KR102383834B1 - Personality type classifying apparatus and method thereof - Google Patents

Abstract

A personality type determination apparatus and method are disclosed.
A personality type determining apparatus according to the present invention is a personality type determining apparatus for determining a personality type of a client, comprising: an input unit into which an answer of a client to a list of questions for determining a personality type is input; a memory unit storing diagnostic keywords for each personality type generated to determine the personality type related to the client's extraversion, openness, friendliness, sincerity, and neuroticism with respect to the question list; a control unit for generating answer keywords from answers input to the input unit, determining a similarity level using the generated answer keywords and diagnostic keywords, and determining a personality type of the client according to the determined similarity level; and an output unit for outputting the determined personality type; includes

Description

Apparatus and method for determining personality type

The present invention relates to personality type determination, and more particularly, to a personality type determination apparatus and method capable of classifying a client's personality type by comparing and analyzing a preset question list with the client's answers.

Recently, the number of counseling service workers and customer demand for counseling services are increasing in society, and the need for on-demand services is increasing along with the global coaching industry development trend.

Professional coaching industries such as life, business, career (career), and learning coaching are growing independently of consulting and consulting businesses. In particular, coaching services in Korea are also rapidly increasing. It occupies more than 35%.

In addition, the B2B (Business to Business) market is in full swing due to the rapid growth of the Employee Assistance Program (EAP) market, which is an expert counseling support program for job stress/mental health of organizational members.

90% of the top 100 U.S. companies have introduced worker support programs, and in Japan, it is expected to increase from 21.4 billion yen in 2014 to 35 billion yen by 2020 due to the enforcement of the Occupational Safety and Health Act in 2015. As a result, the introduction of worker support program services is increasing, and it is expected to grow to 120 billion won by 2022.

Moreover, with the Emotional Workers Protection Act that took effect in October 2018, the B2B market for treatment and counseling support is rapidly expanding.

According to the Emotional Workers Protection Act, domestic emotional workers are 31 to 41% of all workers, or 5.6 to 7.4 million, and preventive measures and counseling support are mandatory to protect emotional workers. included in the market, which is expected to grow rapidly.

In addition, as the number of depressed patients changes, the perception of mental health services is changing and the demand for psychological counseling is increasing, so the use of mental health services is increasing.

According to the World Health Organization (WHO), between 2005 and 2015, the number of patients with depression increased by about 20%, and it is estimated that more than 300 million people in the world.

In Korea, the officially counted number of depressed patients is about 640,000, and it is estimated that the number of patients with hidden depression is at least 1.2 million.

For reference, according to data from the National Health Insurance Corporation in 2017, it is reported that mental health treatment expenses increased from 2.22 trillion won in 2012 to 3.248.3 trillion won in 2016, surpassing 3 trillion won.

Accordingly, in recent years, the use of mental health services is increasing due to a change in awareness of mental health services and an increase in demand for psychological counseling.

However, the domestic mental health service use rate is still significantly lower than that of other countries. This is higher than the lifetime usage rate.

Negative perceptions about the use of mental health services, many people do not recognize their own mental health problems, and mental health counseling and treatment are not covered by insurance, so the financial burden on the household economy is high. there is.

Accordingly, although the problems with the use of mental health services are gradually being improved, the supply is still very insufficient compared to the demand.

In order to solve this problem, recently, various projects that graft big data and artificial intelligence (AI) technology to mental health services are being carried out around the world, mainly in the United States.

In particular, mental health issues are greatly influenced by psychological and social cultures, so if you use artificial intelligence, you can solve the problem of supply shortage through various data analysis related to this and at the same time be protected from negative views of society. It is believed to be helpful in diagnosing and treating diseases.

As such, when mental health services using artificial intelligence are commercialized, the accessibility of the services is convenient and the understanding of one's own psychological state through one's own language and behavioral patterns increases, so that early detection of mental illness may be possible. It can be expected to reduce the fear of stigma since it is possible to escape from the negative gaze of the people around the service.

Accordingly, there is a need to develop a system that can provide big data and artificial intelligence-based consultation and analysis reports.

Korean Patent Publication No. 10-1731561 (Registered on April 24, 2017)

An object of the present invention is to analyze a client's answers to a list of various types of questions, classify them into a predetermined type, and provide a visualized analysis data according to the classified type or a personality type determination device capable of providing a suitable counselor recommendation and to provide that method.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to the present invention, there is provided a personality type determining apparatus for determining a personality type of a client, comprising: an input unit into which an answer of a client to a list of questions for determining a personality type is input; a memory unit storing diagnostic keywords for each personality type generated to determine the personality type related to the client's extraversion, openness, friendliness, sincerity, and neuroticism with respect to the question list; a controller for generating answer keywords from answers input to the input unit, determining a degree of similarity using the generated answer keywords and diagnostic keywords, and determining a personality type of a client according to the determined degree of similarity; and an output unit for outputting the determined personality type; It can be achieved by a personality type determining device comprising a.

In the personality type determination device, the input unit includes a list of questions for each personality type within 10 to 15, and the memory unit contains diagnostic keywords classified into positive and negative types with respect to the question list by personality type. can be saved.

In the personality type determining device, a corpus obtained from crawling news articles, movie scripts, and movie reviews is stored in the memory unit, and diagnosis of the corpus obtained based on diagnostic keywords using the word embedding technique A keyword vector may be constructed.

In the personality type determining apparatus, the controller may generate an answer keyword from the client's answer, and extract an answer keyword vector for the corpus secured based on the answer keyword using a word embedding technique.

Also, the controller may compare the diagnosis keyword vector and the answer keyword vector, and calculate a distance between the diagnosis keyword vector and the answer keyword vector to determine the similarity for each personality type.

Here, when calculating the distance between the diagnostic keyword vector and the answer keyword vector, the controller may determine the degree of similarity between the two vectors by using a cosine value between the two vectors.

The list of questions in the personality type determination device is, 'Let's imagine yourself standing in the middle of Daehak-ro on Christmas Eve, where so many people gather. How do you feel or feel when you go to a place with so many people?' or 'Think of the person you think you know best at work or school. What kind of personality do you think that person has?', 'The company started a new project, so a task force was formed. What role do you want to take on?', 'I had a hard time finding the item I wanted on this Black Friday and ordering it, but I got a call saying that the product was lost due to the courier company's mistake and I am checking it. In this case, how would you respond?', 'What is your interpersonal style?', 'How do you react to new experiences and changes, such as changing jobs or moving?' ', 'What do you look like when there is a conflict of opinion or conflict in a relationship', 'Which way do you prefer to study or acquire skills?', 'What kind of student were you in school?', 'One day Suddenly, your boss calls and tells you to write a business plan for next year within a week. What do you think, 'What kind of side do you think your mood changes in the change of seasons or in your daily life', 'What types of leisure activities do you like' and/or 'What do you think of yourself? What are the disadvantages?'

The output unit in the personality type determination device outputs at least one of a displayed report with the results and explanations for each determined personality type, a graph that digitizes the similarity determined by the control unit, and Wordnet that displays the word frequency of the client's answer keyword. can

In this case, the graph output from the output unit may be provided as at least one of a radial graph and a bar graph.

In addition, the report output from the output unit may include a personality profile analysis result for each personality type, and results and explanations for each personality type of extraversion, openness, friendlyity, conscientiousness, and nervousness.

Meanwhile, according to another field of the present invention, the above object is, according to the present invention, in the personality type determination method for determining the personality type of a client using the personality type determination device, a list of questions for determining the personality type outputting; receiving the client's answer to the outputted question list; extracting diagnostic keywords from the question list through morpheme analysis, and extracting answer keywords from the received answers through morpheme analysis; determining the similarity by comparing the extracted answer keywords and diagnostic keywords for the question list for each personality type including extraversion, openness, friendliness, sincerity, and nervousness; determining a personality type according to the determined similarity; and outputting the determined personality type; It can be achieved by a personality type determination method comprising

In the step of determining the similarity in the personality type determination method, the distance between the diagnostic keyword vector extracted from the diagnostic keyword and the answer keyword vector extracted from the answer keyword is calculated using the word embedding technique, and the The degree of similarity by personality type can be judged.

The personality type determining apparatus and method of the present invention can determine the degree of similarity to a predetermined extraversion, openness, friendliness, conscientiousness, and neuroticism by analyzing the client's answers to various question lists, and according to the determined similarity, the client's By determining the personality type and providing the determined personality type as visualized data such as graphs and reports, the client can easily identify his or her personality type.

Effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description.

1 is a block diagram of an apparatus for determining a personality type according to an embodiment of the present invention.
FIG. 2 is a view for explaining the input unit shown in FIG. 1 .
FIG. 3 is a diagram for explaining the memory unit shown in FIG. 1 .
4 to 8 are diagrams showing a list of questions of extraversion, openness, friendliness, sincerity, and nervousness stored in the memory unit.
FIG. 9 is a view for explaining the control unit shown in FIG. 1 .
FIG. 10 is a diagram for explaining a case in which a result of personality type determination output by the output unit shown in FIG. 1 is expressed in graphs and wordnet.
FIG. 11 is a diagram for explaining a case in which a result of personality type determination output by the output unit shown in FIG. 1 is displayed as a report.
12 is a flowchart illustrating a method for determining a personality type using the apparatus for determining a personality type according to an embodiment of the present invention.
13 is a block diagram illustrating a method for determining a personality type shown in FIG. 12 .
14 is a diagram schematically illustrating a method for determining a personality type shown in FIG. 13 .

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

It is noted that the drawings are schematic and not drawn to scale. Relative dimensions and proportions of parts in the drawings are shown exaggerated or reduced in size for clarity and convenience in the drawings, and any dimensions are illustrative only and not limiting. And the same reference numerals are used to denote like features to the same structure, element, or part appearing in two or more drawings.

The embodiments of the present invention specifically represent ideal embodiments of the present invention. As a result, various modifications of the drawings are expected. Accordingly, the embodiment is not limited to a specific shape of the illustrated area, and includes, for example, a shape modification by manufacturing.

Hereinafter, an apparatus and method for determining a personality type according to an embodiment of the present invention will be described with reference to the accompanying drawings.

First, an apparatus for determining a personality type according to an embodiment of the present invention will be described with reference to FIGS. 1 to 10 .

1 , the apparatus 100 for determining a personality type according to an embodiment of the present invention includes an input unit 110 , a memory unit 120 , a control unit 130 , and an output unit 140 .

1 and 2 , the input unit 110 is a part into which an answer to a question list for determining a personality type is input.

For example, the input unit 110 may be a device equipped with an input means such as a wired or wireless phone such as a smart phone, a tablet, a notebook computer, or the like, but is not necessarily limited thereto. In this case, a device input to the input unit 110 may be changed by selection of a client using the personality type determining apparatus 100 .

An answer to a list of questions for determining a personality type is input by the client into the input unit 110 .

For reference, the client can store basic data such as gender, age, occupation, etc. when using a wired/wireless phone or smartphone application, listen to a question on a pre-stored question list, and input a corresponding answer.

Then, the answer to the question list for each personality type input by the client through a wired/wireless phone or smartphone application is input to the input unit 110 .

1 and 3 , the memory unit 120 stores diagnosis keywords for each personality type of the client.

In other words, diagnosis keywords for each personality type may be stored in the memory unit 120 to determine the client's personality type with respect to the question list.

In this case, personality type and question list can be obtained through a separate institution, such as a partner university, personality type related data. For reference, the obtained personality type-related data can be processed and processed into CSV data that is stored by dividing items based on commas.

For reference, as shown in FIG. 2 , the memory unit 120 is stored in a separate cloud server 102 in which an answer input to the input unit 110 is stored.

On the other hand, the list of questions for each personality type stored in the memory unit 120 may include contents related to a psychological type, a love type, an aptitude type, and the like.

The list of questions including these contents is extroversion to judge physical and psychological energy, openness to judge receptiveness to new experiences and changes, friendliness to judge interpersonal tendencies, sincerity to judge work and academic performance, and emotional response It can be defined as 5 groups including neuroticism that judges propensity.

That is, the memory unit 120 stores diagnosis keywords for each personality type in order to determine personality types related to extraversion, openness, friendliness, sincerity, and nervousness with respect to the question list.

For reference, the controller 130, which will be described later, may extract diagnostic keywords for each personality type for the question list through morphological analysis from the question list.

Here, in the personality type determining apparatus 100 according to an embodiment of the present invention, the question list for each personality type may include 10 to 15 questions for each personality type.

For example, referring to FIGS. 4 to 8 , the question list is 'Let's think of you standing in the middle of Daehak-ro on Christmas Eve, where so many people gather. How do you feel or feel when you go to a place with so many people?' or 'Think of the person you think you know best at work or school. What kind of personality do you think that person has?', 'The company started a new project, so a task force was formed. What role do you want to take on?', 'I had a hard time finding the item I wanted on this Black Friday and ordering it, but I got a call saying that the product was lost due to the courier company's mistake and I am checking it. In this case, how would you respond?', 'What is your interpersonal style?', 'How do you react to new experiences and changes, such as changing jobs or moving?' ', 'What do you look like when there is a conflict of opinion or conflict in a relationship', 'Which way do you prefer to study or acquire skills?', 'What kind of student were you in school?', 'One day Suddenly, your boss calls and tells you to write a business plan for next year within a week. What do you think, 'What kind of side do you think your mood changes in the change of seasons or in your daily life', 'What types of leisure activities do you like' and/or 'What do you think of yourself? What are the disadvantages?'

Here, the list of questions for each personality type for determining the personality types of extroversion, openness, friendlyity, conscientiousness, and neuroticism may have overlapping lists, and accordingly, the number of questions for each personality type may be different.

In addition, the memory unit 120 may store diagnostic keywords classified into positive and negative types with respect to the question list for each personality type of extraversion, openness, friendliness, sincerity, and neuroticism.

The intrinsic type of the question list may mean a case in which the client's answer to the question list for each type is positive, while the low type may mean a case in which the client's answer to the question list corresponding to each type is negative. it is not going to be

Here, as described above, the intrinsic and low-type words for the question list for each personality type may mean diagnostic keywords for determining the personality type of the client with respect to the question list.

For reference, although not shown in the drawings, the memory unit 120 may include answer data for a question list for each personality type. In this case, the answer data for the question list can secure answers to the question list by personality type for in-house employees, which can be used as basic data for personality type classification.

In addition, the memory unit 120 may store a corpus secured from crawling 786,000 news articles, about 180 movie scripts and movie reviews from August 2017 to July 2019 in order to determine the personality type. there is. Here, a diagnostic keyword vector for a corpus secured based on a diagnostic keyword may be constructed using a word-embedding technique.

As such, the constructed word vector is used to measure the degree of similarity between a diagnostic keyword for determining a client's personality type and a client's answer keyword, which will be described later.

For reference, a corpus refers to a set of data collected in a form that can process, process, and analyze texts using a computer for language research.

Also, in the memory unit 120 , data pre-processing and a related word dictionary are built. For reference, the update cycle of the various data stored in the memory unit 120 may relearn word embeddings, that is, word vectors based on the client's answer data.

Also, the size of data stored in the memory unit 120 may be N/A (not applicable).

Meanwhile, when the client uses a wired or wireless phone, the memory unit 120 may text the client's answer through the voice recognition module, ie, convert it into data, and store it. In other words, when the client uses the ARS service system over a wired/wireless phone, the client's voice answer may be extracted, converted into text through a voice recognizer, and accumulated.

At this time, when texturing the client's answer in the memory unit 120, a text mining technique for extracting statistically meaningful concepts or characteristics of unstructured data and extracting high-quality information such as patterns or trends between them can be used, but is not necessarily limited thereto.

For reference, a conventional commercial program may be separately applied to the ARS service system and the voice recognizer, and the types of the ARS service system and the voice recognizer are not limited thereto.

Referring to FIGS. 1 and 9 , the controller 130 is a part that determines the personality type by determining the degree of similarity.

The control unit 130 generates an answer keyword from the answer input to the input unit 110 , determines the similarity to the personality type using the answer keyword and the diagnosis keyword, and determines the client's personality type according to the determined similarity.

In particular, the control unit 130 extracts answer keywords for natural language processing, morpheme analysis/frequency analysis, and key words/sentences from the client's answer data, and through this, by determining the degree of similarity with pre-generated diagnostic keywords and morphemes for each personality type. According to the judged value, the personality type of the client can be determined. Also, as described above, the controller 130 may extract a diagnostic keyword from the question list through morphological analysis.

For reference, a morpheme is the smallest unit of speech that has a meaning, and refers to a word or word component that only has a grammatical or relational meaning.

Hereinafter, the control unit 130 will be briefly described.

First, the controller 130 generates an answer keyword from the client's answer.

Then, an answer keyword vector is extracted for the corpus secured based on the answer keyword by using the word embedding technique.

Next, the diagnosis keyword vector constructed in the memory unit 120 and the answer keyword vector are compared. At this time, the distance between the diagnosis keyword vector and the answer keyword vector is calculated to determine the similarity for each personality type.

Meanwhile, in order to calculate the distance between the diagnostic keyword vector and the answer keyword vector, the cosine similarity of determining the degree of similarity between the two vectors by using the cosine value between the two vectors may be used.

At this time, the similarity determined by the control unit 130 is a similarity value between 0 and 1, and the higher the similarity between the individual personality type and the client's answer, the closer to '1', and the lower the similarity, the lower the value is ' appears close to 0'.

That is, when the cosine similarity is close to 1, the direction between the diagnostic keyword vector and the answer keyword vector is the same and the angle is close to 0°, so it can be determined that the similarity is high. Conversely, when the cosine similarity is close to 0, the direction between the diagnostic keyword vector and the answer keyword vector is the same and the angle is close to 90°, so it can be determined that the similarity is low.

As described above, when cosine similarity is used, similarity between data is determined based on an angle value between two vectors.

As described above, smart big data specialized for consultation can be built by the memory unit 120 and the control unit 130 .

The output unit 140 outputs the personality type determined by the control unit 130 .

In this case, the output unit 140 may visually output the personality type. In other words, the output unit 140 may output the similarity for each personality type as at least one of a graph and a report.

For example, if the cosine values of the similarity for each personality type are openness: 0.402, conscientiousness: 0.414, neuroticism: 0.603, extraversion: 0.395, and affinity: 0.572, as shown in FIG. It can be output in the form of a graph.

In addition, as shown in the lower part of FIG. 10 , the output unit 140 may output in the form of a wordnet indicating the word frequency of the client's answer keyword.

For reference, when the output unit 140 is displayed as a graph, it may be in the form of a photo file such as a PNG file, but is not necessarily limited thereto.

In addition, as shown in FIG. 11 , the report output from the output unit 140 may include a personality profile analysis result for each personality type, and results and explanations for each personality type of extraversion, openness, friendlyity, conscientiousness, and nervousness. That is, in the report output from the output unit 140 , a detailed description of each personality type of the client may be output based on the client personality type determination result value.

In addition, in the report, the description of the intrinsic type and the low type may be classified and output for each personality type according to the result of the client's personality classification.

When the output unit 140 is output as a report, it may be in the form of a JSON file, but is not necessarily limited thereto.

For reference, a JSON file is derived from the JavaScript language and follows the syntax format of JavaScript, and as a language-independent data format, it may become possible to store and structure information very accidentally.

Meanwhile, although not shown in the drawing, a counselor recommendation may be provided according to the personality type determined by the output unit 140 .

Hereinafter, a method S100 for determining a personality type using the apparatus 100 for determining a personality type according to an embodiment of the present invention will be briefly described with reference to FIGS. 12 to 14 .

First, the personality type determination method ( S100 ) according to an embodiment of the present invention outputs a list of questions for determining the personality type ( S110 ).

The question list is stored in the memory unit 120 of the personality type determining device 100, and includes 10 to 15 questions for determining a personality type including extraversion, openness, friendly, conscientiousness, and neuroticism.

Then, an answer to the output question list is received (S120).

At this time, the client's answer to the question list for determining the client's personality type is input to the input unit 110 of the personality type determining device 100 through the ARS service system.

Here, as shown in FIG. 13, real-time recording of answers to the question list can be made using an IP-PBX-based one-to-one counseling relay system.

In this case, the IP-PBX-based one-to-one counseling relay system can enable prepaid and postpaid billing according to the client's needs. For reference, the IP-PBX-based one-to-one consultation relay system may be a conventionally developed system, but is not limited thereto.

An answer to the question list recorded in real time may be stored in real time in a separately provided server 102 .

Then, keywords and morphemes are extracted from the input answer (S130).

In other words, diagnostic keywords are extracted by analyzing morphemes from the question list, and answer keywords are extracted by analyzing morphemes from received answers.

At this time, using the controller 130 of the personality type determining apparatus 100, the client's voice data and the counselor's voice data are converted into text and the converted text is analyzed.

13 and 14, the client's voice data and the counselor's voice data are voiced using natural language voice recognition technology, morpheme voice recognition technology, and key word detection and indexing technology through a separately provided voice recognition/analysis server 102. It can be textualized.

Next, the similarity is determined by comparing the answer keyword extracted through morpheme analysis from the answer and the diagnostic keyword for the question list for each personality type including extraversion, openness, friendliness, sincerity, and nervousness (S140).

Next, a personality type is determined according to the determined similarity (S150).

Here, through the controller 130 of the personality type determination apparatus 100, the distance between the diagnostic keyword vector extracted from the diagnostic keyword and the answer keyword vector extracted from the answer keyword is calculated using the word embedding technique, and the The degree of similarity for each personality type is determined according to the level of similarity, and the personality type can be determined according to the determined degree of similarity.

The controller 130 calculates the distance between the diagnosis keyword vector and the answer keyword vector using the cosine similarity method.

When the calculated cosine value is close to 1, it is determined that the diagnostic keyword vector and the answer keyword vector have the same direction and the angle between the two vectors converges to 0°, so that the similarity can be determined to be high. Conversely, when the calculated cosine value is close to 0, it is determined that the diagnosis keyword vector and the answer keyword vector have the same direction and the angle between the vectors converges to 90°, so that the similarity may be low.

Finally, the determined personality type is output (S160).

In this case, using the output unit 140 of the personality type determining apparatus 100, the results of the client's personality type may be visualized in a report, graph, word net, or the like.

In addition, the output unit 140 may not only visualize the results for the determined personality type, but also recommend a counselor suitable for the determined personality type to the client.

With the above configuration, the personality type determining apparatus 100 and the method S100 according to an embodiment of the present invention can classify the client's personality type by securing a list of questions about the personality type and analyzing the client's answer. It has the effect of building a data-based AI personality type diagnosis service that can provide customized reports and statistics according to the classified personality types.

Moreover, according to this, since the client can receive the data visualized as the result of the personality type diagnosis, it is possible to more conveniently identify his or her personality type.

In addition, the personality type determining apparatus 100 and the method S100 according to an embodiment of the present invention can provide a customized UI (User Interface) system for companies and organizations that need to introduce a counseling service.

As described above, in one embodiment of the present invention, specific matters such as specific components, etc., and limited embodiments and drawings have been described, but these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. It is not limited, and various modifications and variations are possible from these descriptions by those of ordinary skill in the art to which the present invention pertains. Accordingly, the spirit of the present invention should not be limited to the described embodiments, and not only the claims described below, but also all of the claims and all equivalents or equivalent modifications will fall within the scope of the spirit of the present invention.

100: personality type determination device
102: server
110: input unit
120: memory unit
130: control unit
140: output unit

Claims (12)

A personality type determining device for determining a client's personality type, comprising:
an input unit into which a client's answer to a list of questions for determining a personality type is input;
a memory unit storing diagnostic keywords for each personality type generated to determine the personality type related to the client's extraversion, openness, friendliness, sincerity, and neuroticism with respect to the question list;
a control unit for generating answer keywords from answers input to the input unit, determining a similarity level using the generated answer keywords and diagnostic keywords, and determining a personality type of the client according to the determined similarity level; and
an output unit for outputting the determined personality type;
including,
The input section contains a list of no more than 10 to 15 questions for each personality type,
The memory unit includes diagnostic keywords classified into positive and negative types for the question list by personality type and answer data for the question list by personality type, and the answer data includes questions by personality type for clients It is used as basic data for personality type classification by securing answers to the list.
The control unit extracts answer keywords for natural language processing, morpheme analysis/frequency analysis, and key words/sentences from the client's answer data, and uses the extracted answer keywords to determine the degree of similarity with pre-created diagnostic keywords for each personality type and morphemes. A personality type determining device that determines the client's personality type according to the determined value.
delete According to claim 1,
In the memory section,
Personality type determination, in which a corpus obtained from crawling news articles, movie scripts, and movie reviews is stored, and a diagnostic keyword vector is constructed for the corpus obtained based on the diagnostic keyword using the word embedding technique Device.
4. The method of claim 3,
the control unit,
A personality type determination device that extracts an answer keyword vector for a corpus secured based on an answer keyword using a word embedding technique.
5. The method of claim 4,
the control unit,
A personality type determining device that compares the diagnostic keyword vector and the answer keyword vector, and determines the similarity for each personality type by calculating the distance between the diagnostic keyword vector and the answer keyword vector.
6. The method of claim 5,
the control unit,
When calculating the distance between the diagnostic keyword vector and the answer keyword vector, a personality type determination device that determines the degree of similarity between the two vectors by using the cosine value between the two vectors.
According to claim 1,
The list of questions is
'On Christmas Eve, imagine yourself standing in the middle of Daehak-ro, where so many people gather. How do you feel or think when you go to a place with so many people?' or 'Think of the person you think you know best at work or school. What kind of personality do you think that person has?', 'The company started a new project, so a task force was formed. What role do you want to take on?', 'I had a hard time finding the item I wanted on this Black Friday and ordering it, but I got a call saying that the product was lost due to the courier company's mistake and is being checked. In this case, how would you respond', 'What is your interpersonal style', 'How do you react to new experiences and changes, such as changing jobs or moving', 'What are your strengths that you acknowledge yourself? ', 'What does it look like when there is a conflict of opinion or conflict in a relationship', 'What kind of method do you prefer to study or acquire skills?', 'What kind of student were you in school?', 'One day Suddenly, your boss calls and tells you to write a business plan for next year within a week. What do you think, 'What kind of side do you think your mood changes with the change of seasons or in your daily life', 'What types of leisure activities do you like' and/or 'What do you think of yourself? Personality type determination device, including 'What are your weaknesses?
6. The method of claim 5,
the output part,
A personality type determination device that outputs at least one of a report displaying the results and explanations for each personality type determined, a graph quantifying the similarity determined by the control unit, and Wordnet indicating the word frequency of the client's answer keyword.
9. The method of claim 8,
The graph output from the output section is,
A personality type determining device, provided with at least one of a radar graph and a bar graph.
9. The method of claim 8,
The report output from the output unit is,
A personality type determining device, including the results of analyzing the personality profile for each personality type, and the results and explanations for each personality type of extraversion, openness, friendly, conscientious and neurotic.
A method for determining a personality type for determining a personality type of a client using the personality type determining device according to claim 1, the method comprising:
outputting a list of questions for determining a personality type;
receiving the client's answer to the outputted question list;
extracting diagnostic keywords from the question list through morpheme analysis, and extracting answer keywords from the received answers through morpheme analysis;
determining the similarity by comparing the extracted answer keywords and diagnostic keywords for the question list for each personality type including extraversion, openness, friendliness, sincerity, and nervousness;
determining a personality type according to the determined similarity; and
outputting the determined personality type;
including,
The list of questions is provided within 10 to 15 for each personality type, and the diagnostic keywords that are classified into positive and negative types for the question list by personality type are stored,
In the reception stage, answer data for a list of questions by personality type is included, and the answer data is used as basic data for personality type classification by securing answers to a list of questions by personality type for clients,
In the extraction and decision stages, answer keywords for natural language processing, morpheme analysis/frequency analysis, and key words/sentences are extracted from the client's answer data, and diagnostic keywords and morphemes for each personality type generated in advance using the extracted answer keywords A personality type determination method that determines the client's personality type according to the determined value by judging the similarity of
12. The method of claim 11,
In the step of determining the similarity,
A personality type determination method that calculates the distance between a diagnostic keyword vector extracted from a diagnostic keyword and an answer keyword vector extracted from an answer keyword using a word embedding technique, and determines the similarity for each personality type according to the calculated numerical value.

Images