Text creation support system, text creation support method, and program

Abstract

To provide a text creation support system, etc. allowing job applicants to utilize scouting documents that they receive.SOLUTION: There is provided is a text creation support system. The text creation support system includes a processor. The processor is configured to execute the following steps: a receiving step of receiving input of a plurality of scout documents transmitted to a job applicant; a creation step of instructing artificial intelligence to create a summary obtained by summarizing the plurality of scout documents, inputting the plurality of scout documents into the artificial intelligence, and causing it to create the summary; and a presentation step of presenting correction content for a first sentence relating to a job history of the job applicant based on the summary.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 Documents 1 and 2, systems are known in which a recruiter such as a company sends a scouting document to a job seeker by referring to the job seeker's resume and curriculum vitae. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-4048 A [Patent Document 2] JP 2007-323514 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned conventional technology, a job seeker can consider which companies to apply to from the scouting document, but no further use of the scouting document is anticipated.

[0005] In view of the above circumstances, the present invention provides a writing support system etc. that can utilize the scouting documents received by job seekers. [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 execute the following steps: In the reception step, an input of a plurality of scout documents sent to a job seeker is received. In the creation step, an artificial intelligence is instructed to create a summary that aggregates the plurality of scout documents, and the AI ​​is caused to create the summary by inputting the plurality of scout documents. In the presentation step, corrections to a first sentence regarding the job seeker's work history are presented based on the summary.

[0007] According to this embodiment, a plurality of scout documents received by a job seeker are aggregated and summarized, allowing the job seeker to utilize the scout documents. [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] FIG. 2 is a block diagram showing the hardware configuration of a recruiter terminal 20 and a job seeker terminal 30. [Figure 4] FIG. 2 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiter 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 scout document. [Figure 6] 13 is an example of a scout document list screen LD displayed on the job seeker terminal 30. [Figure 7] 13 is an example of a summary screen TD of a scout document displayed on a job seeker terminal 30. [Figure 8] 13 is an example of a summary screen DD of a scout document displayed on a job seeker terminal 30. [Figure 9] 13 is an example of a skill addition screen AD displayed on the job seeker terminal 30. [Figure 10]2 is an activity diagram showing a flow of information processing (processing for presenting corrections to a first sentence) executed by the writing support system 1. FIG. 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 comprises a communication line 2, a server device 10, a plurality of recruiter terminals 20, and a plurality of job seeker terminals 30. The server device 10, the recruiter terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the recruiter terminals 20, and the job seeker terminals 30 and the communication line 2 may be wired or wireless.

[0015] The writing support system 1 constitutes part of a recruitment and job search system used by recruiters of multiple companies and the like (first recruiter U1 and second recruiter U2) and multiple job seekers (first job seeker U3 and second job seeker U4). The writing support system 1 mainly creates resumes and curriculum vitae for job seekers, and sends scouting documents (scouting emails or scouting messages) from recruiters to job seekers. 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] <Employer Terminal 20> Fig. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the recruiter terminal 20 comprises 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 inside the recruiter terminal 20 via the communication bus 26. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here as they are the same as the explanation of each unit in the server device 10. Note that the recruiter terminal 20 may be a terminal operated by an intermediary who interacts with job seekers on behalf of the recruiter.

[0022] <Input section 24> The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 may execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter 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 tap operations, swipe operations, and the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, and 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 the user. The output unit 25 may be included in the housing of the recruiter 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 recruiter 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 the same as the descriptions of the respective units in the recruiter 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 recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0027] As shown in Fig. 4A, server device 10 (control unit 11) includes a basic display control unit 111, a recruiter registration unit 112, a job seeker registration unit 113, a history storage unit 114, a flag assignment unit 115, a reception unit 116, a statistical display control unit 117, a creation unit 118, a presentation unit 119, a correction unit 120, and an artificial intelligence unit 121. As shown in Fig. 4B, recruiter terminal 20 (control unit 21) includes a display unit 211 and an operation reception unit 212. As shown in Fig. 4C, job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation reception unit 312.

[0028] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the recruiter terminal 20 or the job seeker terminal 30. For example, the basic display control unit 111 displays, on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30, resumes and curriculum vitae prepared by the job seeker, scouting documents prepared by the recruiter or intermediary, summaries prepared by the preparation unit 118, corrections presented by the presentation unit 119, etc.

[0029] <Employer Registration Section 112> The recruiter registration unit 112 is configured to register recruiters to use the service. For example, the recruiter registration unit 112 accepts input from the operation acceptance unit 212 of the recruiter terminal 20, and stores the name, location, representative, business details, working conditions (job advertisement), etc. of the recruiter in the memory unit 12. Recruiters include organizations such as profit-making corporations (e.g., companies, etc.), non-profit corporations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.). If the recruiter terminal 20 is a terminal operated by an intermediary that interacts with job seekers on behalf of recruiters, the recruiter registration unit 112 is configured to register the intermediary to use the service.

[0030] <Job Seeker Registration Department 113> The job seeker registration unit 113 is configured to register a job seeker to use the service. For example, the job seeker registration unit 113 accepts an input from the operation acceptance unit 312 of the job seeker terminal 30, and stores the job seeker information including the job seeker's resume, curriculum vitae, and other profile information in the storage unit 12.

[0031] A "resume" is a document that mainly describes a job seeker's profile, current situation, educational background, employment history, desired working conditions, etc., while a "career history" is also called a résumé, and is a document in which a job seeker conveys to a recruiter or intermediary his or her work history, experience, skills, qualifications, etc. regarding his or her past work. The job seeker registration unit 113 also registers the industry and occupation desired by the job seeker as job seeker information.

[0032] <History memory section> The history storage unit 114 stores the transmission history of multiple scout documents. Specifically, the history storage unit 114 stores, as the transmission history, information about the sender (recruiter or intermediary), the destination job seeker, the job posting linked to the scout document, the transmission date and time, etc., for scout documents sent directly or indirectly by recruiters to job seekers.

[0033] Scouting documents may be created and sent by the employer themselves, or by an intermediary on behalf of the employer. An intermediary is an agent who acts as an intermediary between the job seeker and the employer, and is also called a headhunter or agent. The scouting documents handled by writing support system 1 include scouting documents sent by the employer to the job seeker, and scouting documents sent by an intermediary on behalf of the employer (scouting documents sent indirectly by the employer).

[0034] FIG. 5 is a diagram showing an example of a display screen SD for a scout document. On the display screen SD, a scout document DO is displayed together with a summary DS of the job information in the scout document (items extracted from the job posting). A back button SB1, a reply button SB2, and a delete button SB3 are arranged in the header of the display screen SD. The back button SB1 is a button for returning to the list of scout documents. The reply button SB2 is a button for calling up a function for creating a reply document. The delete button SB3 is a button for deleting the open scout document. Each button (including buttons on other screens described later) functions when pressed using an input device (e.g., a mouse, a trackpad, a touch panel, etc.).

[0035] <Flag assignment section> The flagging unit 115 assigns to the multiple scout documents a ranking flag indicating the transmission ranking of the multiple scout documents sent based on the same job posting. Specifically, the flagging unit 115 assigns a ranking flag indicating the transmission ranking, such as 1st, 2nd, 3rd, etc., to each of the multiple scout documents created based on one job posting and addressed to a job seeker, in order of the earliest transmission date and time, based on the transmission history. This allows the job seeker who receives the scout document to understand the degree of attention given to him / her by the recruiter or intermediary from information based on the ranking flag. In other words, the job seeker who receives the scout document sent in an earlier order can understand that he / she is highly noticed by the recruiter or intermediary. In addition, the ranking flag can be used as a condition when the job seeker searches for, rearranges, or narrows down a specific scout document from the multiple scout documents he / she has received, and when selecting a target for creating a summary of the multiple scout documents.

[0036] The ranking flag may be displayed on the job seeker terminal 30 in a manner that includes information on the ranking sent as is, such as "Second scout." The ranking flag may also be displayed on the job seeker terminal 30 in a manner that indicates that the scout document was sent up to a predetermined specific round number (round number). For example, for the scout documents sent up to the 10th, the ranking flag may be displayed on the job seeker terminal 30 in a manner that converts information on the ranking sent into a label or tag that includes a predetermined round number, such as "First 10 people."

[0037] When an intermediary sends a scouting document as an agent of a recruiter, the flagging unit 115 may add up the scouting document sent directly from the recruiter and the scouting document sent from the intermediary (the scouting document sent indirectly from the recruiter) linked to a specific job posting, and may add a ranking flag. Also, when scouting documents are sent from multiple intermediaries for one job posting, the flagging unit 115 may add up the scouting documents sent from all the intermediaries and add a ranking flag.

[0038] <Reception Section 116> The reception unit 116 is configured to receive a designation of a scout document from the job seeker terminal 30. Specifically, the reception unit 116 receives input of a plurality of scout documents sent to the job seeker by the employer or intermediary. Here, the input scout documents include the message portion of the scout document and any attachments such as job advertisements that are attached to the message. The job seeker uses the job seeker terminal 30 to select some or all of the plurality of scout documents that have already been received as targets for creating a summary.

[0039] Fig. 6 is an example of a list screen LD of scout documents displayed on the job seeker terminal 30. The list screen LD displays a list of summaries SS of each scout document received by the job seeker terminal 30. The summary SS includes a facial photo MP of the recruiter, the name MN of the recruiter, the name ON of the employer who sent the scout document, the scout document heading ST, a first label L1, a second label L2, a third label L3, a sending date DT, and a check box CB. The display screen SD of Fig. 5 is displayed by selecting any scout document from the list screen LD.

[0040] The labels L1-L3 given to the summary SS are given based on the job information, the scout document information, other information, etc. The number and types of labels given to one scout document are not particularly limited.

[0041] The first label L1 and the second label L2 are attached based on job information such as whether the job content (industry, job type, working conditions, etc.) matches the job seeker's desired conditions (desired industry, job type, etc.), whether the job advertisement is attached to the scouting document, whether the job is public or private, etc.

[0042] The third label L3 is attached based on scout document information related to the properties of the scout document. The scout document information includes, for example, the sending order of multiple scout documents based on the same job posting, and the third label L3 includes the above-mentioned order flag.

[0043] The checkboxes CB are used to select any scout document when performing processing on multiple scout documents (for example, creating a summary of multiple scout documents, displaying statistics, etc.).

[0044] <Statistics display control unit 117> The statistical display control unit 117 displays the number of scout documents received by the job seeker for each category that has as classification conditions at least one of the target industry, target job type, reception date and time, and classification flag based on any information included in the scout documents. This allows the job seeker to know the number of scout documents received for each category specified as a classification condition, and therefore to check the trends of scout documents sent to him / her. It also makes it easy to narrow down the scout documents whose contents should be checked.

[0045] 7 is an example of a scout document tally screen TD displayed on the job seeker terminal 30. The tally screen TD displays a number of classification display fields CC that display the number of scout documents for each classification item, a selection display field SC that displays the number of scout documents selected by the job seeker, a confirmation button RB, and an analysis button AB.

[0046] The categories (classification items) in the classification display field CC include the target industry, the target job type, the reception date and time, and the classification flag. The categories displayed on the summary screen TD can be arbitrarily selected by the job seeker or the administrator of the writing support system 1.

[0047] In the example of Figure 7, the categories displayed are a category based on the target industry ("Industry: IT"), a category based on the target job type ("Job: Sales"), a category based on the date and time of receipt ("Scouts received within the last week"), and a category based on a classification flag ("Scouts that match desired conditions" and "Top 10 people").

[0048] The classification flag includes the properties of the scout document and the recruitment conditions based on the contents of the scout document. The properties of the scout document include, for example, whether the target recruitment is ongoing, whether a reply to the scout document has been received, whether the selection process for the target recruitment is progressing, etc. The status of the scout document also includes the order in which the scout document was sent among multiple scout documents sent based on the same job posting.

[0049] The recruitment conditions based on the contents of the scout document are extracted from the main text of the scout document or the contents of the recruitment advertisement attached to the main text, and are detailed conditions other than the industry and job type. Examples of the recruitment conditions include the job title (e.g., "management position"), whether remote work is possible, whether side jobs are possible, whether the company is listed or unlisted, whether it is a large company or a small or medium-sized company, whether there will be transfers, whether weekends and holidays are off, whether there is flextime, etc.

[0050] The selection display field SC displays the number of scout documents whose check boxes CB are checked on the list screen LD. When the confirmation button RB is pressed, the job seeker terminal 30 receives any unreceived scout documents. When the analysis button AB is pressed, the creation unit 118 starts creating summaries of the scout documents.

[0051] <Creation Department 118> The creation unit 118 is configured to perform information processing on scout documents received by a job seeker. The creation unit 118 instructs the artificial intelligence to create a summary that aggregates a plurality of scout documents, and inputs the plurality of scout documents to the artificial intelligence to create the summary. Specifically, the creation unit 118 instructs the artificial intelligence to create a summary that integrates the plurality of scout documents by using a prompt, and inputs a sample of the plurality of scout documents and a sample of a summary created from the sample of the plurality of scout documents to the artificial intelligence as templates. Then, the creation unit 118 inputs the plurality of scout documents to be processed to the artificial intelligence to create a summary that aggregates the plurality of scout documents. Alternatively, the creation unit 118 prepares an artificial intelligence equipped with a learning model that has been trained using the sample of the plurality of scout documents and the sample of a summary created from the sample of the plurality of scout documents as teacher data, inputs the plurality of scout documents to be processed to the artificial intelligence, and instructs the artificial intelligence to create a summary that aggregates the plurality of scout documents, thereby causing the artificial intelligence to create the summary.

[0052] A summary created by aggregating multiple scout documents is a single document that takes a collection of different scout documents as input, consolidates and summarizes their contents, and summarizes them into a short document. In other words, this summary is different from a collection of multiple scout documents, each of which is summarized individually. Furthermore, this summary may contain multiple sentences or items. By creating this summary, a job seeker who has received many scout documents can efficiently understand the contents of the scout documents they have received without having to open each one.

[0053] The creation unit 118 creates, as a summary, a second sentence regarding points on which the sender of the scouting document has focused on the job seeker. Specifically, the creation unit 118 extracts points on which the sender of the scouting document (employer or intermediary) is presumed to have focused on the job seeker from multiple scouting documents, and creates a second sentence including the extracted points. This makes it possible to create a summary that enables a job seeker who has received many scouting documents to efficiently understand the evaluation from the recruiter or intermediary. The points that have been focused on are, for example, points evaluated or expected by the recruiter or intermediary, and include items related to the job seeker's experience, qualifications, skills, etc.

[0054] The creation unit 118 creates a summary from multiple scouting documents selected by the job seeker. This allows the creation of a summary that focuses on scouting documents that are of great interest to the job seeker, making it possible to create a summary that is highly useful to the job seeker.

[0055] Specifically, the creation unit 118 creates a summary of the scout documents displayed as the number of items in the selection display field SC on the tally screen TD (that is, selected by the job seeker on the list screen LD).

[0056] Furthermore, the creation unit 118 creates summaries from scout documents that satisfy at least one specified condition among the target industry, target job type, reception date and time, and classification flags based on any information included in the scout documents. This allows a summary to be obtained based on scout documents that are of high interest to the job seeker, so that the job seeker can check the evaluation from the sender of the scout document according to the industry, job type, conditions, etc. that the job seeker desires.

[0057] For example, the creation unit 118 creates a summary from scout documents that are displayed as a number in one classification display field CC selected on the tally screen TD (i.e., those included in the category selected by the job seeker). When a ranking flag category such as "top 10 people" is selected from among these, the creation unit 118 creates a summary from those scout documents that satisfy the specified conditions related to the ranking flag among multiple scout documents. This allows a summary to be obtained that aggregates scout documents that show a high desire to hire the job seeker, allowing the job seeker to know the contents that are particularly highly evaluated by employers or intermediaries. Note that the creation of a summary from scout documents that satisfy the specified conditions related to the ranking flag may be performed automatically without receiving instructions from the job seeker.

[0058] The creation unit 118 may also refer to the desired industry, occupation, or organization registered by the job seeker, and create a summary from a scout document that satisfies a specified condition related to these. For example, the creation unit 118 may set the job seeker's desired industry itself or the industry in which the desired organization is hiring as a specified condition, and then create a summary from a scout document that satisfies the specified condition.

[0059] Furthermore, when the job seeker does not specify a desired industry, occupation, or organization, the creation unit 118 may create a summary from the scout document of the industry or occupation that is received most frequently among the multiple scout documents received by the job seeker. This makes it possible to propose the industry or occupation that is attracting attention to the job seeker as a candidate for employment to the job seeker who has not yet decided on a desired industry or occupation.

[0060] 8 is an example of a summary screen DD of a scout document displayed on the job seeker terminal 30. The summary screen DD includes a summary display field DF for the scout document, a correction presentation field FF, and a skill presentation field SF. The summary created by the creation unit 118 is displayed in the summary display field DF.

[0061] The summary may be one sentence including one period, or may be a sentence consisting of two or more sentences. The summary does not have to be a complete sentence, but may be an incomplete sentence consisting of one word or multiple words. The summary may also include multiple items (sentences).

[0062] <Presentation part 119> The presenting unit 119 presents corrections to the first text regarding the work history of the job seeker based on the summary created by the creating unit 118. The first text includes job seeker information including a resume, a curriculum vitae, and other profile information created by the job seeker.

[0063] The presentation unit 119 instructs the artificial intelligence to create corrections from the summary, and inputs the summary to the artificial intelligence to create the corrections. Specifically, the presentation unit 119 prompts the artificial intelligence to create corrections from a summary that aggregates multiple scout documents, and inputs a sample of the summary and a sample of corrections to the sample of the summary to the artificial intelligence as templates. Then, the presentation unit 119 inputs the summary to be processed to the artificial intelligence and causes the artificial intelligence to create the corrections. Alternatively, the presentation unit 119 prepares an artificial intelligence equipped with a learning model that has been trained using the sample of the summary and the sample of corrections to the sample of the summary as teacher data, inputs the summary to be processed to the artificial intelligence, and instructs the artificial intelligence to create corrections, thereby causing the artificial intelligence to create the corrections.

[0064] The correction content created by the presentation unit 119 is displayed in the correction presentation field FF on the summary screen DD. The correction content may be one sentence including one period, or may be a sentence consisting of two or more sentences. Furthermore, the correction content does not need to be a complete sentence, and may be an incomplete sentence consisting of one word or multiple words. Furthermore, the correction content may include multiple items (sentences).

[0065] The presentation unit 119 creates the correction content by comparing the first sentence with the second sentence created as a summary by the creation unit 118. Specifically, by generating a prompt for the artificial intelligence, the first sentence and the second sentence to be processed are input to the artificial intelligence, the difference between the first sentence and the second sentence is extracted, and based on the extracted difference, the artificial intelligence is instructed to create the correction content of the first sentence, thereby causing the artificial intelligence to create the correction content. In this way, it is possible to present to the job seeker that the first sentence should reflect points of interest from the sender of the scouting document that are not included in the current first sentence.

[0066] The correction content may include a content that further emphasizes the content already included in the first sentence. In this case, the presentation unit 119 inputs the first sentence and the second sentence to be processed to the artificial intelligence, and instructs the artificial intelligence to create the correction content by comparing the first sentence with the second sentence and creating the content that is identified as being to be emphasized in the first sentence as the correction content, thereby causing the artificial intelligence to create the correction content.

[0067] Furthermore, the presentation unit 119 creates the revision content by referring to the recruitment information of the industry, occupation, or organization that the job seeker desires. This makes it possible to present to the job seeker the revisions required to obtain a first sentence that can effectively appeal to the recruitment of the industry, occupation, or organization that the job seeker desires.

[0068] Specifically, the presentation unit 119 extracts job information related to the desired industry, occupation or organization registered by the job seeker from the database of the writing support system 1, and creates the revision content by comparing the summary created by the creation unit 118 with the extracted job information. For example, the presentation unit 119 incorporates items included in both the summary and the job information related to the desired industry, occupation or organization registered by the job seeker as important items in the revision content.

[0069] The presentation unit 119 presents a correction to the expression included in the first sentence based on the summary created by the creation unit 118 or the phrase used in the job seeker search by the sender of the scout document. For example, the presentation unit 119 creates a correction content to change the expression "sales" included in the first sentence to "CS (customer success)" included in the summary or the phrase used in the job seeker search by the recruiter or intermediary. Such a rephrasing of synonyms or similar words may be presented with reference to a list of synonyms and similar words stored in advance in the storage unit 12. This makes it possible to present the expression used by the recruiter or intermediary in the scout document or job seeker search as the correction content for the first sentence. As a result, the job seeker can change the first sentence to a content that is easily searched for by the recruiter or intermediary.

[0070] The presentation unit 119 may create and present the correction content of the first sentence based only on the job information. Specifically, when a scout document from the industry, job type, or organization desired by the job seeker is not included among the multiple scout documents received by the job seeker, the presentation unit 119 may extract job information related to the industry, job type, or organization desired by the job seeker, and words and phrases used in job seeker searches in the industry, job type, or organization desired by the job seeker, and present them as the correction content of the first sentence.

[0071] The presentation unit 119 presents candidates for skill information to be added to the first sentence. This allows the job seeker to understand the skills that the recruiter or intermediary agent is paying attention to, and allows the job seeker to add the skill to the first sentence in a simple procedure by selecting the candidate.

[0072] Specifically, the presentation unit 119 first extracts keywords related to the skills of the job seeker contained in the summary or the points of interest. A list of skill-related keywords is registered in advance in the database of the storage unit 12. The keywords may be extracted by comparing with the list, or may be extracted by natural language processing using artificial intelligence. Next, the presentation unit 119 determines whether the extracted keywords are registered as "skill" information in the job seeker information recorded in the storage unit 12. If the keyword is not registered, the presentation unit 119 presents the keyword as a candidate for skill information. This makes it possible to identify and present, for example, skills that are described as part of a sentence in a resume but are not registered as "skill" information and that are evaluated by a recruiter or an intermediary. This makes it easier to create job seeker information that is easier for recruiters or intermediaries to search.

[0073] The skill candidates SK presented by the presentation unit 119 are displayed in the skill presentation field SF of the summary screen DD. When the job seeker selects any candidate SK, the skill information corresponding to the selected candidate SK is added to the first document (either a resume, a curriculum vitae, or other profile information).

[0074] The presentation unit 119 assigns a weighted score to the summaries created by the creation unit 118, and presents the revision contents by preferentially referring to summaries with high scores. This makes it easier for summaries that are important to the job seeker to be reflected in the revision contents, so that it is possible to present revision contents that are more beneficial to the job seeker.

[0075] Specifically, the presentation unit 119 assigns a weighting score to each item or sentence included in the summary. Furthermore, the presentation unit 119 creates a prompt written to reflect items or sentences with high scores in the correction content in preference to items or sentences with low scores, and causes the artificial intelligence to create the correction content. Note that items or sentences with scores below a certain value may not be reflected in the correction content. Furthermore, the presentation unit 119 may display items or sentences with high scores in preference to items or sentences with low scores on the summary screen DD for items or sentences included in the summary. Furthermore, the presentation unit 119 may not display items or sentences with scores below a certain value on the summary screen DD.

[0076] Furthermore, the presentation unit 119 assigns a weighted score to the correction content, and presents the correction content with a higher score preferentially. This makes it possible to prevent the excessive number of correction contents from causing a decrease in the visibility of information, and makes it easier for the job seeker to understand the correction content that is important to him or her. Therefore, the job seeker can select the correction content that is more beneficial to him or her.

[0077] Specifically, the presentation unit 119 assigns a weighted score to each item or sentence included in the correction content. Furthermore, the presentation unit 119 displays items or sentences with high scores in the correction suggestion column FF or the skill presentation column SF in preference to items or sentences with low scores. Furthermore, the presentation unit 119 may not display items or sentences with scores below a certain value in the correction suggestion column FF or the skill presentation column SF.

[0078] The presentation unit 119 gives a high score to an abstract or revision content related to words used in a job seeker search by the sender of the scout document. This allows the job seeker to create an abstract or revision content that reflects words used by a recruiter or intermediary agent when searching for a job seeker, so that the job seeker can revise the first sentence to a content that is easily searched for by a recruiter or intermediary agent.

[0079] Specifically, the presentation unit 119 increases the score of an item or sentence that includes an expression that is the same as or similar to a term used in a job seeker search by a recruiter or intermediary among items or sentences included in the summary or items or sentences included in the revision content. Furthermore, the presentation unit 119 adjusts the score so that the score is higher for an item or sentence that includes an expression that is the same as or similar to a term that is used frequently in a job seeker search.

[0080] In addition, the presentation unit 119 increases the score for the summary or correction content related to the recruitment information of the industry, occupation, or organization that the job seeker desires. This makes it possible to present to the job seeker effective selling points for the recruitment of the industry, occupation, or organization that the job seeker desires.

[0081] Specifically, the presentation unit 119 increases the score of items or sentences included in the summary or the items or sentences included in the revision content that contain expressions that are identical or similar to words and phrases contained in job information related to the industry, job type, or organization desired by the job seeker.

[0082] Furthermore, the presenting unit 119 gives a higher score to summaries or revisions based on multiple scout documents with recent reception dates. This prevents the creation of summaries or revisions based on scout documents for which job offers have already ended or on scout documents with old information. This makes it possible to create summaries or revisions that are more useful to job seekers.

[0083] Specifically, the presentation unit 119 refers to the first record stored by the creation unit 118 when the summary was created, or the second record stored by the presentation unit 119 when the correction contents were created, and assigns a higher score to an item or sentence included in the summary or an item or sentence included in the correction contents, the newer the average value of the reception date and time of the referenced scout document. Furthermore, the presentation unit 119 does not need to display correction contents that reference a scout document whose reception date and time is older than a predetermined date and time in the correction presentation column FF or skill presentation column SF.

[0084] The first record is information indicating the scout document that the creation unit 118 referenced (used as a source) for each item or sentence of the summary, and is stored in the memory unit 12 by the creation unit 118. The second record is information indicating the item or sentence of the summary that the presentation unit 119 referenced for each item or sentence of the correction contents, and is stored in the memory unit 12 by the presentation unit 119. By linking the item or sentence of the summary of the second record with the scout document of the first record, the scout document that was referenced for each item or sentence of the correction contents is identified.

[0085] In this way, the presentation unit 119 assigns a weighted score to the summary or revision content based on at least one of the words used in the job seeker search, the job seeker's desired conditions (industry, job type, or organization), and the date and time of receipt of the scout document.

[0086] Furthermore, the presenting unit 119 may weight according to the information on which the presented correction content is based. For example, the presenting unit 119 may weight based on the type of information source, such as items or sentences based only on the scout document, items or sentences based on the job information of the organization desired by the job seeker, items or sentences based on the job information of organizations other than the organization desired by the job seeker, etc. In this case, items or sentences based on the job information of the organization desired by the job seeker are given a higher score than other items or sentences.

[0087] For example, an item or sentence based on a normal scouting document (a scouting document sent from an organization other than the job seeker's desired organization) may be scored at 10 points, an item or sentence based on a scouting document from the job seeker's desired organization may be scored at 20 points, and an item or sentence related to a term used in a job seeker search may be scored at 30 points. Similarly, the presenting unit 119 may weight the summary according to the information on which the created summary is based. Specifically, for items or sentences included in the summary, an item or sentence based on a scouting document that matches the job seeker's desired conditions (industry, job type, or organization) may be scored at 20 points, and an item or sentence based on a scouting document from another industry, job type, or organization may be scored at 10 points.

[0088] <Correction part 120> The correcting unit 120 receives a correction instruction from the job seeker terminal 30 to which the correction content is presented, and corrects the first sentence according to the correction instruction. The correction instruction includes adding and correcting items to the first sentence.

[0089] The correction instruction may include a freely input sentence, word, etc., or may include the whole or part of the correction content presented by the presentation unit 119. Based on the input of the correction instruction from the job seeker terminal 30, the correction unit 120 may automatically reflect the correction content presented by the presentation unit 119 in the first sentence.

[0090] When the job seeker selects a skill candidate SK on the summary screen DD in Fig. 8, the correction instruction includes skill information linked to the selected candidate SK. The correction unit 120 may also accept input of a skill candidate via an add skill button SA1 on the summary screen DD. Fig. 9 is an example of a skill addition screen AD displayed on the job seeker terminal 30. When the add skill button SA1 is pressed, the skill addition screen AD is displayed on the job seeker terminal 30. The skill addition screen AD includes a skill input frame SI, a save button SA2, and an add frame button SA3.

[0091] In the skill input box SI, the job seeker can input any skill name. When the save button SA2 is pressed, the skills input in the multiple skill input boxes SI are added to the skill presentation field SF on the summary screen DD. When the add box button SA3 is pressed, a new skill input box SI is added.

[0092] The correction unit 120 reflects the correction items included in the correction instruction in any of the resume, curriculum vitae, and other profile information included in the first sentence. Specifically, in the case of correction items based on points of interest, the correction unit 120 reflects the contents included in the correction items in the "job summary" or "work history" included in the curriculum vitae.

[0093] <Artificial Intelligence Department 121> The artificial intelligence unit 121 is configured to receive input from each functional unit and return an 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.

[0094] The artificial intelligence unit 121 is an AI (Artificial Intelligence) equipped with language models such as 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), and Recurrent Neural Networks (RNN), and includes a generative AI.

[0095] 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. The artificial intelligence unit 121 can apply the above algorithms as appropriate.

[0096] The artificial intelligence unit 121 has, as artificial intelligence, a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data is composed of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

[0097] The artificial intelligence unit 121 includes, as the artificial intelligence, a general-purpose learning model for natural language processing, such as a large-scale language model (LLM) that has learned a huge amount of data. Such a general-purpose learning model includes a language model that can handle various tasks without fine tuning by one-shot learning, few-shot learning, or the like. 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.

[0098] For example, the artificial intelligence unit 121 may include another learning model (artificial intelligence) used between the creation of the summary by the creation unit 118 and the creation of the correction content by the presentation unit 119. One learning model is trained to take multiple scout documents as input and output a summary, and another learning model is trained to take the summary as input and output the correction content of the first sentence. In addition, when a general-purpose learning model is used, a prompt is issued to input multiple scout documents and output a summary, and a prompt is issued to input the summary and output the correction content of the first sentence.

[0099] The artificial intelligence included in the artificial intelligence unit 121 is capable of additional learning. For example, the artificial intelligence unit 121 learns whether the proposed correction content was used by the job seeker in the first sentence. That is, the artificial intelligence unit 121 performs additional learning and fine-tuning using a teacher data set that is a combination of the scout document and the actual correction result of the first sentence, which is labeled as feedback for the correction content created by the artificial intelligence. As a result, the correction content output from the learning model is optimized and presented to the user.

[0100] <Display section> The display unit 211 of the recruiter terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen indicated by the screen data transmitted from the server device 10.

[0101] <Operation reception section> The operation acceptance unit 212 of the recruiter terminal 20 accepts operations by a user (recruiter) who uses the recruiter terminal 20. The operation acceptance unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

[0102] 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.

[0103] Specifically, this information processing method includes a receiving step, a creating step, a presenting step, and a correcting step. In the receiving step, input of multiple scout documents sent to a job seeker from an employer or an intermediary is received. In the creating step, an artificial intelligence is instructed to create a summary that aggregates the multiple scout documents, and the AI ​​is caused to create the summary by inputting the multiple scout documents. In the presenting step, corrections to a first sentence regarding the job seeker's work history are presented based on the summary. In the correcting step, the correction instructions are received, and the first sentence is corrected in accordance with the correction instructions.

[0104] 10 is an activity diagram showing the flow of information processing (processing of presenting corrections to the first sentence) executed by the writing support system 1. The information processing will be described below along with each activity in this activity diagram.

[0105] The process of presenting corrections to the first sentence begins when the job seeker receives a scout document sent to the job seeker terminal 30. The job seeker selects the scout document for which a summary is to be created (analyzed) on the job seeker terminal 30 (activity A101). Next, the job seeker instructs the server device 10 on the job seeker terminal 30 to create a summary (activity A102).

[0106] The server device 10 accepts input of the scout document to be analyzed, which is included in the instructions sent from the job seeker terminal 30 (reception step, activity A103). Next, the server device 10 causes the artificial intelligence to create a summary of the scout document (creation step, activity A104). Furthermore, the server device 10 creates revisions based on the summary, and performs control to display (present) the summary and revisions on the job seeker terminal 30 (presentation step, activity A105). Through this control, the summary and revisions are displayed on the job seeker terminal 30 (activity A106).

[0107] After the summary and the corrections are displayed on the job seeker terminal 30, the job seeker inputs the corrections to the first sentence on the job seeker terminal 30 (activity A107). The server device 10 accepts the corrections from the job seeker terminal 30 (activity A108). Next, the server device 10 corrects the first sentence (activity A109).

[0108] 4. Effect The operation of this embodiment can be summarized as follows: Based on the summary of the scout document received by the job seeker, suggestions are made to correct the job seeker's work history. As a result, the job seeker can confirm an objective evaluation of himself / herself and can add information required by the recruiter or intermediary agent to the work history.

[0109] 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.

[0110] 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 121 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 121, 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.

[0111] 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.

[0112] It may be provided in any of the following ways:

[0113] (1) A writing support system comprising a processor configured to execute each of the following steps: a reception step, receiving input of a plurality of scout documents sent to a job seeker; a creation step, instructing an artificial intelligence to create a summary aggregating the plurality of scout documents; inputting the plurality of scout documents into the artificial intelligence to cause it to create the summary; and a presentation step, presenting corrections to a first sentence regarding the job seeker's work history based on the summary.

[0114] (2) In the writing support system described in (1) above, in the writing step, a second sentence is created as the summary, which is a second sentence regarding a point that has attracted the attention of the sender of the scouting document.

[0115] (3) In the writing support system described in (2) above, in the presenting step, the correction content is created based on a comparison between the first sentence and the second sentence.

[0116] (4) In the writing support system described in any one of (1) to (3) above, in the presentation step, the revision content is created by referring to job information for the industry, job type, or organization desired by the job seeker.

[0117] (5) In the writing support system described in any one of (1) to (4) above, in the presenting step, a correction to an expression contained in the first sentence is suggested based on words used in a job seeker search by the sender of the summary or the scout document.

[0118] (6) In the writing support system according to any one of (1) to (5) above, in the presenting step, candidates for skill information to be added to the first sentence are presented.

[0119] (7) In the writing support system described in any one of (1) to (6) above, in the presentation step, an artificial intelligence is instructed to create the correction content from the summary, and the summary is input to the artificial intelligence to create the correction content.

[0120] (8) In the writing support system described in any one of (1) to (7) above, in the presentation step, a weighted score is assigned to the correction content, and the correction content with a high score is presented preferentially.

[0121] (9) A writing support system according to any one of (1) to (8) above, wherein in the presentation step, a weighted score is assigned to the summaries, and the summaries with higher scores are given priority in presenting the revisions.

[0122] (10) In the writing support system described in (8) or (9) above, in the presentation step, the score is increased for the summary or the correction content related to words used in a job seeker search by the sender of the scout document.

[0123] (11) In the writing support system described in any one of (8) to (10) above, in the presentation step, the score is increased for the summary or the correction content related to the job information in the industry, job type, or organization desired by the job seeker.

[0124] (12) In the writing support system described in any one of (8) to (11) above, in the presentation step, the score is increased for the summary or the correction content based on the multiple scout documents with the most recent reception date and time.

[0125] (13) In the writing support system described in any one of (1) to (12) above, in the creating step, the summary is created from the plurality of scout documents selected by the job seeker.

[0126] (14) In the writing support system described in any one of (1) to (13) above, in the creation step, the summary is created from a scout document among the plurality of scout documents that satisfies specified conditions regarding at least one of the target industry, the target job type, the date and time of receipt, and a flag based on any information contained in the scout document.

[0127] (15) In the writing support system described in any one of (1) to (14) above, in the creation step, when the job seeker does not specify a desired industry, job type, or organization, the summary is created from a scout document that is received more frequently from the multiple scout documents received by the job seeker and that corresponds to the industry or job type that is received more frequently from the multiple scout documents received by the job seeker.

[0128] (16) In the writing support system described in any one of (1) to (15) above, the processor is configured to further execute the following steps, in which in the statistical display control step, the number of the multiple scout documents received by the job seeker is displayed for each category using at least one of the target industries, target job types, reception dates and times, and flags based on any information contained in the scout documents as classification conditions.

[0129] (17) In the writing support system described in any one of (1) to (16) above, the processor is configured to further execute the following steps: in a history storage step, storing a sending history of the plurality of scout documents; and in a flagging step, assigning to the plurality of scout documents a ranking flag indicating the sending ranking among the plurality of scout documents sent based on the same job posting.

[0130] (18) In the writing support system described in (17) above, in the creation step, the summary is created from a scout document among the plurality of scout documents that satisfies a specified condition regarding the ranking flag.

[0131] (19) A method for assisting with writing, comprising the steps of the writing support system described in any one of (1) to (18) above.

[0132] (20) A program that causes a computer to execute each step of the writing support system described in any one of (1) to (18) above. Of course, this is not the case.

[0133] 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]

[0134] 1: Writing support system 2: Communication lines 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter 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: Basic display control unit 112: Employer Registration Department 113: Job Seeker Registration Department 114: History memory unit 115: Flag assignment section 116: Reception 117: Statistics display control section 118: Creation Department 119: Presentation section 120: Correction section 121: 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 presentation step, the document creation support system presents revisions to the first document concerning the job seeker's work history, based on at least one of the job information related to the job seeker's desired industry, occupation, or organization, extracted from the database, and the terms used in the job seeker search by the employer or intermediary, wherein the revisions include candidate skill information to be added to the first document.

2. In the document creation support system described in Claim 1, The aforementioned processor is configured to perform the following steps: In the registration step, the applicant receives input from multiple recruitment documents sent to the aforementioned job seeker. The aforementioned presentation step involves a document creation support system that presents the revised content based on the terms used in the job seeker search conducted by the recruiter or intermediary who sent the scouting document.

3. In the document creation support system described in Claim 1, The aforementioned modifications include revisions to expressions contained in the first sentence, and are part of a document creation support system.

4. In the document creation support system described in claim 1, In the aforementioned presentation step, the document creation support system assigns a weighted score to the revisions and prioritizes presenting the revisions with the highest scores.

5. In the document creation support system described in claim 4, The aforementioned step involves a document creation support system that increases the score for the modified content related to the terms used in job seeker searches by the employer or the intermediary.

6. In the document creation support system described in claim 4, The aforementioned presentation step involves a document creation support system that increases the score for the modifications related to the job posting.

7. A method for assisting in writing, A document creation support method comprising an information processing device that performs each step of the document creation support system described in any one of claims 1 to 6.

8. 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 6.

Images