center degree measures the degree of the node between other nodes, the closeness measures the distance between one node and other nodes, and the larger the contact degree, center degree and closeness of the node is, the more likely it is the core of the network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910752829.XA CN112446795A (en) | 2019-08-15 | 2019-08-15 | System and method for measuring and calculating individual influence in tissue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910752829.XA CN112446795A (en) | 2019-08-15 | 2019-08-15 | System and method for measuring and calculating individual influence in tissue |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112446795A true CN112446795A (en) | 2021-03-05 |
Family
ID=74742027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910752829.XA Pending CN112446795A (en) | 2019-08-15 | 2019-08-15 | System and method for measuring and calculating individual influence in tissue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446795A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130085745A1 (en) * | 2011-10-04 | 2013-04-04 | Salesforce.Com, Inc. | Semantic-based approach for identifying topics in a corpus of text-based items |
| CN104008182A (en) * | 2014-06-10 | 2014-08-27 | 盐城师范学院 | Measuring method of social network communication influence and measure system thereof |
| US20170017908A1 (en) * | 2015-07-15 | 2017-01-19 | Sap Se | Churn risk scoring using call network analysis |
-
2019
- 2019-08-15 CN CN201910752829.XA patent/CN112446795A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130085745A1 (en) * | 2011-10-04 | 2013-04-04 | Salesforce.Com, Inc. | Semantic-based approach for identifying topics in a corpus of text-based items |
| CN104008182A (en) * | 2014-06-10 | 2014-08-27 | 盐城师范学院 | Measuring method of social network communication influence and measure system thereof |
| US20170017908A1 (en) * | 2015-07-15 | 2017-01-19 | Sap Se | Churn risk scoring using call network analysis |
Non-Patent Citations (1)
| Title |
|---|
| 孙晓玲等: "人际网络关系抽取和结构挖掘", 《微电子学与计算机》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829166B (en) | People and host customer opinion mining method based on character-level convolutional neural network | |
| CN103246670B (en) | Microblogging sequence, search, methods of exhibiting and system | |
| CN109492101A (en) | File classification method, system and medium based on label information and text feature | |
| CN105302911B (en) | A kind of data screening engine method for building up and data screening engine | |
| CN109711424B (en) | Behavior rule acquisition method, device and equipment based on decision tree | |
| Nithyanand et al. | Measuring offensive speech in online political discourse | |
| CN110472057B (en) | Topic label generation method and device | |
| Gokulkumari et al. | Analyze the political preference of a common man by using data mining and machine learning | |
| CN115033668B (en) | Story venation construction method and device, electronic equipment and storage medium | |
| Peng et al. | Predictive analytics for University of Virginia football recruiting | |
| CN110633410A (en) | Information processing method and device, storage medium, and electronic device | |
| CN108509588A (en) | A kind of lawyer's appraisal procedure and recommendation method based on big data | |
| Sahu et al. | Automatic question tagging using multi-label classification in community question answering sites | |
| CN106055657B (en) | Viewing index assessment system for specific crowd | |
| CN111859146B (en) | Information mining method and device and electronic equipment | |
| Fraxanet et al. | Unpacking polarization: Antagonism and Alignment in Signed Networks of Online Interaction | |
| CN110532374A (en) | The processing method and processing device of insurance information | |
| Szyjewski et al. | A study on existing and actually used capabilities of mobile phones technologies | |
| US11134045B2 (en) | Message sorting system, message sorting method, and program | |
| CN116340387A (en) | Statistical analysis method and system for personal information disclosure condition of data table | |
| Ferrara et al. | Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE | |
| CN112446795A (en) | System and method for measuring and calculating individual influence in tissue | |
| CN112989217B (en) | System for managing human veins | |
| CN111090742B (en) | Question-answer pair evaluation method, question-answer pair evaluation device, storage medium and equipment | |
| Sudhakar et al. | Fake profile identification using machine learning |
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 |
Application publication date: 20210305 |
|
| RJ01 | Rejection of invention patent application after publication |