KR102291799B1 - Apparatus and method for Self-introduction quantification - Google Patents

Abstract

It relates to a self-introduction quantification apparatus and method for identifying a keyword by analyzing the text of the self-introduction letter, and quantifying the score of the self-introduction letter by comparing the identified keyword with a reference keyword.
A self-introduction letter quantification apparatus for quantifying a cover letter according to an embodiment of the present invention, the cover letter quantification apparatus includes a processor having an arithmetic processing function, the processor extracts text from the cover letter, and the extracted text to identify the keyword, compare the identified keyword with the stored standard propensity keyword and standard business keyword, and calculate the score of the self-introduction letter based on the comparison result.

Description

Apparatus and method for Self-introduction quantification

The present invention relates to a self-introduction quantification apparatus and method, and in more detail, a self-introduction letter quantification apparatus for analyzing the text of an input self-introduction letter to identify a keyword, and quantifying the score of the self-introduction letter by comparing the identified keyword with a reference keyword and methods.

A cover letter is recognized as one of the documents that must be submitted for employment. Applicants can introduce necessary information about themselves, such as growth process, strengths and weaknesses, motives, and aspirations, to HR managers through the self-introduction letter.

However, it takes an excessively long time for the HR manager to read and evaluate thousands of self-introductions one by one, and there is a problem in that the concentration of work is also lowered. On the other hand, when a large number of HR managers divide and evaluate their self-introductions, it is difficult to evaluate the applicant's talent, competency, and ability in accordance with the organization on an objective basis. In addition, there is a problem in that, when the personnel manager reads and evaluates thousands of self-introductions one by one, it is impossible to review the overlap between self-introductions published on the Internet or between applicants.

The present invention provides an apparatus and method for quantifying a self-introduction letter to solve the problem described above, by analyzing the text of the self-introduction letter to identify a keyword, and quantifying the score of the self-introduction letter by comparing the identified keyword with a reference keyword aim to do

In addition to the technical problems of the present invention mentioned above, other features and advantages of the present invention will be described below or will be clearly understood by those skilled in the art from such description and description.

A self-introduction quantification apparatus for quantifying a self-introduction letter according to an embodiment of the present invention for achieving the above-described object includes a processor having an arithmetic processing function, the processor extracts text from the self-introduction letter, and extracts the extracted text It is possible to identify keywords by analyzing, compare the identified keywords with the stored standard propensity keywords and standard business keywords, and calculate the score of the self-introduction letter based on the comparison results.

In addition, the self-introduction letter quantification method performed by the self-introduction letter quantification apparatus according to an embodiment of the present invention for achieving the above-described object includes extracting text from the self-introduction letter, and analyzing the extracted text to identify keywords And, comparing the identified keyword with the stored reference tendency keyword and the reference work keyword, calculating a score of the self-introduction based on the comparison result, and outputting the ranking of the self-introduction letter determined according to the calculated score of the self-introduction letter It may include the step of providing through.

The self-introduction quantification apparatus and method according to an embodiment of the present invention may analyze the input text of the self-introduction letter to identify a keyword, and quantify the score of the self-introduction letter by comparing the identified keyword with a reference keyword.

In addition, even if the HR manager does not read the self-introduction letter one by one, it is possible to determine the individual inclinations and talents of the applicants.

In addition, it is possible to review the redundancy between self-introductions published on the Internet or between applicants.

In addition, other features and advantages of the present invention may be newly recognized through embodiments of the present invention.

1 is a diagram showing the configuration of a self-introduction quantification apparatus according to an embodiment of the present invention.
2 is a diagram illustrating text extraction of a self-introduction letter according to an embodiment of the present invention.
3 is a diagram illustrating identification of a keyword from text according to an embodiment of the present invention.
4 is a diagram illustrating comparison of an identified keyword with a reference propensity keyword according to an embodiment of the present invention.
5 is a diagram illustrating comparison of an identified keyword with a reference business keyword according to an embodiment of the present invention.
6 is a diagram illustrating a method for quantifying a personal statement according to an embodiment of the present invention.

In order to clearly explain the present invention, parts irrelevant to the description are omitted, and the same reference numerals are given to the same or similar elements throughout the specification.

Although not defined otherwise, all terms including technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention belongs. Commonly used terms defined in the dictionary are additionally interpreted as having a meaning consistent with the related technical literature and the presently disclosed content, and unless defined, they are not interpreted in an ideal or very formal meaning.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein.

1 is a diagram showing the configuration of a self-introduction quantification apparatus according to an embodiment of the present invention.

Referring to FIG. 1 , an apparatus 100 for quantifying a personal statement according to an embodiment of the present invention may include a processor 110 and an output device 120 .

The processor 110 extracts text from the self-introduction 300, analyzes the extracted text to identify a keyword, compares the identified keyword with the stored reference propensity keyword and reference business keyword, and based on the comparison result, the self-introduction letter (300) can be calculated.

The keyword identified from the self-introduction 300 may include a word representing a talent image, a word related to a job, and the like. For example, the word representing the talent image among the keywords identified from the self-introduction 300 may include 'challenge', 'best', and the like, and among the keywords identified from the self-introduction 300, job-related words are 'fair', It may include a 'plant' and the like.

In addition, the reference propensity keyword may be a word representing a talent image, the reference work keyword may be a word related to a job, and the reference propensity keyword and the reference work keyword may be preset and stored in the database 200 . The standard propensity keyword and the standard work keyword may be words set by each company to be suitable for each company's human resources and work. In addition, the processor 110 adds keywords used in the self-introduction 300 or more among the keywords identified in the self-introduction letter 300 of the passed applicant as a reference tendency keyword and a reference work keyword to store in the database 200 . can

The processor 110 may extract text from the self-introduction 300 through text mining, and may identify keywords by analyzing the extracted text. The processor 110 may determine a propensity keyword similar to the reference propensity keyword among the identified keywords. For example, when the reference propensity keyword is 'challenge', the processor 110 may determine the same keyword as 'challenge' among the identified keywords as the propensity keyword. Also, the processor 110 may determine a keyword having a similar meaning to 'challenge' among the identified keywords as the propensity keyword. For example, if there is 'adventure' among the identified keywords, the processor 110 may determine 'adventure' as the propensity keyword.

The processor 110 may calculate the score of the self-introduction 300 based on the number of keywords determined as propensity keywords. Here, scores may be set according to the number of propensity keywords, and scores according to the number of propensity keywords may be stored in the database 200 . For example, when the number of propensity keywords is less than 10, it is set to 10 points, when the number of propensity keywords is 10 or more and less than 20, it is set to 20 points, and when the number of propensity keywords is 30 or more, it is set to 30 points. may have been

The processor 110 may calculate the number of keywords determined as propensity keywords, and read the score for the calculated number from the database 200 . For example, when the number of keywords determined as propensity keywords is 15, the processor 110 reads 20 points, which is a score in the range where the number of propensity keywords is 10 or more and less than 20 from the database 200 . can

In addition, the processor 110 may calculate the score of the self-introduction 300 based on the similarity between the propensity keyword and the reference propensity keyword. The processor 110 may calculate the same disposition keyword as the reference disposition keyword among the disposition keywords as a high score, and may calculate a disposition keyword similar to the reference disposition keyword among the disposition keywords as a low score. For example, when the reference propensity keyword is 'challenge', the processor 110 may calculate the score of the 'challenge' keyword among the propensity keywords as 5 points and calculate the score of the 'adventure' keyword as 2 points.

The processor 110 may calculate a score for each of the overlapping keywords among the propensity keywords, and may calculate a score by reflecting the frequency of the overlapping keywords. In addition, the processor 110 may calculate a score using a keyword that overlaps among the propensity keywords as one keyword. For example, when there are ten 'challenge' keywords among the propensity keywords, the processor 110 may calculate a score for each of the ten 'challenge' keywords. In addition, when the 'challenge' keyword among the propensity keywords is 10, the processor 110 may calculate a score by reflecting the frequency of 10. Also, when there are ten 'challenge' keywords among the propensity keywords, the processor 110 may calculate a score for only one 'challenge' keyword.

The processor 110 may calculate the score of the self-introduction 300 using the number of propensity keywords, or may calculate the score of the self-introduction 300 based on the similarity between the propensity keyword and the reference propensity keyword, and the number of propensity keywords And the final score may be calculated by combining the scores of the self-introduction 300 determined based on the similarity between the propensity keyword and the reference propensity keyword.

In addition, the processor 110 may calculate the score of the self-introduction 300 based on the number of keywords determined as business keywords. Here, scores may be set according to the number of business keywords, and the scores according to the number of business keywords may be stored in the database 200 . For example, if the number of business keywords is less than 10, it is set to 10 points, if the number of business keywords is 10 or more but less than 20, it is set to 20 points, and if the number of business keywords is 30 or more, it is set to 30 points. may have been

The processor 110 may calculate the number of keywords determined as business keywords, and read a score for the calculated number from the database 200 . For example, when the number of keywords determined as the business keywords is 15, the processor 110 reads 20 points, which is a score in the range where the number of business keywords is 10 or more and less than 20 from the database 200. can

In addition, the processor 110 may calculate the score of the self-introduction 300 based on the similarity between the work keyword and the reference work keyword. The processor 110 may calculate the same business keyword as the reference business keyword among the business keywords as a high score, and may calculate a business keyword similar to the reference business keyword among the business keywords as a low score. For example, when the reference work keyword is 'plant', the processor 110 may calculate the score of the 'plant' keyword among the business keywords as 5 points, and calculate the score of the 'factory' keyword as 2 points.

The processor 110 may calculate a score for each overlapping keyword among the business keywords, and may calculate a score by reflecting the frequency of the overlapping keywords. In addition, the processor 110 may calculate a score using a keyword that overlaps among the business keywords as one keyword. For example, when there are 10 'plant' keywords among the business keywords, the processor 110 may calculate a score for each of the 10 'plant' keywords. In addition, when there are 10 'plant' keywords among the business keywords, the processor 110 may score a score by reflecting the frequency of 10. In addition, when there are 10 'plant' keywords among the business keywords, the processor 110 may calculate a score for only one 'plant' keyword.

The processor 110 may calculate the score of the self-introduction 300 by using the number of business keywords, or calculate the score of the self-introduction 300 based on the similarity between the business keyword and the reference business keyword, and the number of business keywords And the final score may be calculated by combining the score of the self-introduction 300 determined based on the similarity between the business keyword and the reference business keyword.

In addition, the processor 110 may calculate the score of the self-introduction 300 by comparing the propensity keyword and the standard propensity keyword, or calculate the score of the self-introduction 300 by comparing the work keyword and the standard work keyword. have. In addition, the processor 110 may calculate the score of the self-introduction letter 300 by combining the comparison result between the propensity keyword and the reference propensity keyword and the comparison result between the work keyword and the reference work keyword.

The processor 110 may provide the calculated score of the self-introduction 300 to the user through the output device 120 . In addition, the processor 110 may provide the ranking of the self-introduction 300 determined according to the score of the self-introduction sheet 300 to the personnel manager through the output device 120 .

In addition, the processor 110 determines the personal information such as school, residence, age, gender, etc. of the applicants written in the self-introduction letter 300, and provides the result of statistics for each personal information to the personnel manager through the output device 120. can provide For example, the processor 110 may identify the 'school' keyword from the text extracted from the self-introduction 300, and determine the school from which the applicants came based on the text written adjacent to the identified keyword. That is, when the applicant's school is Seoul National University, the processor 110 may identify the 'school' keyword and may identify 'Seoul National University' which is a text adjacent to the identified keyword. Accordingly, the processor 110 may determine that the applicant's school is Seoul National University. In addition, the processor 110 may identify keywords such as academic background and academic background from the text extracted from the self-introduction letter 110 , and identify keywords adjacent to the identified keyword to determine the applicant's school of origin.

The processor 110 groups the applicants' schools of origin by region, and may provide statistics on the grouped schools. For example, the processor 110 may group the applicants' school of origin into a Seoul area school, a Gyeonggi area school, a Gangwon area school, etc., and may provide statistics on the grouped school origins. Here, although it has been said that the applicants' schools are grouped by region, the grouping criteria may be grouped by other criteria than by region.

In addition, the processor 110 may identify a keyword such as a resident registration number from the text extracted from the self-introduction 300 and identify a keyword near the identified keyword to determine the age and gender of the applicant. For example, the processor 110 identifies the 'resident registration number' keyword from the text extracted from the self-introduction 300, and the text written adjacent to the identified keyword may be 860526-1xxxxxx. The processor 110 may determine from this text that the applicant is a male born in 1986.

The processor 110 groups the age or gender of the applicants, and may generate statistics on the grouped age or gender. For example, the processor 110 groups the gender of the applicants into female or male, and may generate statistics on the grouped gender. Also, the processor 110 may group the applicants' ages by year, and may generate statistics on the grouped ages.

The processor 110 may provide the HR manager through the output device 120 with statistical results for each personal information of the applicants described in the self-introduction letter 300 .

The processor 110 may compare the text extracted from the self-introduction letter 300 with the self-introduction letter known on the Internet. Here, the self-introductions known on the Internet may be stored as text in the database 200, and the processor 110 reads the self-introductions known on the Internet from the database 200 and input the self-introduction letter 300 ) can be compared with Accordingly, the processor 110 may determine whether the self-introduction letter 300 is plagiarized by analyzing the similarity between the self-introduction statements known on the Internet and the input self-introduction letter 300 . For example, the processor 110 compares the self-introduction statements known on the Internet with the input self-introduction letter 300, and when the number of identical keywords is equal to or greater than a certain value, the input self-introduction letter 300 is suspected of plagiarism. , and may be stored in the database 200 . In addition, when the processor 110 outputs the self-introduction 300 to the output device 120, the self-introduction suspected of plagiarism may be separately displayed so that the personnel manager can check the self-introduction suspected of plagiarism.

The processor 110 may reflect the similarity between the self-introductions known on the Internet and the input self-introduction 300 in determining the score of the self-introduction letter 300 .

The output device 120 may output the score of the self-introduction 300 determined by the processor 110 under the control of the processor 110 and the ranking of the self-introduction 300 determined according to the score of the self-introduction 300 . . The output device 120 outputs the score and rank of the self-introduction letter 300, so that the personnel manager can determine the pass or fail of the applicant by reflecting the score and rank of the self-introduction letter 300.

In addition, the output device 120 may output the statistical results for each personal information of the applicants described in the self-introduction 300 under the control of the processor 110 .

2 is a diagram illustrating text extraction of a self-introduction letter according to an embodiment of the present invention.

Referring to FIG. 2 , the processor 110 may extract text from the self-introduction 300 through text mining. For example, from the self-introduction (300), the processor 110 says 'personality and strengths and weaknesses', 'adaptation and work performance are quick.' 'I think these skills will be highly utilized for the development of the head office after joining the company.', 'In addition, he has excellent leadership and good human relations.' I am confident that I will lead the way to the next level, and I think it will have a positive impact on my work.', 'Motivation for application and aspirations after joining the company', 'I actively participate and share as a team member the ability to accomplish goals with others. While studying the core technology necessary for product development and the knowledge of raw materials, manufacturing process, quality control, and cost structure required for production, perform tasks such as prior research, product design, design, specifications, patents, and R&D planning. You can extract texts such as 'I will do my job.'

3 is a diagram illustrating identification of a keyword from text according to an embodiment of the present invention.

Referring to FIG. 3 , the processor 110 may identify the keyword 310 from the extracted text. Here, the keyword 310 may include a word representing an image of a person or a word related to a job. For example, the processor 110 may identify 'adaptability', 'task performance ability', 'leadership', 'personal relationship', 'positive', and 'member' as words representing the talent image from the text.

In addition, the processor 110 is a word related to the job from the text 'development', 'technology', 'production', 'manufacturing process', 'quality control', 'design', 'design', 'standard', 'patent' ', 'R&D' can be identified.

4 is a diagram illustrating comparison of an identified keyword with a reference propensity keyword according to an embodiment of the present invention.

Referring to FIG. 4 , the processor 110 may determine propensity keywords 312a and 312b that are the same as or similar to the reference propensity keyword 210 among the keywords 310 identified from the text. For example, the standard tendency keyword 210 is 'adaptation', 'challenge', 'leader', 'human relationship', 'positive', 'colleague', 'responsibility', 'creativity', 'ability', 'differentiation', It can be 'effort' or 'sincere'. Here, the reference propensity keyword 210 may be stored in the database 200 , and the processor 110 reads the reference propensity keyword 210 from the database 200 to include the propensity keywords 312a and 312b and the reference propensity keyword. (210) can be compared.

The processor 110 may determine the same keyword 312a as the reference tendency keyword 210 among the identified keywords 310 as the tendency keyword. For example, among the identified keywords 310 , the keyword 312a identical to the reference tendency keyword 210 may be 'adaptability', 'leadership', 'personal relationship', and 'positive'. The processor 110 may determine the same 'adaptability', 'leadership', 'interpersonal relationship', and 'positive' as the reference tendency keyword 210 as the tendency keyword 312a.

Also, the processor 110 may determine a keyword 312b having a similar meaning to the reference tendency keyword 210 among the identified keywords 310 as the tendency keyword. For example, a keyword 312b having a similar meaning to the reference tendency keyword 210 among the identified keywords 310 may be 'work performance' and 'member'. The processor 110 includes 'work performance ability', which can be interpreted as similar to 'capability' of the reference tendency keyword 210 , and 'member' that can be interpreted as a meaning similar to 'colleague' of the reference tendency keyword 210 . may be determined as the propensity keyword 312b.

The processor 110 may calculate the score of the self-introduction 300 based on the number of keywords determined as the propensity keywords 312a and 312b and the degree of similarity between the propensity keywords 312a and 312b and the reference propensity keyword 210 .

5 is a diagram illustrating comparison of an identified keyword with a reference business keyword according to an embodiment of the present invention.

Referring to FIG. 5 , the processor 110 may determine business keywords 314a and 314b that are the same as or similar to the reference business keyword 220 among the keywords 310 identified from the text. For example, the reference work keyword 220 may be 'process', 'plant', 'production', 'design', 'business', 'industrial equipment', 'power generation technology', and 'heavy industry'. Here, the standard work keyword 220 may be stored in the database 200 , and the processor 110 reads the standard work keyword 220 from the database 200 to include the work keywords 314a and 314b and the standard work keyword. (220) can be compared.

The processor 110 may determine the same keyword 314a as the reference business keyword 220 among the identified keywords 310 as the business keyword. For example, among the identified keywords 310 , the keywords 314a identical to those of the reference business keyword 220 may be 'production' and 'design'. The processor 110 may determine the same 'production' and 'design' as the reference business keyword 220 as the business keyword 314a.

In addition, the processor 110 may determine a keyword 314b having a similar meaning to the reference business keyword 220 among the identified keywords 310 as the business keyword. For example, the keyword 314b having a similar meaning to the reference business keyword 220 among the identified keywords 310 may be 'development', 'technology', 'manufacturing process', and 'design'. The processor 110 may be interpreted as 'development', 'design', which can be interpreted in a meaning similar to 'design' of the reference business keyword 220, and 'which can be interpreted as a meaning similar to 'process' of the reference business keyword 220 . Manufacturing process' and 'technology', which can be interpreted in a similar meaning to 'development technology' of the standard business keyword, may be determined as the business keyword 314b.

The processor 110 may calculate the score of the self-introduction 300 based on the number of keywords determined as the business keywords 314a and 314b and the similarity between the business keywords 314a and 314b and the reference business keyword 220 .

6 is a diagram illustrating a method for quantifying a personal statement according to an embodiment of the present invention.

Referring to FIG. 6 , the processor 110 may extract text from the self-introduction 300 ( S100 ). The processor 110 may extract text from the contract 300 through text mining.

The processor 110 may identify the keyword by analyzing the extracted text (S200). The keyword identified from the text may include a word representing a talent image, a word related to a job, and the like. For example, the word representing the talent image among the keywords identified from the self-introduction 300 may include 'challenge', 'best', and the like, and among the keywords identified from the self-introduction 300, job-related words are 'fair', It may include a 'plant' and the like.

The identified keyword may be compared with the reference propensity keyword and the reference business keyword (S300). The reference tendency keyword and the reference work keyword may be preset and stored in the database 200 . The standard propensity keyword and the standard work keyword may be words set by each company to be suitable for each company's human resources and work.

The processor 110 may determine a propensity keyword identical to or similar to the reference propensity keyword among the identified keywords, and may compare the determined propensity keyword with the reference propensity keyword. In addition, the processor 110 may determine a work keyword that is the same as or similar to the reference work keyword among the identified keywords, and may compare the determined work keyword with the reference work keyword.

The score of the self-introduction letter can be calculated based on the result of comparing the identified keyword with the reference propensity keyword and the reference work keyword (S400). The processor 110 may calculate the score of the self-introduction 300 based on the number of keywords determined as the propensity keyword and the business keyword. In addition, the processor 110 may calculate the score of the self-introduction 300 based on the degree of similarity between the propensity keyword and the reference propensity keyword and the similarity between the work keyword and the reference work keyword.

The processor 110 may control the output device 120 to provide the score of the self-introduction 300 determined by the processor 110 and ranking information according to the score of the self-introduction letter (S500). The output device 120 may output the score of the self-introduction 300 determined by the processor 110 under the control of the processor 110 and the ranking of the self-introduction 300 determined according to the score of the self-introduction 300 . . The output device 120 outputs the score and rank of the self-introduction letter 300, so that the personnel manager can determine the pass or fail of the applicant by reflecting the score and rank of the self-introduction letter 300.

As described above, the self-introduction quantification apparatus and method according to an embodiment of the present invention analyzes the text of the input self-introduction letter to identify keywords, and compares the identified keywords with reference keywords to quantify the self-introduction letter quantification device and methods may be realized.

Those skilled in the art to which the present invention pertains should understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential characteristics thereof, so the embodiments described above are illustrative in all respects and not restrictive. only do The scope of the present invention is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. .

110: processor
120: output device
200: database
300: self-introduction

Claims (17)

In the self-introduction quantification device for quantifying the self-introduction,
output device; and
A processor having an arithmetic processing function, the processor comprising:
Calculate the score for each of the plurality of self-introductions based on the pre-stored reference propensity keyword and the reference work keyword,
Determine a ranking for each of the plurality of self-introductions according to the calculated score,
Control the output device to output score and ranking information for the plurality of self-introductions,
The score for each of the plurality of self-introductions, identifies a keyword from each self-introduction, compares the identified keyword with the reference propensity keyword and reference work keyword, and is calculated based on the comparison result, self-introduction quantification device .
According to claim 1,
The reference propensity keyword is a word representing a talent image, and the reference work keyword is a word related to a job, a self-introduction quantification device.
According to claim 1,
The processor determines a propensity keyword similar to the reference propensity keyword among the identified keywords, and scores each of the plurality of self-introduction statements based on the number of the determined propensity keywords and the degree of similarity between the propensity keyword and the reference propensity keyword A self-introduction quantification device that calculates.
4. The method of claim 3,
The score, the self-introduction quantification apparatus, wherein the number of propensity keywords is within a certain range, and the higher the degree of similarity between the propensity keyword and the reference propensity keyword is, the higher the score.
According to claim 1,
The processor determines a business keyword similar to the reference business keyword among the keywords identified from each of the plurality of self-introduction statements, and based on the number of the determined business keywords, and the degree of similarity between the business keyword and the reference business keyword A self-introduction quantification device that calculates a score for each of a plurality of self-introduction statements.
6. The method of claim 5,
The score, the self-introduction quantification apparatus, wherein the number of work keywords is within a certain range, and the higher the degree of similarity between the work keyword and the reference work keyword, the higher.
According to claim 1,
The processor, based on the first self-introduction, to update the reference tendency keyword and the reference work keyword,
Based on the second self-introduction, confirming whether plagiarism is suspected for each of the plurality of self-introductions,
The first self-introduction letter is the self-introduction letter of the successful applicant,
The second self-introduction is a self-introduction known on the Internet, a self-introduction quantification device.
The method of claim 1, wherein the processor obtains the reference propensity keyword and the reference business keyword pre-stored in a database,
The reference tendency keyword and the reference work keyword are updated by the keywords included in the first self-introduction letter,
The first self-introduction is a self-introduction of an accepted applicant, self-introduction quantification device.
9. The method of claim 8,
The processor, when outputting at least one self-introduction among the plurality of self-introduction statements to the output device, separately displays information indicating whether or not plagiarism is suspected for the at least one self-introduction letter;
Whether the plagiarism is suspected is determined according to a comparison result of the at least one self-introduction and at least one second self-introduction stored in a database,
The second self-introduction is a self-introduction known on the Internet, a self-introduction quantification device.

In the self-introduction quantification method performed by the self-introduction quantification device,
calculating a score for each of the plurality of self-introductions based on the pre-stored reference propensity keyword and reference work keyword; and
Comprising the step of outputting the score for the plurality of self-introductions and ranking information according to the score,
The step of calculating the score is
identifying keywords from each cover letter; and
Comprising the step of comparing the identified keyword with the reference propensity keyword and the reference work keyword, and calculating a score for each of the plurality of self-introductions based on the comparison result, self-introduction quantification method.
11. The method of claim 10,
The reference propensity keyword is a word representing a talent image, and the reference work keyword is a word related to a job, a self-introduction quantification method.
11. The method of claim 10,
The step of calculating the score is
Determining a propensity keyword similar to the reference propensity keyword among the identified keywords, and calculating a score for each of the plurality of self-introduction statements based on the number of the determined propensity keywords, and the degree of similarity between the propensity keyword and the reference propensity keyword , CV quantification method.
13. The method of claim 12,
The score is
The self-introduction quantification method, wherein the number of the propensity keywords is within a certain range, and the higher the degree of similarity between the propensity keyword and the reference propensity keyword is, the higher the determination.
11. The method of claim 10,
The step of calculating the score is
Determining a work keyword similar to the reference work keyword among the identified keywords, and calculating the score for each of the plurality of self-introduction statements based on the number of the determined work keywords, and the degree of similarity between the work keyword and the standard work keyword , CV quantification method.
15. The method of claim 14,
The score is
The self-introduction quantification method, wherein the number of the work keywords is within a certain range, and the higher the degree of similarity between the work keywords and the reference work keywords is, the higher.
11. The method of claim 10,
updating the reference propensity keyword and the reference work keyword based on the first self-introduction letter; and
Based on the second self-introduction, further comprising the step of confirming whether plagiarism is suspected for each of the plurality of self-introductions,
The first self-introduction letter is the self-introduction letter of the successful applicant,
The second self-introduction is a self-introduction known on the Internet, self-introduction quantification method.
17. The method of claim 16,
When at least one of the plurality of self-introductions is output to an output device, information indicating whether or not plagiarism is suspected for the at least one self-introduction is displayed separately,
Whether the suspicion of plagiarism is, the self-introduction quantification method is determined according to a comparison result of the at least one self-introduction letter and the second self-introduction letter.

Images