KR20220106297A - verification system for achievements of faculty - Google Patents

Abstract

The present invention relates to a teacher achievement verification system, and more particularly, by automatically performing the entire process of verifying achievement information input by a teacher, it is possible to significantly reduce manpower, time and cost, and to It relates to a teacher performance verification system that can be verified more accurately by judging similarity rather than identity.
The present invention for achieving the above object is an information input step in which teachers input achievement information, an information extraction step of extracting achievement-related information from the web through the received achievement information, and achievement-related information extracted in the information extraction step It is characterized in that it consists of a data verification step that compares and verifies achievement information.

Description

Teacher achievement verification system {verification system for achievements of faculty}

The present invention relates to a teacher achievement verification system, and more particularly, by automatically performing the entire process of verifying achievement information input by a teacher, it is possible to significantly reduce manpower, time and cost, and to It relates to a teacher achievement verification system that can be verified more accurately by judging similarity rather than identity.

In order to verify the achievements of teachers working at universities, etc., it is necessary to search for and compare the contents of the thesis, patent, book, or translation written by each professor. In general, there are more than 3,000 papers to be collated and verified, and about 3,000 patents. More than 400, and in the case of translations or books, about 200 or more.

In order to verify such a large amount of theses, patents, books, or translations, a large number of workers must manually visit each website to verify it, and it is not completed at once, but cross-verifies each other. Because of this, a considerable cost is incurred.

Accordingly, when the above-described verification operation is performed automatically using a specific system instead of manually, there is an effect of reducing manpower, time, and cost.

As an example of a technology for automatically performing such a verification operation, there is a technology described in Korean Patent Application Laid-Open No. 10-2020-0082218 as shown in FIGS. 1 and 2, and its technical feature is to increase the reliability of untrusted data. extracting, by a server for verification, a keyword from a post that an individual has launched on SNS; crawling news articles including the keyword on the web; and evaluating the reliability of a post published by the individual on SNS based on the number of crawled news articles.

However, the technology described in Korean Patent Application Laid-Open No. 10-2020-0082218 is a technology that automatically verifies reliability by crawling news articles published on the web for the contents of posts uploaded to SNS, etc. Although there is an advantage, there is a problem in that it is impossible to accurately determine when a keyword is modified for various reasons because only a case in which the keyword exactly matches is considered during verification.

Korean Patent Publication No. 10-2020-0082218 (published on July 8, 2020) Korean Patent Registration No. 10-1153138 (Registered on May 29, 2012)

The present invention has been devised to solve the above problems, and an object of the present invention is to extract information through an extraction module having a crawler function from a website having the corresponding information on the basis of the achievement information described by teachers to obtain achievement information It is to provide a teacher performance verification system that can automatically perform the entire process and significantly save manpower, time, and cost by automatically comparing it with

And, another object of the present invention is when comparing the information extracted from each website with the achievement information through the extraction module, if the achievement information is an alphabet, it is converted to all lowercase letters, and in the case of Hangul, it undergoes a preprocessing process of decomposing it into consonants and vowels. It is to provide a teacher performance verification system that can increase the accuracy of verification results by making verification according to similarity by adding additional points to continuity based on sequence matching at the time of verification.

The present invention for solving these problems;

The input achievement information DB storage step of storing the achievement information input by the teachers in the teacher DB, the information extraction step of extracting achievement-related information from the web through the input achievement information, the achievement-related information extracted in the information extraction step and the It is characterized in that it consists of a data verification step of comparing and verifying input achievement information.

Here, the input achievement information is characterized in that the information about their thesis, patent, book, or translation entered by each teacher.

In addition, the information extraction step includes an access step of accessing a website from which information on a thesis, patent, book or translation can be obtained through an extraction module provided in the server, and information through a crawling operation on the accessed website It is characterized in that it consists of a data extraction step of extracting the data, and a data trimming step for extracting only achievement-related information from the information extracted in the data extraction step.

In this case, the data trimming step is characterized by removing irrelevant characters including special characters other than achievement-related information from the extracted information with reference to the format of each website.

On the other hand, the data verification step includes a pre-processing step of changing the input achievement information stored in the faculty DB and the achievement-related information extracted through the information extraction step into a set format and processing, and the pre-processed achievement-related information and input achievement information It is characterized in that it consists of a comparison step of comparing and verifying.

Here, the pre-processing step is characterized in that the input achievement information and achievement-related information is converted to a lowercase letter in the case of an alphabet, and separated into consonants and vowels in the case of Hangul.

In this case, the comparison step is characterized in that by adding a weight to the continuity in the editing distance (Levenstein Distance) algorithm among the string comparison (sequence matching) method, the achievement information and the achievement-related information are compared.

In addition, the comparison step is characterized in that the similarity is determined by the weight editing distance value (D(i,j)) derived through the following process.

[process]

1. If A[i] and B[j] of the string to be compared match,

D(i,j) = D(i-1,j-1),

If b == True then w = w + 1,

If b != True then b = true.

2. If A[i] and B[j] of the string to be compared do not match,

D(i,j) = min( D(i-1,j)+1/w, D(i,j-1)+1/w, D(i-1,j-1)+1/w ) ego,

b = False.

{ D(i,j) = weight edit distance value, initial value D(0,0)=0,

A[i] = i-th character of string A,

B[j] = jth character of string B,

w = continuity weights (w is initialized to 0),

b = Boolean to determine continuity (initial value of b is False),

i,j = 0 to n }

According to the present invention of the above configuration, based on the achievement information described by the teachers, information is extracted from the website having the corresponding information through an extraction module having a crawler function and automatically compared with the achievement information, so that the entire process is This can be done automatically, resulting in significant manpower, time and cost savings.

And, in the present invention, when comparing the information extracted from each website with the achievement information through the extraction module, if the achievement information is an alphabet, it is converted to all lowercase letters, and in the case of Hangul, it undergoes a pre-processing process of decomposing it into consonants and vowels, At the time of verification, it is possible to increase the accuracy of the verification result by using the sequence matching method as a basis, but by adding an additional point to the continuity to perform verification according to the similarity.

1 is a schematic diagram of a verification method through a conventional crawling.
2 is an exemplary view of a web page for extracting data including keywords in a verification method through a conventional crawling.
3 is a conceptual diagram of a teacher achievement verification system according to the present invention.
4 is a block diagram of a teacher achievement verification system according to the present invention.
5 is a flowchart of a teacher achievement verification system according to the present invention.
6 is an exemplary diagram of a general Levenstein Distance, which is an example of a sequence matching technique.
7 is an exemplary view of a screen showing a result upon completion of verification in the teacher achievement verification system according to the present invention.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. The same reference numerals are used for the same components in the drawings, and repeated descriptions of the same components are omitted. And, it should be understood that the present invention may be implemented in many different forms and is not limited to the described embodiments.

Figure 3 is a conceptual diagram of a teacher achievement verification system according to the present invention, Figure 4 is a block diagram of the teacher achievement verification system according to the present invention, Figure 5 is a flow chart of the teacher achievement verification system according to the present invention, Figure 6 is a sequence It is an exemplary view of a general Levenstein Distance as an example of a matching technique, and FIG. 7 is an exemplary view of a screen showing a result when verification is completed in the teacher achievement verification system according to the present invention.

The present invention relates to a teacher achievement verification system, and as shown in FIGS. 3 to 5 , the configuration includes the steps of storing achievement information input by teachers in the teacher DB 110 provided in the server 100 (S100) and It consists of an information extraction step (S200) of extracting achievement-related information from the web through the received achievement information and a data verification step (S300) of comparing and verifying the achievement-related information extracted in the information extraction step (S200) with the input achievement information .

Here, the teachers connect to the server 100 provided with the communication module 120 through the terminals 200 such as smartphones, desktop cup computers, and tablets each possessed as shown in FIGS. 3 and 4 . Thus, the achievement information of each teacher is entered.

At this time, the server 100 is provided with a teacher DB 110 to store achievement information input by each teacher by accessing the server 100 , and such teacher input achievement information is typically a thesis, patent, book or Information about the translation is included.

In addition, the information extraction step (S200) includes the access step (S210) of accessing the website 300 that can obtain information on the thesis, patent, book or translation, and the crawling operation on the accessed website 300. It consists of a data extraction step (S220) of extracting information through the data extraction step (S220) and a data trimming step (S230) for extracting only achievement-related information from the information extracted in the data extraction step (S220).

Here, the server 100 is provided with an extraction module 130, and the extraction module 130 performs the function of a crawler to extract information from the website 300 through a crawling operation, the extraction module ( 130) is provided with a web DB 134 in which information of a web site 300 that can obtain information on a thesis, patent, book, or translation is stored.

So, in the access step (S210), the extraction module 130 accesses the website 300 through the information of the website stored in the web DB 134, and in the data extraction step (S220), as described above Similarly, information related to the input achievement information is extracted through a crawling operation and stored in the temporary storage unit 132 provided in the extraction module 130 .

On the other hand, in the data trimming step (S230), the work is performed by deleting information other than the achievement-related information of the teachers. Deletes missing characters.

That is, there is a difference in the format for displaying each field in each website 300. For example, even when displaying a title in a thesis, a colon (:) or semicolon (;) may be written before and after the title, You can use quotation marks (") or other special characters, and you can also use multiple spaces between each special character and the title.

Here, in the data trimming step (S230), the web DB 134 includes the format information of each web site 300, and the information extracted by the extraction module 130 with reference to this includes special characters other than achievement-related information. Removes extraneous characters including .

In this way, the achievement-related information processed by the extraction module 130 is stored in the temporary storage unit 132 provided in the extraction module 130 and compared with the achievement information input in the data verification step (S300) to be described later, more accurately can be compared.

That is, in the present invention, when comparing the achievement-related information extracted from the website 300 with the achievement information input by the teacher, a sequence matching method is used. If the comparison target string includes special characters constituting the format of the web site 300, it is difficult to make accurate comparisons because it is compared to determine whether they match.

And, the data verification step (S300) is a pre-processing step (S310) of processing the input achievement information stored in the faculty DB 110 and the achievement-related information extracted through the information extraction step (S200) to a set format and processing; A comparison step (S320) of comparing and verifying the pre-processed achievement-related information with the input achievement information is performed.

Here, in the pre-processing step (S310), when the input achievement information stored in the teacher DB 110 and the achievement-related information extracted through the extraction module 130 are alphabetic, they are all converted to lowercase and unified, and in the case of Korean All letters are separated into consonants and vowels and stored in a part allocated separately to the teacher DB 110 .

In other words, taking the case of Hangeul as an example, when comparing Hong Gil -dong and Hong Gal -dong, one middle letter out of the three letters is different, so 1/3 is different, so it looks quite different. When comparing ㅇㄱㅣㄴㅗㅇ and ㅎㅗㅇㄱㄹㅇㅇ, only one phoneme out of the 9 phonemes is different, so 1/9 is different, so the similarity seems to be high.

In addition, since initials are sometimes expressed in the case of alphabets, the converted initials may be stored in a portion additionally allocated to the faculty DB 110 .

Meanwhile, in the comparison step (S330), weight is added to continuity in the Levenstein Distance algorithm among the sequence matching methods to compare and verify the input achievement information and achievement-related information.

Here, the general editing distance (Levenstein Distance) algorithm compares two strings and determines how many times one of three operations of insertion, deletion, and replacement should be performed to make the same string. will be.

Looking at the programmatic representation of this process:

1. If A[i] and B[j] of the string to be compared match,

D(i,j) = D(i-1,j-1),

2. If A[i] and B[j] of the string to be compared do not match,

D(i,j) = min( D(i-1,j), D(i,j-1), D(i-1,j-1) ).

At this time, D(i,j) = edit distance value (how many times the above three operations are performed), the initial value is D(0,0)=0, and A[i] in the two strings A, B = i-th character of character string A, B[j] = means j-th character of character string B

Therefore, in order to compare each character constituting the character string, the editing distance value (D(i,j)) can be derived by performing the above process of solving the editing distance (Levenstein Distance) algorithm, and the editing distance value is as described above. It indicates how many times one of the above three operations must be performed in order to compare and change two strings to be the same, and the larger the edit distance value, the lower the similarity between the two strings.

An example of such an editing distance (Levenstein Distance) algorithm can be clearly seen by moving a table comparing the character string ABC and the character string QWC as shown in FIG. 6 .

However, in a general editing distance (Levenstein Distance) algorithm, only a few different characters can be checked, and although the number of different characters is large, a character string with higher similarity cannot be identified.

For example, com pa r is o n and co n pa l is e n are completely unrelated strings, but there is a difference in the underlined 3 parts, so the edit distance becomes 3, and compar ison and compar e do not have a significant similarity. Since there is a difference in the 4 underlined parts of the dumpling strings, the editing distance becomes 4, so it is judged that the similarity is inferior.

Therefore, in the present invention, although the Levenstein Distance algorithm is used to solve this problem, the similarity is determined by adding a weight to the continuity as described above in consideration of the fact that the more consecutive matching parts, the higher the similarity. will do

And, looking at the programmatic representation of the weighting process of the Levenstein Distance algorithm:

1. If A[i] and B[j] of the string to be compared match,

D(i,j) = D(i-1,j-1),

If b == True then w = w + 1,

If b != True then b = True.

2. If A[i] and B[j] of the string to be compared do not match,

D(i,j) = min( D(i-1,j)+1/w, D(i,j-1)+1/w, D(i-1,j-1)+1/w ) ego,

b = False.

{ D(i,j) = weight edit distance value, initial value D(0,0)=0,

A[i] = i-th character of string A,

B[j] = jth character of string B,

w = continuity weights (w is initialized to 0),

b = Boolean to determine continuity (initial value of b is False),

i,j = 0 to n }

Here, when comparing two strings with the weighted Levenstein Distance algorithm of the present invention,

1. com pa r is o n VS co n pa l is e n (requires 3 operations)

The edit distance value = 1 + 1/2 + 1/3 = 11/6, which is about 1.83.

At this time, looking at the process of deriving the value: If there are consecutively matching characters, the value of w increases (when the b value at the time of comparison is True), and the initial value of the edit distance value is 0.

When comparing the character 'c', since the two characters are the same, D(1,1)=D(0,0)=0. changed to True.

When comparing the character 'o', since the two characters are the same, D(2,2)=D(1,1)=0 , since the value of b is True, the value of w is incremented by 1 to become 1, and the value of b is does not change

When comparing the character 'm', the two characters do not match, so D(3,3) = D(2,2)+1/w = 0+1/1, the value of b is changed to False, and the value of w does not change and is still 1.

When comparing the character 'p', since the two characters are the same, D(4,4)=D(3,3)=1. .

When comparing the character 'a', since the two characters are the same, D(5,5)=D(4,4)=1 , and since the existing b value is True, the w value is increased by 1 to become 2, and b is does not change

When comparing the character 'r', the two characters do not match, so D(6,6) = D(5,5)+1/w = 1+1/2, the value of b is changed to False, and the value of w does not change and is still 2.

When comparing the character 'i', since the two characters are the same, D(7,7) = D(6,6) = 1+1/2. changed to true.

When comparing the character 's', since the two characters are the same, D(8,8)=D(7,7)=1/2/2, and since the existing b value is True, the w value increases by 1 to become 3. , and b does not change.

When comparing the character 'o', the two characters do not match, so D(9,9) = D(8,8)+1/w = 1+1/2+1/3, and the value of b is changed to False , and the value of w does not change and is still 3.

When comparing the character 'n', since the two characters are the same, D(10,10) = D(9,9) = 1+1/2+1/3. Since the existing b value is False, the w value does not change. 3 and b is changed to true.

Therefore, the D(10,10) value, which is the final weighted edit distance value, becomes 1+1/2+1/3.

2. compar ison VS compar e (requires 4 operations)

The edit distance value = 1/5 + 1/5 + 1/5 + 1/5 = 4/5, resulting in 0.8.

Therefore, when two strings are compared with the weighted Levenstein Distance algorithm of the present invention, in the second case, the edit distance value is lower as 0.8, indicating high similarity, which is consistent with the actual similarity. It can be seen that the resulting

So, in the present invention, by comparing achievement information and achievement-related information using a weighted editing distance (Levenstein Distance) algorithm in the comparison step (S330) constituting the data verification step (S300), when inputting by a teacher or each Even if there is a typo when writing on the website, the accuracy of verification can be increased through similarity.

In addition, after the data verification step (S300), a verification result checking step (S400) for checking the verification result may be further performed.

Here, in the data verification step (S300), information on the parts that do not match during verification is stored in the result storage unit 142 separately provided in the verification module 140, and in the verification result verification step (S400), the As shown in FIG. 7 with reference to the information stored in the result storage unit 142, the result is output together with a brief comment.

At this time, in the verification result confirmation step (S400), if there is an error in the input data, the result information is notified to the teacher through the information stored in the corresponding teacher DB 110 so that the error can be corrected.

Although preferred embodiments of the present invention have been described above, the scope of the present invention is not limited thereto, and the scope of the present invention extends to those substantially equivalent to the embodiments of the present invention. Various modifications are possible by those of ordinary skill in the art to which the invention pertains without departing from the scope of the invention.

The present invention relates to a teacher achievement verification system, and more particularly, by automatically performing the entire process of verifying achievement information input by a teacher, it is possible to significantly reduce manpower, time and cost, and to It relates to a teacher performance verification system that can be verified more accurately by judging similarity rather than identity.

100: Server 110: Faculty DB
120,210: communication module 130: extraction module
140: verification module 200: terminal
220: display unit 300: website
S100: information input step
S200: information extraction step
S300: data verification step
S400: Verification result confirmation step

Claims (8)

An input achievement information DB storage step of storing the achievement information entered by the teachers in the teacher DB;
An information extraction step of extracting achievement-related information from the web through the input achievement information;
Teacher achievement verification system, characterized in that consisting of a data verification step of verifying by comparing the achievement-related information extracted in the information extraction step and the input achievement information.
According to claim 1,
The input achievement information is a teacher achievement verification system, characterized in that the information on their thesis, patent, book, or translation entered by each teacher.
3. The method of claim 2,
The information extraction step includes an access step of accessing a website that can obtain information on a thesis, patent, book or translation through an extraction module provided in the server;
A data extraction step of extracting information from the accessed website through crawling;
Teacher achievement verification system, characterized in that consisting of a data trimming step for extracting only achievement-related information from the information extracted in the data extraction step.
4. The method of claim 3,
The data trimming step is a teacher achievement verification system, characterized in that by removing irrelevant characters including special characters other than achievement-related information from the extracted information with reference to the format of each website.
4. The method of claim 3,
The data verification step includes a pre-processing step of processing the input achievement information stored in the teacher DB and the achievement-related information extracted through the information extraction step to a set format;
Teacher achievement verification system, characterized in that it comprises a comparison step of comparing and verifying the pre-processed achievement-related information and the input achievement information.
6. The method of claim 5,
In the pre-processing step, if the input achievement information and achievement-related information is an alphabet, it is converted to a lowercase letter, and in the case of Hangul, the teacher achievement verification system, characterized in that it is separated into consonants and vowels.
6. The method of claim 5,
The comparison step is a teacher achievement verification system, characterized in that by adding a weight to the continuity in the editing distance (Levenstein Distance) algorithm among the string comparison (sequence matching) method to compare the achievement information with the achievement-related information.
8. The method of claim 7,
In the comparison step, the teacher achievement verification system, characterized in that the similarity is determined by the weight editing distance value (D(i,j)) derived through the following process.

[process]
1. If A[i] and B[j] of the string to be compared match,
D(i,j) = D(i-1,j-1),
If b == True then w = w + 1,
If b != True then b = true.

2. If A[i] and B[j] of the string to be compared do not match,
D(i,j) = min( D(i-1,j)+1/w, D(i,j-1)+1/w, D(i-1,j-1)+1/w ) ego,
b = False.

{ D(i,j) = weight edit distance value, initial value D(0,0)=0,
A[i] = i-th character of string A,
B[j] = jth character of string B,
w = continuity weights (w is initialized to 0),
b = Boolean to determine continuity (initial value of b is False),
i,j = 0 to n }

Images