Information processing device, method, program and system

Abstract

To provide a technique capable of reducing an input burden of a work history.SOLUTION: A program causes a computer to function as means of: acquiring first text data on the basis of work history data representing a work history of a target person; generating second text data obtained by organizing the first text data according to a sentence structure; and acquiring information of the target person organized by category name relating to the work history by providing a generation model with a prompt based on the second text data and the category name relating to the work history.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, method, program, and system.

Background Art

[0002] When a job seeker uses a job hunting support service such as a job transfer support service or a personnel matching service, they may be required to input their work history. If the burden of such input work can be reduced, it may promote the acquisition of users of the job hunting support service.

[0003] Patent Document 1 describes that a system analyzes a resume and extracts data corresponding to database fields such as contact information, work history, and academic background.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the technical idea of Patent Document 1, terms that match a database of known resume terms or terms displayed in a special font are considered as field names, associated with the field names, or field data close to the field names is extracted. That is, in this technical idea, if the terms and fonts used in the resume are not appropriate, there is a risk that necessary information cannot be extracted or inappropriate information is extracted.

[0006] An object of the present disclosure is to provide a technology capable of reducing the input burden of work history.

Means for Solving the Problems

[0007] A program according to one aspect of the present disclosure causes a computer to function as means for acquiring first text data based on resume data representing the work history of a target person, means for generating second text data obtained by organizing the first text data according to the structure of the sentences, and means for obtaining information on the target person organized by category name related to the work history by providing a prompt based on the second text data and the category name related to the work history to a generation model.

Brief Description of Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0009] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In the drawings for explaining the embodiment, the same components are generally denoted by the same reference numerals, and the repeated description thereof will be omitted.

[0010] (1) Configuration of Information Processing System The configuration of the information processing system will be described. FIG. 1 is a block diagram showing the configuration of the information processing system of the present embodiment.

[0011] As shown in FIG. 1, the information processing system 1 includes a client device 10 and a server 30. The client device 10 and the server 30 are connected via a network (for example, the Internet or an intranet) NW.

[0012] The client device 10 is an example of an information processing device that transmits a request to the server 30. The client device 10 is, for example, a smartphone, a tablet terminal, or a personal computer.

[0013] The user of the client device 10 is typically, but not limited to, a job seeker. In this specification, a job seeker includes a person who is engaged in job hunting activities or (re)employment activities, a person who is interested in these activities, or a person who has an intention to seek a job. For example, a job seeker can include a person who registers his or her own information on a job hunting support service or prepares for registration (for example, uploads a resume file or a work history file, or inputs his or her work history). The user of the client device 10 may be a person (input proxy) who inputs work history information on behalf of the person himself or herself.

[0014] The server 30 is an example of an information processing device that provides a response corresponding to a request transmitted from the client device 10 to the client device 10. The server 30 is, for example, a server computer. The server 30 can also manage job hunting support services such as a job hunting support service and a personnel matching service.

[0015] (1-1) Configuration of the client device The configuration of the client device will be described. FIG. 2 is a block diagram showing the configuration of the client device of the present embodiment.

[0016] As shown in FIG. 2, the client device 10 includes a storage device 11, a processor 12, an input / output interface 13, and a communication interface 14. The client device 10 is connected to a display 21.

[0017] The storage device 11 is configured to store programs and data. The storage device 11 is, for example, a combination of a ROM (Read Only Memory), a RAM (Random Access Memory), and a storage (e.g., a flash memory or a hard disk).

[0018] The program includes, for example, the following programs. · An OS (Operating System) program · A program of an application that executes information processing (e.g., a web browser)

[0019] The data includes, for example, the following data. · A database referred to in information processing · Data obtained by executing information processing (i.e., the execution result of information processing)

[0020] The processor 12 is a computer that realizes the functions of the client device 10 by starting the programs stored in the storage device 11. The processor 12 is, for example, at least one of the following. · A CPU (Central Processing Unit) · A GPU (Graphic Processing Unit) · An ASIC (Application Specific Integrated Circuit) · An FPGA (Field Programmable Gate Array)

[0021] The input / output interface 13 is configured to acquire information (e.g., a user's instruction) from an input device connected to the client device 10 and output information (e.g., an image) to an output device connected to the client device 10.

[0022] The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display 21, a speaker, or a combination thereof.

[0023] The communication interface 14 is configured to control communication between the client device 10 and an external device (such as the server 30).

[0024] The display 21 is configured to display an image (a still image or a moving image). The display 21 is, for example, a liquid crystal display or an organic EL display.

[0025] (1-2) Configuration of the server The configuration of the server will be described. FIG. 3 is a block diagram showing the configuration of the server of the present embodiment.

[0026] As shown in FIG. 3, the server 30 includes a storage device 31, a processor 32, an input / output interface 33, and a communication interface 34.

[0027] The storage device 31 is configured to store programs and data. The storage device 31 is, for example, a combination of a ROM, a RAM, and a storage (such as a flash memory or a hard disk).

[0028] The programs include, for example, the following programs. · An OS program · An application program for executing information processing

[0029] The data includes, for example, the following data. · A database referred to in information processing · The execution result of information processing

[0030] The processor 32 is a computer that realizes the functions of the server 30 by starting the program stored in the storage device 31. The processor 32 is, for example, at least one of the following. · CPU · GPU · ASIC · FPGA

[0031] The input / output interface 33 is configured to acquire information (for example, a user's instruction) from an input device connected to the server 30 and output information (for example, an image) to an output device connected to the server 30.

[0032] The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display.

[0033] The communication interface 34 is configured to control communication between the server 30 and an external device (for example, the client device 10).

[0034] (2) One aspect of the embodiment One aspect of this embodiment will be described. FIG. 4 is an explanatory diagram of one aspect of this embodiment.

[0035] As shown in FIG. 4, the user US1 uses the client device 10 to transmit (upload) resume data (file) related to the work history of the target person to the server 30. The target person may be the user US1 himself / herself or another person. The resume data may be data created, for example, by scanning or photographing a paper resume to convert it into an electronic file, or an electronic file created by editing work history information using document creation software. For example, it is assumed that documents or electronic files created by the target person in the past for job hunting activities are used as resume data.

[0036] Server 30 acquires (extracts) text data based on the acquired work history document data. Then, Server 30 organizes this text data according to the structure of the text.

[0037] Server 30 generates a prompt based on the organized text data and a predetermined category name related to the work history. Server 30 provides the generated prompt to generation model GM2. Generation model GM2 generates text data in which the information (work history information) of the target person is organized by category name, and outputs the text data.

[0038] Server 30 extracts information (elements by category name of work history information) of the target person by category name from the text data generated by generation model GM2. Server 30 presents an input screen for the work history to the user via client device 10 with the extracted information set in the input fields of the corresponding categories.

[0039] In this way, according to the present embodiment, user US1 can, for example, upload already created work history document data and does not have to input at least part of the work history information of the target person. That is, the input burden of the work history can be reduced.

[0040] (3) Information processing The information processing of the present embodiment will be described.

[0041] (3-1) Work history extraction process The work history extraction process of the present embodiment will be described. FIG. 5 is a flowchart of the work history extraction process of the present embodiment. FIG. 6 is a diagram showing a structured document acquired in the work history extraction process of the present embodiment. FIG. 7 is a diagram showing an example of a screen displayed in the work history extraction process of the present embodiment.

[0042] The job history extraction process of this embodiment can be started, for example, when the user of the client device 10 uploads job history data (for example, a PDF file or a document file in another format) to the server 30 through the interface displayed on the display 21 of the client device 10.

[0043] Note that before uploading the job history data, the client device 10 may present a message to alert the user to input the job history data into the generation model, and further receive explicit consent from the user before uploading the job history data.

[0044] As shown in FIG. 6, the server 30 executes acquisition of job history data (S130). Specifically, the server 30 receives the job history data from the client device 10 and stores it in the storage device 31. The server 30 may perform conversion of the file format of the job history data.

[0045] After step S130, the server 30 executes extraction of text data (S131). Specifically, the server 30 performs character recognition processing on the job history data acquired in step S130, and acquires text data (an example of "first text data") included in the job history data and corresponding text coordinate information. The text coordinate information is, for example, the two-dimensional coordinates (xy coordinates) of the pixels representing the corresponding text in the layout of the job history data. As another example, the text coordinate information may be the position (page number, line number, number of characters from the beginning of the line, or a combination thereof) occupied by the corresponding text in the layout of the job history data. Further, when the job history data includes data representing a table describing the job history of the target person, the server 30 may extract coordinate information corresponding to the rows, columns, or cells constituting the table. Alternatively, when text data is embedded in the job history data acquired in step S130, the server 30 may use the text data as the extraction result.

[0046] After step S131, the server 30 executes the organization of text data (S132). Specifically, the server 30 organizes the text data according to the structure of the sentence based on the text data and text coordinate information extracted in step S131, thereby obtaining text data ((an example of "second text data")) more suitable for subsequent processing (especially natural language processing). Here, the organization of text data can include, for example, dividing one or more text chunks included in the text data into a larger number of text chunks, integrating a plurality of text chunks included in the text data into a smaller number of text chunks, swapping the order of the texts included in the text data, summarizing the texts included in the text data, or a combination thereof. As an example, the server 30 gives the model input based on the text data and text coordinate information extracted in step S131 to a delimiter estimation model to estimate the delimiter position on the sentence. The delimiter position on the sentence is, for example, a paragraph position, a line break position, or a combination thereof. As the delimiter estimation model, a learned model that has acquired the ability to estimate the delimiter position from the text data and the corresponding text coordinate information by learning the structure of a large number of documents (preferably resume) (for example, the relationship between the text data and the corresponding text coordinate information obtained from a large number of documents and the delimiter position (correct data)) can be used.

[0047] The server 30 chunks the text data according to the estimated delimiter position (for example, paragraph position). Also, the server 30 adds line break data to the text data according to the estimated delimiter position (for example, line break position). Note that it is also possible to realize the organization of text data based on rules instead of using the delimiter estimation model.

[0048] Further, the server 30 may further organize the text data based on the coordinate information corresponding to the rows, columns, or cells constituting the table describing the work history of the target person. For example, the server 30 may chunk the text data in units of rows, columns, or cells, or add line break data.

[0049] Note that depending on the format of the work history document data acquired in step S130, text data in an organized state according to the delimiter position may be extracted in step S131. In this case, step S132 can be omitted.

[0050] Note that before or after step S132, or in parallel with step S132, the server 30 may determine the format requirements of the work history document data. Specifically, the server 30 determines whether the work history document data acquired in step S130 or the text data obtained in step S131 or step S132 meets the format requirements. As a first example, the server 30 determines that the data to be determined does not meet the format requirements when it does not have a predetermined required item such as a header sentence like "Work History Document". As a second example, the server 30 gives model input based on the data to be determined to the format determination model, and determines that the format requirements are not met when a determination result that it is not a work history document is obtained. As the format determination model, a learned model that has acquired the ability to distinguish between a work history document and other documents by learning the characteristics of the structures of a large number of work history documents can be used. When the server 30 determines that the data to be determined does not meet the format requirements, it may present an error screen to the user via the client device 10 and end the work history extraction process.

[0051] After step S132, the server 30 executes acquisition of a structured document (S133). Specifically, the server 30 provides the generation model with a prompt including the text data obtained in step S132, thereby obtaining text data (an example of "third text data"), which is a structured document based on the text data. The generation model may be a large language model trained with a large amount of text data, or a model obtained by transfer learning or fine-tuning the large language model. Further, the generation model may be constructed in a system external to the information processing system 1 (for example, a cloud environment).

[0052] An example of the structured document is shown in FIG. 6. The structured document is a document including a sentence in which the information included in the resume is divided into personal-related information and company-affiliation-related information. Each piece of information may be described in chronological order. The structured document may include information on the creation date in addition to the personal-related information and the company-affiliation-related information. The personal-related information can include, for example, the name of the target person, acquired qualifications, self-promotion, self-improvement, or a combination thereof. The company-affiliation-related information can include achievements and initiatives, roles, tenure, job summaries, or a combination thereof for each organization or company the target person has belonged to in the past.

[0053] After step S133, the server 30 executes the acquisition of information sorted by category name (S134). Specifically, the server 30 provides the generation model with a prompt including the text data (structured document) obtained in step S133, a predetermined category name related to the work history, and an instruction for extracting information about the target person from the generation model. As a result, the server 30 acquires text data (an example of "fourth text data") from which information about the target person (elements of work history information by category name) sorted by this category name can be extracted. As an example, the server 30 can provide the generation model with a prompt that extracts work history information for each category name from the text data and instructs the generation model to output the extracted work history information in the form of text data in a format associated with the corresponding category name (for example, a format such as category name A: work history information α,...). Then, the server 30 may extract information about the target person from the text data obtained from the generation model by category name related to the work history.

[0054] The predetermined category name can include, for example, company name, project name, role, job type, project period, utilized technology, project details, or a combination thereof. The predetermined category name is determined to correspond to the input items on the input screen for work history of the job hunting support service provided by the server 30.

[0055] Note that when the server 30 extracts text data from the work history document data in PDF file format in step S131, in this step S134, the prompt may include information for informing the generation model that the format may be disrupted because the text data (structured document) is extracted from the PDF file.

[0056] Furthermore, as an option, the server 30 may correct the text data obtained from the generation model in this step S134. Specifically, the server 30 provides the generation model with a prompt including the text data (structured document) obtained in step S133, a predetermined category name related to the work history, the text data obtained from the generation model in this step S134, and an instruction for correcting the text data when there is an excess or deficiency by comparing these text data with the generation model. As a result, the server 30 acquires text data (an example of "fifth text data") that can extract the information of the target person sorted by category name related to the work history. Here, having an excess or deficiency may include, for example, that the elements of the work history information included in the text data obtained from the generation model in this step S134 are not based on the text data obtained in step S133 (there is no corresponding description). And the server 30 may extract the information of the target person by category name related to the work history from the text data obtained from the generation model.

[0057] Furthermore, as an option, the server 30 may summarize the text data (which may include the corrected text data described above) obtained from the generation model in this step S134. Specifically, the server 30 provides the generation model with a prompt including the text data obtained from the generation model in this step S134 and an instruction for summarizing the text data to the generation model. As a result, the server 30 acquires the summary result of this text data. And the server 30 may extract the information of the target person by category name related to the work history from the summary result. Note that whether to summarize or not may be switched according to the volume of the text data obtained from the generation model in this step S134. For example, summarization may be performed when the volume of the text of the whole or a specific category name exceeds the threshold, and summarization may be omitted otherwise.

[0058] After step S134, the server 30 executes the presentation of the input screen (S135). Specifically, the server 30 presents a screen (hereinafter referred to as the “input screen”) for receiving the input of the target person's work history in a state where the information of the target person sorted by category names related to the work history is stored in the corresponding objects respectively. For example, for each object (such as a text box) arranged on the input screen, the server 30 extracts the information of the category name corresponding to the input item of the object from the text data obtained in step S134 and sets it in the object. Then, the server 30 transmits the information for displaying the input screen to the client device 10. In addition, when the input item of the object is different from the category name, the server 30 may instruct the generation model to regenerate the text data. The prompt for instructing the generation model to regenerate may include an instruction to associate a blank with a category name for which the information corresponding to the original work history document data (the text data (structured document) obtained in step S133) is not described. Then, the server 30 sets information in the object based on the text data obtained by regeneration.

[0059] The client device 10 displays the input screen on the display 21 based on the information from the server 30. An example of the input screen is shown in FIG. 7. The input screen in FIG. 7 includes objects J20 to J28. The object J20 is in one-to-one correspondence with the object J21 and represents the input item (category name) assigned to the corresponding object J21.

[0060] The object J21 receives the input of the information (work history information) of the target person regarding the assigned input item. Note that information may already be set in the object J21 by the above-described presentation of the input screen (S135). When there are excesses, shortages, or errors in the information set in the object J21, or when the object J21 is blank, the user can edit the information set in the object J21 or add appropriate information. The objects J20 to J21 are arranged on the input screen for each input item.

[0061] Object J22 receives a user instruction to add an object (for example, objects J20 to J21) for accepting further input of work history. When object J22 is selected, the client device 10 adds an object for accepting further input of work history to the input screen.

[0062] Object J23 receives a user instruction to return to the previous screen from the input screen. When object J23 is selected, the client device 10 transitions from the input screen to the previous screen.

[0063] Object J24 receives a user instruction to save work history information. When object J24 is selected, the client device 10 creates a work history document file based on the input values of each object and saves it in the storage device 11. The work history document file can be used as a work history document in a format different from the work history document uploaded by the user. Note that in response to the selection of object J24, the client device 10 may present a message alerting that the work history document file to be saved may contain errors, and may further save the work history document file in the client device 10 after receiving explicit consent from the user.

[0064] Object J25 receives a user instruction to register work history information with the job transfer support service. When object J25 is selected, the client device 10 transmits the input values of each object to the server 30. The server 30 registers the input values of each object in a database (not shown) in association with information for identifying the target person.

[0065] Object J26 receives a user instruction to re-extract work history information. When Object J26 is selected, the client device 10 displays a message on the display 21 prompting the user to re-upload work history document data. The server 30 re-executes the work history extraction process based on the re-uploaded work history document data. However, in the re-execution of the work history extraction process, the server 30 may provide a prompt including an instruction for causing the generation model to generate a different sentence from the previously executed work history extraction process to the generation model. Also, the client device 10 may receive a request from the user to describe a specific work history in detail or to describe a specific work history briefly (summarize), and transmit the received information to the server 30. Then, the server 30 may reflect an instruction for causing the generation model to generate text data according to the user's request in the prompt. Further, the client device 10 may receive a pointing out from the user regarding a missing extraction part (a sentence related to a specific category or a specific work history), and transmit the received information to the server 30. Then, the server 30 may reflect an instruction for causing the generation model to generate text data including information on the part pointed out by the user in the prompt.

[0066] Object J27 receives a user instruction to schedule an interview. When Object J27 is selected, the client device 10 may start another program and start scheduling the interview.

[0067] Object J28 receives a user instruction to request a proxy service for creating a work history document. When Object J28 is selected, the client device 10 may start another program and start requesting the proxy service for creating a work history document.

[0068] (4) Parentheses As described above, the server 30 of the present embodiment acquires the first text data based on the work history document data representing the work history of the target person, and generates the second text data obtained by organizing the first text data according to the structure of the sentence. The server 30 provides the generation model with a prompt based on the second text data and the category name related to the work history, thereby acquiring the information of the target person organized by category name related to the work history. As a result, the server 30 can acquire the information of the target person organized by category name related to the work history without imposing on the user the burden of organizing and inputting the work history information in accordance with the format required by the system side. That is, the input burden of the work history can be reduced.

[0069] The server 30 may generate the second text data based on the first text data and the coordinate information corresponding to the first text data. Thereby, the second text data in which each text constituting the first text data is appropriately organized according to the position in the document can be obtained, and the quality of the finally extracted information can be improved.

[0070] The server 30 may determine the delimiter position in the sentence structure based on the first text data and the coordinate information corresponding to the first text data, and obtain the second text data by chunking the first text data based on the delimiter position. Thereby, the second text data in which each text constituting the first text data is appropriately organized according to the delimiter position in the sentence structure can be obtained, and the quality of the finally extracted information can be improved.

[0071] The work history data may include data representing a table that describes the work history of the target person. The server 30 may generate second text data based on coordinate information corresponding to rows, columns, or cells constituting the table, first text data, and coordinate information corresponding to the first text data. As a result, second text data in which each text constituting the first text data is appropriately arranged according to the structure of the table included in the work history data can be obtained, and the quality of the information finally extracted can be improved.

[0072] The server 30 provides a prompt including the second text data to the generation model to perform the first-phase process of obtaining third text data, which is a structured document based on the second text data, and provides a prompt including the third text data, the category name related to the work history, and an instruction for causing the generation model to extract the information of the target person for each category name to the generation model, so as to perform the second-phase process of obtaining fourth text data in which the information of the target person is organized for each category name related to the work history. As a result, the process using the generation model is performed step by step in the process of generating a structured document and the process of organizing the information of the structured document by category, so that the quality of the information finally extracted can be improved.

[0073] In the second-phase process, the server 30 may obtain the fourth text data by providing a prompt further including information for informing the generation model that the format of the third text data may be disrupted because the third text data is extracted from a PDF file. Thereby, even when the format of the third text data is disrupted, appropriate fourth text data can be easily obtained.

[0074] The server 30 may further execute the processing of the third phase of obtaining the fifth text data capable of extracting the information of the target person sorted by the category name related to the work history by giving the generation model a prompt including the third text data, the category name related to the work history, the fourth text data, and an instruction to correct the excess or deficiency when comparing the third text data and the fourth text data with the generation model. As a result, since the fifth text data in which the deficiencies of the fourth text data are corrected can be obtained, the quality of the finally extracted information can be improved.

[0075] The server 30 may obtain the summary result of the fourth text data by giving the generation model a prompt based on the fourth text data and an instruction to summarize the fourth text data to the generation model, and extract the information of the target person by the category name related to the work history from the summary result. As a result, since a summary result in which the key points of the fourth text data are aggregated can be obtained, the quality of the finally extracted information can be improved.

[0076] The server 30 may present a screen for receiving the input of the work history of the target person in a state where the information of the target person sorted by the category name related to the work history is respectively stored in the corresponding objects. Thereby, the input burden on the user can be reduced.

[0077] The server 30 may receive from the user an instruction to regenerate at least one of the information stored in any of the objects. Thereby, even when the information is not extracted appropriately, the user can redo it until they are satisfied.

[0078] The server 30 may determine whether the work history data meets the formal requirements, and when it is determined that the work history data does not meet the formal requirements, may present an error screen. Thereby, for example, the user can be notified early of uploading incorrect data, and the load on the server 30 and the generation model due to processing inappropriate data can be avoided.

[0079] (5) Other Modification Examples The storage device 11 may be connected to the client device 10 via the network NW. The display 21 may be integrated with the client device 10. The storage device 31 may be connected to the server 30 via the network NW.

[0080] Each step of the above information processing can be executed by either the client device 10 or the server 30. In the above description, an example in which each step is executed in a specific order in each process is shown, but the execution order of each step is not limited to the example described as long as there is no dependency.

[0081] In the above description, an example in which the server 30 performs information processing using the generation model (steps S133 to S134) is shown. When an error occurs in such information processing, the server 30 may present an error screen to the user via the client device 10. The error screen may include information indicating the reason for the error and the error subject (for example, the server 30 or the generation model). Also, the information presentation mode may be varied depending on the error subject. Furthermore, when an error occurs, information prompting the user to re-upload the work history data may be presented.

[0082] As described above, the embodiments of the present invention have been described in detail, but the scope of the present invention is not limited to the above embodiments. Also, the above embodiments can be variously improved and modified without departing from the gist of the present invention. Also, the above embodiments and modification examples can be combined.

[0083] (6) Supplementary Notes Matters described in the embodiments and modification examples are appended below.

[0084] (Supplementary Note 1) A computer (30) means (S131) for obtaining first text data based on work history data representing the work history of a target person Means (S132) for generating second text data obtained by organizing first text data according to the structure of the article Means (S133 - S134) for obtaining information of the target person organized by category name related to work experience by providing a prompt based on the second text data and the category name related to work experience to a generation model A program that functions as

[0085] (Appendix 2) The means for generating the second text data generates the second text data based on the first text data and the coordinate information corresponding to the first text data. The program described in Appendix 1.

[0086] (Appendix 3) The means for generating the second text data determines the delimiter positions in the structure of the article based on the first text data and the coordinate information corresponding to the first text data, and obtains the second text data by chunking the first text data based on the delimiter positions. The program described in Appendix 2.

[0087] (Appendix 4) The work experience document data includes data representing a table describing the work experience of the target person. The means for generating the second text data generates the second text data based on the coordinate information corresponding to the rows, columns, or cells constituting the table, the first text data, and the coordinate information corresponding to the first text data. The program described in Appendix 1.

[0088] (Appendix 5) The means for obtaining information of the target person organized by category name related to work experience The processing of the first phase of obtaining third text data, which is a structured document based on the second text data, by providing a prompt including the second text data to a generation model By providing a prompt including the third text data, the category name related to the work history, and an instruction for the generation model to extract the information of the target person for each category name to the generation model, the second-phase process of obtaining the fourth text data from which the information of the target person organized by category name related to the work history can be extracted, and Execute The program described in Appendix 1.

[0089] (Appendix 6) The means for obtaining the information of the target person organized by category name related to the work history further includes providing a prompt to the generation model that includes information for telling the generation model that in the second-phase process, since the third text data is extracted from a PDF file, the format may be disrupted, and obtaining the fourth text data. The program described in Appendix 5.

[0090] (Appendix 7) The means for obtaining the information of the target person organized by category name related to the work history further executes the third-phase process of obtaining the fifth text data from which the information of the target person organized by category name related to the work history can be extracted by providing a prompt including the third text data, the category name related to the work history, the fourth text data, and an instruction for the generation model to compare the third text data and the fourth text data and correct them if there are any deficiencies to the generation model. The program described in Appendix 6.

[0091] (Appendix 8) The means for obtaining the information of the target person organized by category name related to the work history Obtain the summary result of the fourth text data by providing a prompt based on the instruction for the generation model to summarize the fourth text data to the generation model, and extract the information of the target person by category name related to the work history from the summary result. The program described in Appendix 7.

[0092] (Appendix 9) function the computer as means (S135) for presenting a screen for receiving input of the work history of the target person in a state where information of the target person sorted by category names related to the work history is respectively stored in corresponding objects The program according to Appendix 1.

[0093] (Appendix 10) function the computer as means for receiving an instruction from the user to regenerate at least one of the information stored in any of the objects The program according to Appendix 9.

[0094] (Appendix 11) function the computer as means for determining whether the work history data satisfies the formal requirements means for presenting an error screen when it is determined that the work history data does not satisfy the formal requirements The program according to Appendix 1.

[0095] (Appendix 12) means (S131) for obtaining first text data based on work history data representing the work history of the target person means (S132) for generating second text data obtained by organizing the first text data according to the structure of the text means (S133 to S134) for obtaining information of the target person sorted by category names related to the work history by giving a prompt based on the second text data and the category names related to the work history to a generation model An information processing apparatus (30) comprising:

[0096] (Appendix 13) The computer (30) performs a step (S131) of obtaining first text data based on work history data representing the work history of the target person performs a step (S132) of generating second text data obtained by organizing the first text data according to the structure of the text​ By providing a generation model with a prompt based on the second text data and the category name related to the work history, steps (S133 to S134) of obtaining information of the subject person sorted by category name related to the work history, and A method of executing.

[0097] (Appendix 14) A system (1) including a plurality of information processing devices (10, 30), Means (S131) for obtaining first text data based on work history document data representing the work history of a subject person, Means (S132) for generating second text data obtained by organizing the first text data according to the structure of the text, Means (S133 to S134) for obtaining information of the subject person sorted by category name related to the work history by providing a generation model with a prompt based on the second text data and the category name related to the work history, and A system comprising.

Explanation of Signs

[0098] 1: Information processing system 10: Client device 11: Storage device 12: Processor 13: Input / output interface 14: Communication interface 21: Display 30: Server 31: Storage device 32: Processor 33: Input / output interface 34: Communication interface

Claims

1. A program that causes a computer to function as means for obtaining first text data based on resume data representing the work history of a target person, means for generating second text data obtained by organizing the first text data according to the structure of the text, means for obtaining information on the target person organized by category name related to the work history by providing a prompt based on the second text data and the category name related to the work history to a generation model, a program.

2. The means for generating the second text data generates the second text data based on the first text data and coordinate information corresponding to the first text data. The program according to claim 1.

3. The means for generating the second text data determines a delimiter position in the structure of the text based on the first text data and coordinate information corresponding to the first text data, and obtains the second text data by chunking the first text data based on the delimiter position. The program according to claim 2.

4. The resume data includes data representing a table describing the work history of the target person, The means for generating the second text data generates the second text data based on coordinate information corresponding to rows, columns, or cells constituting the table, the first text data, and coordinate information corresponding to the first text data. The program according to claim 1.

5. The means for obtaining information on the target person organized by category name related to the work history includes a first-phase process of obtaining third text data, which is a structured document based on the second text data, by providing a prompt including the second text data to the generation model, and a second-phase process of obtaining fourth text data from which information on the target person organized by category name related to the work history can be extracted by providing a prompt including the third text data, the category name related to the work history, and an instruction for causing the generation model to extract information on the target person by category name and executing. The program according to claim 1.

6. The means for obtaining the information of the target person sorted by category name related to the work history further includes information for informing the generation model that in the processing of the second phase, since the third text data is extracted from a PDF file, the format may be disrupted, and gives a prompt including such information to the generation model, thereby obtaining the fourth text data. The program according to claim 5.

7. The means for obtaining the information of the target person sorted by category name related to the work history further executes the processing of the third phase of obtaining the fifth text data from which the information of the target person sorted by category name related to the work history can be extracted, by giving a prompt including an instruction for comparing the third text data, the category name related to the work history, the fourth text data, and the generation model and correcting them if there are excesses or deficiencies to the generation model. The program according to claim 6.

8. The means for obtaining the information of the target person sorted by category name related to the work history obtains the summary result of the fourth text data by giving a prompt based on an instruction for summarizing the fourth text data to the fourth text data and the generation model, and extracts the information of the target person by category name related to the work history from the summary result. The program according to claim 7.

9. causes the computer to function as means for presenting a screen for receiving an input of the work history of the target person in a state where the information of the target person sorted by category name related to the work history is respectively stored in corresponding objects. The program according to claim 1.

10. causes the computer to function as means for receiving an instruction from the user to regenerate at least one of the information stored in any of the objects. The program according to claim 9.

11. The computer functions as means for determining whether the work history data satisfies the formal requirements and means for presenting an error screen when it is determined that the work history data does not satisfy the formal requirements. functions as The program according to claim 1.

12. means for obtaining first text data based on work history data representing the work history of the target person Means for generating second text data obtained by organizing the first text data according to the structure of the article; Means for obtaining information of the target person organized by category name related to the work history by providing a prompt based on the second text data and the category name related to the work history to a generation model; An information processing apparatus comprising the above.

13. A computer: The step of obtaining first text data based on work history data representing the work history of the target person; The step of generating second text data obtained by organizing the first text data according to the structure of the article; The step of obtaining information of the target person organized by category name related to the work history by providing a prompt based on the second text data and the category name related to the work history to a generation model; A method of executing the above.

14. A system comprising a plurality of information processing apparatuses, Means for obtaining first text data based on work history data representing the work history of the target person; Means for generating second text data obtained by organizing the first text data according to the structure of the article; Means for obtaining information of the target person organized by category name related to the work history by providing a prompt based on the second text data and the category name related to the work history to a generation model; A system comprising the above.

Images