KR20170129347A - System and method for estimating coporative social responsibility - Google Patents

System and method for estimating coporative social responsibility Download PDF

Info

Publication number
KR20170129347A
KR20170129347A KR1020160059901A KR20160059901A KR20170129347A KR 20170129347 A KR20170129347 A KR 20170129347A KR 1020160059901 A KR1020160059901 A KR 1020160059901A KR 20160059901 A KR20160059901 A KR 20160059901A KR 20170129347 A KR20170129347 A KR 20170129347A
Authority
KR
South Korea
Prior art keywords
information
social
social contribution
probability
keyword
Prior art date
Application number
KR1020160059901A
Other languages
Korean (ko)
Inventor
이수호
윤정심
Original Assignee
(주)에릭스팩토리
윤정심
이수호
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by (주)에릭스팩토리, 윤정심, 이수호 filed Critical (주)에릭스팩토리
Priority to KR1020160059901A priority Critical patent/KR20170129347A/en
Publication of KR20170129347A publication Critical patent/KR20170129347A/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2219—Large Object storage; Management thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • 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
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Computational Mathematics (AREA)
  • Operations Research (AREA)
  • Software Systems (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Databases & Information Systems (AREA)
  • Pure & Applied Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The social contribution activity evaluation system of the enterprise and the evaluation method thereof are provided. The corporate social contribution activity evaluation system collects the first information from the comparative information by collecting the comparative information based on predetermined criteria, collects the second information related to the corporate social contribution activity, A big data analysis unit for extracting third information different from the first information, and an evaluation unit for scoring the social contribution activities of the company based on the first information and the third information.

Description

The social contribution activity evaluation system of the enterprise and the evaluation method of the social contribution activity evaluation system

The present invention relates to a corporate social contribution activity evaluation system and an evaluation method thereof.

In the mid to late 2000s, corporate social responsibility began to attract attention as an important issue in academia and business, and society and consumers' expectation for corporate CSR activities became very high. Over the past decade, corporate CSR activities have evolved to be one of the major management strategies of each company, beyond simple PR activities for corporate image management.

CSR is important to companies because CSR is not only about raising corporate brand value, but also has a real impact on consumers' purchasing of products or services. Consumers think that they contribute to society by consuming the products or services of companies contributing to society. Therefore, in order to maximize the added effect of CSR from the corporate viewpoint, it should not be merely doing a good job, but the process should gain social sympathy and be recognized by consumers.

However, most of the cases of CSR in domestic companies are merely to perform activities related to social responsibility. For example, simple volunteer activities or donation activities, which would not be a problem for any company, are concentrated at the end of the year. These activities will not attract the attention of the media and consumers, and will be finished without additional effects such as enhancing corporate image or increasing sales. Apart from the additional benefits that companies have, they do not contribute much to making society a better place for CSR's ultimate goal.

Therefore, it is necessary to study evaluation system and evaluation method that can objectively evaluate CSR of current companies and maximize social contribution degree and its additional effect through it.

Korean Patent Publication No. 2016-0010834 (disclosed on January 28, 2016)

Some technical problems to be solved by the present invention are to provide a corporate social contribution activity evaluation system that can systematically and quantitatively evaluate corporate social contribution activities.

Another technical problem to be solved by the present invention is to provide a corporate social contribution activity evaluation method that can systematically and quantitatively evaluate the corporate social contribution activities.

The technical objects of the present invention are not limited to the technical matters mentioned above, and other technical subjects not mentioned can be clearly understood by those skilled in the art from the following description.

According to another aspect of the present invention, there is provided a system for evaluating social contribution activities of a corporation, comprising: collecting comparison information based on predetermined criteria, extracting first information from the comparison information, A big data analysis unit for collecting second information related to the first information and extracting third information other than the first information from the second information and an evaluation unit for scoring the social contribution activity of the company based on the first information and the third information do.

In an embodiment, the first information includes a first keyword extracted from the comparison information and probability information about the first keyword, the third information includes a second keyword extracted from the second information, And the evaluator may score the social contribution activity of the corporation using the probability information about the first keyword and the probability information about the second keyword.

In an embodiment, the comparison information may include social issue information collected via web crawling.

In an embodiment, the comparison information may include interest information of a consumer of the product or service of the enterprise.

In the embodiment, the evaluator may calculate the issue probability of the corporate social contribution activity using the following equation.

≪ Equation &

Figure pat00001

In an embodiment, the first information includes a reference amount of a social contribution activity of a first company, the third information includes a reference amount of a social contribution activity of a second company different from the first corporation, It is possible to evaluate the spreading power of the corporate social contribution activities by comparing the amounts of the social contribution activities of the first and second companies.

According to another aspect of the present invention, there is provided a method of evaluating a social contribution activity of a company, comprising collecting comparison information based on a predetermined criterion of a big data analysis unit, Extracting second information related to the social contribution activity of the big data analysis unit; extracting third information other than the first information from the second data analysis unit second information; 1 < / RTI > information and the third information based on the relationship between the first information and the third information.

 In an embodiment, the step of collecting the comparison information by the big data analysis unit includes collecting a document through web crawling and performing text mining on the collected document, 1 information includes extracting a social issue keyword and an occurrence probability of the social issue keyword, a related word of the social issue keyword, and an association probability of the related word from the text mining-processed document .

In an embodiment, the step of collecting the comparison information by the big data analysis unit may further include filtering the document on which the text mining is performed using the following equation.

≪ Equation &

Figure pat00002

In an embodiment, the step of collecting second information related to the social contribution activity of the big data analysis unit includes collecting a web document through a web crawl using the corporate social contribution activity as a keyword, The step of extracting third information different from the first information from the second information includes extracting an association probability associated with the social contribution activity of the corporation and the association word of the association word from the collected web document Step < / RTI >

In the embodiment, the step of scoring the social contribution activity of the company based on the first information and the third information may include calculating a probability of an issue of the social contribution activity, Of the social contribution activities of the company can be scored through comparison with other social contribution activities. In the embodiment, the step of calculating the issue probability of the corporate social contribution activity may include calculating the probability of the social contribution activity And calculating the issue probability.

≪ Equation &

Figure pat00003

In an embodiment, the step of collecting the comparison information by the big data analysis unit includes the step of identifying a consumer layer for the product or service of the enterprise and collecting documents related to the identified consumer layer, The step of extracting the first information may include extracting a probability distribution of the interest keyword and the interest keyword of the identified consumer layer from the collected document.

The details of other embodiments are included in the detailed description and drawings.

1 is a block diagram of a corporate social contribution activity assessment system in accordance with some embodiments of the present invention.
2 is an exemplary detailed block diagram of the big data analysis unit of FIG.
3 is an exemplary detailed block diagram of the analyzer of FIG.
FIG. 4 is a flowchart showing a method for evaluating a social contribution activity of a corporation based on the social necessity.
FIG. 5 is a flowchart showing a method of evaluating a corporate social contribution activity on the basis of an enterprise association.
6 is a flowchart showing a method of evaluating a corporate social contribution activity based on the SNS diffusion power.
FIG. 7 is an exemplary graph showing a method of scoring a standard score to a score of 5 points.
Fig. 8 is a diagram showing an example of visualization of the evaluation score.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention and the manner of achieving them will become apparent with reference to the embodiments described in detail below with reference to the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. The dimensions and relative sizes of the components shown in the figures may be exaggerated for clarity of description. Like reference numerals refer to like elements throughout the specification and "and / or" include each and every combination of one or more of the mentioned items.

The terminology used herein is for the purpose of illustrating embodiments and is not intended to be limiting of the present invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. The terms " comprises "and / or" comprising "used in the specification do not exclude the presence or addition of one or more other elements in addition to the stated element.

Although the first, second, etc. are used to describe various elements or components, it is needless to say that these elements or components are not limited by these terms. These terms are used only to distinguish one element or component from another. Therefore, it is needless to say that the first element or the constituent element mentioned below may be the second element or constituent element within the technical spirit of the present invention.

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs. Also, commonly used predefined terms are not ideally or excessively interpreted unless explicitly defined otherwise.

1 is a block diagram of a corporate social contribution activity assessment system in accordance with some embodiments of the present invention.

Referring to FIG. 1, a corporate social contribution activity evaluation system may include a big data analysis unit 100, an evaluation unit 200, a panel interface 300, and a visualization unit 400.

The big data analysis unit 100 can collect and analyze big data in order to automatically evaluate some of the evaluations of the corporate social contribution activities. Specifically, the big data analysis unit 100 collects information related to the social contribution activities of the enterprise, and collects the comparison information necessary for evaluating the social contribution activities of the enterprise. In addition, the big data analysis unit 100 can extract, for example, a keyword from the collected information and extract a probability distribution of the keyword.

The evaluation unit 200 can score and evaluate the corporate social contribution activities based on the information collected and analyzed through the big data analysis unit 100 and the panel interface 300 to be described later. For example, the evaluation unit 200 evaluates factors such as social necessity of social contribution activities, corporate relevance, stone output, contribution degree, empathy, public confidence, participation degree, SNS diffusion power, .

Concrete operations of the big data analysis unit 100 and the evaluation unit 200 will be described later.

The panel interface 300 may include an evaluation panel that is difficult to automatically evaluate, for example, a contribution to a corporate social contribution activity that determines whether the beneficiary is satisfied with the above evaluation factors, Provides an interface to the parts that need to be evaluated and entered manually. The panel interface 300 receives evaluation values of some evaluation factors from the respective panel terminals 500 and delivers them to the evaluation unit.

The visualization unit (400) visualizes the score evaluated by the evaluation unit (200). For example, the visualization unit 400 can visualize (400) the overall evaluation through the radar chart as shown in FIG.

2 is an exemplary detailed block diagram of the big data analysis unit 100 of FIG.

2, the big data analysis unit 100 includes a controller 110, a lexicon DB 120, a crawler 130, a storage interface 140, a storage 150, and an analysis unit 160, . ≪ / RTI >

The control unit 110 may control the vocabulary DB 120 to be updated through machine learning. In addition, the controller 110 may perform an interface function between the lexical DB 120 and other components such as the analysis unit 160. In addition, detailed operation of the control unit 110 will be described later.

The crawler 130 may download a web page via a plurality of distributed systems.

The storage interface 140 filters or classifies a web document and an SNS document (Social Network Service document, hereinafter referred to as "social document") downloaded from the crawler 130 on a predetermined basis and stores the same in the storage 150. The filtering or classification criteria will be described later in the description of the system operation.

The storage 150 may compress and store downloaded web pages. In some embodiments, the repository 150 may store web documents and social documents separately according to the classification of the storage interface 140.

The analysis unit 160 may decompress the document in the repository 150 and analyze it in various ways. 3, the analysis unit 160 may include a parsing module 161, an appearance probability calculation module 162, and an LDA module 163. [ Detailed operation of the analysis unit 160 will be described later along with each evaluation method.

The system according to some embodiments of the present invention described with reference to Figures 1 to 3 can evaluate various factors to evaluate a company's social contribution activities. For example, the system of the present invention can evaluate the social contribution activities of a company by evaluating factors such as social necessity of social contribution activity, business association, stone output, contribution degree, empathy degree, public confidence, participation degree, SNS diffusion power, .

Some or all of the evaluation factors described above can be automatically evaluated by data collection and analysis of the big data analysis unit 100. [ For example, the evaluation factors shown in Table 1 below can be used to evaluate a company's social contribution activities by an automated evaluation of the big data analysis unit 100.

Evaluation factor Contents Compare information Social necessity Is the social contribution activity of a corporation a social issue that a majority of the general public sympathize with? Relevance to social issues Business associativity Does the social contribution activity of a company directly relate to the essence of the business or the business area? Consumer interest issues of the company concerned SNS (Press) Spreading power Is the social contribution activity of the company social network users want to spread voluntarily?
Is it possible for corporate social contribution activities to be reported through credible media, or to be positively evaluated in the media? Positive amount of increase in social contribution activities

Hereinafter, a method of evaluating a social contribution activity of a company according to some embodiments of the present invention will be described with reference to FIGS. 4 to 6. FIG.

1. Social needs assessment

FIG. 4 is a flowchart showing a method for evaluating a social contribution activity of a company based on the social necessity.

1.1 Web document collection and filtering

Referring to FIG. 4, first, in order to extract a social issue keyword, a web document related to a social issue is collected, and a web document unrelated to a social issue is filtered in order to reduce the overall amount of calculation (S410).

The big data analysis unit 100 may collect news documents for a certain period of time, for example, the past one year from the crawling time, through web crawling or the like in order to extract social issue keywords. The big data analysis unit 100 may perform text mining to extract a document containing only text by removing a moving image or an image from the collected news documents.

2, the control unit 110 of the big data analysis unit 100 controls the crawler 130 to download web documents. The crawler 130 may be implemented as a distributed system for fast and efficient web document collection.

The web documents downloaded through the crawler 130 are filtered according to a predetermined criterion by the storage interface 140, and text mining can be performed.

According to an embodiment of the present invention, the storage interface 140 assigns a filtering score as shown in Equation (1) to each collected web document, and a predetermined criterion, for example, You can remove Web documents. For this purpose, words in the vocabulary DB are words that are irrelevant to social issues such as culture, entertainment, entertainment, movies, baseball, reviews, novels, girl groups, Can be stored.

&Quot; (1) "

Figure pat00004

(Where, n k denotes a single news article given as input, and, f (n k) represents the filtered scores n k. Also │n │ k is the number of all words in a k n, and │ The function D (w i , w j ) returns 1 if the words w i and w j are equal to each other, and 0 otherwise and. all of the words in the n k is the be included in the pre-f (n k) = 0. )

The filtered web documents are text mined by the storage interface 140 as described above. The storage interface 140 may remove objects other than text such as moving images, images, etc. from the filtered web document. And the text may be stored in the repository 150 on a document basis. In this case, the storage 150 may compress and store the collected web documents for securing storage space.

1.2 Social issues Keyword and related vocabulary extraction

Next, the big data analysis unit 100 extracts an association vocabulary with respect to n social problem keywords and social issue keywords (S420).

For this, the analysis unit 160 of the big data analysis unit 100 decompresses the collected web documents, and extracts words in the web document through morphological analysis.

Specifically, the parsing module 161 in the analysis unit 160 analyzes the morpheme of text in each filtered document to extract words. For example, in the case of Hangul, a noun is extracted by removing words corresponding to an investigation and a suffix (e.g., ~), or a word is extracted by replacing a verb and adjective with a basic type. In English, words are extracted by replacing the plural form of the word with a singular form, or replacing the past form of the verb or the passive form with the basic form.

The extracted words are extracted through the appearance probability calculation module 162 of the analysis unit 160 and extracted from a predetermined number n (for example, 100) social issue keywords. For example, the appearance probability of each word can be derived from the occurrence frequency of the issue keyword through the occurrence frequency of the corresponding word with respect to the total number of emerging words.

Next, the LDA module 163 of the analysis unit 160 extracts the associated vocabulary and the association probability by applying the topic modeling algorithm, for example, the LDA algorithm, using the derived issue keyword as a search term. The LDA algorithm analyzes the words in the original text, finds the related vocabularies of the search terms statistically within the original text, and can calculate the probability of association for each word.

For example, the results of applying the LDA algorithm based on the collected news documents may be as shown in Table 2 below.

ranking keyword Probability of emergence Related vocabulary Association probability One Economic democratization 0.0200201 inequality 0.0012053 Win-Win 0.0004210 Soil cutlery 0.000125 ... ... 2 health 0.017924 obesity 0.02003261 Exercise 0.010210 depression 0.0051003 ... ... ... ... ...

The extracted social issue keywords, related words, and association probabilities may be stored in a vocabulary DB (120 in FIG. 1) in the form of Table 2, for example. However, in this case, the associated vocabulary may be extracted by a predetermined number m for efficiency. For example, the top 100 words based on the association probability can be extracted as an associated word. Also, the social issue keyword, the associated vocabulary, and the association probability can be updated periodically.

1.3 Extraction of related words of social contribution activities

Next, l (l is a natural number) words are extracted from the words related to the social contribution activities of the corporation using the keyword (S430).

For example, if the social contribution activity of the corporation is supportive of Lou Gehrig's disease, the big data analysis unit 100 applies the LDA algorithm based on the news web document previously collected with the keyword 'Lou Gehrig's disease' Can be extracted.

1.4 Calculating the Issue Probability of Social Contribution Activities

Next, the issue probability is calculated by comparing keywords related to the social contribution activities of the referral corporation and social issue keywords (S440).

For example, the evaluation unit (200 in FIG. 1) compares the keyword related to the social contribution activity with the social issue keyword to calculate the probability as shown in Equation (2) below.

 &Quot; (2) "

Figure pat00005

(Where P (SCA c) is a provider of social issues and the social contributions of the c issues probability of how much you can become a social issue, E (W i, W j ) the word (W j-related social contributions) If there is a match and associated vocabulary (W i) is a value that returns zero if the returns 1, and do not match. P (W i) is the product of the associated probability of the associated vocabulary, consistent with the occurrence probability of a social issue keyword n, m, and l are the number of social issue keywords, the number of associated vocabularies, and the number of associated vocabularies of social contribution activities, respectively, as described above.

For example, if the social contribution activity is support for Lou Gehrig's disease, and the overlapping word of the related vocabulary associated with the social issue keyword described above is depression, inequality, P (SCAc) = (probability of appearance of economic democratization Χ inequality association probability) + (probability of health emergence △ depression association probability).

1.5 Scoring through comparison with other social contribution activities

The calculated probability of issue of social contribution activity itself is meaningless as it is merely a reference amount of related keywords. Therefore, we compare the probability of issues with other social contribution activities for scoring.

For scoring purposes, the vocabulary DB can store words for other social contribution activities. For example, words associated with other types of social contribution activities, such as donations and services, can be stored. In order to store such words, the big data analysis unit 100 may extract the type-related words in an automated manner through the LDA algorithm, or manually input and store the words.

We can calculate the probability of each issue for 1.4 social contribution activities by using the words related to each other social contribution activity as keywords.

Each calculated social contribution activity can be organized, for example, as shown in Table 3 below.

ranking Social Contribution Activities Issue probability One donate 0.00000154 2 volunteer 0.00001301 3 ALS 0.000115548 ... ... ...

After obtaining the probability of an issue for each social contribution activity, the evaluation unit 200 scales each social contribution activity to a score of 5 on the basis of each issue probability. For example, a score can be obtained by obtaining the mean and standard deviation of the probability of each social contribution activity and using a predetermined reference score based on a normal distribution.

Hereinafter, the scoring method of the evaluating unit 200 will be described with reference to the examples of FIG. 7 and Table 3 above.

7 is an example of a standard score. Reference numeral 710 in FIG. 7 is a normal distribution curve, reference numeral 720 is a variance, and reference numeral 730 is an exemplary score reference.

In Table 3, the average probability of social contribution activities is 0.000043366, and the standard deviation is 6.28 × 10 -5. Therefore, the standard score of Lou Gehrig's disease is 1.14, and compared with the score standard (730) 4 points.

As another example, the standard score of donations during social contribution activities is -0.67, which corresponds to 2 points for the final five-point scale when compared with the score standard (730). The standard score for service is -0.48, with a final score of two.

Based on the above results, it can be seen that social contribution activities related to Lou Gehrig's disease can be mentioned much more as social issues in contrast to other social contribution activities such as donation or service. In other words, if a company engages in social contribution activities, it can be seen that social contribution activities related to Lou Gehrig's disease are more relevant to the current social issues than to simple donations or volunteer activities.

However, the above scoring is illustrative, and those skilled in the art can score through other existing statistical scoring methods.

In addition, in the present embodiment, the scores are scored simply by taking into account social issues in news, but it is also possible to evaluate social contribution activities through an increase in the amount of the reference. For example, based on the time of corporate social contribution activity, it is possible to investigate the amount of news mention in the immediately preceding 3 months and immediately after 3 months, and then calculate the issue probability through the method described above, and score using the increase in the issue probability Do.

Hereinafter, a method of evaluating a social contribution activity based on an enterprise relationship will be described with reference to FIGS. 5 and 2. FIG.

2. Business relevance assessment

2.1 Extracting Products / Services

Referring to FIG. 5, first, a product or service of the company is extracted and the main consumer layer of the company is identified based on the extracted information (S510).

For example, the control unit 110 of the big data analysis unit 100 can control to extract the product or service of the company through the enterprise DB stored in the vocabulary DB or the enterprise DB information operated by the government or the like .

2.2 Identify the main consumers of the enterprise

Next, the control unit 110 uses the social document and its metadata to identify the main consumer layer of the company (S520)

For this, the control unit 110 may control the crawler 130 to perform crawling on the social document. The downloaded social documents through the crawler 130 are transferred to the storage interface 140. [

The storage interface 140 may use the metadata of the social document to distinguish the documents and store them in the storage 150. For example, it may be stored in each storage space in the storage 150 separated by age / gender based on age and gender data included in the metadata of the social document.

Again, the storage interface 140 counts the number of documents related to the company's product / service among the entire documents, using the product / service of the company as a keyword, to identify the main consumer. The product / service may be simply a keyword, or the keyword may be filtered with an expanded keyword through a thesaurus stored in the vocabulary DB. Alternatively, the LDA module of the analysis unit 160 may be used to search the related vocabulary using the entire document as a product or service as a keyword, and to filter documents containing related vocabularies.

The storage interface 140 counts the number of related documents by age / gender, and uses the results to identify the main consumer segment. The identified consumer information is transmitted to the control unit 110 and can be utilized for data analysis work in the future.

2.3 Keyword Extraction of Interested Consumers

Next, the analysis unit 160 extracts n (n is a natural number) of interest keywords based on the social documents created by the creator corresponding to the age / gender corresponding to the main consumer layer among the documents stored for each age group / gender (S530).

For example, the big data analysis unit 100 extracts n (n is a natural number) interest keywords of the consumer group identified through the SNS (Social Network Service) document of the identified consumer segment, The related probabilities of related words can be extracted. The concrete procedure for this can be similar to the process of extracting the social issue keyword described above.

2.4 Problem extraction and scoring of social contribution activities

Extract m (m is a natural number) vocabulary related to the social contribution of the company from the stored document, and extract the issue probability of each related vocabulary (S540). And the relevance of the related vocabulary related to other social contribution activities (S550).

The detailed process of this can be performed in a similar way to the evaluation of social contribution activities centered on the social necessity, so redundant explanation is omitted.

3. Evaluation of SNS diffusion

6 is a flowchart showing a method of evaluating a social contribution activity of a corporation based on SNS or media diffusion power.

Referring to FIG. 6, a competitor company of a company commissioned for evaluation of social contribution activities is extracted (S610).

For example, the control unit 110 of the big data analysis unit 100 can search for a company that is duplicated with the product or service of the referral company through the enterprise DB to extract the competitor of the referral company.

Next, a positive amount of reference to the social contribution activities of the evaluation requesting company and the competitor is calculated (S620, S630).

More specifically, the control unit 110 of the big data analysis unit 100 can download the social document and the web document through the crawler 130. [ In addition, the storage interface 140 may filter related documents by using the social contribution activities and related vocabulary as keywords, and store them in the storage 150 for each company.

The analysis unit 160 examines the amounts of references of the positive vocabulary through text mining for each company based on the documents stored in the storage unit 150. For this purpose, the words mentioned through the affix / adjective dictionary stored in the vocabulary DB are scored by document and the scored contents are averaged.

Finally, the change scores are scored as 5 out of 10 using the standard score for each company, and finally the SNS spreading power of the evaluation requesting company is calculated (S640)

For the sake of simplicity, the description of the social contribution activities and the overlapping contents are omitted from the above based on the social necessity or enterprise relation with respect to this embodiment.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It is to be understood that the invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

100: Big data analysis unit
200:
300: Panel interface unit
400: visualization unit

Claims (13)

Collecting second information related to a social contribution activity of a corporation, collecting third information different from the first information from the second information, collecting first information from the first information, A big data analyzing unit for extracting; And
And an evaluation unit for scoring the social contribution activities of the company on the basis of the first information and the third information. The method according to claim 1,
Wherein the first information includes a first keyword extracted from the comparison information and probability information about the first keyword,
Wherein the third information includes a second keyword extracted from the second information and probability information about the second keyword,
Wherein the evaluating unit scales the social contribution activity of the company using probability information about the first keyword and probability information about the second keyword. 3. The method of claim 2,
Wherein the comparison information includes a social issue information collected through web crawling. 3. The method of claim 2,
Wherein the comparison information includes interest information of a consumer of the product or service of the enterprise. 3. The method of claim 2,
Wherein the evaluating unit calculates a probability of an issue of the corporate social contribution activity using the following equation:
≪ Equation &
Figure pat00006
 The method according to claim 1,
Wherein the first information includes a reference to a social contribution activity of the first company,
Wherein the third information includes a reference to a social contribution activity of a second company different from the first company,
Wherein the evaluation unit compares the reference amounts of the social contribution activities of the first and second companies and evaluates the spreading power of the social contribution activities of the company. Collecting comparison information based on a predetermined criterion;
Extracting first information from the comparison information by the big data analyzing unit;
Collecting second information related to the social contribution activity of the big data analysis unit;
Extracting third information different from the first information from the second information; And
And the evaluating unit scoring the social contribution activity of the company on the basis of the relationship between the first information and the third information. 8. The method of claim 7,
Wherein the step of collecting the comparison information comprises:
Collecting the document through web crawling, and performing text mining on the collected document,
Wherein the step of extracting the first information comprises:
Extracting a social issue keyword and an occurrence probability of the social issue keyword, a related word of the social issue keyword, and an association probability of the related word from the text mining-processed document. 9. The method of claim 8,
Wherein the step of collecting the comparison information comprises:
And performing filtering on the document on which the text mining is performed by using the following equation.
≪ Equation &
Figure pat00007
 9. The method of claim 8,
The step of collecting the second information related to the social contribution activity of the big data analysis unit comprises:
Collecting a web document through a web crawl using the corporate social contribution activity as a keyword,
Wherein the step of extracting third information different from the first information from the second information comprises:
And extracting from the collected web documents a related word related to a social contribution activity of a corporation and a probability of association of the related word. 8. The method of claim 7,
Wherein the step of scoring the social contribution activity of the corporation based on the first information and the third information includes:
Calculating a probability of an issue of the social contribution activity; and scoring the social contribution activity of the enterprise by comparing it with other social contribution activities. 12. The method of claim 11,
The step of calculating the issue probability of the corporate social contribution activity includes calculating the issue probability of the corporate social contribution activity using the following equation.
≪ Equation &
Figure pat00008
 8. The method of claim 7,
Wherein the step of collecting the comparison information comprises:
Identifying a consumer segment for the product or service of the enterprise and collecting documents related to the identified consumer segment,
Wherein the step of extracting the first information comprises:
And extracting a probability distribution of the interest keyword and the interest keyword of the identified consumer layer from the collected documents.
KR1020160059901A 2016-05-17 2016-05-17 System and method for estimating coporative social responsibility KR20170129347A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020160059901A KR20170129347A (en) 2016-05-17 2016-05-17 System and method for estimating coporative social responsibility

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020160059901A KR20170129347A (en) 2016-05-17 2016-05-17 System and method for estimating coporative social responsibility

Publications (1)

Publication Number Publication Date
KR20170129347A true KR20170129347A (en) 2017-11-27

Family

ID=60810902

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020160059901A KR20170129347A (en) 2016-05-17 2016-05-17 System and method for estimating coporative social responsibility

Country Status (1)

Country Link
KR (1) KR20170129347A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020130418A1 (en) * 2018-12-17 2020-06-25 지속가능발전소 주식회사 Method for analyzing supply chain risk of suppliers
KR102341697B1 (en) * 2020-08-11 2021-12-21 샬레코리아(주) Method of supporting private enterprise holiday and server performing the same
CN114139539A (en) * 2021-12-06 2022-03-04 城云科技（中国）有限公司 Enterprise social responsibility index quantification method, system and application
CN114819686A (en) * 2022-05-10 2022-07-29 武汉鸿榛园林绿化工程有限公司 Landscape landscaping planning, designing, analyzing, evaluating and managing system based on visualization

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020130418A1 (en) * 2018-12-17 2020-06-25 지속가능발전소 주식회사 Method for analyzing supply chain risk of suppliers
US11610168B2 (en) 2018-12-17 2023-03-21 Isd Inc. Method for analyzing risk of cooperrator supply chain
KR102341697B1 (en) * 2020-08-11 2021-12-21 샬레코리아(주) Method of supporting private enterprise holiday and server performing the same
KR20220020236A (en) * 2020-08-11 2022-02-18 샬레코리아(주) Vacation support server to promote corporate social contribution activities
CN114139539A (en) * 2021-12-06 2022-03-04 城云科技（中国）有限公司 Enterprise social responsibility index quantification method, system and application
CN114819686A (en) * 2022-05-10 2022-07-29 武汉鸿榛园林绿化工程有限公司 Landscape landscaping planning, designing, analyzing, evaluating and managing system based on visualization

Similar Documents

Publication Publication Date Title
US9767166B2 (en) System and method for predicting user behaviors based on phrase connections
EP3819792A2 (en) Method, apparatus, device, and storage medium for intention recommendation
US11663254B2 (en) System and engine for seeded clustering of news events
Batool et al. Precise tweet classification and sentiment analysis
US10268670B2 (en) System and method detecting hidden connections among phrases
US20180300315A1 (en) Systems and methods for document processing using machine learning
KR101463974B1 (en) Big data analysis system for marketing and method thereof
Kang et al. Modeling user interest in social media using news media and wikipedia
CN103023714B (en) The liveness of topic Network Based and cluster topology analytical system and method
CN108563620A (en) The automatic writing method of text and system
US20130091117A1 (en) Sentiment Analysis From Social Media Content
US9785704B2 (en) Extracting query dimensions from search results
US20100306144A1 (en) System and method for classifying information
CN107544988B (en) Method and device for acquiring public opinion data
US20110040769A1 (en) Query-URL N-Gram Features in Web Ranking
US20100125531A1 (en) System and method for the automated filtering of reviews for marketability
US9858332B1 (en) Extracting and leveraging knowledge from unstructured data
CN102722498A (en) Search engine and implementation method thereof
CN104281702A (en) Power keyword segmentation based data retrieval method and device
KR20170129347A (en) System and method for estimating coporative social responsibility
Filho et al. Gender classification of twitter data based on textual meta-attributes extraction
CN103714120A (en) System for extracting interesting topics from url (uniform resource locator) access records of users
CN105512300A (en) Information filtering method and system
KR102413961B1 (en) Method for providing news analysis service using robotic process automation monitoring
US11295078B2 (en) Portfolio-based text analytics tool

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E902 Notification of reason for refusal
E601 Decision to refuse application