Text creation support system, text creation support method and program

Abstract

To provide a text creation support system, etc. capable of supporting creation of text according to profile information of an organization or an individual.SOLUTION: There is provided a text creation support system. The text creation support system includes a processor. The processor is configured to execute the following steps: a first receiving step of receiving input of source text including profile information relating to at least one of an organization and an individual; an extraction step of extracting the profile information from the source text, as evaluation items; a second receiving step of receiving input of an evaluation for the extracted evaluation items; a creation step of instructing artificial intelligence to create approach text to the source text based on the profile information and the evaluation, and causing the artificial intelligence to create the approach text.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a writing support system, a writing support method, and a program. [Background technology]

[0002] As disclosed in Patent Document 1, a technique is known for creating advertising e-mails based on user profile items. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2002-123739 A Summary of the Invention [Problem to be solved by the invention]

[0004] The above-mentioned conventional technology can select the target of advertising e-mail, but cannot adjust the wording of the e-mail for each user. Therefore, the above-mentioned conventional technology cannot be applied to the creation of e-mails that need to be created according to individual profile information, such as offers from companies or other employers to job seekers, offers from buyers wishing to acquire companies or other organizations to sellers wishing to sell, and replies to these offers.

[0005] In view of the above circumstances, the present invention provides a writing support system etc. that can support writing of text according to profile information of an organization or an individual. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided a writing support system. The writing support system includes a processor. The processor is configured to be able to execute the following steps. In a first reception step, an input of a source text including profile information related to at least one of an organization and an individual is received. In an extraction step, the profile information is extracted from the source text as an evaluation item. In a second reception step, an input of an evaluation for the extracted evaluation item is received. In a creation step, an artificial intelligence is instructed to create an approach text to the source text based on the profile information and the evaluation, and the artificial intelligence is caused to create the approach text.

[0007] According to this embodiment, an approach text to be sent to a profile information holder (organization or individual) is automatically created by inputting evaluation items automatically extracted from the source text. Therefore, it is possible to support the creation of a text that includes a reference to the profile information of an organization or individual. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a configuration diagram showing a writing support system 1. [Diagram 2] 2 is a block diagram showing a hardware configuration of the server device 10. FIG. [Diagram 3] 2 is a block diagram showing the hardware configuration of an organization terminal 20 and a job seeker terminal 30. FIG. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (control unit 11), an organization terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Diagram 5] FIG. 13 is a diagram showing an example of a display screen SD of a source document (scout document). [Figure 6] 13 is a diagram showing an example of a first input screen D1 that the display control unit 111 causes the job seeker terminal 30 to display. FIG. [Figure 7] 13 is a diagram showing an example of a second input screen D2 that the display control unit 111 causes the job seeker terminal 30 to display. FIG. [Figure 8]FIG. 13 is a diagram showing an example of sample text SA corresponding to a scout document. [Figure 9] FIG. 13 is a diagram showing an example of a sample sentence ST of an evaluation item. [Figure 10] FIG. 13 is a diagram showing another example of the second input screen D2. [Figure 11] 2 is a diagram showing an example of a table TB1 stored in a server device 10. FIG. [Figure 12] FIG. 13 is a diagram showing an example of an approach text RO (a response text to a scout text) created by a creation unit 117. [Figure 13] 1 is an activity diagram showing a flow of information processing (processing for creating a scout document) executed by writing support system 1. FIG. [Figure 14] FIG. 2 is an activity diagram showing the flow of information processing (processing of creating a response document to a scout document) executed by writing support system 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic features shown in the following embodiments can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] In addition, in this embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, in this embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0012] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0013] 1. Hardware Configuration This section describes the hardware configuration.

[0014] <Text creation support system 1> 1 is a configuration diagram showing a writing support system 1. Writing support system 1 includes a communication line 2, a server device 10, a plurality of organization terminals 20, and a plurality of job seeker terminals 30. The server device 10, the organization terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The server device 10, the organization terminals 20, and the job seeker terminals 30 may be connected to the communication line 2 via either a wired or wireless connection.

[0015] The writing support system 1 constitutes a part of a recruitment and job search system used by recruiters from multiple organizations such as companies and multiple job seekers. The writing support system 1 mainly creates scouting documents from organizations to job seekers, and creates response documents to scouting documents from job seekers to organizations. In one embodiment, the writing support system 1 is made up of one or more devices or components. These components will be described below.

[0016] <Server device 10> 2 is a block diagram showing a hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected to each other inside the server device 10 via the communication bus 14.

[0017] <Control unit 11> The control unit 11 performs processing and control of the overall operation related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 can be specifically realized by the control unit 11, which is an example of hardware, and executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and may be implemented with multiple control units 11 for each function. Also, a combination of these may be used.

[0018] <Storage section 12> The storage unit 12 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0019] <Communications Division 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0020] The server device 10 may be in an on-premise form or in a cloud form. As the server device 10 in a cloud form, the above-mentioned functions and processes may be provided in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0021] <Organization Terminal 20> Fig. 3 is a block diagram showing the hardware configuration of the organization terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the organization terminal 20 includes a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected via the communication bus 26 inside the organization terminal 20. Descriptions of the control unit 21, the memory unit 22, and the communication unit 23 will be omitted because they are similar to the descriptions of the respective units in the server device 10.

[0022] <Input section 24> The input unit 24 accepts an operation input made by a user. The operation input is transferred as a command signal to the control unit 21 via the communication bus 26. The control unit 21 may execute a predetermined control or calculation based on the transferred command signal as necessary. The input unit 24 may be included in the housing of the tissue terminal 20, or may be externally attached. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input a tap operation, a swipe operation, or the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, or the like can be adopted instead of a touch panel.

[0023] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by a user. The output unit 25 may be included in the housing of the tissue terminal 20 or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them according to the type of the tissue terminal 20.

[0024] <Job Seeker Terminal 30> 3B, the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected inside the job seeker terminal 30 via the communication bus 36. Descriptions of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are similar to the descriptions of the respective units in the organization terminal 20.

[0025] 2. Functional configuration In this section, the functional configuration of the present embodiment will be described. Information processing by the software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (a processor included in the writing support system 1).

[0026] FIG. 4 is a block diagram showing functions realized by the server device 10 (control unit 11), the organization terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0027] As shown in Fig. 4A, the server device 10 (control unit 11) includes a display control unit 111, an organization registration unit 112, a job seeker registration unit 113, a first reception unit 114, an extraction unit 115, a second reception unit 116, a creation unit 117, a third reception unit 118, a sample addition unit 119, and an artificial intelligence unit 120. As shown in Fig. 4B, the organization terminal 20 (control unit 21) includes a display unit 211 and an operation reception unit 212. As shown in Fig. 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation reception unit 312.

[0028] <Display control unit 111> The display control unit 111 is configured to display various information on the organization terminal 20 or the job seeker terminal 30. For example, the display control unit 111 displays the source text, the evaluation items extracted by the extraction unit 115, the approach text created by the creation unit 117, etc. on the display unit 211 of the organization terminal 20 or the display unit 311 of the job seeker terminal 30.

[0029] <Organization Registration Division 112> The organization registration unit 112 is configured to register organizations (employers) to use the service. For example, the organization registration unit 112 accepts input from the operation acceptance unit 212 of the organization terminal 20, and stores the name, location, representative, business details, working conditions (job posting), and the like of the organization in the storage unit 12. Note that "organizations" include profit-making corporations (e.g., companies, etc.), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.).

[0030] <Job Seeker Registration Department 113> The job seeker registration unit 113 is configured to register job seekers to use the service. For example, the job seeker registration unit 113 accepts input from the operation acceptance unit 312 of the job seeker terminal 30, and stores the job seeker's resume, curriculum vitae, etc. in the storage unit 12. Note that a "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, employment history, desired working conditions, etc., and a "curriculum vitae," also called a résumé, is a document in which a job seeker conveys to an organization his or her career history, experience, skills, qualifications, etc., related to his or her previous work.

[0031] <First Reception Section 114> The first reception unit 114 is configured to receive a designation of a source text from the organization terminal 20 or the job seeker terminal 30. The first reception unit 114 receives an input of a source text including profile information related to at least one of an organization and an individual (job seeker). "Profile information related to an organization" is, for example, the name, location, representative, business content, working conditions, appealing points to a job seeker, and items to be written in a job posting. Such profile information is included in the body of a scouting document sent by an organization to a job seeker, or in a job posting attached to the body. "Profile information related to an individual" is, for example, educational background, work history, skills, qualifications, appealing points to an employer, and the like. Such profile information is included in a job seeker's resume and curriculum vitae.

[0032] Specifically, when the first reception unit 114 assists in the creation of a scouting document for an organization, it accepts a resume or curriculum vitae created by a job seeker and stored in the memory unit 12 as a source document based on input from the organization terminal 20.

[0033] In addition, when the first reception unit 114 assists a job seeker in creating a response document to a scout document, it accepts, based on input from the job seeker terminal 30, a scout document for the job seeker created by the organization and stored in the memory unit 12 as a source document.

[0034] 5 is a diagram showing an example of a display screen SD of a source document (a scouting document from a recruiter). The display screen SD is displayed by selecting a scouting document from a list of scouting documents. The display screen SD displays the scouting document DO together with a summary DS of the job information in the scouting document (items extracted from the job posting).

[0035] The header of the display screen SD has a back button SB1, an automatic reply button SB2, a reply button SB3, and a delete button SB4. Each button (including buttons on other screens described below) functions when pressed with an input device (e.g., a mouse, a trackpad, a touch panel, etc.). The back button SB1 is a button for returning to the list of scout documents. The automatic reply button SB2 is a button for calling up processing by the extraction unit 115. The reply button SB3 is a button for calling up a function for manually creating a reply document. The delete button SB4 is a button for deleting an open scout document.

[0036] <Extraction part 115> The extraction unit 115 is configured to perform information processing on the source text. First, the extraction unit 115 extracts basic information from the source text received by the first reception unit 114. The "basic information" includes information such as the creator's name, affiliation, and job title, and information corresponding to the delivery destination or reply destination of the document whose creation is supported by the artificial intelligence. Specifically, the extraction unit 115 inputs a sample of text belonging to the same type as the input source text (source text sample) and a sample of basic information (e.g., a name sample, etc.) to the artificial intelligence by generating a prompt for the artificial intelligence, and inputs the source text to the artificial intelligence and instructs the artificial intelligence to extract the basic information from the source text, thereby causing the artificial intelligence to extract the basic information from the source text.

[0037] FIG. 6 is a diagram showing an example of a first input screen D1 that the display control unit 111 causes the job seeker terminal 30 to display. The first input screen D1 includes a basic information display field S1 for displaying the basic information extracted by the extraction unit 115, a link display field S2 for adjusting the schedule (schedule sharing), a check box CB1 for inputting whether the schedule is confirmed or not, a job hunting status input field I1, an activity phase input field I2, a back button B1, and a forward button B2. Elements of the first input screen D1 other than the basic information display field S1 will be described later. The "job hunting status" includes options such as "currently job hunting", "planning to job hunt", "want to hear more", "want to participate as a side job / concurrent job", and "not considering job hunting at the moment". The "activity phase" includes options such as "offer received", "final selection phase", "selection phase", "casual interview phase", and "just started job hunting". The "job hunting status" also includes the "activity phase".

[0038] Furthermore, the extraction unit 115 extracts profile information from the source text as an evaluation item. The "evaluation item" is an item that is to be evaluated in the processing of the second reception unit 116. Specifically, the extraction unit 115 generates a prompt for the artificial intelligence to instruct the artificial intelligence to extract multiple pieces of profile information included in the source text as multiple evaluation items, and causes the artificial intelligence to extract the multiple evaluation items.

[0039] When the source document is a resume or curriculum vitae prepared by a job seeker, the extraction unit 115 extracts, from the profile information, words or phrases corresponding to, for example, the job seeker's skills, qualifications, work experience, job experience, etc., as evaluation items. When the source document is a scouting document prepared by an organization, the extraction unit 115 extracts, for example, words or phrases corresponding to, for example, organizational culture, organizational attractiveness, business characteristics, business attractiveness, job attractiveness, role expected of the job seeker, etc., as evaluation items.

[0040] 7 is a diagram showing an example of the second input screen D2 that the display control unit 111 causes the job seeker terminal 30 to display. The second input screen D2 includes a plurality of evaluation items EI extracted by the extraction unit 115 from the scout document, categories EC of the evaluation items, a plurality of evaluation boxes CB2, a back button B3, and a complete button B4. The plurality of evaluation items EI are displayed for each category EC of the evaluation items. Each evaluation item EI is assigned one evaluation box CB2. Elements of the second input screen D2 other than the evaluation items EI and categories EC will be described later.

[0041] When the source document is a scout document, the extraction unit 115 instructs the artificial intelligence to extract profile information from the job posting included in the scout document as evaluation items, and causes the artificial intelligence to extract the evaluation items. The extraction unit 115 also instructs the artificial intelligence to extract the organization's attention points for the job seeker from the scout document as evaluation items, and causes the artificial intelligence to extract the evaluation items. The "attention points" are contents that the artificial intelligence extracts from the resume or work history of the job seeker that are highly correlated with the contents of the organization's job posting and inserts into the scout document. The "attention points" are points that a recruiter who wishes to hire a human resource pays attention to in the resume or work history of the job seeker. Here, the job posting may be included in the main text of the scout document, or may be attached to the scout document. By extracting the evaluation items in this way, support for creating a response document that includes an evaluation of the attention points that the organization is highly interested in is realized. In other words, a response document that can give a good impression to the organization can be created without the job seeker spending time searching for the attention points himself. In addition, the risk that the job seeker will misjudge the attention points is also reduced.

[0042] When creating a scouting document, points of interest are created, for example, in the following procedure. First, a feature vector (job posting feature vector) obtained by syntactic analysis (morphological analysis) of the entire job posting is compared with multiple feature vectors (resume feature vectors) obtained by syntactic analysis of each sentence in the resume or curriculum vitae. Next, from the contents of the resume or curriculum vitae, sentences having resume feature vectors close to the feature vector in the job posting are created as points of interest and inserted into the scouting document. Note that feature vectors are composed of the number of times a word appears, distributed representations of words or sentences, etc. Alternatively, the similarity between the entire job posting and each sentence in the resume or curriculum vitae may be calculated by a known method, and points of interest may be created based on this similarity.

[0043] Also, the points of interest may be extracted by a learning model (artificial intelligence) that has learned the correlation between parameters related to the employment of job seekers (e.g., a response rate to a scouting document, etc.) and a group of words contained in a resume or a curriculum vitae. This learning model learns information about scouting documents sent in the past. Specifically, the learning model is generated by learning the correlation between a group of words contained in a scouting document sent in the past and the presence or absence of a response to a scouting document sent in the past. In other words, the learning model is generated so that the weighting of a group of words contained in a scouting document to which a job seeker has responded is relatively high, and the weighting of a group of words contained in a scouting document to which a job seeker has not responded is relatively low. When generating a new scouting document, the learning model inputs a group of words contained in a resume or a curriculum vitae, and outputs a group of words that have a positive effect on the employment of a job seeker as a point of interest.

[0044] When the source text is a resume or curriculum vitae of a job seeker and the approach text to be created is a scouting document, the extraction unit 115 may cause the artificial intelligence to extract points of interest in the above-mentioned procedure and present the extracted points of interest to the user as evaluation items. Specifically, the extraction unit 115 instructs the artificial intelligence to extract points of interest from the resume or curriculum vitae and causes the artificial intelligence to extract evaluation items.

[0045] When the source document is a scout document, the artificial intelligence determines whether or not the scout document contains a point of interest, and when it is determined that the scout document contains a point of interest, extracts the point of interest as an evaluation item. Whether or not the scout document contains a point of interest is determined, for example, by syntactic analysis of the scout document. In addition, when the scout document is created using the function of extracting points of interest using the learning model described above, the server device 10 stores the points of interest in association with the scout document. In this case, the artificial intelligence can extract the points of interest from the stored information (information on the points of interest embedded in the scout document).

[0046] In particular, when it is determined that the scout document does not include a point of interest, the artificial intelligence may create a point of interest in the same manner as in the procedure for creating a point of interest when creating the scout document described above, and extract the created point of interest. That is, first, a feature vector (scout document feature vector) obtained by syntactic analysis (morphological analysis) of the entire scout document is compared with a plurality of feature vectors (resume feature vectors) obtained by syntactic analysis of each sentence in the resume or job history. Next, from the contents of the resume or job history, sentences having a resume feature vector close to the scout document feature vector are extracted as points of interest. In addition, points of interest may be extracted by a learning model (artificial intelligence) that has learned the correlation between parameters related to the employment of job seekers (e.g., response rate to scout documents, etc.) and groups of words included in the resume or job history.

[0047] The display control unit 111 may display evaluation items based on attention points extracted from the scout document in a form that is differentiated from other evaluation items on the job seeker terminal 30. For example, the display control unit 111 may display evaluation items based on attention points on a different page (screen) from other evaluation items, or may display evaluation items based on attention points in a font (size, color, etc.) different from other evaluation items.

[0048] Furthermore, the extraction unit 115 instructs the artificial intelligence to extract, as evaluation items, contents that are highly correlated with the contents of the scout document from the resume or work history of the job seeker, and causes the artificial intelligence to extract the evaluation items. By extracting the evaluation items in this manner, support is realized for creating a response document in which the contents of the scout document or job posting are matched with the job seeker's own resume or work history. This can save the job seeker the trouble of reviewing the scout document, resume, work history, etc., and also suppresses omissions of responses to matters described in the scout document. Therefore, it is possible to create a response document to the scout document that includes points that should appeal to the employer. In addition, when the source text is the resume or work history of the job seeker and the approach text to be created is a scout document, it is possible to create a scout document tailored to each individual job seeker by instructing the artificial intelligence to extract, as evaluation items, contents that are highly correlated with the contents of the job posting from the resume or work history of the job seeker and causing the artificial intelligence to extract the evaluation items.

[0049] The extraction unit 115 selects a sample sentence corresponding to the category of the evaluation item from sample sentences registered in advance and corresponding to the type of source sentence, and inputs the source sentence and the sample sentence into the artificial intelligence, thereby causing the artificial intelligence to extract the evaluation items from the source sentence. The type of source sentence is distinguished according to the attributes of the creator or recipient of the source sentence, the purpose of the source sentence, etc. For example, a job seeker's resume or curriculum vitae and a scouting document are different types of source sentence because the attributes of the creator and recipient are different and the purposes are also different.

[0050] FIG. 8 is a diagram showing an example of sample sentences SA corresponding to a scout document. FIG. 9 is a diagram showing an example of sample sentences ST of evaluation items. The sample sentences SA in FIG. 8 are samples (source sentence samples) of sentences belonging to the same type as the input source sentences, and are samples including sample sentences ST of evaluation items. The sample sentences ST in FIG. 9 are registered for each category EC of evaluation items. The sample sentences ST are sample sentences corresponding to evaluation items identified (extracted) from the sample sentences SA (source sentence samples). The process of identifying sample sentences corresponding to evaluation items from the sample sentences SA (source sentence samples) may be performed manually or by artificial intelligence. When the source sentence is a resume or curriculum vitae of a job seeker, sample sentences (source sentence samples) including categories and sample sentences different from the example in FIG. 9 are used.

[0051] The sample sentence ST may be a single sentence including one period, or may be a sentence consisting of two or more sentences. Also, the sample sentence ST does not have to be a complete sentence, but may be an incomplete sentence consisting of one word or multiple words.

[0052] The extraction unit 115 uses the sample sentence SA to extract evaluation items for each category EC of multiple evaluation items. Specifically, the extraction unit 115 inputs the sample sentence ST included in the category EC of "corporate culture and corporate attractiveness" together with the source sentence into the artificial intelligence, thereby extracting multiple evaluation items EI included in the category EC of "corporate culture and corporate attractiveness" shown in FIG. 7, which are included in the source sentence. The extraction unit 115 performs this operation for each category EC to extract items. In the artificial intelligence used by the extraction unit 115, the sample sentence SA (source sentence sample) is input as a prompt together with the source sentence so that the sample sentence SA is an input example and the sample sentence ST included in the sample sentence SA is an output example, and the extraction of evaluation items from the source sentence is instructed. In this way, the sample sentence SA (source sentence sample) corresponding to the attribute of the source sentence and the sample sentence ST corresponding to the category of the evaluation item are inserted into the prompt for the artificial intelligence and used, thereby improving the extraction accuracy of the evaluation items. In addition, it is possible to customize the evaluation items to be extracted without re-learning the artificial intelligence. In other words, general-purpose learning models such as large-scale language models (LLM) can be used as they are for artificial intelligence. In addition, by using actual source sentences created in the past as sample sentences SA (source sentence samples) and specifically specifying patterns for extracting sample sentences from them and instructing the artificial intelligence to output them, it is possible to input not only the categories and contents of the evaluation items to be extracted, but also elements such as writing style (such as ending with a noun) and appropriate sentence length as output examples to the artificial intelligence.

[0053] <Second Reception Section 116> The second reception unit 116 is configured to receive evaluations for the evaluation items from the organization terminal 20 or the job seeker terminal 30. The second reception unit 116 receives input of evaluations for each of the multiple evaluation items extracted by the extraction unit 115. Specifically, the second reception unit 116 sets options according to the contents of the evaluation items, and allows the user to input an evaluation by selecting an option. This makes it possible to efficiently create an approach document that reflects the evaluations for the evaluation items. In addition, when there are many evaluation items, the input load on the user can be reduced. Note that the evaluation is an index indicating the degree or method of reflection of the extracted evaluation items, such as whether the user wants to reflect them in the approach document to be created, to what level the user wants to reflect them, and how the user wants to reflect them.

[0054] Specifically, the second reception unit 116 receives the evaluation of each evaluation item EI based on the input to the evaluation box CB2 assigned to each evaluation item EI on the second input screen D2 of Fig. 7. For example, the user checks the evaluation items that he / she wants to reflect in the approach text he / she creates. The checked items are reflected in the approach text, and the unchecked items are discarded.

[0055] The second reception unit 116 receives an evaluation of the evaluation item EI for which the evaluation box CB2 is checked, such as whether the user is highly interested in it, whether the user wants to reflect it in the document to be created, whether the user wants to appeal to the reply recipient, whether the item matches the user's career, skills, etc. In other words, the evaluation box CB2 is a UI that presents two options.

[0056] FIG. 10 is a diagram showing another example of the second input screen D2. As shown in FIG. 10A, the second input screen D2 may be provided with a selection button MB including a plurality of icons linked to options instead of the evaluation box CB2. The second reception unit 116 receives the evaluation linked to the selected icon. In the example of FIG. 10A, the leftmost icon corresponds to the evaluation with the highest interest of the user, and the rightmost icon corresponds to the evaluation with the lowest interest of the user. Furthermore, the evaluation of the evaluation item EI may be selectable in a pull-down manner. The content and number of options may be appropriately set by the artificial intelligence based on the content of the evaluation item EI. The artificial intelligence may be equipped with a learning model that has learned the evaluation items and the options corresponding to them as a set. The learning model may be a model that inputs the evaluation items and outputs the options corresponding to them.

[0057] Also, as shown in FIG. 10B, the second input screen D2 may be provided with a pull-down button PB. When the pull-down button PB is selected with the evaluation box CB2 of the corresponding evaluation item EI checked, the pull-down button PB transitions to a state in which multiple options are displayed, as shown in FIG. 10C. With the pull-down button PB expanded in this manner, the user can input a selection for the option. The options displayed in the pull-down button PB include specific evaluation contents such as "matches skills and experience," "not confident in skills and experience," and "does not match expectations." If the source text is a resume or a curriculum vitae and the approach text is a scouting document, specific evaluation contents from the perspective of the recruiter, such as "matches the desired talent" and "does not match the desired talent," may be included.

[0058] Furthermore, if the source document is a scout document, the second reception unit 116 further receives input of the job-hunting status of the job seeker from the job seeker terminal 30. Specifically, the second reception unit 116 receives input in the job-hunting status input field I1 and the activity phase input field I2 on the first input screen D1 in FIG. 6. In the example of FIG. 6, these items are input by selecting from a pull-down menu, but these items may also be input by free description. Furthermore, if the source document is a resume or a curriculum vitae, the second reception unit 116 may receive input of the recruiting activity status of the employer. Specifically, the recruiting activity status is information indicating the status of the recruiting activity of the recruiter, and is an item such as "actively recruiting," "job posting to close soon," and "newly posted job posting."

[0059] <Creation Department 117> The creation unit 117 is configured to create a scout document or a response document to the scout document. The creation unit 117 instructs the artificial intelligence to create an approach document to the source document (a scout document or a response document to the scout document) based on the profile information included in the source document and the evaluation accepted by the second acceptance unit 116 by generating a prompt for the artificial intelligence, and causes the artificial intelligence to create the approach document.

[0060] The creation unit 117 instructs the artificial intelligence to create insertion words that are abstracted from words included in the profile information, and inserts the insertion words created by the artificial intelligence into the approach text. This makes it possible to avoid creating text that may give a mechanical impression by simply repeating words included in the source text. As a result, it is possible to improve the impression of the approach text on the recipient. Specifically, the artificial intelligence may be equipped with a model that is trained to input the words in the profile information and output abstracted words. The artificial intelligence may also be equipped with a model that has been trained using a set of the profile information and the abstracted words (correct answer data) as training data.

[0061] The creation unit 117 also instructs the artificial intelligence to create insertion text by removing the numerical value from the text of the profile information including the numerical value, and inserts the insertion text created by the artificial intelligence into the approach text. This avoids the creation of text that may give a mechanical impression by including the specific numerical value contained in the source text as it is. Specifically, the artificial intelligence may be equipped with a model trained to input the text of the profile information and output the text with the numerical value removed therefrom. The artificial intelligence may also be equipped with a model trained using a set of the profile information and the text with the numerical value removed therefrom (correct answer data) as training data.

[0062] The creation unit 117 may insert the wording of the profile information directly into the approach text. In other words, the creation unit 117 may copy the wording of the source text directly and insert it into the approach text, or may insert the wording of the source text summarized by artificial intelligence (abstracted or excluding numerical values) into the approach text.

[0063] When the approach text is a response text to a scout text, the creation unit 117 instructs the artificial intelligence to create the approach text based on the profile information, the evaluation, and the job hunting status, and causes the artificial intelligence to create the approach text. This makes it possible to efficiently create a response text to a scout text that reflects the individual circumstances of the job hunting status, independent of the evaluation by the job seeker. This improves the convenience of the job seeker. Also, when the approach text is a scout text, the creation unit 117 may instruct the artificial intelligence to create the approach text based on the profile information, the evaluation, and the recruitment activity status, and causes the artificial intelligence to create the approach text. This makes it possible to efficiently create an approach text that reflects information indicating the user's situation (activity status), such as the job hunting status and the recruitment activity status.

[0064] The creation unit 117 may create an approach sentence based on the job hunting situation or the recruiting activity situation by referring to a table. Fig. 11 is a diagram showing an example of a table TB1 stored in the server device 10. The creation unit 117 may refer to the table TB1, call up a sentence or a template according to the job hunting situation as an input as an output, and insert it into a prompt for the artificial intelligence or into the approach sentence.

[0065] A specific algorithm for creating text by the creation unit 117 will be described below. First, the creation unit 117 inputs the source text, evaluation items, etc., and causes the structure creation model (artificial intelligence) to output the entire structure of the approach text. Next, the creation unit 117 inputs multiple evaluations one by one into multiple text creation models (artificial intelligence) to output text corresponding to each of the multiple evaluation items in parallel to the multiple text creation models. Specifically, the creation unit 117 inserts the text output by the text creation model into multiple paragraphs included in the structure output by the structure creation model. This makes it possible to reduce the time required to create the approach text even when there are many evaluation items extracted from the source text. Therefore, the consumption of time resources is reduced when a user creates many approach texts (when an organization sends multiple scouting documents or when a job seeker replies to multiple scouting documents).

[0066] Fig. 12 is a diagram showing an example of an approach text RO (a response text to a scout text) created by the creation unit 117. The approach text RO in Fig. 12 includes multiple paragraphs P1-P6. The first paragraph P1 is the addressee, and the creator's affiliation, title, name, etc. extracted from the source text (scout text) are inserted into it. The second paragraph P2 is a standard opening phrase that includes the name of the author of the approach text RO.

[0067] The third paragraph P3 and the fourth paragraph P4 are sentences created by artificial intelligence based on the profile information of the source sentence and the evaluation of the evaluation items. The third paragraph P3 and the fourth paragraph P4 are created based on the evaluation of different evaluation items. For example, the third paragraph P3 is created based on the evaluation of the organization's business in the scouting document, and the fourth paragraph P4 is created based on the evaluation of the reference to the job seeker's skills or experience in the scouting document. Note that FIG. 12 shows an image of the state in which the third paragraph P3 and the fourth paragraph P4 are created simultaneously, and the sentences are not necessarily created from the beginning to the end.

[0068] <Third Reception Section 118> The third reception unit 118 is configured to receive edits to the evaluation items extracted by the extraction unit 115 from the organization terminal 20 or the job seeker terminal 30. This allows the user, that is, the organization or job seeker, to add appropriate evaluation items, thereby increasing the degree of freedom for the user to create the approach text. Furthermore, the creation unit 117 inputs the edited evaluation items together with the source text to the artificial intelligence, thereby outputting the approach text reflecting the edits.

[0069] Editing an evaluation item includes modifying the wording of the evaluation item, deleting an evaluation item, and adding an evaluation item. When adding an evaluation item, the third reception unit 118 may receive a part of the source text selected by an operation such as dragging on the organization terminal 20 or the job seeker terminal 30 as the evaluation item to be added.

[0070] <Sample Addition Section 119> The sample adding unit 119 is configured to add the evaluation item edited by the third receiving unit 118 to a sample sentence corresponding to the category of the evaluation item. Specifically, the sample adding unit 119 adds the sample sentence ST edited or created by the user in association with the category EC. This allows the results of editing the evaluation items by the user to be reflected in the evaluation items extracted by the extracting unit 115, making it possible to extract evaluation items that are more appropriate for the user. As a result, user convenience is continuously improved.

[0071] In addition, the output by the artificial intelligence performed by the extraction unit 115, the creation unit 117, etc. may be optimized for each user. That is, the server device 10 may optimize the prompt for the artificial intelligence for each user by automatically feeding back the corrections, additions, etc. made by the user to the evaluation items or the approach sentences created by the artificial intelligence to a user-specific prompt (a command or input sentence that instructs the artificial intelligence to create an approach sentence). That is, the prompt prepared for each user is optimized by feeding back the user's evaluations on the evaluation items, and is stored in the server device 10. Specifically, the sample adding unit 119 adds the edited evaluation items as sample sentences and the source sentences from which the evaluation items are extracted as source sentence samples to the user-specific prompt as a set, and stores them in the server device 10. In this way, the user's own characteristics are automatically learned.

[0072] The sample adding unit 119 inserts the edited evaluation items as sample sentences and the source sentences from which the evaluation items are extracted as source sentence samples into the prompt as a set. This increases the number of sample sentences in the prompt. Therefore, when creating approach sentences from the next time onwards, the added and updated source sentence samples and sample sentences are input to the artificial intelligence, making it possible to extract more appropriate evaluation items. In addition, the evaluation items extracted by the artificial intelligence may be labeled as to whether they were used in the actual approach sentence, and the source sentences from which the evaluation items are extracted may be used as source sentence samples and used as a set for reinforcement learning of the artificial intelligence. In this way, the evaluation of the evaluation items extracted by the artificial intelligence is fed back to the artificial intelligence or a prompt to the artificial intelligence, thereby improving the accuracy of sentence creation.

[0073] The sample adding unit 119 may add the evaluation items edited by the user as they are as sample sentences ST. Also, the sample adding unit 119 may instruct the artificial intelligence to correct the evaluation items edited by the user to sentences of an appropriate format (sentence structure), and add the sentences corrected by the artificial intelligence as sample sentences ST. That is, the control unit 11 receives feedback on the user's evaluation items and self-corrects the samples included in the prompts for the artificial intelligence.

[0074] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0075] The artificial intelligence unit 120 is an AI equipped with language models represented by transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, and GPT-3), BERT (Bidirectional Encoder Representations from Transformers), and BART (Bidirectional and Auto-regressive Transformer).

[0076] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. Unlike those trained for a specific task, a language model is a general-purpose model that can be used for a wide range of tasks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0077] The artificial intelligence unit 120 has a trained model constructed by supervised learning or unsupervised learning as its artificial intelligence. In supervised learning, machine learning is performed using teacher data (training data). The teacher data is composed of a pair of input data for learning and output data (correct answer data). The artificial intelligence unit 120 also includes a general-purpose learning model such as a large-scale language model (LLM) as its artificial intelligence. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or may be a common general-purpose learning model.

[0078] When a general-purpose learning model (e.g., LLM) is used, the artificial intelligence unit 120 may include another learning model (artificial intelligence) used between the extraction of evaluation items by the extraction unit 115 and the creation of approach sentences by the creation unit 117. The learning model is trained to input source sentences and output appropriate evaluation items. The learning model optimizes the evaluation items output from the LLM and presents them to the user.

[0079] When a separate learning model is used in each functional unit, the artificial intelligence included in the artificial intelligence unit 120 can perform additional learning. Specifically, the artificial intelligence unit 120 may perform the following additional learning. For example, the artificial intelligence unit 120 learns whether a sentence inserted into an approach sentence based on a user's evaluation of an evaluation item was used as is. That is, the artificial intelligence unit 120 performs machine learning using a teacher data set in which an approach sentence created by the artificial intelligence is labeled with an actual transmission result (i.e., the content of the approach sentence edited by the user) and a scout document are combined. In addition, the artificial intelligence unit 120 performs machine learning of the learning model described in each functional unit (for example, a learning model used for extracting points of interest, setting options for evaluation items, abstracting the wording of profile information, excluding numerical values ​​from the wording of profile information, etc.).

[0080] 3. Information processing method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

[0081] Specifically, this information processing method includes a first reception step, an extraction step, a second reception step, a creation step, a third reception step, and a sample addition step. In the first reception step, an input of a source sentence including profile information related to at least one of an organization and an individual is accepted. In the extraction step, the profile information is extracted from the source sentence as an evaluation item. In the second reception step, an input of an evaluation for the extracted evaluation item is accepted. In the creation step, an artificial intelligence is instructed to create an approach sentence to the source sentence based on the profile information and the evaluation, and the artificial intelligence is caused to create the approach sentence. In the third reception step, edits to the extracted evaluation items are accepted. In the sample addition step, the evaluation item edited in the third reception step is added to a sample sentence corresponding to the category of the evaluation item.

[0082] <Creating Scout Documents> 13 is an activity diagram showing the flow of information processing (processing for creating a scout document) executed by writing support system 1. The information processing will be described below along with each activity in this activity diagram.

[0083] The process of creating a scout document begins with the organization's person in charge searching for job seekers from the organization terminal 20. Specifically, the organization's person in charge inputs search conditions and a search instruction into the organization terminal 20 (activity A101). The server device 10 executes a search for job seekers in the database based on the search conditions and the search instruction sent from the organization terminal 20, and controls the display of the search results on the organization terminal 20 (activity A102). Through this control, the search results for job seekers are displayed on the organization terminal 20 (activity A103).

[0084] After the search results are displayed on the organization terminal 20, the person in charge at the organization checks the information (resumes and curriculum vitae) of the searched job seekers and decides which job seekers to send the scouting document to. The person in charge at the organization terminal 20 selects the target job seekers and inputs an instruction to create a scouting document (activity A104).

[0085] The server device 10 receives input of the resume or curriculum vitae (source text) of the job seeker to whom the scout document is to be sent, and an instruction to create the scout document from the organization terminal 20 (first reception step, activity A105). Next, the server device 10 causes the artificial intelligence to extract evaluation items from the source text (extraction step, activity A106). Furthermore, the server device 10 performs control to display the evaluation items on the organization terminal 20. As a result of this control, the evaluation items are displayed on the organization terminal 20 (activity A107).

[0086] After the evaluation items are displayed on the organization terminal 20, the person in charge at the organization inputs an evaluation for the evaluation item and edits the evaluation item as necessary (activity A108). The server device 10 accepts the evaluation and edits for the evaluation items from the organization terminal 20 (second and third reception steps, activity A109). Next, the server device 10 causes the artificial intelligence to create a scout document and adds the edited evaluation items to the sample sentences (creation step and sample addition step, activity A110). Furthermore, the server device 10 performs control to display the created scout document on the organization terminal 20. By this control, the scout document is displayed on the organization terminal 20 (activity A111).

[0087] After the scout document is displayed on the organization terminal 20, the person in charge of the organization checks the contents of the scout document and modifies the document as necessary on the organization terminal 20. After completing the scout document, the person in charge of the organization inputs an instruction to send the scout document on the organization terminal 20 (activity A112). The server device 10 accepts the instruction to send the scout document from the organization terminal 20 and sends it to the job seeker terminal 30 (activity A113).

[0088] <Create a response document to a scout document> 14 is an activity diagram showing the flow of information processing (processing of creating a response document to a scout document) executed by writing support system 1. The information processing will be described below along with each activity in this activity diagram.

[0089] The process of creating a response document to a scout document begins with the job seeker checking the scout document sent to the job seeker terminal 30. Specifically, the job seeker receives the scout document at the job seeker terminal 30 and checks its contents (activity A201). When creating a response document to a scout document (i.e., when applying for a job), the job seeker selects the target scout document and inputs an instruction to create a response document at the job seeker terminal 30 (activity A202). Specifically, the automatic response creation button SB2 on the display screen SD of FIG. 5 is pressed.

[0090] The server device 10 receives an input of a scout document (source document) to be responded to and an instruction to create a response document sent from the job seeker terminal 30 (first reception step, activity A203). Next, the server device 10 causes the artificial intelligence to extract evaluation items from the source document (extraction step, activity A204). Furthermore, the server device 10 controls the display of the basic information and evaluation items on the job seeker terminal 30. As a result of this control, the basic information and evaluation items are displayed on the job seeker terminal 30 (activity A205).

[0091] After the basic information and evaluation items are displayed on the job seeker terminal 30, the job seeker inputs the status of his / her job search on the job seeker terminal 30 (activity A206). Furthermore, the job seeker inputs evaluations of the evaluation items on the job seeker terminal 30 and edits the evaluation items as necessary (activity A207).

[0092] In the activities A206 and A207, specifically, input is made into the job-hunting status input field I1 and the activity phase input field I2 in the first input screen D1 shown in FIG. 6. In addition, input is also made into the link display field S2 and the check box CB1 as appropriate. After inputting the job-hunting status, etc., when the Next button B2 is pressed, the second input screen D2 shown in FIG. 7 is displayed on the job seeker terminal 30. In the second input screen D2 in FIG. 7, an evaluation for each evaluation item EI is input. After inputting the evaluation, when the Complete button B4 is pressed, the evaluation is transmitted from the job seeker terminal 30 to the server device 10. In addition, when the Back button B3 is pressed on the second input screen D2, the display returns to the first input screen D1. Note that the second input screen D2 may be displayed before the first input screen D1. In other words, the evaluation items may be evaluated before inputting the job-hunting status.

[0093] The server device 10 accepts from the job seeker terminal 30 the job search status, evaluations for the evaluation items, and edits to the evaluation items (second and third reception steps, activity A208). Next, the server device 10 causes the artificial intelligence to create a response document to the scout document, and adds the edited evaluation items to the sample sentences (creation step and sample addition step, activity A209). Furthermore, the server device 10 performs control to display the created response document on the job seeker terminal 30. Through this control, the response document is displayed on the job seeker terminal 30 (activity A210).

[0094] After the response document is displayed on the job seeker terminal 30, the job seeker checks the contents of the response document and, if necessary, modifies the document at the job seeker terminal 30. After completing the response document, the job seeker inputs an instruction to send the response document at the job seeker terminal 30 (activity A211). The server device 10 accepts the instruction to send the response document from the job seeker terminal 30 and sends it to the organization terminal 20 (activity A212).

[0095] 4. Effect The operation of this embodiment can be summarized as follows: An approach text to be sent to the profile information holder (organization or individual) is automatically created by inputting evaluation items automatically extracted from the source text. Therefore, it is possible to support the creation of text that includes a reference to the profile information of an organization or individual.

[0096] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and can be modified as appropriate without departing from the technical concept of the invention.

[0097] 5.Other In the above embodiment, the server device 10 performs various storage and control, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 120, which is an external configuration, is configured to receive input from each functional unit of the server device 10 and return the instructed output to the server device 10.

[0098] The aspect of the present embodiment is not limited to the writing support system 1, and may be an information processing method or a program. The writing support method includes each step of the writing support system 1. The program causes a computer to execute each step of the writing support system 1.

[0099] The writing support system 1 can be applied to an M&A matching system for companies and other organizations, in addition to a job-seeking and recruitment system. The M&A matching system is a system that matches a seller who wishes to sell an organization with a buyer who wishes to acquire the organization. When the writing support system 1 is applied to an M&A matching system, the source documents include explanatory materials about the seller and acquisition offer documents from the buyer to the seller. If the source documents are explanatory materials about a company considering selling, the approach documents are acquisition offer documents from the buyer to the seller, and if the source documents are acquisition offer documents, the approach documents are response documents to the acquisition offer documents from the seller to the buyer. In addition, explanatory materials about a seller who wishes to sell an organization correspond to information (resume or curriculum vitae) of a job seeker, and an acquisition offer document from a buyer who wishes to acquire an organization to a seller corresponds to a scouting document from a job seeker to a job seeker.

[0100] It may be provided in any of the following ways:

[0101] (1) A writing support system comprising a processor, the processor being configured to be able to execute each of the following steps: a first reception step, receiving an input of a source text including profile information related to at least one of an organization and an individual; an extraction step, extracting the profile information from the source text as an evaluation item; a second reception step, receiving an input of an evaluation for the extracted evaluation item; and a creation step, instructing an artificial intelligence to create an approach text to the source text based on the profile information and the evaluation, and having the artificial intelligence create the approach text.

[0102] (2) In the writing support system described in (1) above, the source document is a scouting document for a job seeker created by the organization, or a resume or curriculum vitae created by the job seeker.

[0103] (3) In the writing support system described in (2) above, in the extraction step, the artificial intelligence is instructed to extract the profile information from the job posting included in the scout document as the evaluation item, and the artificial intelligence is caused to extract the evaluation items.

[0104] (4) In the writing support system described in (2) or (3) above, in the extraction step, the artificial intelligence is instructed to extract the organization's points of interest regarding the job seeker from the scouting document as the evaluation items, and the artificial intelligence is caused to extract the evaluation items.

[0105] (5) In the writing support system described in (4) above, the point of interest is that the artificial intelligence extracts content from the resume or the curriculum vitae of the job seeker that is highly correlated with the content of the organization's job posting and inserts it into the scouting document.

[0106] (6) In the writing support system described in any one of (2) to (5) above, in the extraction step, the artificial intelligence is instructed to extract content from the resume or the curriculum vitae of the job seeker that is highly correlated with the content of the scout document as the evaluation item, and the artificial intelligence is caused to extract the evaluation items.

[0107] (7) In the writing support system described in any one of (1) to (6) above, in the creation step, the artificial intelligence is instructed to create insertion text that abstracts text included in the profile information, and the insertion text created by the artificial intelligence is inserted into the approach text.

[0108] (8) In the writing support system described in any one of (1) to (7) above, in the creating step, the artificial intelligence is instructed to create an insertion phrase by excluding the numerical value from the text of the profile information including the numerical value, and the insertion phrase created by the artificial intelligence is inserted into the approach text.

[0109] (9) In the writing support system described in any one of (1) to (8) above, in the extraction step, a sample sentence corresponding to the category of the evaluation item is selected from sample sentences that are registered in advance and correspond to the type of the source sentence, and the source sentence and the sample sentence are input to the artificial intelligence, thereby causing the artificial intelligence to extract the evaluation item from the source sentence.

[0110] (10) In the writing support system described in (9) above, the processor is configured to further execute the following steps: in a third reception step, edits to the extracted evaluation items are accepted; and in a sample addition step, the evaluation items edited in the third reception step are added to the sample sentences corresponding to the categories of the evaluation items.

[0111] (11) In the writing support system described in any one of (1) to (10) above, in the second reception step, options are set according to the content of the evaluation item, and the evaluation is input by selecting one of the options.

[0112] (12) In the writing support system described in any one of (1) to (11) above, the source text is a scouting document for a job seeker created by the organization, and the second reception step further receives input of the job hunting status of the job seeker, and the creation step instructs the artificial intelligence to create the approach text based on the profile information, the evaluation, and the job hunting status, and causes the artificial intelligence to create the approach text.

[0113] (13) In the writing support system described in any one of (1) to (12) above, in the extraction step, the artificial intelligence is instructed to extract a plurality of the profile information contained in the source text as a plurality of the evaluation items, causing the artificial intelligence to extract the plurality of the evaluation items, in the second reception step, input of a plurality of the evaluations for each of the plurality of the evaluation items is received, and in the creation step, the plurality of the evaluations are input one by one into a plurality of writing models, thereby outputting sentences corresponding to each of the plurality of the evaluation items in parallel to the plurality of the writing models.

[0114] (14) A method for assisting with writing, comprising the steps of the writing support system described in any one of (1) to (13) above.

[0115] (15) A program that causes a computer to execute each step of the writing support system described in any one of (1) to (13) above. Of course, this is not the case.

[0116] Finally, although various embodiments according to the present disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0117] 1: Writing support system 2: Communication lines 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Organization terminal 21: Control section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job Seeker Terminal 31: Control section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 111: Display control unit 112: Organization Registration Department 113: Job Seeker Registration Department 114: First Reception Section 115:Extraction part 116: Second Reception Section 117: Creation Department 118: Third Reception Section 119: Sample Addition Section 120: Artificial Intelligence Department 211:Display section 212: Operation reception section 311: Display section 312: Operation reception section

Claims

1. It is a document creation support system, Equipped with a processor, The aforementioned processor is configured to perform the following steps: In the first application step, the input of source documents relating to at least one of an organization and / or an individual is accepted, where the source documents are recruitment documents for job seekers created by the organization, or resumes or work histories created by the job seekers. In the second submission step, the user submits an evaluation of the source text. In the creation step, the system instructs artificial intelligence to create an approach document to the source document based on the source document and the evaluation, causing the artificial intelligence to create the approach document, where the approach document is a recruitment document to a job seeker or a response document to a recruitment document, in a document creation support system.

2. In the document creation support system described in Claim 1, The aforementioned processor is configured to perform the following steps: In the extraction step, profile information related to at least one of the organization and the individual is extracted from the source document as evaluation items. In the second reception step, the evaluation is performed by receiving input of the evaluation for the extracted evaluation items. A document creation support system that, in the creation step, instructs the artificial intelligence to create the approach document based on the profile information and the evaluation, and causes the artificial intelligence to create the approach document.

3. In the document creation support system described in claim 2, In the extraction step, the document creation support system instructs the artificial intelligence to extract the profile information from the job posting included in the scout document as evaluation items, and causes the artificial intelligence to extract the evaluation items.

4. In the document creation support system described in claim 2, In the extraction step, the document creation support system instructs the artificial intelligence to extract the organization's points of interest regarding the job seeker from the scouting document as evaluation items, and causes the artificial intelligence to extract the evaluation items.

5. In the document creation support system described in claim 4, The aforementioned point of interest is a document creation support system in which the artificial intelligence extracts content that is highly correlated with the content of the organization's job posting from the job seeker's resume or work history and inserts it into the recruitment document.

6. In the document creation support system described in claim 2, In the extraction step, the document creation support system instructs the artificial intelligence to extract content from the job seeker's resume or work history that is highly correlated with the content of the scouting document as evaluation items, and causes the artificial intelligence to extract the evaluation items.

7. In the document creation support system described in claim 2, In the extraction step, the artificial intelligence is instructed to extract the multiple profile information contained in the source document as multiple evaluation items, and the artificial intelligence is made to extract the multiple evaluation items. In the second reception step, inputs of multiple evaluations for each of the multiple evaluation items are received. In the creation step, the document creation support system inputs one of the multiple evaluations into multiple document creation models, thereby outputting documents corresponding to each of the multiple evaluation items in parallel from the multiple document creation models.

8. A method for assisting in writing, A document creation support method comprising an information processing device performing each step of the document creation support system described in any one of claims 1 to 7.

9. It is a program, A program that causes a computer to perform each step of the document creation support system described in any one of claims 1 to 7.

Images