KR101997111B1 - Apparatus for calculating convergence rate according to web page analysis based on artificial intelligence and operating method thereof - Google Patents

Abstract

The present invention relates to a device for calculating a fusion index based on webpage analysis based on artificial intelligence and an operating method thereof. The present invention determines an industrial fusion index between first industries selected with regard to a first region and second industries selected with regard to a second region based on the industrial fusion index, transmits a regional fusion index calculated after determining an average value of the determined industrial fusion index as the regional fusion index to a terminal of a manager, and allows companies to perform fusion activities so as to use a separate inter-industry relation table after extracting company information of various industries, thereby analyzing various fusion information and providing the analyzed fusion information to the companies for contributing new technology development and increase of competitiveness which are a goal of the companies.

Description

TECHNICAL FIELD [0001] The present invention relates to an apparatus for calculating a fusion index based on artificial intelligence based web page analysis, and a method of operating the same. [0002]

The present invention relates to a device for extracting keyword information of a company operating a corresponding web page through analysis of a web page and then calculating a fusion index based on the extracted enterprise keyword information and an industrial fusion composite index, and an operation method thereof.

The development of new technologies and the creation of new markets are essential activities for enhancing competitiveness of enterprises. To effectively develop these new technologies and create new markets, companies need to combine technologies and ideas from different fields through convergence activities. According to the "Survey on the status of industrial field convergence activities" jointly conducted by the Digital Times and Korea Industrial Technology Promotion Association in 2015, more than 80% of Korean companies answered that convergence activities are necessary. This shows that companies are also aware of the importance of convergence. In addition, the reason why companies think that convergence is necessary is that 'new technology · new product development' (42.5%) is the most, and among the companies that have actually converged, 56.1% of companies have increased their sales. This is a very high figure compared to the 5% who said they had decreased. Therefore, it can be seen that convergence activities contribute to the development of new technologies and enhancement of competitiveness.

Currently, government and private organizations are providing financial support for the development of convergence products and services as a policy for convergence of companies, and they are carrying out projects to strengthen exchanges and cooperation between companies to develop new markets through convergence. However, the biggest obstacle to convergence is the lack of information on convergence-related markets and technologies.

Currently, the Bank of Korea is issuing an industry association chart that can be used to provide information on the linkages among domestic industry groups. However, there is a disadvantage that additional information such as business or regional convergence is unknown. In the existing domestic research, "Scouting system and recommendation algorithm for small and medium sized manufacturing companies" has been studied, but it is difficult to provide convergence information for the entire industrial group because it is limited to manufacturing companies.

Therefore, in order to contribute to the development of new technologies and enhance competitiveness of companies by performing convergence activities, companies extract information of companies in various industries, analyze various fusion information using a separate industry association table, And to provide them to companies.

A fusion index computing device based on the artificial intelligence-based web page analysis according to the present invention and its operation method are characterized in that a first industry group selected for the first region and a second industry group selected for the second region And then transmits the calculated regional fusion index to the terminal of the manager so that the companies can perform the convergence activities, and thus the new technology In order to contribute to development and competitiveness enhancement, it is necessary to extract company information of various industrial groups, analyze various fusion information using a separate industry association table, and provide the analyzed fusion information to companies.

The apparatus for calculating a fusion index based on the analysis of a web page based on an artificial intelligence according to an embodiment of the present invention is characterized in that a company address and at least one industry group of a plurality of pre- An industrial complex index storage unit for storing an industrial composite index between the predetermined plurality of industries and a first area name and a second area name from an administrator terminal, Based on a business address matching the company information stored in the first region and the second region based on the first region name and the second region based on the first region name, A number of companies for each industry, for counting the number of companies and the number of companies per second industry; Selecting a first industry group of N - N, where N is an integer equal to or greater than 1, in a descending order of the number of enterprises located in the first region among a plurality of industry groups, An industry group selection unit for selecting the second industry groups that are M - M in the descending order of the number of enterprises located in the second region and the M is an integer of 1 or more; A fusion index calculation unit for determining an industrial fusion composite index between the first industry groups and the second industry groups selected for the second region and determining an average value of the determined industrial fusion composite indexes as a regional fusion index, And transmits the index to the terminal of the manager.

Also, the operation method of the fusion index computing device based on the analysis of the web page based on the artificial intelligence according to the embodiment of the present invention is characterized in that, for each of a plurality of companies, at least one industry group among a plurality of industries The method comprising the steps of: maintaining an enterprise information storage unit for storing enterprise information that is stored in the enterprise information storage unit; 2, a first area name and a second area name according to the first area name are registered for each of the plurality of industry groups based on a business address matched with the enterprise information stored in the enterprise information storage unit Counting the number of companies in the first industry and the number of companies in the second industry located in the second region according to the first mountain, The number of companies located in the first region among the plurality of industry groups is selected in the order of N - N, where N is an integer of 1 or more, based on the number of companies by business, Selecting, based on the number of industries located in the second region among the plurality of industry groups, M - the second industry groups in which M is an integer equal to or greater than 1, Determining a composite industrial composite index between the first industry groups selected for the first region and the second industry groups selected for the second region and determining an average value of the determined composite industrial composite index as a regional fusion index; And transmitting the local fusion index to the terminal of the manager.

A fusion index computing device based on the artificial intelligence-based web page analysis according to the present invention and its operation method are characterized in that a first industry group selected for the first region and a second industry group selected for the second region And then transmits the calculated regional fusion index to the terminal of the manager so that the companies can perform the convergence activities, and thus the new technology In order to contribute to development and competitiveness enhancement, it is possible to extract information on companies in various industrial groups, analyze various fusion information using a separate industry association table, and provide analyzed fusion information to companies.

1 is a diagram illustrating a structure of a fusion index computing apparatus based on analysis of a web page based on an artificial intelligence according to an embodiment of the present invention.
2 is a flowchart illustrating an operation method of a fusion index computing apparatus based on analysis of a web page based on an artificial intelligence according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. It is to be understood that the description is not intended to limit the invention to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals in the drawings are used for similar elements and, unless otherwise defined, all terms used in the specification, including technical and scientific terms, are to be construed in a manner that is familiar to those skilled in the art. It has the same meaning as commonly understood by those who have it.

1 is a diagram illustrating a structure of a fusion index calculating apparatus 100 based on analysis of a web page based on an artificial intelligence according to an embodiment of the present invention.

1, a fusion index computing apparatus 100 based on analysis of a web page based on an artificial intelligence according to an embodiment of the present invention includes an enterprise information storage unit 110, an industry word storage unit 120, An industry cluster number storage unit 140, an industry sector number count unit 150, an industry group selection unit 160, a fusion index calculation unit 170, and a fusion index transmission unit 180.

The enterprise information storage unit 110 stores company information for each of a plurality of companies, and company information in which at least one industry group among a plurality of predetermined industry groups is matched. In addition, the enterprise information storage unit 110 may further store important words for each of the plurality of companies.

For example, information may be stored in the enterprise information storage unit 110 as shown in Table 1 below.

Company Information Index Company Address Industry information Important word Company Information 1 Address 1 Agriculture, forestry and fisheries products Word 1, Word 2, Word 3 Company Information 2 Address 2 Agriculture, forestry and fisheries products Word 1, word 3 Company Information 3 Address 3 Minerals Word 4, Word 5, Word 6 Company Information 4 Address 4 Food and beverage Word 7, word 8 Company Information 5 Address 5 Culture and other services Word 9, Word 10, Word 11 Company Information 6 Address 6 Culture and other services Word 9, Word 11, Word 12 ... ... ... ...

The industry word storage 120 may store a plurality of predetermined industry group word groups including a plurality of predetermined industry group words to which different characteristic vectors are assigned. Here, the plurality of industry group words included in each of the plurality of industry group words may be words whose similarity calculated using the feature vector between them is equal to or greater than a predetermined reference similarity degree.

The industry word storage unit 120 may store a plurality of preset industry word groups including a plurality of preset industry word words to which different characteristic vectors are allocated as shown in Table 2 below.

Industry Group Word Index Industry word Characteristic vector Industry Group 1 computer (1, 2, 0, 0, 3) cellphone (2, 1, -1, -1, 2) laptop (3, 2, 0, -1, 1) Industry Group Word 2 Mackerel (-1, 1, 4, 3, 1) Pacific saury (0, -1, 3, 6, 2) Anchovy (-1, -1, 5, 2, -1) ... ... ...

Here, industry word group 1 may be electrical and electronic devices, and industry word group 2 may be agriculture, forestry and fisheries products.

Here, the similarity between the vectors can be calculated according to the following equation (1).

Here, S is a similarity between the characteristic vectors A and B, and has a value between -1 and 1, and the larger the value is, the similar characteristic vector, A _i is the i-th component of the characteristic vector A, B _i is the characteristic vector And the i-th component of B, respectively.

For example, when the similarity degree between the industrial word word "computer" and the characteristic word " mobile phone ", respectively, in Table 2 is calculated, the following equation (2) can be calculated.

For example, when the similarity degree between the industry word word "computer" and the characteristic word assigned to the industry word word "mackerel" is calculated in the above Table 2, it can be calculated as follows.

The similarity (ie, 0.8058) between the industry word word "computer" and the industry word word "mobile phone", and the similarity degree between the industry word word "computer" and the industry word word "mackerel" (Ie, 0.2020), it can be seen that the industry word "computer" is similar to the industry word "mobile" but not the industry word "mackerel". Here, it is possible to determine whether it is a similar industrial word based on a predetermined reference similarity degree (e.g., 0.5000).

The plurality of industry word words stored in the industry word storage unit 120 as shown in Table 2 are words arbitrarily set by the administrator, and the characteristic vectors assigned to the respective industry word words are similar to the similarity standard between the words set by the administrator And may be a value assigned to calculate a predetermined degree of similarity. In this case, the similarity criterion between the words of each industry group may be based on the result of analyzing the relation information between various industry groups through analyzing and learning various information through the web.

The company information input unit 130 accesses the web page of the first company on the basis of the input address of the web page of the first company, The enterprise information stored in the enterprise information storage unit 110 can be updated by generating the enterprise information for the first enterprise using the plurality of first texts stored in the enterprise information storage unit. The enterprise information input unit 130 includes a text extracting unit 131, a word extracting unit 132, an enterprise address determining unit 133, an important word selecting unit 134, an industry group determining unit 135, (136).

When the access address for the web page of the first company is inputted, the text extracting unit 131 accesses the web page of the first company on the basis of the access address, extracts the web page of the first company from the web page of the first company, A plurality of first texts existing on the web page can be extracted.

In this case, according to an embodiment of the present invention, the text extracting unit 131 parses HTML (Hypertext Markup Language) code constituting the web page of the first company, extracting the plurality of first texts existing on the web page of the first company by extracting the inserted text through a tag, if a hyperlink tag exists on the HTML code, Tag, and extracting texts inserted through a tag associated with text input from the HTML code of the sub-page, together with the plurality of texts existing on the web page of the first company, 1 < / RTI > texts.

In this regard, the text extracting unit 131 extracts the text inserted through the tag associated with the text input in the HTML code constituting the web page of the first company, and a hyperlink tag such as "<a href> & , It is possible to access the sub page linked through the hyperlink tag and to extract the texts inserted through the tag associated with the text input from the HTML code of the sub page to be present on the web page of the first company A plurality of first texts may be extracted.

The word extracting unit 132 may extract a plurality of first words from the plurality of first texts by performing morphological analysis on the plurality of first texts.

The enterprise address determination unit 133 may determine the enterprise address of the first company based on the plurality of first words. For example, if the consecutive words among the plurality of first words are words indicating local information (e.g., "Seoul City", "Yeongdeungpo-gu", "Yeouido-dong" And consecutive words indicating the local information can be determined as the corporate address of the first company.

The important word selection unit 134 may select at least one important word among the plurality of first words based on the frequency of occurrence on the web page of the first company of the plurality of first words.

Specifically, the important word selection unit 134 selects at least one important word among the plurality of first words based on the frequency of occurrence on the web page of the first company, At least one important word can be selected to match a stored industry word. Accordingly, even if the word &quot; pay &quot; appears most frequently on the web page of the first company, if the industry word word &quot; pay &quot; is not stored in the industry word storage unit 120, May not select the &quot; pay &quot; as an important word.

When the at least one important word is selected, the industry group determining unit 135 refers to the industry word storage unit to identify a characteristic vector for the at least one important word, and calculates a characteristic vector for the at least one important word Calculating a degree of similarity between feature vectors for each of the plurality of industry group words contained in each of the plurality of industry group words, and calculating, based on the calculated degree of similarity, at least one of the plurality of industry groups Of the industry. At this time, the industry group decision unit 135 calculates an average of the similarities between the at least one important word and the plurality of industry group words included in each of the plurality of industry word groups as a similarity to the at least one important word can do.

For example, if the at least one important word is selected as "mobile phone", "notebook", and "mackerel" on the web page of the first company, (2, 1, -1, -1, 2), (3, 2, 0, -1, 1) and (-1, 1, 4, 3, 1) for the mackerel And calculates the similarity between the characteristic vector for "mobile phone", "notebook" and "mackerel" and the characteristic vector for each of the plurality of industry word words contained in each of the plurality of industry word groups, And determine at least one industry group of the plurality of industry groups for the first enterprise based on the similarity degree. At this time, the industry group decision unit 135 determines the average value of the similarities calculated between the characteristic vector for "mobile phone", "notebook" and "mackerel" and the characteristic vector for each industry word included in the industry word group 1, Based on the average value of the similarities calculated between the characteristic vectors for the "mobile phone", "notebook" and "mackerel" and the characteristic vectors for the respective industry words included in the industry word group 2, .

The company information input unit 136 generates company information for the first company by matching the determined company address and the determined at least one industry group to the first company, Lt; / RTI &gt;

For example, if the corporate address of the first company is address 7, the industry group information is determined to be electrical and electronic, and the at least one important word on the web page of the first company is &quot; If "mackerel" is selected, the enterprise information input unit 136 can update the enterprise information as shown in Table 1 as shown in Table 3 below.

Company Information Index Company Address Industry information Important word Company Information 1 Address 1 Agriculture, forestry and fisheries products Word 1, Word 2, Word 3 Company Information 2 Address 2 Agriculture, forestry and fisheries products Word 1, word 3 Company Information 3 Address 3 Minerals Word 4, Word 5, Word 6 Company Information 4 Address 4 Food and beverage Word 7, word 8 Company Information 5 Address 5 Culture and other services Word 9, Word 10, Word 11 Company Information 6 Address 6 Culture and other services Word 9, Word 11, Word 12 Company Information 7 Address 7 Electrical and electronic equipment Mobile phones, notebooks, mackerel ... ... ... ...

Meanwhile, the company information input unit 136 may include a business information input unit 136 for inputting a plurality of business word groups corresponding to the industry group information of the first company among the at least one important word, In case of an important word of similarity or less, it may not be stored in matching with the company information. Accordingly, &quot; mackerel &quot; among &quot; mobile phone &quot;, &quot; notebook &quot;, and &quot; mackerel &quot; may not be included in the enterprise information for the first company.

Next, the industrial integrated complex index storage unit 140 may store the industrial integrated complex index among the predetermined plurality of industries. Here, the Industrial Composite Complex Index is a value obtained by normalizing the values of the components described in the matrix so that the sum of the rows is 1 after transposing the matrix of the input coefficient table of the Korean among the industry association tables issued by the Bank of Korea .

For example, the industrial fusion complex index storage unit 140 may store information as shown in Table 4 below.

Agriculture, forestry and fisheries products Minerals Food and beverage ... Culture and other services Sum Agriculture, forestry and fisheries products 0.130024 0.000059 0.405923 ... 0.003776 One Minerals 0.002392 0.000000 0.002877 ... 0.010724 One Food and beverage 0.408163 0.000272 0.17488 ... 0.002731 One ... ... ... ... ... ... ... Culture and other services 0.002662 0.000026 0.059479 ... 0.033729 One

Table 4 shows that for agriculture, forestry and fisheries products, there are 0.130024, 0.1000024, minerals and 0.000059, food and beverage products and 0.405923, and cultural and other services and 0.003776, respectively. Similarly, in the case of culture and other services, it has the Industrial Combined Composite Index of Agriculture, Forestry and Fisheries, 0.002662, Minerals and 0.000026, F & B and 0.059479 and Cultural and Other Services and 0.033729, The sum is 1.

If the first area name and the second area name are input from the terminal 190 of the manager, the number of companies for each industry sector counting unit 150 is calculated based on the company address matched with the company information stored in the enterprise information storage unit The number of companies in the first industry and the number of companies in the second industry, which are located in the second area according to the first area name and the second area name, may be counted for each of the plurality of industries. If the first area name and the second area name inputted from the terminal 190 of the manager are identical to each other, the industry-specific number-of-enterprises counting unit 150 can count the number of the first industry and the number of the second- . At this time, the terminal data receiving unit 155 can receive the first area name and the second area name from the terminal 190 of the administrator.

For example, if the companies 1 to 3 each having the company information 1 to 3 are located in the first area according to the first area name, and the companies 4 to 6 each having the company information 4 to 6 are located according to the second area name In the case of being located in the second region, the number-of-enterprises counting section 150 counts the number of companies per 1 industry for the agriculture, forestry and marine products of the first region as 2, counts the number of enterprises per 1 industry as 1 for mining products, For food and beverages in the second region, the number of enterprises by the second industry is counted as 1, and the number of enterprises by the second industry is counted as 2 for culture and other services. However, for example, if the first area name and the second area name are identical to each other, the industry-specific number-of-businesses counting unit 150 counts the number of companies for the first and second industries as 2 Counts the number of companies in the first and second industries as 1, counts the number of companies in the first and second industries as 1, counts the number of companies in the first and second industries for culture and other services as 1 Can be counted.

The industry group selection unit 160 selects N first industry groups in descending order of the number of companies located in the first region among the plurality of industry groups based on the number of the first industry groups, The number of the second industry groups can be selected in descending order of the number of the enterprises located in the second region among the plurality of industry groups based on the number of the second industry groups. N and M are integers of 1 or more.

For example, when N and M are 1, the industry group selection unit 160 selects agricultural and marine aquatic products having a first industry number of 2 for the first region as the first industry group and selects the second industry as the second industry Cultural and other services with two companies can be selected as the second industry group. On the other hand, if, for example, the first area name and the second area name are the same, and N and M are two, the industry group selection unit 160 selects the first and second industries 2 people, agriculture, forestry, marine products, culture and other services can be selected as the first and second industry groups.

The fusion index computing unit 170 determines an industrial fusion composite index between the first industry groups selected for the first region and the second industry groups selected for the second region based on the industrial fusion composite index, The average value of the composite composite index can be determined by the regional fusion index. Specifically, the fusion index calculation unit 170 determines the composite index for each of the second industry groups of each of the first industry groups and determines the composite index of each industry for each of the first industry groups of the second industry groups The average value of the INDFs determined above may be determined as a regional fusion index.

For example, if agricultural and marine products are selected as the first industry group for the first region and culture and other services are selected as the second industry group for the second region, the fusion index calculation unit 170 calculates the fusion index The industrial complex index for culture and other services of the second industrial group was determined to be 0.003776 and the industrial composite index for agriculture, forestry and marine products, the first industrial group of culture and other services of the second industrial group, was determined to be 0.002662, The average value of the composite index (i.e., 0.003219) can be determined as the regional fusion index between the first region and the second region.

However, for example, if the first area name and the second area name are the same, and the agricultural, forestry, marine products, culture and other services are selected as the first and second industries for the first and second areas, , The industrial industrial complex index for agriculture, forestry, marine products and culture and other services is determined to be 0.130024 and 0.003776, and the second industry of military industry and culture and other services The composite indices were determined to be 0.002662 and 0.033729, and the industrial composite index for agriculture, forestry and fisheries products and culture and other services, which are the first industries of agriculture, forestry and marine products, was determined as 0.130024 and 0.003776, , The industry industrial composite index for agriculture, forestry and fisheries products and culture and other services was 0.002662 and 0.033729, Value (that is, 0.0425477) can be determined by local fusion index of the first region (or second region).

The fusion index calculation unit 170 determines the FDI index between the first industry group and the second industry group, and determines the FDI index between the first industry group and the third industry group that overlaps with the second industry group The regional fusion index can be used to determine the average value of the industrial fusion composite index excluding the composite industrial composite index.

For example, when the agricultural, forestry, marine products, culture, and other services are simultaneously included in the first industry group and the second industry group, the fusion index computing unit 170 may calculate the fusion index, (Ie, 0.130024) for the first industrial group, agriculture, forestry and marine products, and the industrial composite index (ie, the index for the second or first industry group culture and other services of the first or second industrial group culture and other services) 0.033729) can be determined by the regional fusion index (ie, 0.003219).

The fusion index transmitting unit 180 may transmit the calculated local fusion index to the terminal 190 of the administrator.

The convergence index computing device 100 based on the above-described artificial intelligence-based web page analysis is a system that extracts corporate information from various industries in order to contribute to the development of new technologies and competitiveness of companies by performing convergence activities Then, it can analyze various fusion information by using a separate industry association table and provide the analyzed fusion information to the companies.

In addition, the convergence index computing apparatus 100 based on the above-described artificial intelligence-based web page analysis may calculate an ICCI between enterprises and transmit the calculated ICC index to the terminal 190 of the administrator .

When the second company name and the third company name are input from the terminal 190 of the manager, the fusion index calculation unit 170 performs a matching operation on the second company according to the second company name, And at least one industry group that is matched for at least one industry group that is in the third enterprise group and the third enterprise group that is the third enterprise name. At this time, the terminal data receiving unit 155 can receive the second company name and the third company name from the terminal 190 of the manager.

For example, when the industry group of the second company corresponding to the second company name is a mineral product and the industry group of the third company corresponding to the third company name is a food or beverage product, the fusion index operating unit 170 reads the second company name (0.001575) between at least one industry group matched for the second company according to the third company name and at least one industry group matching for the third company according to the third company name. At this time, the Fusion Indicator represents the Fusion Index (0.002877) for at least one industry group matching at least one industry group matching at least one industry group (0.002877) and at least one (0.000272) for at least one industry group that is matched for the second firm of the industry group.

The fusion index transmitter 180 may transmit the calculated FER index (0.001575) to the terminal 190 of the administrator.

2 is a flowchart showing a method of automatically extracting keyword information based on a web page analysis.

Referring to FIG. 2, in step S210, a plurality of companies may be provided with a company information storage unit for storing company addresses in which a company address and at least one industry group of a plurality of predetermined industry groups are matched.

In step S220, an industrial complex index storing unit that stores an industrial composite index between the predetermined plurality of industries can be maintained.

In step S230, when the first area name and the second area name are input from the terminal of the administrator, the management information is stored for each of the plurality of industries based on the enterprise address matched with the enterprise information stored in the enterprise information storage unit The number of the first industry and the number of the second industry can be counted in the first region according to the first region name and the second region according to the second region name.

In step S240, N first industry groups are selected in descending order of the number of companies located in the first region among the plurality of industry groups on the basis of the number of companies by the first industry, The M second industry groups can be selected in descending order of the number of enterprises located in the second region among the plurality of industry groups.

In step S250, an industrial composite index between the first industry groups selected for the first region and the second industry groups selected for the second region is determined based on the composite industrial composite index, The average value of the index can be determined by the regional fusion index.

The step S250 is to determine the IND complex index between the first industry group and the second industry group, and determine the IND complex index between the first industry group and the second industry group, The average value of industrial composite composite indexes can be determined by regional fusion index.

In step S260, the calculated regional fusion index may be transmitted to the terminal of the administrator.

The automatic keyword information extraction method based on the web page analysis according to an embodiment of the present invention as described above stores a plurality of preset group of industry word groups including a plurality of predetermined industry group words assigned different characteristic vectors Storing an industry word storage unit; when a connection address for a web page of a first company is inputted, accessing a web page of the first company based on the connection address, Extracting a plurality of first texts existing on a web page of the plurality of first texts, performing a morphological analysis on the plurality of first texts to extract a plurality of first words from the plurality of first texts, Determining an enterprise address of the first company based on a plurality of first words, Selecting at least one important word among the plurality of first words on the basis of a frequency of occurrence on a web page of a first company; if the at least one important word is selected, Identifying a feature vector for at least one important word and comparing a feature vector for the at least one important word with a feature vector for each of the plurality of industry word words contained in each of the plurality of industry word groups, And determining at least one industry group of the plurality of industry groups for the first enterprise based on the calculated degree of similarity, determining the determined enterprise address for the first enterprise and the determined enterprise group for the first enterprise After generating enterprise information for the first company by matching at least one industry group, And storing it in an information storage unit.

In the method for automatically extracting keyword information based on analysis of a web page according to an embodiment of the present invention as described above, the step of maintaining the enterprise information storage unit may further include matching of important words with respect to each of the plurality of companies Wherein the enterprise information storing step stores the enterprise information stored in the enterprise information storing step, wherein the enterprise information storing step stores enterprise information for the first company, And can be stored in an information storage unit.

In addition, if the second company name and the third company name are inputted from the terminal of the manager, the automatic keyword information extraction method based on the web page analysis according to an embodiment of the present invention as described above, Calculating an enterprise convergence index between at least one industry group matched to a second company according to the second company name and at least one industry group matching a third company according to the third company name; And transmitting the calculated FER to the terminal of the manager.

The operation method of the fusion index calculating apparatus according to the embodiment of the present invention has been described above with reference to FIG. Here, the operation method of the fusion index calculating apparatus according to an embodiment of the present invention may correspond to the operation of the operation of the fusion index calculating apparatus 100 described with reference to FIG. 1, so that a detailed description thereof will be omitted. .

The operation method of the fusion index computing apparatus according to an embodiment of the present invention may be implemented by a computer program stored in a storage medium for execution through a combination with a computer.

Also, the method of operating the fusion index computing device according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains.

Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

Claims (12)

An enterprise information storage unit for storing company information for each of a plurality of companies, the company information having at least one industry group matching a company address and a predetermined plurality of industry groups;
The Industrial Merger Composite Index (MCCI) between the above-mentioned predetermined plurality of industry groups - the Industrial Merger Composite Index is obtained by transposing a matrix of the input coefficient table of Korean among the industry association tables issued by the Bank of Korea, Which is a value calculated by normalizing the values of the industrial complex index;
When the first area name and the second area name are inputted from the terminal of the manager, the first area name and the second area name are stored for each of the plurality of industry groups based on the enterprise address matched with the enterprise information stored in the enterprise information storage unit An industry-specific number-of-businesses counting unit for counting the number of first-industry and second-industry companies located in a second region according to a first region and a second region name,
The first industry groups are selected in order of N - N, where N is an integer of 1 or more, in the order of the number of enterprises located in the first region among the plurality of industry groups based on the number of the first industry groups, An industry group selection unit for selecting, based on the number of companies, M - M, where M is an integer equal to or greater than 1, in order of the number of enterprises located in the second area among the plurality of industry groups;
A first industry group selected for the first region and a second industry group selected for the second region based on the composite industrial complex index among the plurality of industry groups stored in the industrial fusion complex index storage unit; A fusion index calculating unit for determining a composite index and determining an average value of the determined IND complex index as a regional fusion index between the first region and the second region; And
And for transmitting the determined regional fusion index to the terminal of the manager
Lt; / RTI &gt;
The fusion index calculation unit determines an industrial fusion composite index between the first industry group and the second industry group, and determines the composite index of the first industry group and the second industry group, excluding the composite index of industrial combination determined between the first industry group and the third industry group The average value of the industrial fusion composite index is determined as the regional fusion index between the first region and the second region,
Wherein the convergence index calculating unit calculates the convergent index based on the composite index of the industries among the plurality of industry groups stored in the composite index storing unit when the second company name and the third company name are inputted from the terminal of the manager, Further determining an industrial fusion composite index between at least one industry group matching the second company according to the company name and at least one industry group matching the third company according to the third company name, The average value of the industrial combined composite index is determined as the enterprise convergence index between the second company and the third company,
And the convergence index transmission unit transmits the determined enterprise fusion index to the terminal of the manager
Fusion index computing device. delete The method according to claim 1,
A plurality of industry group word groups including a plurality of predetermined industry group words assigned different characteristic vectors, a plurality of industry group words included in each of the plurality of industry group word groups, Wherein the similarity degree is more than a predetermined reference similarity degree;
When a connection address for a web page of a first company is input, accessing a web page of the first company based on the connection address, and accessing a web page of the first company from the web page of the first company, A text extracting unit for extracting first texts of the text data;
A word extraction unit for performing morphological analysis on the plurality of first texts to extract a plurality of first words from the plurality of first texts;
An enterprise address determination unit for determining an enterprise address of the first company based on the plurality of first words;
An important word selection unit for selecting at least one important word among the plurality of first words based on an appearance frequency on the web page of the first company of the plurality of first words;
If the at least one important word is selected, identifying the feature vector for the at least one important word by referring to the industry word storage, and comparing the feature vector for the at least one important word with the plurality of industry word groups An industry group decision to calculate the similarity between feature vectors for each of the plurality of industry group words included in each of the plurality of industry groups and to determine at least one industry group among the plurality of industry groups for the first company based on the calculated degree of similarity part; And
A company information input unit for generating the company information for the first company by matching the determined company address and the determined at least one industry group to the first company,
Further comprising: The method of claim 3,
Wherein the enterprise information storage unit stores enterprise information in which important words are more matched to each of the plurality of companies,
Wherein the enterprise information input unit generates enterprise information for the first company matching the at least one important word with respect to the first enterprise and stores the enterprise information in the enterprise information storage unit
Fusion index computing device. delete Maintaining an enterprise information storage unit for storing company information for each of a plurality of companies, the enterprise addresses matching at least one industry group among a plurality of industry groups and a predetermined address;
The Industrial Merger Composite Index (MCCI) between the above-mentioned predetermined plurality of industry groups - the Industrial Merger Composite Index is obtained by transposing a matrix of the input coefficient table of Korean among the industry association tables issued by the Bank of Korea, A value obtained by normalizing the value of the industrial complex index storage unit;
When the first area name and the second area name are inputted from the terminal of the manager, the first area name and the second area name are stored for each of the plurality of industry groups based on the enterprise address matched with the enterprise information stored in the enterprise information storage unit Counting the number of first industries and the number of second industries in the second region according to the first region and the second region name according to the first region and the second region;
The first industry groups are selected in order of N - N, where N is an integer of 1 or more, in the order of the number of enterprises located in the first region among the plurality of industry groups based on the number of the first industry groups, Selecting a second industry group in which M - M is an integer equal to or more than 1 - in order of the number of enterprises located in the second region among the plurality of industry groups based on the number of enterprises;
A first industry group selected for the first region and a second industry group selected for the second region based on the composite industrial complex index among the plurality of industry groups stored in the industrial fusion complex index storage unit; Determining a composite index and determining an average value of the determined composite index as a regional fusion index between the first region and the second region;
Transmitting the determined regional fusion index to the terminal of the manager;
When the second company name and the third company name are inputted from the terminal of the manager, the second company name and the third company name are inputted from the terminal of the manager, And further determining an industrial composite index between at least one industry group matched for the second enterprise and at least one industry group matched for the third enterprise according to the third enterprise name, Determining an average value as an enterprise convergence index between the second company and the third company; And
And transmitting the determined FER to the terminal of the manager
Lt; / RTI &gt;
Wherein the step of determining the regional fusion index comprises determining an index of industrial complexity between the first industry group and the second industry group and determining an industrial fusion composite index between the first industry group and the second industry group, The average value of the industrial combined composite index excluding the composite index is determined as the regional fusion index between the first region and the second region
A method of operating a fusion index computing device. delete The method according to claim 6,
A plurality of industry group word groups including a plurality of predetermined industry group words assigned different characteristic vectors, a plurality of industry group words included in each of the plurality of industry group word groups, Wherein the similarity degree is greater than or equal to a predetermined reference similarity degree;
When a connection address for a web page of a first company is input, accessing a web page of the first company based on the connection address, and accessing a web page of the first company from the web page of the first company, Extracting first texts of the text;
Performing morphological analysis on the plurality of first texts to extract a plurality of first words from the plurality of first texts;
Determining an enterprise address of the first company based on the plurality of first words;
Selecting at least one important word of the plurality of first words based on an appearance frequency on a web page of the first company of the plurality of first words;
If the at least one important word is selected, identifying the feature vector for the at least one important word by referring to the industry word storage, and comparing the feature vector for the at least one important word with the plurality of industry word groups Computing the similarity between the feature vectors for each of the plurality of industry words included in each of the plurality of industry groups and determining at least one industry group among the plurality of industry groups for the first company based on the calculated similarity; And
Generating company information for the first company by matching the determined company address and the determined at least one industry group with respect to the first company to the first company and storing the generated company information in the company information storage unit
Further comprising the step of: 9. The method of claim 8,
The step of maintaining the enterprise information storage unit may include maintaining the enterprise information storage unit storing the enterprise information in which the important words are more matched to the plurality of enterprises,
Wherein the step of storing in the enterprise information storage unit stores enterprise information for the first company matching the at least one important word with respect to the first enterprise and stores the information in the enterprise information storage unit
A method of operating a fusion index computing device. delete A computer-readable recording medium recording a program that causes a computer to perform the method of any one of claims 6, 8, and 9. A computer program stored in a storage medium for executing the method of any one of claims 6, 8, or 9 through a combination with a computer.

Images