JP2024008344A - Information processing device, information processing method, information processing program - Google Patents

Abstract

[Problem] To provide an information processing device, information processing method, and information processing program capable of effectively communicating the needs of a job seeker. [Solution] The information processing device according to the present invention comprises an acquisition unit that acquires information on at least one of a job seeker and a recruiter, an extraction unit that extracts an entity of at least one of a job seeker and a recruiter from the information on at least one of the job seeker and the recruiter, and a classification unit that classifies the entity of at least one of a job seeker and a recruiter extracted by the extraction unit into a predetermined category. [Selected Figure] Figure 1

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Many matching systems have been proposed for matching job seekers and job seekers over the Internet. For example, conventionally, there is a system that aims to provide a matching device that calculates a matching score that accurately represents the degree of match between the abilities sought by job seekers and the abilities possessed by job seekers.

Re-table 2020/003355

However, in conventional systems, matching is performed based on the skills possessed by job seekers and the skills desired by job seekers, so there is a problem in that job seekers' requests are not properly communicated.

The present invention has been made in view of the above problems, and an object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can effectively communicate the requests of job seekers.

In order to solve the above-mentioned problems, an information processing device according to the present invention includes an acquisition unit that acquires information on at least one of a job applicant and a job offerer; and a classification unit that classifies into a predetermined category at least one of the job seeker and job offerer entities extracted by the extraction unit.

According to the present invention, it is possible to provide an information processing device, an information processing method, and an information processing program that can effectively communicate the requests of job seekers.

1 is an example of a schematic configuration diagram of an information processing system according to an embodiment. 1 is an example of a hardware configuration of a server (information processing device) according to an embodiment. It is an example of the database stored in the storage device of the server according to the embodiment. 1 is an example of a functional configuration of a server according to an embodiment. 1 is an example of a hardware configuration of a terminal according to an embodiment. 1 is an example of a functional configuration of a terminal according to an embodiment. 3 is an example of a screen displayed on a display device of a terminal according to an embodiment. 3 is an example of a screen displayed on a display device of a terminal according to an embodiment. 3 is an example of a screen displayed on a display device of a terminal according to an embodiment. 3 is an example of a flowchart illustrating an example of information processing by the information processing system according to the embodiment. 3 is an example of a flowchart illustrating an example of information processing by the information processing system according to the embodiment. 3 is an example of a flowchart illustrating an example of information processing by the information processing system according to the embodiment. 3 is an example of a flowchart illustrating an example of information processing by the information processing system according to the embodiment. 3 is an example of a flowchart illustrating an example of information processing by the information processing system according to the embodiment. 3 is an example of a flowchart illustrating an example of information processing by the information processing system according to the embodiment.

Embodiments of the present invention will be described below with reference to the drawings. In addition, in the following explanation,
``Job seekers'' include job seekers, job changers, part-time workers, interns, part-time worker candidates, as well as candidates for outsourcing contracts.
"Recruiters" include individuals (for example, sole proprietorships), various corporations, associations, institutions, individuals, organizations, business entities, and the like.
"Entities" are objects to be managed, such as events and concepts related to business, skills, roles (positions), organizations, desired conditions, personalities, interests (things of interest (e.g. programs, languages, etc.)), etc. It is about. Note that the type of information to be used as an entity is arbitrary.
Note that "skills" include qualifications (e.g., IT passport, IT strategist, etc.), abilities (e.g., PC skills (Word, Excel, PowerPoint, etc.), programming skills (Java, C++, Ruby, Python, Perl, etc.)), etc. This is information that indicates a job applicant's abilities.

[Embodiment]
First, the configuration of the information processing system 1 will be explained with reference to FIG. 1. The information processing system 1 has a configuration in which a server 2, a job applicant terminal 3, and a job applicant terminal 4 are connected via a network 5. Note that the number of servers 2, job applicant terminals 3, and job applicant terminals 4 included in the information processing system 1 is arbitrary.

Connected to the network 5 is a WWW server that provides information in file formats such as HTML, JSON, and CSV (hereinafter, files in these formats are simply referred to as HTML files), and the server 2 is connected to a web site. The device is configured to be able to acquire information (for example, text data, audio data, and image data (including video)). Software such as crawlers and scrapers can be used to obtain information from websites. Note that the type of communication network that constitutes the network 5 is arbitrary.

(Server 2)
FIG. 2 is a configuration diagram of the server 2. FIG. 2 shows the main hardware configuration of the server 2, and the server 2 has a configuration in which a communication IF 200A, a storage device 200B, and a CPU 200C are connected via a bus (BUS) or the like. Note that the server 2 may also include input devices such as a keyboard, mouse, and touch panel, and display devices such as a liquid crystal monitor and an organic EL monitor.

The communication IF 200A is an interface for communicating with other devices (for example, a website, job applicant terminal 3, job applicant terminal 4, etc.). The storage device 200B is, for example, a HDD (Hard Disk Drive) or a semiconductor storage device (SSD (Solid State Drive)). The CPU 200C controls the server 2 and includes a ROM (Read Only Memory) and a RAM (Random Access Memory), which are not shown.

Note that in this embodiment, as shown in FIG. 2, the server 2 is configured to include a storage device 200B, but another server connected to the server 2 via the network 5 may store all or the storage device 200B. A configuration including a portion thereof may also be used. In this case, server 2 refers to storage device 200B provided in another server. Further, the information processing program described later may be configured to be downloadable from another server connected to the server 2 via the network 5.

FIG. 3 is an example of a database stored in the storage device 200B of the server 2. The storage device 200B stores information processing programs, various databases, and the like. Although this embodiment includes a plurality of databases, it may be one database.

(Visiting destination DB1)
The visited DB 1 stores URLs (Uniform Resource Locators) of web sites that the server 2 visits to obtain information. This URL may be stored in the visited destination DB 1 in advance by the administrator of the server 2 or the like. Alternatively, the server 2 may automatically add the link destination URL of the visited website as the visited URL. Here, the WEB site is not particularly limited, but is preferably a site published by an individual on a network, such as a blog, home page, or SNS (Social Networking Service). This is because it is easier to obtain information on job seekers and job seekers.

(Job applicant DB2)
The job seeker DB 2 contains information extracted by the server 2 based on the results of analyzing information obtained by visiting websites and information input by job seekers (e.g., various information such as resumes and job history documents). Job applicant's attribute information (hereinafter referred to as first attribute information), such as name, gender, address, contact information (phone number, email address, etc.), entity, entity classification results, attributes and level, etc. It is stored in association with an identifier (hereinafter referred to as job applicant ID) and a time stamp. Note that what kind of information is acquired as attribute information is arbitrary.

(Recruiter DB3)
The recruiter DB 3 contains information obtained by the server 2 by visiting websites (for example, job information (for example, job postings, scout emails, notices of interest, etc.), company corporate sites, company blogs, etc.), recruiters, etc. Recruiter attribute information (hereinafter referred to as secondary attribute information) extracted based on the results of analyzing the information entered by , such as name, gender, address or residence, contact information (phone number, email address, etc.) , entities, classification results of entities, attributes, and levels are stored in association with recruiter identifiers (hereinafter referred to as recruiter IDs) and time stamps. Note that what kind of information is acquired as attribute information is arbitrary.

(Question DB4)
The question DB 4 stores questions for job seekers and recruiters. A question extraction unit 211, which will be described later, refers to the question DB 4 and extracts questions for the job applicant according to the entity of the job applicant. Further, a question extraction unit 211, which will be described later, refers to the question DB 4 and extracts questions for the recruiter according to the entity of the recruiter.

(template DB5)
The template DB 5 stores various templates necessary for job hunting and recruiting, such as resumes, job history records, job information (for example, job postings, scout emails, notices of interest, etc.). For example, by inserting entities extracted by the extraction unit 207 into predetermined positions of various templates, resumes, job history documents, job information, etc. are generated.

(Dictionary DB6)
The dictionary DB 6 stores entities to be extracted and non-extracted for each job applicant and job offerer. In other words, the dictionary DB 6 stores entities that are extracted and non-extracted for job seekers, and entities that are extracted and non-extracted for job seekers.
Note that it is preferable that the extracted and non-extracted entities stored in the dictionary DB 6 can be edited (added, deleted, changed, etc.) from the job applicant terminal 3 and the recruiter terminal 4. .

Entities that will not be extracted include, for example, inappropriate words (such as words that violate public order and morals), personal information that requires consideration (medical history, criminal history, etc.), and information that should not be considered in hiring (ideas, beliefs, etc.). Alternatively, entities to be excluded from extraction may be selected by adding words that many users have deleted by themselves to an exclusion list.
The dictionary DB 6 also contains vector representations of entities to be extracted and non-extracted (for example, they may be generated from entities using existing algorithms such as Word2vec), and machine learning models (for example, neural networks, etc.). It may also be stored in the form of learned parameters. In the case of a learned parameter format, for example, as a binary classification task to classify entities as extracted or non-extracted, a machine learning algorithm is executed so that entities that are deleted by many job seekers or job seekers are not extracted. The learned parameters obtained by this may be stored in the dictionary DB 6.

(Function of server 2)
FIG. 4 is a functional block diagram of the server 2. As shown in FIG. 4, the server 2 includes a reception section 201, a transmission section 202 (output section), a storage device control section 203 (history registration section), an acquisition section 204, an analysis section 205, a first classification section 206, and an extraction section. 207, second classification unit 208 (classification unit), presentation information generation unit 209 (obtainment source presentation unit, entity presentation unit), attribute assignment unit 210, question extraction unit 211, level assignment unit 212, map data generation unit 213 (display It has functions such as a data generation section), a matching degree calculation section 214, a recommendation section 215, a job information generation section 216, and a resume generation section 217. Note that the functions shown in FIG. 4 are realized by the CPU 200C executing an information processing program stored in the ROM (not shown) of the server 2.

The receiving unit 201 receives information transmitted from the job applicant terminal 3 and the recruiter terminal 4. Further, the receiving unit 201 receives information from a website when the acquiring unit 204 acquires information.

The transmitter 202 (output unit) transmits information to the job applicant terminal 3 and the recruiter terminal 4, for example.

The storage device control unit 203 (history registration unit) controls the storage device 200B. The storage device control unit 203 controls the storage device 200B to write and read information, for example.
In addition, the storage device control unit 203 (history registration unit) stores, for example, the entities extracted by the extraction unit 207, the classification results of the entities, the attributes assigned by the attribute assignment unit 210, and the levels assigned by the level assignment unit 212 at the date and time. The job applicant DB2 and job offerer DB3 of the storage device 200B are stored in association with each other.
Note that the storage device control unit 203 stores the job applicant entity and classification results in the job applicant DB2, and stores the job applicant entity and classification results in the recruiter DB3.

For example, the acquisition unit 204 accesses the website based on the URL stored in the visited DB 1 and reads the HTML file provided from the website, thereby acquiring information on the website (for example, text data, audio data, etc.). data, and image data (including video)).
Further, the acquisition unit 204 acquires, for example, information input by job seekers and job seekers (for example, various information such as resumes and job history documents).
Further, the acquisition unit 204 acquires information on job seekers and recruiters from answers to questions. Note that, for example, the acquisition unit 204 may also acquire information about the website of the URL of the linked website of the accessed website.
Furthermore, the information acquired by the acquisition unit 204 includes information that specifies job seekers and recruiters. Information that identifies job seekers and job seekers includes, for example, information such as identification names (handle names), identification numbers, email addresses, and names used by blogs, homepages, SNS, etc. to identify job seekers. .

The analysis unit 205 analyzes the information acquired by the acquisition unit 204. When the information acquired by the acquisition unit 204 is image data (including video data), the analysis unit 205 extracts text data included in the image data by image processing (known optical character recognition (OCR)). recognition) technology, etc. may be used). Further, when the information acquired by the acquisition unit 204 is voice data, the analysis unit 205 converts the voice data into text data (known voice recognition technology or the like may be used).
The analysis unit 205 performs processing such as morphological analysis on the text data acquired by the acquisition unit 204, text data extracted from image data by OCR etc., text data converted from audio data, etc., and obtains the acquired information. Break down into words. Here, a word may be a word consisting of a single morpheme, such as "technology" and "programming," or a word consisting of multiple consecutive morphemes, such as "technology development" and "C programming". It may also be a compound word consisting of.

The first classification unit 206 classifies the information analyzed by the analysis unit 205 into job seekers and job seekers based on information that specifies job seekers and job seekers. In other words, the first classification unit 206 specifies which job applicant and job offerer the information analyzed by the analysis unit 205 relates to, and associates the information with the specified job applicant and job offerer. The first classification unit 206 processes all of the information analyzed by the analysis unit 205.

For example, the extraction unit 207 extracts job applicant and job offerer entities from job applicant and job offerer information. For example, the extraction unit 207 refers to the dictionary DB6 of the storage device 200B, and extracts words or compound words included in the job applicant and job offerer information based on the entity to be extracted stored in the dictionary DB6, Based on the entities stored in the dictionary DB 6 that are to be non-extracted, words or compound words included in the job seeker and job offerer information are not extracted.
In addition, when entities to be extracted or not extracted are stored in the dictionary DB 6 in the form of a vector representation, the degree of similarity (Euclidean distance, Pearson's product moment correlation coefficient, Jaccard coefficient, etc.) with the entities to be extracted or not extracted is stored in the form of a vector representation. , a known method may be used) to extract or non-extract words or compound words included in the information of job seekers and recruiters.
In addition, when entities to be extracted or not extracted are stored in the dictionary DB 6 in the form of learned parameters, words or compound words included in job applicant and job offerer information are Extraction or non-extraction.
Note that instead of not extracting words or compound words included in the information on job seekers and recruiters, the second classification unit 208 refers to the storage unit in which entities that are not to be classified are stored, and the extraction unit 207 The configuration may be such that the extracted job seeker or job offerer entity is not classified. Further, the dictionary DB 6 of the storage device 200B that stores entities to be displayed or hidden may be referred to, and the entity of the job seeker or job offerer extracted by the extraction unit 207 may be displayed or hidden.

The second classification unit 208 classifies the entities extracted by the extraction unit 207 (associates them with categories).
The second classification unit 208 may, for example, classify the entity extracted by the extraction unit 207 (associate it with a category) with reference to a dictionary that associates entities with categories. Note that the second classification unit 208 performs horizontal category classification (major classification) and vertical category classification (medium classification) for entities. The major classification and medium classification will be explained with reference to FIG.
Further, the second classification unit 208 may classify entities (associate them with categories) based on the distance between the vector representation of the entity (such as Word2vec) and the vector representation of the category, for example. In this case, the entity is classified into the category with the smallest distance.
As a result, entities can be correctly classified into categories without the need to prepare a dictionary that associates entities and categories in advance.
Further, the second classification unit 208 may classify entities (associate them with categories) based on a machine learning model, for example. In this case, a machine learning model is trained in advance using learning data in which vector representations of entities are input and categories to be classified are output. The second classification unit 208 classifies entities into categories based on the estimation results of the trained model.
Note that existing methods such as neural networks and logistic regression can be used as the machine learning model.
Further, the learning data used here may be data edited by a job seeker or job offerer by operating an input device 300C or an input device 400C, which will be described later. Specifically, when a job seeker or recruiter moves an entity from one category to another, the source category is set as a category in which the entity should not be classified (negative example), and the destination category is changed. It may be used in learning data as a category (positive example) into which the entity should be classified. Alternatively, the estimation results of the learned model may be registered in a dictionary in which the aforementioned entities and categories are associated with each other.
Further, the second classification unit 208 may classify the entities by, for example, clustering. In this case, the features used for clustering include, for example, the vector representation of the entity, the work history from which the entity is extracted (start/end dates, company name, position name, etc.), character type (hiragana, kanji, katakana, English characters, etc.), word length, word genre (technical or business-oriented, etc.), word granularity (abstraction level), creation date and time of the entity, etc. may be used.
As a clustering algorithm, for example, an existing clustering algorithm such as k-means, which sorts by feature amount and divides into N clusters (N is a natural number) in descending order, may be used. In this case, each cluster may be automatically given a name that has a similar meaning common to the entities belonging to the cluster (for example, the distance in the vector representation of the entities is close), or it may be an anonymous category.
Further, as the clustering algorithm, a clustering algorithm that generates a hierarchical structure such as hierarchical cluster analysis may be used. In this case, the hierarchical structure of the clusters may be associated with the category classification, such as setting the cluster at the highest level as a large category and the cluster at the second level as a medium category. Note that the correspondence between the hierarchical structure and the category classification is arbitrary, and the category classification is not limited to the two hierarchies of major classification and medium classification.

The presentation information generation unit 209 (acquisition source presentation unit) generates information that presents the acquisition source of the entity, that is, where and how the entity was extracted (for example, what line in the resume, which What page and line of the website it is on, whether it was extracted from information automatically obtained by crawling the website, or whether it was extracted from information entered by the job seeker or recruiter such as a work history, etc. In addition, in the case of information automatically obtained by crawling a Web site, information such as which Web site the information was obtained from is generated.
Further, the presentation information generation unit 209 (entity presentation unit) generates information for presenting missing entities to job seekers. For example, the presentation information generation unit 209 compares entities that are often requested in job information and entities of job seekers, and generates information that presents entities that job seekers do not have among entities that are often requested in job information. .
Note that the number of job information in which a certain arbitrary entity is listed may be aggregated, and if the aggregated value is greater than or equal to a predetermined number, it may be determined that the entity is frequently sought in job information, or all job information may be If the percentage of job information in which an arbitrary entity is described is a predetermined number or more, it may be determined that the entity is frequently sought in job information.
Alternatively, the number of job information in which an arbitrary entity is described for each job type may be aggregated, and if the aggregated value is a predetermined number or more, it may be determined that the entity is frequently sought in job information. If the proportion of job information in which an arbitrary entity is described among all job information for each job category is a predetermined number or more, it may be determined that the entity is frequently sought in job information.

The attribute assigning unit 210 assigns attributes to at least one of the job seeker and job offerer entities extracted by the extracting unit 207 in accordance with at least one of job demand and job search demand. The attribute assigning unit 210 assigns attributes such as high demand and low demand to an entity.
The level of demand can be determined by, for example, summing up the number of job information or job search information in which a certain arbitrary entity is listed, and if the total value is greater than or equal to a predetermined number, the entity is often sought after in job information or job search information. Alternatively, if the proportion of job information or job search information in which an arbitrary entity is listed among all job information is greater than or equal to a predetermined number, it is determined that the entity is frequently sought in job information or job search information. It may be determined that there is.
In addition, the number of job information or job search information in which an arbitrary entity is listed for each job type is totaled, and if the total value is a predetermined number or more, it is determined that the entity is frequently sought after in job information or job search information. Alternatively, if the proportion of job information or job search information in which an arbitrary entity is listed among all job information for each job category is a predetermined number or more, the entity is often sought in job information or job search information. It may be determined that
The attributes assigned by the attribute assignment unit 210 are used to display the entity, and are displayed in different ways (for example, text thickness, color, background color, display change, etc.) depending on the assigned attributes.

The question extracting unit 211 refers to the question DB 4 of the storage device 200B that stores a plurality of questions to at least one of job seekers and job seekers, and asks questions according to the entity of at least one of job seekers and job seekers extracted by the extraction unit 207. , extract questions for at least one of the job seeker and the recruiter.
For example, the question extraction unit 211 cannot create an entity map (described later) or documents (e.g., various documents necessary for job search and recruitment, such as resumes, job history, job information, etc.) using only the entities extracted by the extraction unit 207. When there is a shortage of entities necessary for the acquisition, the question DB 4 in the storage device 200B is referred to and questions necessary for acquiring the missing entities are extracted. The question extracted by the question extraction unit 211 is transmitted to the job applicant terminal 3 or the job offerer terminal 4 by the transmission unit 202. Answers to the questions are transmitted from the job seeker terminal 3 or the recruiter terminal 4. The answer sent from the job applicant terminal 3 or the job offerer terminal 4 is received by the receiving unit 201 of the server 2 . For example, questions such as ``Where in your career did you experience the new entity ``C++''? '', ``If you want to write ``programming language'' such as ``C++'' on your resume, write it like this.'' In this example, by inserting existing entities and categories into the "C++" and "programming language" sections, it is possible to extract questions needed to obtain missing entities for various entities.

The level assigning unit 212 assigns a level to the entity extracted by the extracting unit 207 according to at least one of the appearance frequency in the job applicant information acquired by the acquiring unit 204 and the experience value of the job applicant.
For example, the level assigning unit 212 assigns a higher level to an entity as the frequency of appearance is higher in the job applicant information acquired by the acquiring unit 204, and a lower level as the frequency of appearance is lower.
Further, the level assigning unit 212 assigns a higher level to the entity as the experience value in the job seeker information acquired by the acquiring unit 204 is higher, and assigns a lower level to the entity as the experience value decreases, for example. Here, the experience value includes, for example, the job seeker's length of experience (the longer the experience, the higher the experience value, and the shorter the experience, the lower the experience value), position (position (for example, manager > section manager > chief, senior The higher the rank (Fellow > Fellow, etc.), the higher the experience value, and the lower the position, the lower the experience value).

The map data generation unit 213 generates entity map display data as illustrated in FIG. 7, which will be described later. Note that in the following explanation, the entity map is also simply referred to as a map.
The map data generation unit 213 generates categories of entities classified by the second classification unit 208, attributes assigned to the entities by the attribute assignment unit 210, levels assigned to the entities by the level assignment unit 212, classification results by the second classification unit 208, etc. Based on this, the extraction unit 207 generates a map of the extracted entities.
The map data generation unit 213 creates a tree structure by, for example, associating the entities extracted by the extraction unit 207 based on the classification results by the second classification unit 208.
As a result, a tree structure in which entities are hierarchized by category based on the classification by the second classification section is generated.
Note that a configuration may be adopted in which a plurality of tree construction methods are prepared and can be switched by a job seeker or a recruiter by operating the job seeker terminal 3 or the recruiter terminal 4. For example, the feature quantities used for machine learning or clustering in the second classification unit 208 may be switchable.
Similarly, when using classification, a plurality of classifiers may be prepared, and the job seeker or recruiter may operate the job seeker terminal 3 or the recruiter terminal 4 to switch between them.
Furthermore, regarding the method of arranging the nodes, an existing algorithm such as Compound Spring Embedder (CoSE) may be used to spread out the nodes neatly, in other words, to make it easier to grasp the overall picture.
Furthermore, in order to display the nodes so that they spread out neatly, the following methods may be used in combination.
(1) From a random initial arrangement, determine the repulsion and attraction between nodes and arrange them by physical simulation.
(2) Decide the initial arrangement so that the entity is displayed in the same place every time.
(3) Determine the initial arrangement by sorting the entities based on their feature amounts and arranging them in a predetermined order (for example, clockwise).
(4) The order in which the user placed the items last time is memorized, and the next time they are displayed, the order in which they were placed is the same as the previous order (as long as no contradiction occurs).
In addition, the user may perform processing such as freely arranging nodes or storing node positions in XY coordinates.
In addition to the company and employee maps, the recruiter's map can be created by merging multiple people's maps from the employee map to create a team map, or by creating a map from the union of multiple people's entities. You can.

The matching degree calculation unit 214 calculates the matching degree between the job applicant and job offerer entities extracted by the extraction unit 207. Note that a known method can be used to calculate the degree of matching. For example, Euclidean distance, Pearson's product moment correlation coefficient, Jaccard coefficient, etc. can be used. Alternatively, the degree of matching may be calculated using the number of matching entities or the feature amount of an existing graph. In particular, nodes that the user emphasizes as "things they want to do" may be given a higher weight when calculating the degree of matching.

The recommendation unit 215 recommends job seekers to job seekers according to the degree of matching calculated by the degree of matching calculation unit 214. For example, the recommendation unit 215 recommends job seekers whose degree of matching is equal to or higher than a predetermined value to job seekers. Note that if there are many job seekers whose degree of match is greater than or equal to a predetermined value, a predetermined number of job seekers may be recommended to job seekers in descending order of degree of match.
Further, the recommendation unit 215 recommends job seekers to job seekers according to the degree of matching calculated by the degree of matching calculation unit 214. For example, the recommendation unit 215 recommends job seekers whose degree of matching is equal to or higher than a predetermined value to the recruiter. Note that if there are many job seekers whose degree of match is equal to or higher than a predetermined value, a predetermined number of job seekers with a higher degree of match may be recommended to the employer. Further, the recommendation unit 215 may recommend job seekers who are candidates from the missing entities.

For example, the job information generation unit 216 refers to the template DB 5 of the storage device 200B in which job information templates are stored, and transmits the job information to the job applicant based on the entity and job applicant information received by the reception unit 201. Generate job information (job postings, scout emails, interest notifications, etc.). The job information generation unit 216 generates job information by inserting the entity extracted by the extraction unit 207 into the job information template stored in the template DB 5 of the storage device 200B, for example. In this case, a structure may be adopted in which a sentence is generated by selecting where in the template to insert the extracted entity. Additionally, job information may be generated from newly added entities. Initially, a map is automatically generated from job information, and when the map is manually modified, the corrections are fed back to the job information and a modification proposal is made. It may also be configured to be applied upon approval.
In this way, the job information generation unit 216 can create job information suitable for the job seeker to whom job information is to be sent, by generating job information based on the entity of the job seeker, for example. Further, by generating job information based on the entity of the job offerer, for example, job information suitable for the job offerer who sends the job information can be generated.
Further, the job information generation unit 216 may generate job information based on the entities of both job seekers and job seekers.

The job applicant's resume generation unit 217 generates at least a portion of the job applicant's resume based on the job applicant's entity. For example, the resume generation unit 217 refers to the template DB 5 of the storage device 200B in which templates of resumes are stored, and generates information about the job applicant based on the entity and job applicant information received by the reception unit 201. Generate a resume. The resume generation unit 217 generates a resume by inserting the entity extracted by the extraction unit 207 into the template of the resume stored in the template DB 5 of the storage device 200B, for example. In this case, a configuration may be adopted in which a sentence is added by selecting where in the template the added entity should be placed. Further, the work history may be generated from a newly added entity, and the map is automatically generated from the work history for the first time, and when the map is manually corrected, the correction is fed back to the work history, It may also be configured to be applied when the proposed amendment is approved.

(Job applicant terminal 3)
FIG. 5 is a configuration diagram of the job applicant terminal 3. The job applicant terminal 3 is, for example, a desktop PC, a notebook PC, or the like, but may also be a smartphone, a tablet terminal, or the like. FIG. 5 shows the main hardware configuration of the job applicant terminal 3, which includes a communication IF 300A, a storage device 300B, an input device 300C, a display device 300D, and a CPU 300E connected via a bus (BUS) or the like.

Communication IF 300A is an interface for communicating with other devices (for example, server 2, etc.).

The storage device 300B is, for example, an HDD or a semiconductor storage device. The storage device 300B stores information processing programs and the like. Furthermore, an identifier (job applicant terminal ID) for identifying the job applicant terminal 3 is stored in the storage device 300B. By assigning the job applicant terminal ID to the information transmitted from the job applicant terminal 3, the server 2 can recognize which job applicant terminal 3 the received information has been transmitted from.
Note that the ID may be an IP (Internet Protocol) address, a MAC (Media Access Control) address, or the like, and may be assigned by the server 2 to the job applicant terminal 3.

The input device 300C is, for example, a keyboard, a mouse, a touch panel, etc., and the job seeker can input information by operating the input device 300C.

The display device 300D is, for example, a liquid crystal monitor or an organic EL monitor. The display device 300D displays screens necessary for using the information processing system 1.

The CPU 300E controls the job applicant terminal 3 and includes a ROM and RAM (not shown).

FIG. 6 is a functional block diagram of the job applicant terminal 3. As shown in FIG. 6, the job applicant terminal 3 has functions such as an input reception section 301, a display device control section 302, a transmission section 303, a reception section 304, and a storage device control section 305. Note that the functions shown in FIG. 6 are realized by the CPU 300E executing an information processing program stored in the ROM (not shown) of the job applicant terminal 3.

The input receiving unit 301 receives, for example, information input using the input device 300C.

The display device control unit 302 controls the display device 300D. The display device control unit 302 causes the display device 300D to display, for example, screens shown in FIGS. 7 to 9, which will be described later.

The transmitter 303 transmits, for example, information accepted by the input receiver 301 to the server 2.

The receiving unit 304 receives, for example, information transmitted from the server 2.

The storage device control unit 305 controls the storage device 300B. The storage device control unit 305 controls the storage device 300B to write and read information, for example.

(Recruiter terminal 4)
The job applicant terminal 4 has the same configuration as the job applicant terminal 3 described with reference to FIGS. 5 and 6, so a duplicate explanation will be omitted.

(Screen displayed on job applicant terminal 3 or recruiter terminal 4)
7 to 9 are examples of screens displayed on the display device 300D of the job applicant terminal 3 or the display device 400D of the recruiter terminal 4. The screens displayed on the job seeker terminal 3 or the recruiter terminal 4 (hereinafter, the screens displayed on the job seeker terminal 3 or the recruiter terminal 4 are also simply referred to as screens) will be explained with reference to FIGS. 7 to 9. do.

FIG. 7 is a diagram showing an example of a map displayed on the screen. As shown in FIG. 7, the entities extracted by the extraction unit 207 are displayed in a map format that spreads radially from the root node N1. Here, the root node N1 represents a large category, the intermediate node N2 represents a medium category, and the terminal node N3 represents an entity. Further, in the example shown in FIG. 7, the root node N1 is classified into four categories, and the entity extracted by the extraction unit 207 is connected to the root node N1 or intermediate node N2 depending on the category via the connector L. . Here, classifying entities into the four root node N1 is called horizontal classification (major classification), and further classifying the majorly classified entities into intermediate nodes is called vertical classification (medium classification). .

In the example shown in FIG. 7, the nodes are displayed smaller as they get farther from the root node N1. In other words, the lower the node is in the hierarchy, the smaller the node is displayed. This is because the lower the hierarchy, the greater the number of nodes, making it easier to grasp the overall picture. Although there are three layers in FIG. 7, there may be any number of layers as long as there are multiple layers. In FIG. 7, the categories of the root node are four: business, technology, role/involvement, and organization/environment, but they are not limited to four and can be arbitrary. Furthermore, the category of the root node is arbitrary and is not limited to business, technology, role/interaction, organization/environment.
Further, although not shown in FIG. 7, each entity is displayed in a different display mode (for example, color and size) depending on the assigned level, attribute, classification, and the like. Furthermore, the display mode (color and size) of the entity may be changed depending on the statistical information.
For example, the entity may be displayed larger or in a different color as the demand for the following increases.
(1) Job demand (popular skills, experience, etc.)
(2) Appears often in job offers (3) Often seen by people to whom scouts are sent (4) Often referred to by scouts when sending scouts (5) Frequently viewed or viewed by recruiters or job seekers Clicked (6) Many job seekers or job seekers have (popular) or rare (7) The job seeker or job seeker is identified by a feature value such as TF-IDF is a distinctive entity

FIG. 8 is a diagram illustrating an example of a node replacement operation. A job applicant or a recruiter can edit an entity by operating the input device 300C or the input device 400C. In the example shown in FIG. 8, select the entity P for which you want to replace the node (see FIG. 8(a)), drag it from the replacement source to the replacement destination (see FIG. 8(b)), and drag the entity P to the replacement destination. The node can be replaced by dropping it with (see FIG. 8(c)).
In addition, in this embodiment, the job seeker or recruiter operates the input device 300C or the input device 400C to change the text content of the entity (he or she may be able to freely edit the text, or change the text content included in the dictionary). You may want to be able to select from among the existing words), add a new entity, or delete an entity (for example, you may be able to delete an entity by dragging it away from other nodes. ), etc. Furthermore, the configuration may be configured such that when the entity is deleted, feedback is given that the entity is inappropriate (the user can select why the entity is inappropriate, etc.).
Furthermore, the display device 300D or the display device 400D may recommend an entity that has been deleted by many job seekers or job seekers as an entity that job seekers or job seekers should delete.
Further, the display device 300D or the display device 400D may recommend entities that the job seeker or recruiter should add.
In this case, for example, entities similar to a certain entity may be stored in the dictionary DB 6 in advance to recommend the entity, or entities held by similar job seekers or recruiters may be recommended (for example, existing algorithm), or distance (e.g., Euclidean distance, Pearson's product-moment correlation coefficient, Jaccard You can recommend words that are close to each other (you may use coefficients, etc.), or you can recommend words that are similar to others (for example, colleagues, job seekers who have interviewed job seekers, or job seekers who have interviewed job seekers). An entity recommended by a person (such as a person) using the input device 300C or the input device 400C may be recommended.
Furthermore, the display device 300D or the display device 400D may be configured to recommend movement of an entity that is frequently moved.

In addition, the input device 300C or the input device 400C may be able to edit the display mode (for example, font size, bold font, node size, node shape, etc.) of an entity (for example, an entity related to what you want to do). good. Further, the configuration may be such that the thickness and length of connectors between entities can be edited. Furthermore, the configuration may be such that the strength of the relationship can be edited. In addition, as an editing function, entities can be provided with supplementary information (for example, text, images, URLs, etc.), emotional information (for example, "recommended," "desired," "required," "confident," etc.) and recommendation levels ("recommendation level," etc.). The configuration may be such that a numeric value) can be added.

Note that entities may be displayed in a tag format as shown in FIG. 9 instead of the map structure shown in FIG. 7. This is because although the map illustrated in FIG. 7 has excellent visibility, the tag formation illustrated in FIG. 9 is easier to see when comparing entities for each category.
In the screen illustrated in FIG. 9, entities F111, F121, F131, and F141 classified according to each category F110, F120, F130, and F140 are displayed.
Note that, similar to FIG. 7, the categories are not limited to the four categories of business characteristics, industry/industry type, phase, and business, but are arbitrary. Further, each entity is displayed in a different display mode (for example, color or size) depending on the level, attribute, classification, etc. assigned to it. Furthermore, the display mode (color and size) of the entity may be changed depending on the statistical information.

(Operation of information processing system 1)
10 to 15 are flowcharts showing an example of information processing by the information processing system 1. The processing of the information processing system 1 according to this embodiment will be described below with reference to FIGS. 10 to 15.

(Map display processing)
FIG. 10 is a flowchart illustrating an example of map display processing. The map display process will be described below with reference to FIG.

(Step S101)
The acquisition unit 204 of the server 2 acquires information on job seekers and job seekers from a website and information input by job seekers and job seekers (for example, various information such as resumes and work histories).

(Step S102)
The analysis unit 205 of the server 2 analyzes the information acquired by the acquisition unit 204. Note that the details of the analysis by the analysis unit 205 have already been explained, so a redundant explanation will be omitted.

(Step S103)
The first classification unit 206 classifies the information analyzed by the analysis unit 205 into job seekers and job seekers based on information that specifies job seekers and job seekers.

(Step S104)
The extraction unit 207 of the server 2 extracts entities of job seekers and recruiters from the information of job seekers and recruiters. At this time, the extraction unit 207, for example, refers to the dictionary DB6 of the storage device 200B and extracts words or compound words included in the job applicant and job offerer information based on the entities to be extracted stored in the dictionary DB6. Words or compound words included in the job seeker and job offerer information are not extracted based on the entities that are extracted and are not extracted and stored in the dictionary DB 6.

(Step S105)
The question extraction unit 211 of the server 2 executes question processing. Details of the question processing by the question extraction unit 211 will be described later.

(Step S106)
The second classification unit 208 of the server 2 classifies (categorizes) the entities extracted by the extraction unit 207. The second classification unit 208 may classify (categorize) the entities extracted by the extraction unit 207, for example, with reference to a dictionary that associates entities with categories.

(Step S107)
The attribute assigning unit 210 of the server 2 assigns attributes to at least one of the job seeker and recruiter entities extracted by the extracting unit 207 in accordance with at least one of the job demand and the job search demand. Note that the details of the attribute assignment by the attribute assigning unit 210 have already been explained, so a redundant explanation will be omitted.

(Step S108)
The level assigning unit 212 of the server 2 assigns a level to the entity extracted by the extracting unit 207 according to at least one of the appearance frequency in the job applicant information acquired by the acquiring unit 204 and the experience value of the job applicant. Note that the details of level assignment by the level assignment unit 212 have already been explained, so a redundant explanation will be omitted.

(Step S109)
The storage device control unit 203 (history registration unit) of the server 2 stores the entities extracted by the extraction unit 207, the classification results by the second classification unit 208, the attributes assigned by the attribute assignment unit 210, and the levels assigned by the level assignment unit 212. is stored in the job applicant DB2 or job offerer DB3 of the storage device 200B in association with the date and time.

(Step S110)
The map data generation unit 213 of the server 2 generates entity map display data as illustrated in FIG. Note that the details of map generation by the map data generation unit 213 have already been explained, so redundant explanation will be omitted. Note that display data in a tag format as shown in FIG. 9 may be generated.

(Step S111)
The transmitter 202 of the server 2 transmits the entity map display data generated by the map data generator 213 to at least one of the job applicant terminal 3 and the recruiter terminal 4.

Note that in the description of FIG. 10 above, the order of steps S106 to S108 may be changed.

(Question processing)
FIG. 11 is a flowchart showing an example of question processing. The question processing will be explained below with reference to FIG.

(Step S201)
The question extraction unit 211 of the server 2 determines whether the entities extracted by the extraction unit 207 are insufficient for creating a map. If there is a shortage (YES), the server 2 executes the process of step S202. If there is no shortage (NO), the server 2 ends the process.

(Step S202)
The question extraction unit 211 of the server 2 refers to the question DB 4 in the storage device 200B and extracts questions necessary to obtain missing entities. The question extracted by the question extraction unit 211 is transmitted to the job applicant terminal 3 or the job offerer terminal 4 by the transmission unit 202.

(Step S203)
The acquisition unit 204 of the server 2 determines whether an answer to the question has been received from the job applicant terminal 3 or the recruiter terminal 4. If a reply has been received, the acquisition unit 204 acquires the reply.

(editing process)
FIG. 12 is a flowchart illustrating an example of editing processing. The editing process will be described below with reference to FIG.

(Step S301)
The receiving unit 201 of the server 2 determines whether an entity editing operation has been received from the job applicant terminal 3 or the recruiter terminal 4. If an editing operation has been received (YES), the server 2 executes the process of step S302. If no editing operation has been received (NO), the server 2 ends the process.

(Step S302)
The server 2 reflects the received edited content. The storage device control unit 203 stores the received edited content in the job applicant DB2 or job offerer DB3 of the storage device 200B.

(Document generation process)
FIG. 13 is a flowchart illustrating an example of document generation processing. The document generation process will be described below with reference to FIG. Note that although the generation of a work history will be described below, the flow of generation processing for other documents (for example, job information) is substantially the same, so redundant explanation will be omitted.

(Step S401)
The resume generation unit 217 of the server 2 inserts the entity extracted by the extraction unit 207 into the template of the resume stored in the template DB 5 of the storage device 200B.

(Step S402)
The question extraction unit 211 of the server 2 determines whether or not the entities extracted by the extraction unit 207 are insufficient for creating the job history. If there is a shortage (YES), the server 2 executes the process of step S403. If there is no shortage (NO), the server 2 executes the process of step S406.

(Step S403)
The question extraction unit 211 of the server 2 refers to the question DB 4 in the storage device 200B and extracts questions necessary to obtain missing entities. The question extracted by the question extraction unit 211 is transmitted to the job applicant terminal 3 by the transmission unit 202.

(Step S404)
The acquisition unit 204 of the server 2 determines whether an answer to the question has been received from the job applicant terminal 3. If a reply has been received, the acquisition unit 204 acquires the reply.

(Step S405)
The extraction unit 207 of the server 2 extracts entities from the answers. The resume generation unit 217 inserts the entity extracted from the answer into the template of the resume.

(Step S406)
The transmitter 202 of the server 2 transmits the resume generated by the resume generator 217 to the job applicant terminal 3.

(Recommended processing)
FIG. 14 is a flowchart illustrating an example of recommendation processing. The recommendation process will be described below with reference to FIG.

(Step S501)
The match calculation unit 214 of the server 2 calculates the match between the job applicant and job offerer entities extracted by the extraction unit 207. Note that the details of the matching degree calculation by the matching degree calculation unit 214 have already been explained, so a redundant explanation will be omitted.

(Step S503)
The recommendation unit 215 of the server 2 recommends job seekers to job seekers according to the degree of matching calculated by the degree of matching calculation unit 214. For example, the recommendation unit 215 recommends job seekers whose degree of matching is equal to or higher than a predetermined value to job seekers. Further, the recommendation unit 215 recommends job seekers to job seekers according to the degree of matching calculated by the degree of matching calculation unit 214.

(Missing entity presentation process)
FIG. 15 is a flowchart illustrating an example of the missing entity presentation process. The missing entity presentation process will be described below with reference to FIG.

(Step S601)
The presentation information generation unit 209 (entity presentation unit) of the server 2 acquires information regarding the future image of the job applicant.

(Step S602)
The presentation information generation unit 209 of the server 2 acquires entities necessary for the future image of the job applicant. For example, the presentation information generation unit 209 acquires entities (maps) owned by other job seekers who are the same as or similar to the person they want to become in the future.

(Step S603)
The presentation information generation unit 209 of the server 2 obtains the current entity of the job applicant.

(Step S604)
The presentation information generation unit 209 of the server 2 compares the job applicant's current entity with the entity necessary for the future image.

(Step S605)
As a result of the comparison, the presentation information generating unit 209 of the server 2 instructs the transmitting unit 202 to transmit to the job applicant terminal 3 an entity that is not present in the job applicant's current entity and is necessary for the future image as a missing entity. The transmitter 202 transmits the missing entities to the job applicant terminal 3 based on the instruction.

As described above, the server 2 according to the present embodiment includes an acquisition unit 204 that acquires information on at least one of a job applicant and a job offeror, and an acquisition unit 204 that acquires information on at least one of a job applicant and a job offeror, and an acquisition unit 204 that acquires information on at least one of a job applicant and a job offerer, and a It includes an extraction unit 207 that extracts one entity, and a second classification unit 208 that classifies into a predetermined category at least one of the entities of job seekers and job offers extracted by the extraction unit 207.
In this way, the entities of at least one of job seekers and recruiters can be categorized, and job seekers can effectively communicate their requests to recruiters.

Furthermore, the server 2 according to the present embodiment includes a presentation information generation unit 209 (acquisition source presentation unit) that generates information presenting an acquisition source of an entity.
This is highly convenient because the entity acquisition source can be presented in this way.

The server 2 according to the present embodiment also includes an attribute assignment unit 210 that assigns an attribute to at least one of the job seeker and job offerer entities extracted by the extraction unit 207 in accordance with at least one of job demand and job search demand. .
Since attributes can be assigned to entities in this way, it is possible to check what kind of entity (attributes) the entity is, which is highly convenient.

Further, the server 2 according to the present embodiment includes a storage device control unit 203 (history storage unit) that stores entities extracted by the extraction unit 207 or classification results by the second classification unit 208 in association with date and time.
Since the extracted entities and classification results are stored in the storage device, it is possible to generate an entity map at any point in the past, which is convenient as it allows comparison with the current situation and confirmation of changes. Highly sexual.

In addition, the acquisition unit 204 of the server 2 according to the present embodiment acquires at least one of the job applicant and the job offerer from at least one of text data, audio data, and image data having descriptions regarding at least one of the job applicant and the job offeror. Get information.
Since information is acquired from text data, audio data, image data, etc. in this way, it is possible to acquire a variety of information regarding job seekers and recruiters.

Further, the server 2 according to the present embodiment refers to a storage unit that stores a plurality of questions to at least one of a job applicant and a job offerer, and responds to the entity of at least one of a job applicant and a job offerer extracted by the extraction unit 207. The acquisition unit 204 includes an extraction unit 207 that extracts questions for at least one of a job applicant and a job offerer, and a reception unit 201 that receives answers to the questions extracted by the extraction unit 207. and information on at least one of the job seeker.
When there is missing information in this way, the missing information can be obtained by asking questions, which is highly convenient.

Further, the server 2 according to the present embodiment assigns a level to the entity extracted by the extraction unit 207 according to at least one of the appearance frequency in the job applicant information acquired by the acquisition unit 204 and the experience value of the job applicant. A leveling section 212 is provided.
Since levels are assigned to entities in this way, it is highly convenient because it is possible to check the level of an entity.

Further, the extraction unit 207 of the server according to the present embodiment refers to the storage device 200B (storage unit) in which extracted or non-extracted entities are stored, and extracts the job applicant or Extract or non-extract the recruiter entity.
In this way, a predetermined entity can be non-extracted or extracted, which is highly convenient.

Further, the second classification unit 208 of the server 2 according to the present embodiment refers to the storage device 200B (storage unit) in which entities that are not to be classified is stored, and refers to the job seeker or job offerer entity extracted by the extraction unit 207. No classification is performed.
In this way, predetermined entities can be classified, which is highly convenient.

Further, the server 2 according to the present embodiment refers to the storage device 200B (storage unit) in which entities to be displayed or hidden are stored, and displays or hides the job applicant or job offerer entity extracted by the extraction unit 207. be displayed.
In this way, it is possible to hide a predetermined entity, which is highly convenient.
Note that the display device control section 302 or the display device control section 402 in the job applicant terminal 3 or the job offerer terminal 4 may be configured to hide a predetermined entity.

The server 2 according to the present embodiment also accepts editing of entity classification or attribute assignment to entities.
In this way, entities can be edited, which is highly convenient.

The server 2 also includes a match calculation unit 214 that calculates the match between the job seeker and job offerer entities extracted by the extraction unit 207 of the server 2 according to this embodiment.
In this way, it is possible to calculate the degree of matching between the entities of job seekers and recruiters, which is highly convenient for use in matching.

Further, the server 2 includes a recommendation unit 215 that recommends a job seeker to a job seeker or recommends a job seeker to a job seeker according to the degree of coincidence calculated by the degree of coincidence calculation unit 214 of the server 2 according to the present embodiment.
In this way, recommendations are made depending on the degree of matching between the job seeker and job offer entities, which is highly convenient.

The server 2 according to the present embodiment also includes a receiving unit 201 that receives a selection of a job seeker's entity by a job seeker, and a transmitter that specifies the entity received by the receiving unit 201 and sends job seeker information to the job seeker. 202.
In this way, it is possible to specify an entity and send job applicant information to job seekers, which is highly convenient.

Further, the server 2 according to the present embodiment refers to the storage device 200B (storage unit) in which templates of job information are stored for each entity, and based on the entity and job applicant information received by the receiving unit 201, It includes a job information generation unit 216 that generates job information to be sent to job seekers.
In this way, it is possible to specify an entity and send job applicant information to job seekers, which is highly convenient.

The server 2 according to the present embodiment also includes a resume generation unit 217 that generates at least a portion of a job applicant's resume based on the entity of the job applicant.
In this way, at least a portion of the job history can be generated based on the entity of the job applicant, which is highly convenient.

Further, the career history generation unit 217 of the server 2 according to the present embodiment inserts the job applicant's entity into a predetermined template to generate the job seeker's career history.
In this way, a job history is generated by inserting the job applicant entity into the template.

The server 2 according to the present embodiment also includes an extraction unit 207 that refers to a storage device 200B (storage unit) that stores a plurality of questions for job applicants, and extracts questions for job applicants, and questions extracted by the extraction unit 207. The job seeker's resume generation section 217 generates a job seeker's resume from the answers to the questions.
In this way, it is possible to generate a work history from the answers to the questions, which is highly convenient.

Further, the server 2 according to the present embodiment includes a presentation information generation unit 209 (entity presentation unit) that presents missing entities to job seekers, and an acquisition unit 204 that provides information regarding the future image or ideal image of the job seeker. The presentation information generation unit 209 (entity presentation unit) presents entities necessary for the future image or ideal image based on the job applicant entities extracted by the extraction unit 207.
In this way, entities necessary for a future image or an ideal image can be presented, which is highly convenient.

The server 2 according to the present embodiment also includes a map data generation unit 213 (display data generation unit) that generates information for displaying entities classified into categories based on the classification results by the second classification unit 208. ).
Since the entities are displayed classified into categories in this way, it is possible to provide an entity map with high visibility and easy viewing.

Further, the second classification unit 208 of the server 2 according to the present embodiment classifies entities into a plurality of categories, and further classifies the entities classified into the plurality of categories for each category.
In this way, entities are broadly classified into categories, and the broadly classified entities are further subdivided into categories, so it is possible to provide an entity map with higher visibility and ease of viewing.

The map data generation unit 213 (display data generation unit) of the server 2 according to the present embodiment also displays entities that are further classified into categories and arranged radially for each node with the category as the root node. Generate information to
Since the entities are displayed in a radial arrangement for each node, it is possible to provide an entity map with higher visibility and easier viewing.

Furthermore, the map data generation unit 213 (display data generation unit) of the server 2 according to the present embodiment generates information to be displayed in a display mode according to the level assigned to the entity.
In this way, since the entity map is displayed in a display mode according to the level assigned to the entity, it is possible to provide an entity map with higher visibility and easier viewing.

Furthermore, the map data generation unit 213 (display data generation unit) of the server 2 according to the present embodiment generates information to be displayed in a display mode according to the attribute given to the entity.
In this way, since the entity is displayed in a display mode according to the attribute given to the entity, it is possible to provide an entity map with higher visibility and easier viewing.

Furthermore, the map data generation unit 213 (display data generation unit) of the server 2 according to the present embodiment generates information to be displayed in a display mode depending on the source from which the entity is acquired.
In this way, since the entity map is displayed in a display mode depending on the acquisition source of the entity, it is possible to provide an entity map with higher visibility and easier viewing.

In the above embodiment, the recommendation level input by the input device 300C or the input device 400C, the level assigned by the level assignment unit 212, the classification result by the second classification unit 208, etc. (hereinafter, these are collectively referred to as " The degree-of-match calculation unit 214 may be configured to increase the weight of the entity when calculating the degree of matching (hereinafter referred to as "level, etc.").
Furthermore, when the recommendation unit 215 recommends a job applicant or a job offerer, it may be configured to display a matching entity with a higher (or lower) level etc. as a higher (or lower) recommendation result. .
In addition, when the job information generation unit 216 generates job search information, it places more emphasis on entities with higher levels, etc. (by increasing the selection and order of entities to be inserted into the template, increasing the weight of the text generation algorithm, etc.). may be configured.

[Modified example of embodiment]
Note that in the above embodiment, the server 2 includes an estimating unit that estimates the remuneration of the job seeker whose information the acquisition unit 204 has acquired, based on the relationship between the entity owned by the job seeker and the remuneration of the job seeker. A configuration may also be adopted in which the annual income estimated by the estimator is sent to the job applicant terminal 3. It is very convenient for job seekers because it allows them to know their own market value.
In this case, the entity owned by the job applicant and the job applicant's remuneration are stored in the storage device 200B, and by referring to the data stored in the storage device 200B, the acquisition unit 204 can identify the job applicant whose information has been acquired. , a similarity calculation unit that calculates the similarity between the job applicant stored in the storage device 200B that is different from the job applicant whose information the acquisition unit 204 has acquired, and the transmission unit 202 has a similarity calculation unit that calculates the similarity A configuration may also be adopted in which rewards for other job seekers whose calculated degree of similarity is equal to or higher than a predetermined value are transmitted. Note that the above explanation is an example of annual income estimation by the estimating unit, and the estimating unit may estimate the remuneration of a job applicant whose information is obtained by the obtaining unit 204 using other methods. .
Further, in the above embodiment, the storage device 200B of the server 2 stores an entity possessed by a job applicant in association with the job applicant's career, and the transmitting unit 202 stores the similarity calculated by the similarity calculation unit in a predetermined manner. It may also be configured to transmit the biographies of other job seekers that are greater than or equal to the value. It is very convenient because you can learn about the backgrounds of other similar job seekers.

Furthermore, in the above embodiment, the extraction unit 207 of the server 2 recommends recommended information (for example, news, SNS accounts, etc.) to the job applicant based on the job applicant's entity extracted from the job applicant's information. It may be configured to include a recommendation information recommendation section. In this case, the recommended information recommendation unit recommends information on other job seekers to the job seeker for whom the acquisition unit 204 has acquired the job seeker's information, depending on the degree of similarity with the entity held by the other job seeker. The information may be configured to be recommended as information.

Note that in the above embodiment, the map is displayed in two dimensions as illustrated in FIG. 7, but entities may be displayed in three dimensions. Furthermore, entities may be able to be operated in VR space. Furthermore, past maps may be displayed using information such as entities of job seekers and recruiters and entity classification results stored together with time stamps in the storage device 200B of the server 2. In this case, it is preferable that the job seeker or recruiter be able to specify which point in time the map is to be displayed. Further, the configuration may be such that maps at a specified point in time (for example, the present and one year ago) can be displayed for comparison. Furthermore, a configuration may be adopted in which nodes newly added from a specified time point are highlighted, or changes from the specified time point to the present are displayed as an animation. In this case, the color etc. changes depending on the time elapsed since the extraction (or the number of days elapsed from the start date or end date of the career history in the job history or resume from which it was extracted) (for example, old entities become lighter, etc.) is preferable because it makes it easier to recognize changes.

Further, in the above embodiment, a configuration may be adopted in which a new category node can be created. For example, in the input device 300C or the input device 400C, if a terminal node A is dragged close to another terminal node B, a new category node C is formed, and even in a configuration where nodes A and B are child nodes of node C, a new category node C is formed. Alternatively, the configuration may be such that node A and node B are deleted. In this case, node C may be automatically given a name that has a meaning similar to both node A and node B (for example, the word vectors are close), or node C may be given an anonymous name. good. (In this case, it becomes an (anonymous category) node that simply represents a group).

Alternatively, a configuration may be adopted in which recommended SNS accounts are presented based on the current entity. Recommended SNS accounts include, for example, people who are close to the map (past maps are fine), people the person follows, and people who often talk about technical topics that often appear on the map. is possible. In addition, it is also possible to have a structure in which an entity's ability values and credibility are endorsed by other companies, or other users can view it and receive approval from others by clicking "star" or "like" (for example, It may also be configured such that other people can give points to "skills and characteristics" (one point per person).

Furthermore, the system may be configured to search for and match job seekers or job seekers based on the map. For example, in the above embodiment, job offers and companies with a high degree of match calculated by the degree of match calculation unit 214 are displayed on a map, when an entity is clicked, job offers related to the entity are displayed, and skills that oneself lack are displayed. It may also be configured to display how the map will grow if you change jobs to a certain specific position. Further, it may be configured such that it is possible to search for people with a search entity or subcategory of job seekers, or it is possible to extract entities or map structures common to people with specific skills or experience and use them for search. Further, it may be configured such that a plurality of nodes of the map and their classification structures can be searched. For example, it may be possible to search for job seekers that have a structure in which the nodes "Library" and "Unity" are related, or such a map structure may be linked to a word such as "Game Engineer". It may be configured to search for users with this structure when searching for game engineers.

Further, when transmitting job information from a job seeker to a job seeker, a configuration may be adopted in which an entity can be specified (referenced) and job information (for example, a scout email or an interest notification) can be sent.
In this case, the configuration may be such that an entity with a high level or the like is recommended as an entity to be specifically specified (referenced).
Further, in this case, the entity from which the job information has been sent may be highlighted on the job seeker's map so that the job seeker can see which entity the job information has been sent to. Further, by clicking on an entity, the contents of the scout regarding that entity may be displayed. Furthermore, when an entity is selected from the user's map, related job information may be generated. Alternatively, the response rate may be estimated from the map and the text of the job information. Furthermore, the map of job seekers who have sent job information and the map of job seekers who have received job information may be displayed for comparison. Furthermore, a configuration may be adopted in which a checklist for an interview or an interview is generated from the map. Another possible use is to mark entities that should be mentioned in interviews and check them later. In such a case, it is preferable to have a function such as being able to extract and display only marked entities or checking a checkbox.

Further, information other than job openings and companies (for example, career paths) may be presented based on a map of job seekers or job seekers. In this case, for example, based on the current map of the user, a desired career path may be presented in the future, such as the current career path of a person whose map was similar in the past (when they were young). Further, at this time, an estimated value of annual income after following the presented career path may be presented. Further, based on the map of job seekers or recruiters, technical articles, purchasing information, event information, coupon information, etc. that match the keywords may be suggested to the entity. You may also create and send a feed of technical articles from your technical area of interest. Additionally, advertisement distribution may be performed.

Further, the server 2 may include a degree of association calculation unit that calculates the degree of association between at least one of the job seeker and job offerer entities extracted by the extraction unit 207. Note that a known method can be used to calculate the degree of association between entities. For example, Euclidean distance, Pearson's product moment correlation coefficient, Jaccard coefficient, etc. in a vector representation of an entity (existing methods such as Word2Vec can be used) can be used. Further, in this case, the relevance calculation unit may calculate the relevance from the sentence structure in the information of at least one of the job seeker and job offerer from which the entity extracted by the extraction unit 207 is extracted. In this case, the extraction unit 207 parses the sentence and, for example, assigns a degree of association to entities in a relationship, or gives a degree of association based on the positional relationship in the sentence (the closer the entity is located, the higher the degree of association is given). ), the degree of association may be calculated by performing semantic analysis and assigning a high degree of association to entities that have similar roles in terms of context. Further, the degree of association calculation unit may calculate the degree of association between entities based on the classification by the second classification unit 208. In this case, for example, a constant value (for example, 1) may be given between the entity representing the category and the entity belonging to the category, and the degree of association may be set to zero (not calculated) for other combinations. Further, the degree of association may be calculated based on the distance of the vector representation used for classification by the second classification unit 208, the likelihood in the estimation result of the machine learning model, or the like. For example, by generating entity map display data that arranges at least one of the job seeker and job offerer entities extracted by the extraction unit 207 according to the relevance calculated by the relevance calculation unit, the entity map can be made more effective. It is expected that it will be used for.

[Other embodiments]
Note that although the present embodiment and modified examples have been described above, the present invention is not limited to these examples. For example, a person skilled in the art may appropriately add, delete, or change the design of each of the embodiments and modifications described above, or may suitably combine the features of each embodiment. As long as it has the following, it is included in the scope of the present invention.

1 Information processing system 2 Server 3 Job applicant terminal 4 Recruiter terminal 5 Network 200A Communication IF
200B Storage device 200C CPU
201 Receiving section 202 Transmitting section (output section)
203 Storage device control unit (history registration unit)
204 Acquisition unit 205 Analysis unit 206 First classification unit 207 Extraction unit 208 Second classification unit 209 Presentation information generation unit (acquisition source presentation unit, entity presentation unit),
210 Attribute assignment unit 211 Question extraction unit 212 Level assignment unit 213 Map data generation unit (display data generation unit)
214 Matching degree calculation unit 215 Recommendation unit 216 Job information generation unit 217 Job resume generation unit 300A Communication IF
300B Storage device 300C Input device 300D Display device 300E CPU
301 Input reception unit 302 Display device control unit 303 Transmission unit 304 Receiving unit 305 Storage device control unit

Claims (27)

an acquisition unit that acquires information on at least one of a job applicant and a job offeror;
an extraction unit that extracts an entity of at least one of the job applicant and the job offerer from information on at least one of the job applicant and the job offeror;
a classification unit that classifies into a predetermined category at least one of the job seeker and job offerer entities extracted by the extraction unit;
An information processing device characterized by: comprising an acquisition source presentation unit that generates information presenting an acquisition source of the entity;
The information processing device according to claim 1, characterized in that: comprising an attribute assigning unit that assigns an attribute to at least one entity of the job seeker and the recruiter extracted by the extracting unit in accordance with at least one of job demand and job search demand;
The information processing device according to claim 1, characterized in that: comprising a history storage unit that stores entities extracted by the extraction unit or classification results by the classification unit in association with date and time;
The information processing device according to claim 1, characterized in that: The acquisition unit includes:
acquiring information on at least one of the job applicant and the job offerer from at least one of text data, audio data, and image data having descriptions regarding at least one of the job applicant and the job offeror;
The information processing device according to claim 1, characterized in that: With reference to a storage unit that stores a plurality of questions for at least one of the job seeker and the job offerer, the job seeker and the job offeror are asked in accordance with the entity of at least one of the job seeker and the job offerer extracted by the extraction unit. a question extraction unit that extracts questions for at least one of the job seekers;
a receiving unit that receives an answer to the question extracted by the question extracting unit,
The acquisition unit includes:
obtaining information on at least one of the job applicant and the job offerer from the answers to the questions;
The information processing device according to claim 1, characterized in that: a level assigning unit that assigns a level to the entity extracted by the extracting unit according to at least one of the appearance frequency in the job applicant information acquired by the acquiring unit and the experience value of the job applicant;
The information processing device according to claim 1, characterized in that: The extraction section is
extracting or non-extracting the entity of the job applicant or the recruiter from the information of the job applicant acquired by the acquisition unit by referring to a storage unit in which entities to be extracted or not extracted are stored;
The information processing device according to claim 1, characterized in that: The classification section is
referring to a storage unit in which entities not to be classified are stored, and not performing classification of the job applicant or job offerer entity extracted by the extraction unit;
The information processing device according to claim 1, characterized in that: The information processing device includes:
Referring to a storage unit in which entities to be displayed or hidden are stored, and displaying or hiding the entity of the job applicant or the recruiter extracted by the extraction unit;
The information processing device according to claim 1, characterized in that: accept editing of the classification of the entity or the assignment of attributes to the entity;
The information processing device according to claim 1, characterized in that: comprising a match degree calculation unit that calculates a match degree between the entities of the job applicant and the recruiter extracted by the extraction unit;
The information processing device according to claim 1, characterized in that: comprising a recommendation unit that recommends the job seeker to the job seeker or recommends the job seeker to the job seeker according to the degree of coincidence calculated by the degree of coincidence calculation unit;
13. The information processing device according to claim 12. a receiving unit that receives the job applicant's selection of the job applicant's entity;
a transmitting unit that specifies the entity received by the receiving unit and transmits job applicant information to the job applicant;
The information processing device according to claim 1, characterized in that: Job information that refers to a storage unit in which a template of the job information is stored for each entity, and generates job information to be sent to the job applicant based on information about the entity and the job applicant received by the receiving unit. comprising a generating section;
The information processing device according to claim 14. comprising a resume generation unit that generates at least a part of the job applicant's resume based on the entity of the job applicant;
The information processing device according to claim 1, characterized in that: The job history generation department is
generating a work history of the job applicant by inserting the job applicant's entity into a predetermined template;
17. The information processing apparatus according to claim 16. a question extraction unit that refers to a storage unit that stores a plurality of questions for the job applicant and extracts questions for the job applicant;
a receiving unit that receives an answer to the question extracted by the question extracting unit,
The job history generation department is
generating a work history of the job applicant from the answers to the questions;
The information processing device according to claim 17. comprising an entity presentation unit that presents missing entities to the job applicant;
The acquisition unit includes:
Obtaining information regarding the future image or ideal image of the job applicant,
The entity presentation unit includes:
presenting entities necessary for the future image or the ideal image based on the entities of the job applicant extracted by the extraction unit;
The information processing device according to claim 1, characterized in that: a display data generation unit that generates information for displaying the entities classified into categories based on the classification results of the classification unit;
The information processing device according to claim 1, characterized in that: The classification section is
classifying the entity into a plurality of categories, and further classifying the entity classified into the plurality of categories for each category;
The information processing device according to claim 2, characterized in that: The display data generation unit includes:
generating information that causes the entities to be further classified into the categories and arranged radially for each node with the category as the root node;
22. The information processing device according to claim 21. The display data generation unit includes:
generating information to be displayed in a display mode according to a level given to the entity;
The information processing device according to claim 20. The display data generation unit includes:
generating information to be displayed in a display mode according to an attribute given to the entity;
The information processing device according to claim 20. The display data generation unit includes:
generating information to be displayed in a display mode according to the acquisition source of the entity;
The information processing device according to claim 20. a step in which the acquisition unit acquires information on at least one of a job applicant and a job offeror;
an extraction unit extracting an entity of at least one of the job applicant and the job offerer from information on at least one of the job applicant and the job offeror;
a classification unit classifying at least one of the job seeker and job offerer entities extracted by the extraction unit into a predetermined category;
An information processing method characterized by computer,
an acquisition unit that acquires information on at least one of a job applicant and a job offeror;
an extraction unit that extracts an entity of at least one of the job applicant and the job offerer from information on at least one of the job applicant and the job offeror;
functioning as a classification unit that classifies into a predetermined category at least one entity of the job applicant and the recruiter extracted by the extraction unit;
An information processing program characterized by:

Images