Information processing system, information processing method and program

Abstract

To provide an information processing system etc. that can support the creation of documents related to job seekers or employers. [Solution] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute the following steps by reading a program: an acquisition step acquiring a document relating to a user who is a job seeker or an employer; a selection acceptance step accepting a selection of correction portions in the document from the user; a correction suggestion step presenting the user with at least one correction policy for the correction portions based on information about the correction portions and first reference information and accepting a confirmation of the correction policy from the user; the first reference information including a correlation between information about the correction portions and the correction policy; and a correction step correcting the correction portions based on the selected correction policy.

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a technique for supporting document creation. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-230705 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a need for technology that can assist in the creation of documents relating to job seekers or employers.

[0005] In view of the above circumstances, the present invention provides an information processing system etc. that can support the creation of documents related to job seekers or employers. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor configured to execute the following steps by reading a program: an acquisition step of acquiring a document relating to a user who is a job seeker or an employer; a selection acceptance step of accepting a selection of correction portions in the document from the user; a correction suggestion step of presenting to the user at least one correction policy for the correction portions based on information about the correction portions and first reference information and accepting a confirmation of the correction policy from the user; the first reference information including a correlation between the information about the correction portions and the correction policy; and a correction step of correcting the correction portions based on the selected correction policy.

[0007] According to this aspect, it is possible to support the creation of documents relating to job seekers or employers. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] 2 is a block diagram showing the hardware configuration of the server device 10. FIG. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a recruiting party terminal 20 and a job seeker terminal 30. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiting party terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Figure 5] 10 is a table illustrating an example of a correspondence relationship between correction locations and correction policies. [Figure 6] FIG. 10 is a diagram showing an example of a document correction screen CD displayed on the job seeker terminal 30. [Figure 7] FIG. 10 is a diagram showing an example of a document correction screen CD in which correction options are presented. [Figure 8] FIG. 10 is a diagram showing an example of a document correction screen CD in which a free input field FF is displayed. [Figure 9] FIG. 10 is a diagram showing another example of the document correction screen CD in a state where a free input field FF is displayed. [Figure 10] FIG. 10 is a diagram showing an example of a document correction screen CD in which correction results are displayed. [Figure 11] 1 is an activity diagram showing an example of the flow of information processing (document correction processing) executed by the information processing system 1. FIG. DETAILED DESCRIPTION OF THE INVENTION

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

[0010] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or may be provided so that it can be downloaded 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] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously trained the correlation between input and output, or a generative AI such as a large-scale language model or a visual language model that can output a desired result in response to a prompt input.

[0012] In one embodiment, a "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 one 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 set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, 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.

[0014] 1. Hardware Configuration This section explains the hardware configuration.

[0015] <Information Processing System 1> Fig. 1 is a configuration diagram showing an information processing system 1. The information processing 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 may be wired or wireless.

[0016] The information processing system 1 constitutes at least a part of a recruitment and job search system used by, for example, multiple recruiters (first recruiter U1 and second recruiter U2) and multiple job seekers (first job seeker U3 and second job seeker U4). The information processing system 1 mainly performs functions such as recruiters searching for job seekers, job seekers searching for jobs, and mediating communication between recruiters and job seekers. For example, the information processing system 1 provides and manages a talent matching platform and talent matching services used by recruiters and job seekers. In one embodiment, the information processing system 1 is comprised of one or more devices or components. These components are described below.

[0017] <Server device 10> Fig. 2 is a block diagram showing the hardware configuration of server device 10. As shown in Fig. 2, server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. Control unit 11, storage unit 12, and communication unit 13 are electrically connected within server device 10 via communication bus 14.

[0018] <Control unit 11> The control unit 11 processes and controls the overall operations 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 predetermined programs stored in the storage unit 12. In other words, information processing by 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. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being a single unit, and the server device 10 may have multiple control units 11 for each function. Furthermore, the server device 10 may be configured with a combination of these.

[0019] <Storage section 12> The memory unit 12 stores various pieces of information defined above. 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 operations. The memory unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0020] <Communications Department 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), or wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as LTE / 5G, or BLUETOOTH (registered trademark) communication as needed. That is, it is more preferable to implement it as a collection of multiple communication means. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The server device 10 may be an on-premise server or a cloud server. The cloud server device 10 may provide the above-described functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] <Recruiter Terminal 20> FIG. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. The recruiter terminal 20 is an information processing terminal used by the recruiter. "Recruiters" include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, incorporated foundations), and public corporations (e.g., local governments) or their personnel. Here, the personnel may be called recruiters, and may include personnel in the organization's human resources department or personnel in the department that hires personnel. Recruiters also include recruitment agents who act as agents of organizations to mediate between job seekers and organizations. Recruiters are also called headhunters, agents, etc.

[0023] 3A, the recruiting party 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 via the communication bus 26 inside the recruiting party terminal 20. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is the same as the explanation of each unit in the server device 10, and so will be omitted.

[0024] <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 can 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 attached externally. 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, etc. to the input unit 24. Instead of a touch panel, a switch button, a mouse, a trackpad, a QWERTY keyboard, etc. can be used as the input unit 24.

[0025] <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.

[0026] <Job Seeker Terminal 30> The job seeker terminal 30 is an information processing terminal used by a job seeker. "Job seekers" include, for example, employed people (people looking to change jobs), prospective new graduates (job seekers), students, etc., and also include people who are looking to change jobs or find employment, or people who are interested in changing jobs or finding employment.

[0027] 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 via the communication bus 36 inside the job seeker terminal 30. The explanation 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 explanation of each unit in the recruiter terminal 20.

[0028] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by 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 (at least one processor included in the information processing system 1).

[0029] FIG. 4 is a block diagram showing functions realized by the server device 10 (controller 11), the recruiter terminal 20 (controller 21), and the job seeker terminal 30 (controller 31).

[0030] As shown in FIG. 4A, the server device 10 (control unit 11) includes a basic display control unit 111, an acquisition unit 112, a selection receiving unit 113, a correction suggestion unit 114, a correction unit 115, a reference information update unit 116, and an artificial intelligence unit 120.

[0031] 4B, the recruiting party terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in FIG. 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0032] <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 information about job seekers or recruiters registered in the database on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30 in response to a request from each user (recruiters U1, U2 or job seekers U3, U4).

[0033] <Acquisition part 112> The acquisition unit 112 is configured to acquire registration information of a job seeker. The "registration information of a job seeker" includes, for example, a document related to a job history called a resume, in which the job seeker conveys to a recruiter his or her work history, experience, skills, qualifications, etc. related to his or her past work. In other words, the acquisition unit 112 acquires at least a document related to the job seeker who is the user (hereinafter, the document to be corrected).

[0034] Documents relating to a job seeker's work history (work history documents) may include the job seeker's resume, other profile information, and the job seeker's desired industry and job type, etc. A "resume" is a document that primarily describes the job seeker's profile, current situation, educational background, work history, desired working conditions, etc. The job seeker's registered information may also include information other than documents relating to the job seeker's work history (for example, the job seeker's personal information, attributes, behavioral history, etc.).

[0035] The document to be corrected may be one that is automatically generated by artificial intelligence such as a generation AI, or one that the job seeker created themselves. Furthermore, the document to be corrected may be, for example, one that is registered in a job seeker database stored in the storage unit 12, or one that the job seeker uploaded from the job seeker terminal 30, or one that is stored in external storage designated by the job seeker. In other words, the acquisition unit 112 may accept the designation of the document to be corrected by uploading the document to be corrected from the job seeker terminal 30, inputting the network address of the document to be corrected from the job seeker terminal 30, or the like.

[0036] <Selection Receiving Unit 113> The selection receiving unit 113 is configured to receive, from the job seeker, a selection of a portion to be corrected in the document to be corrected. Specifically, the selection receiving unit 113 displays the document to be corrected acquired by the acquiring unit 112 on the job seeker terminal 30, and receives, from the job seeker terminal 30, a selection input for any selected portion of the document to be corrected.

[0037] The selection input of the part to be corrected is accepted by, for example, an input operation such as tapping (including long tapping, double tapping, etc.), clicking (including double clicking, etc.), dragging, etc., using the input unit 34 of the job seeker terminal 30. The selection accepting unit 113 highlights the selected part to be corrected on the job seeker terminal 30 (for example, by coloring it, changing the font, etc.).

[0038] The unit for selecting the part to be corrected may be, for example, a character unit, a word (including a numerical value), a phrase unit, a sentence unit, a paragraph unit, or the like. The selection receiving unit 113 may receive the selection of the part to be corrected in any unit of selection by the job seeker, or may receive the selection of the part to be corrected in a predetermined unit of selection. For example, if the predetermined unit of selection is a sentence unit, the selection receiving unit 113 may receive the entire sentence including the character or word selected on the job seeker terminal 30 as the selected part. Furthermore, the selection receiving unit 113 may determine a sentence included in an area where a first selection input (e.g., a tap) was made as the selected part, and when a second selection input (e.g., consecutive taps) is made in the same area, determine a word included in the area as the selected part.

[0039] An upper limit may be set for the number of characters in a selected portion. For example, if the number of characters in a selected portion exceeds the upper limit, the selection receiving unit 113 narrows the range of the selected portion so that the number of characters is within the upper limit. Methods for narrowing the range of the selected portion include, for example, dividing the selected portion by punctuation, phrases, context, etc.

[0040] <Revision proposal section 114> The correction suggestion unit 114 is configured to present at least one correction policy for the correction portion to the job seeker (job seeker terminal 30) based on the information on the correction portion received by the selection receiving unit 113 and the first reference information, and to receive confirmation of the correction policy from the job seeker (job seeker terminal 30).

[0041] "Information about the correction portion" includes, for example, the content (text information) expressed in natural language, such as words, numbers, and sentences, contained in the correction portion, as well as the context of the correction portion. "Context of the correction portion" includes, for example, the position of the correction portion in the document to be corrected, the item (category) containing the correction portion, and the relationship between the correction portion and the sentences before and after it. Note that "items" contained in the document to be corrected include, for example, organizational information (industry type, organization name, department name, job title, etc.), job content, work content, achievements, selling points, skills, qualifications, etc. in a work history.

[0042] The "correction policy" includes a policy indicating the direction of correction, such as "I want to change the content" or "I want to delete it," and a policy indicating the specific correction content, such as "correct to the content of XX" or "replace XX with XX." The correction policy may also include the specific sentence after correcting the sentence included in the correction portion.

[0043] "Confirming a revision policy" refers to an operation in which the job seeker accepts or selects the revision policy presented by the revision proposal unit 114 to the job seeker terminal 30. For example, if the number of revision policies presented by the revision proposal unit 114 is one, the revision proposal unit 114 may cause the job seeker terminal 30 to display an acceptance object that accepts the acceptance of the revision policy, and may accept input from the job seeker into the acceptance object as the confirmation of the revision policy. Note that the case in which the revision proposal unit 114 presents multiple revision policies will be described later.

[0044] The first reference information includes a correlation between information on the correction location and the correction policy. The first reference information is stored, for example, in the storage unit 12. The first reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates the correlation between information on the correction location and the correction policy. The correlation included in the first reference information can be constructed, for example, by statistically analyzing data that records information on the correction location and the corresponding correction policy.

[0045] The first reference information may include a learning model that has been machine-learned to input information about correction locations and output a correction policy, or a correction policy creation model that is a generative AI. In this case, the correction suggestion unit 114 inputs information about correction locations into the correction policy creation model and causes the correction policy creation model to output at least one correction policy. This makes it possible to propose corrections based on correction examples of documents related to many job seekers or natural language processing. In the correction policy creation model, parameters calculated, tuned, etc. through learning constitute correlations of the first reference information.

[0046] The correction policy creation model is included in the artificial intelligence unit 120. The correction policy creation model, which has been trained to be able to output a correction policy, is trained using, for example, information on the part to be corrected and data on the corresponding correction policy as training data.

[0047] When the correction policy creation model is a generative AI including a general-purpose language model (natural language model or large-scale language model), the correction proposal unit 114 inputs information about the correction location, inputs a prompt including an instruction to output a correction policy corresponding to the information about the correction location, and causes the correction policy to be output by the correction policy creation model. The correction proposal unit 114 may generate a prompt that gives the correction policy creation model an instruction to create a correction policy, and input the prompt to the correction policy creation model. Furthermore, the correction proposal unit 114 may input, in addition to the instruction to create and output the correction policy and the information about the correction location, a prompt that inserts, for example, one or more samples of information about the correction location and one or more corresponding samples of correction policies as examples, samples, or training data of input and output pairs to the correction policy creation model.

[0048] The revision suggestion unit 114 may create a revision policy using additional information including, in addition to information on the revision portion, portions of the document to be revised other than the revision portion, or other information related to the job seeker (registered information other than the document to be revised).Registered information other than the document to be revised may refer to, for example, information such as the job seeker's current occupation or industry, or the job seeker's desired occupation or industry.

[0049] For example, if the first reference information includes a correction policy creation model, the correction suggestion unit 114 may further input additional information (portions of the document to be corrected other than the portion to be corrected or other information related to the job seeker) into the correction policy creation model. In other words, the correction suggestion unit 114 may create a correction policy based on the information on the portion to be corrected, the additional information, and the first reference information, and present this correction policy to the job seeker terminal 30. In this case, the first reference information includes the correlation between the information on the portion to be corrected, the additional information, and the correction policy.

[0050] Furthermore, the correction suggestion unit 114 may present a plurality of correction options indicating the correction policy to the job seeker terminal 30, and may also accept a selection of a correction option as a confirmation of the correction policy from the job seeker terminal 30. This allows the job seeker to input the correction policy by selecting an option without having to input text, thereby improving the efficiency of correcting the document to be corrected.

[0051] Specifically, the correction suggestion unit 114 displays a plurality of option objects on the job seeker terminal 30, each of which accepts a selection for a plurality of correction options, and accepts an input from the job seeker to any of the option objects (selection of one correction option from the plurality of correction options) as a confirmation of the correction policy. Note that the correction suggestion unit 114 may accept the selection of two or more correction options for the plurality of correction options presented for one correction location.

[0052] The correction suggestion unit 114 may present, to the job seeker terminal 30, as correction options, at least one fixed option that does not change depending on the part to be corrected, and at least one variable option that changes depending on the part to be corrected. This makes it possible to present the job seeker with a general correction policy and a correction policy tailored to the part to be corrected. As a result, the job seeker has a wider range of choices for the correction policy, thereby improving the efficiency of the correction work.

[0053] The revision policies presented as fixed options include, for example, detailed description of the content of the revision part (concreteness), simplification of the content of the revision part (abstraction), correction of the content of the revision part, deletion of the revision part, direct editing of the revision part, free description of revision requests, etc. In particular, it is preferable that at least free description of revision requests be included in the fixed options. In other words, it is preferable that free description of revision requests be always presented as revision options, regardless of the content of the revision part.

[0054] The correction suggestion unit 114 may create a variation option based on the information on the part to be corrected and the first reference information, or may select a variation option from option candidates prepared in advance. This makes it possible to flexibly present to the job seeker correction options that are suitable for the part to be corrected.

[0055] For example, the modification suggestion unit 114 inputs information about the modification location into a modification policy creation model, which is a generation AI, inputs a prompt including an instruction to create a modification policy (variation option) corresponding to the information about the modification location into the modification policy creation model, and causes the modification policy creation model to output the variation option.

[0056] Furthermore, in cases where option candidates (sentences or keywords) are prepared in advance, for example, the correction suggestion unit 114 inputs information about the correction portion and the option candidates into a correction policy creation model, which is a generation AI, inputs a prompt including an instruction to extract a correction policy (variable option) corresponding to the information about the correction portion from the option candidates into the correction policy creation model, and causes the correction policy creation model to output the variable option. For example, if the correction policy creation model determines, based on the input prompt, that the correction portion includes a period, it selects an option included in the option candidates related to the period (e.g., "correct the period") as a variable option. Also, for example, if the correction policy creation model determines, based on the input prompt, that the correction portion includes a business tool, it selects an option included in the option candidates related to the tool (e.g., "correct the tool") as a variable option.

[0057] Furthermore, the correction suggestion unit 114 may extract a correction policy (variable option) corresponding to the information on the correction location from the option candidates, and if there is no appropriate option candidate, input a prompt including an instruction to generate a variable option not included in the option candidates into the correction policy creation model.

[0058] When the part to be corrected includes a numerical value, the correction suggestion unit 114 may present a correction policy indicating how to correct the numerical value to the job seeker terminal 30. This makes it possible to easily correct the numerical value.

[0059] For example, the correction suggestion unit 114 inputs information about the correction portion (numerical values) and information on the basis of the numerical values ​​into a correction policy creation model, which is a generation AI, inputs a prompt including an instruction to create a correction policy for the numerical values ​​into the correction policy creation model, and causes the correction policy creation model to output the correction policy including the correction of the numerical values. The "information on the basis of the numerical values" is a source for obtaining the correction value of the numerical values, and is, for example, a part of the document to be corrected other than the part to be corrected, or other information about the job seeker (registered information other than the document to be corrected).

[0060] The correction policy may include a first option indicating a category of correction and a second option indicating a policy content for the category indicated by the first option. In this case, the correction suggestion unit 114 may present the first option to the job seeker (job seeker terminal 30) and accept a selection of the first option from the job seeker (job seeker terminal 30), and may further present at least one second option to the job seeker (job seeker terminal 30) based on the selected first option and accept a selection of the second option from the job seeker (job seeker terminal 30). This prevents a decrease in operability for the job seeker due to the presentation of many correction options at once, as the correction options are presented to the job seeker in a hierarchical manner. This also makes it easier for the job seeker to find the desired correction option.

[0061] The "categories of correction" include, for example, making the content of the correction more detailed, simplifying the content of the correction, correcting the content of the correction, asking questions about the correction, completing the content of the correction (adding information), changing the context of the correction, changing the expression of the correction, etc. The second option indicates the specific direction of correction in these categories.

[0062] For example, if a job seeker selects "I would like more details" as the first option, the second options corresponding to this first option may include "Please increase the amount of text," "Please include specific examples," or "Please include examples of results including numerical values." For example, if a job seeker selects "(The description of the tool, etc.) is different from the facts" as the first option, a message such as "Which part is different from the facts?" may be displayed along with candidate parts of the facts (numerical values, keywords, etc.). Alternatively, a second option such as "Which of the following is closest to the facts?" may be displayed along with candidate parts (corrected numerical values, keywords, etc.) or "delete." Here, "delete" refers to a correction option that deletes all or part of the selected correction from the document to be corrected. Note that multiple second options may be displayed.

[0063] The correction suggestion unit 114 may create the first option and the second option simultaneously, or may create the first option first and then create the second option after selecting the first option. Furthermore, the first option and the second option may each be a fixed option, a variable option, or a combination thereof.

[0064] For example, when creating a first option and a second option simultaneously, the correction suggestion unit 114 creates the first option and the second option based on information about the part to be corrected and the first reference information. For example, the correction suggestion unit 114 inputs information about the part to be corrected into a correction policy creation model, which is a generation AI, inputs a prompt including instructions to create multiple correction policies for the part to be corrected and categories of these correction policies into the correction policy creation model, and causes the correction policy creation model to output the first option and the second option.

[0065] When creating a second option after selecting a first option, the correction suggestion unit 114 first creates the first option based on information about the correction location and the first reference information. For example, the correction suggestion unit 114 inputs information about the correction location into a correction policy creation model, which is a generation AI, inputs a prompt including an instruction to create a correction category for the correction location into the correction policy creation model, and causes the correction policy creation model to output the first option. Next, the correction suggestion unit 114 creates a second option based on the correction category determined by the selection of the first option, information about the correction location, and the first reference information. For example, the correction suggestion unit 114 inputs a correction category and information about the correction location into a correction policy creation model, which is a generation AI, inputs a prompt including an instruction to create a correction policy for the correction location included in the category into the correction policy creation model, and causes the correction policy creation model to output the second option.

[0066] When the first option selected on the job seeker terminal 30 indicates a correction to the content of the part to be corrected, the correction suggestion unit 114 may present the job seeker (job seeker terminal 30) with a second option indicating the part to be corrected or a correction proposal for the part to be corrected. This allows the job seeker to efficiently correct the part to be corrected. Note that "correction" also includes the process of deleting factually incorrect statements, figures, etc. from the part to be corrected.

[0067] When the first option selected on the job seeker terminal 30 indicates a request for a question about the portion to be corrected, the correction suggestion unit 114 may present the job seeker (job seeker terminal 30) with a question about the portion to be corrected and a second option indicating an answer to the question. This allows the job seeker to correct the description of the portion to be corrected in any direction by answering the question about the portion to be corrected.

[0068] "Questions about the part to be corrected" include, for example, questions about the elements (information) to be used to correct the part to be corrected, questions about the meaning of keywords or numbers included in the part to be corrected, questions about differences between the data included in the part to be corrected and the data of other job seekers, etc. Also, "first option indicating a request for a question about the part to be corrected" includes options that directly indicate a request for a question, such as "Please ask a question about this part," as well as options that require a question (for example, options that indicate a category of correction that requires the job seeker to input or select information).

[0069] For example, the correction suggestion unit 114 inputs information about the correction portion into a correction policy creation model, which is a generation AI, inputs a question about the correction portion and a prompt including an instruction to create answer candidates to the question into the correction policy creation model, and causes the correction policy creation model to output the question and answer candidates (second options). Note that the correction suggestion unit 114 may present "free description" as the second option (an answer option to the question, which is an answer candidate). In this case, a free input field, which will be described later, is provided along with the second option.

[0070] Furthermore, the first option indicating the category of correction may itself have a hierarchical structure. That is, the first option may include a main option indicating a major category of correction and sub-options indicating smaller categories included in the major category indicated by the main option. In this case, the correction suggestion unit 114 presents the main option to the job seeker and accepts the selection of a main option from the job seeker, and further presents at least one sub-option to the job seeker based on the selected main option and accepts the selection of a sub-option from the job seeker, thereby determining the category of correction. For example, if the major category is "Detail the content of the corrections," the sub-categories may include, for example, "Make the description professional," "Emphasis on the achievements," "Clarify the track record," etc.

[0071] Fig. 5 is a table showing an example of the correspondence between correction locations and correction policies. The table in Fig. 5 illustrates combinations of correction locations, correction categories (first option) presented according to the correction locations, policy details (second option) presented by selecting the first option, and selection results of the policy details (correction examples). Note that if the first option is in a category that requires a question (e.g., "emphasize results," "clarify achievements," "supplement anecdotes," etc.), a question about the correction location is presented along with the second option.

[0072] The correction suggestion unit 114 may present a free input field on the job seeker terminal 30 that is displayed in combination with the correction policy and that accepts the input of any text from the job seeker (job seeker terminal 30). This allows the job seeker to directly instruct corrections if the correction policy that the job seeker desires is not presented. This improves convenience for the job seeker in correcting the document to be corrected.

[0073] For example, if the revision policy (revision options) indicates a request for a question about the part to be revised (i.e., if the revision policy requires the job seeker to input additional information such as keywords or numbers), the revision suggestion unit 114 causes a free input field to be displayed on the job seeker terminal 30 along with a question about the part to be revised.

[0074] Furthermore, the correction suggesting unit 114 may display a free input field for the job seeker to input supplementary information (for example, more detailed principles, requests, etc.) along with a correction principle that does not require text input from the job seeker. In this case, the combination of the selected correction principle and the correction principle (text) input in the free input field is accepted as the final correction principle.

[0075] Furthermore, the correction suggestion unit 114 may present a correction policy indicating direct correction by the job seeker in combination with a free input field. For example, the correction suggestion unit 114 may cause the job seeker terminal 30 to display a free input field together with a correction policy of "manual editing." This enables the job seeker to make accurate and prompt corrections to corrections for which the job seeker has prepared specific corrections. Note that in the case of direct corrections, the text of the corrections may be entered (or displayed) by default in the free input field.

[0076] Furthermore, the correction suggesting unit 114 may present a correction policy that accepts correction requests from the job seeker in combination with a free input field. For example, the correction suggesting unit 114 may display a free input field together with the correction policy of "free description" on the job seeker terminal 30. This allows the correction suggesting unit 114 to present a new correction policy, for example, when the correction policy (category) that the job seeker desires is not presented.

[0077] In addition, if the job seeker terminal 30 is a mobile terminal such as a smartphone in which the input unit 34 and the output unit 35 are integrated as a touch panel, a software keyboard for entering text into the free input field is displayed on the job seeker terminal 30 along with the free input field.

[0078] The correction suggestion unit 114 may receive a job seeker's selection of a correction policy that has been set in combination with a free input field and display the free input field on the job seeker terminal 30. This allows the display area for correction points, correction policies, etc. on the job seeker terminal 30 to be wider when no input is required in the free input field, thereby improving operability for the job seeker.

[0079] For example, when presenting to the job seeker terminal 30, as correction options, a correction policy that requests text input from the job seeker and a correction policy that does not request text input from the job seeker, the correction suggesting unit 114 may not display a free input field on the job seeker terminal 30 until a correction policy is selected. In this case, the correction suggesting unit 114 displays a free input field together with the selected correction policy (e.g., question content) on the job seeker terminal 30 only when the job seeker selects a correction policy that requests text input. On the other hand, when the job seeker selects a correction policy that does not request text input, the correction suggesting unit 114 finalizes the correction policy without displaying a free input field on the job seeker terminal 30.

[0080] Alternatively, the correction suggesting unit 114 may first display a free input field on the job seeker terminal 30, and present a correction policy to the job seeker terminal 30 based on the content entered in the free input field. In this case, the correction suggesting unit 114 creates a correction policy based on the information on the part to be corrected, the content entered in the free input field, and the first reference information, and presents this correction policy to the job seeker terminal 30. In this case, the first reference information includes a correlation between the information on the part to be corrected, the content entered in the free input field, and the correction policy.

[0081] Fig. 6 is a diagram showing an example of a document correction screen CD displayed on the job seeker terminal 30. The document to be corrected RD is displayed on the document correction screen CD. When the job seeker selects any part of the document to be corrected RD displayed on the document correction screen CD, the selected part is accepted as the part to be corrected SP. In the example of Fig. 6, the part to be corrected SP is highlighted by shading.

[0082] When a correction portion SP is selected on the document correction screen CD, an initial dialog DG1 for confirming whether to make the correction is displayed on the document correction screen CD. The initial dialog DG1 includes an Execute button B11 and a Cancel button B12. When an input operation is performed on the Execute button B11, correction options for the correction portion SP are presented. When an input operation is performed on the Cancel button B12, for example, the selection of the correction portion SP is deselected and the initial dialog DG1 is closed. Furthermore, when an input operation is performed on the Cancel button B12, an additional selection button such as "Continue selection" that accepts the selection of additional correction portions SP may be displayed. When an input operation is performed on the additional selection button, the currently selected correction portion SP is maintained and the job seeker can additionally select a new correction portion SP.

[0083] 7 is a diagram showing an example of the document edit screen CD in which edit options are presented. As described above, when the execute button B11 is pressed in the initial dialog DG1 of FIG. 6, the edit policy dialog DG2 is displayed on the document edit screen CD. Note that the display of the initial dialog DG1 of FIG. 6 may be omitted. In other words, the edit policy dialog DG2 may be displayed immediately after the edit part SP is selected.

[0084] The revision policy dialog DG2 includes a plurality of option buttons (first option button B21, second option button B22, third option button B23, fourth option button B24, and fifth option button B25), each of which indicates one revision option. When an input operation is performed on any of the option buttons, the corresponding revision policy is accepted and a revision proposal is presented. Among the revision options in FIG. 7, the fourth option button B24 (the revision option for "Not Applicable (Free Text)") and the fifth option button B25 (the revision option for "Edit Manually") are each set to be combined with a free input field. Therefore, when these revision options are selected, a free input field is displayed before the revision policy is confirmed.

[0085] FIG. 8 is a diagram showing an example of the document correction screen CD in a state in which the free input field FF is displayed. As described above, when the fourth option button B24 or the fifth option button B25 is input in the correction policy dialog DG2 of FIG. 7, the free input field FF and the send button BF are displayed on the document correction screen CD. Furthermore, if the job seeker terminal 30 is a mobile terminal, a software keyboard SK is displayed together with the free input field FF. Note that FIG. 8 shows a state in which the fourth option button B24 (the correction option of "None of the above (free description)") has been selected and the job seeker has entered text explaining the correction policy. When an input operation is performed on the send button BF, the text entered in the free input field FF is accepted as the correction policy, and a correction proposal is presented.

[0086] Fig. 9 is a diagram showing another example of the document correction screen CD in which a free input field FF is displayed. In the example of Fig. 9, a free input field FF and a send button BF are displayed in advance on the document correction screen CD along with a plurality of option buttons. In Fig. 9, the text entered in the free input field FF and the correction policy corresponding to the entered option button are simultaneously accepted as the correction policy for the correction portion SP.

[0087] <Correction part 115> The correction unit 115 is configured to correct the part to be corrected based on the correction policy selected by the job seeker terminal 30.

[0088] When the correction suggestion unit 114 presents a first option and a second option, the correction unit 115 corrects the part to be corrected based on the policy content indicated by the selected second option. When the correction suggestion unit 114 presents a free input field, the correction unit 115 corrects the part to be corrected based on the correction policy and the text entered in the free input field.

[0089] If the selected correction policy is the correction result of the correction portion itself (for example, the corrected sentence, etc.), the correction unit 115 corrects the correction portion by replacing the correction portion of the document to be corrected with the correction result presented by the correction policy. Also, if the selected correction policy is direct correction by the job seeker, the correction unit 115 corrects the correction portion based on the information entered in the free input field. Specifically, the correction unit 115 corrects the correction portion of the document to be corrected by replacing it with the information (text) entered in the free input field. Note that the correction unit 115 may make partial corrections to the sentence entered by the job seeker and then replace it with the correction portion. Here, "partial correction" may include, for example, corrections to match the sentences before and after the correction portion, or formal corrections such as typos and omissions.

[0090] On the other hand, if the selected correction policy is not the correction result itself, the correction unit 115 may create a correction result in which the correction portion is corrected based on the correction policy and the second reference information, and may present the correction result to the job seeker (job seeker terminal 30). This allows the job seeker to check the correction result before reflecting it in the correction portion, thereby reducing the occurrence of backtracking due to unintended corrections.

[0091] The second reference information includes information on the correction location and a correlation between the correction policy and the correction result. The second reference information is stored, for example, in the storage unit 12. The second reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates the correlation between the information on the correction location and the correction policy and the correction result. The correlation included in the second reference information can be constructed, for example, by statistically analyzing data that records combinations of information on the correction location and the correction policy and the corresponding correction results.

[0092] The second reference information may include a learning model that has been machine-learned to input information about the correction portion and the correction policy, and output a correction result, or a correction model that is a generative AI. In this case, the correction unit 115 inputs the information about the correction portion and the correction policy into the correction model and causes the correction model to output the correction result. This makes it possible to create correction results based on correction examples of documents related to many job seekers or natural language processing. In the correction model, parameters calculated, tuned, etc. through learning constitute the correlations of the second reference information.

[0093] The correction model is included in the artificial intelligence unit 120. The correction model, which has been trained to be able to output correction results, is trained using, for example, a combination of information on correction locations and correction policies, and data on the corresponding correction results, as training data.

[0094] When the correction model is a generative AI including a general-purpose language model, the correction unit 115 receives information about the correction location and a correction policy as input, inputs a prompt including an instruction to output a correction result corresponding to the information about the correction location and the correction policy to the correction model, and causes the correction model to output the correction result. The correction unit 115 may generate a prompt that instructs the correction model to create the correction result and input the prompt to the correction model. Furthermore, the correction unit 115 may input, in addition to the instruction to create and output the correction result, the information about the correction location, and the correction policy, a prompt into which, for example, one or more samples of information about the correction location and the correction policy and one or more corresponding samples of the correction result are inserted as examples, samples, or training data of input and output pairs to the correction model.

[0095] For example, the correction unit 115 inputs a prompt such as "The user said ____. Please correct the {selected sentence} accordingly" into the correction model. The "____" in this prompt is inserted with the correction policy determined by the job seeker. Furthermore, the "{selected sentence}" refers to the sentence included in the correction portion.

[0096] The correction unit 115 may create a correction result using, in addition to the information on the correction portion and the correction policy, portions of the document to be corrected other than the correction portion or other information related to the job seeker (registered information other than the document to be corrected). For example, if the second reference information includes a correction model, the correction unit 115 may further input portions of the document to be corrected other than the correction portion or other information related to the job seeker (additional information) into the correction model. This can improve the accuracy of the correction result for the correction portion. In particular, since the document to be corrected may contain portions that require correction, the creation of inappropriate correction results can be suppressed by referring to information other than the document to be corrected.

[0097] In this way, the correction suggestion unit 114 may create a correction result based on the information on the correction portion, the correction policy, the additional information, and the second reference information, and present this correction result to the job seeker terminal 30. In this case, the second reference information includes the information on the correction portion, the correction policy, and the correlation between the additional information and the correction policy. For example, the correction unit 115 may insert an instruction such as "Please refer to {the entire resume} and make corrections" into the prompt for the correction model. Here, "{the entire resume}" refers to the entire document to be corrected.

[0098] The correction unit 115 creates a plurality of mutually different correction results corresponding to the correction policy decided by the job seeker, and may present the plurality of correction results to the job seeker (job seeker terminal 30), and further may accept a selection of a correction result from the job seeker (job seeker terminal 30). This allows the job seeker to correct the document to be corrected using a more appropriate correction result, thereby efficiently improving the quality of the document to be corrected.

[0099] The correction suggestion unit 114 may present, as the multiple correction results, multiple (e.g., three) correction results with different information granularity (specificity) or multiple (e.g., three) correction results with different numeric values ​​or keyword genres, etc. This allows the job seeker to have a wider range of choices for the correction results.

[0100] When the selected revision policy is to refine the revision portion, the revision unit 115 may create a revision result that includes keywords or numerical values ​​contained in parts of the document other than the revision portion or other information (additional information) related to the job seeker. This allows the creation of a revision result that is embodied using information contained in parts other than the revision portion.

[0101] After presenting the corrected result, the correction unit 115 may receive an instruction to re-present the corrected result from the job seeker terminal 30, and based on the instruction, create a new corrected result and present the corrected result to the job seeker terminal 30. When re-presenting the corrected result, the correction unit 115 inputs, for example, the necessary input information and a prompt including an instruction to create a corrected result that is different from the previously presented corrected result to the corrected model, and causes the corrected model to output the new corrected result.

[0102] If the revision policy is revisions made by the job seeker (such as text directly revised by the job seeker), the revision unit 115 inputs a prompt such as "Please replace {selected text} with the text . . . " into the revision model. The ". . . " part of this prompt is replaced with the revisions entered by the job seeker in the free input field.

[0103] The correction unit 115 may input a goal, such as outputting a correction result, to the AI ​​agent included in the artificial intelligence unit 120. The AI ​​agent generates and executes a task according to the input goal, and generates and outputs the targeted correction result. For example, the AI ​​agent collects information necessary for generating and outputting the correction result (e.g., information on the correction location, the correction policy, additional information, etc.) from the memory unit 22, an external information providing device, etc., and inputs the collected information to the generation AI, causing it to generate the targeted correction result.

[0104] Fig. 10 is a diagram showing an example of the document correction screen CD with the correction results displayed. As described above, when any of the selection buttons in Fig. 7, Fig. 8, or Fig. 9 is selected, multiple correction results CR created based on the selected correction policy (or entered in the free input field FF) are displayed on the document correction screen CD. In addition, a correction operation dialog DG3 is displayed on the document correction screen CD along with the multiple correction results CR.

[0105] The multiple correction results CR are objects that each accept exclusive (alternative) selection. The correction operation dialog DG3 also includes a Confirm button B31 indicating that the correction is to be made, a Re-correction button B32 indicating that the correction is to be made again, and a Cancel button B33 indicating that the correction is to be cancelled. When an input operation is performed on the Confirm button B31 while one of the correction results CR is selected, the selected correction result CR is reflected in the correction portion of the document to be corrected. When an input operation is performed on the Re-correction button B32, multiple new correction results CR are displayed on the document correction screen CD. When an input operation is performed on the Cancel button B33, for example, the display of the correction result CR is erased and the correction operation dialog DG3 is closed.

[0106] <Reference information update section 116> The reference information update unit 116 is configured to update the first reference information using a combination of information on the correction portion selected by the job seeker terminal 30 and the correction policy selected by the job seeker terminal 30. This makes it possible to improve the accuracy of presenting a correction policy in the first reference information (e.g., a correction policy creation model) based on the relationship between the content of the correction portion that was actually corrected and the correction policy requested by the job seeker for that correction portion. For example, the reference information update unit 116 makes the correction policy creation model learn tendencies regarding job seekers' correction needs, such as the tendency that a correction policy of "correcting numbers" is likely to be selected for correction portions related to "performance."

[0107] The reference information update unit 116 may update the second reference information using a combination of information on the correction portion selected by the job seeker terminal 30 and the correction result selected (or input) by the job seeker terminal 30. This makes it possible to improve the accuracy of presenting the correction result of the second reference information (e.g., the correction model) based on the relationship between the content of the correction portion that was actually corrected and the correction result requested by the job seeker for the correction portion.

[0108] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0109] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with a learning model such as a language model, such as a Transformer (including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4)), a Bidirectional Encoder Representations from Transformers (BERT), a Bidirectional and Auto-regressive Transformer (BART), or a Recurrent Neural Network (RNN). The artificial intelligence unit 120 may be, for example, a generative AI or an AI agent including a large-scale language model. A large-scale language model is a type of generative AI and includes models provided by services such as OpenAI's GPT, Google's Gemini, and Microsoft's Azure AI Studio. The artificial intelligence unit 120 may also include any machine learning model, deep learning model, artificial intelligence model, or the like.

[0110] 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 120 can apply the above algorithms as appropriate.

[0111] The artificial intelligence unit 120 may have 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 consists of pairs of input data for learning and output data (correct answer data). Furthermore, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0112] The artificial intelligence unit 120 may include a natural language model as its artificial intelligence, or may be a general-purpose natural language processing trained model such as a large-scale language model (LLM). An LLM is a learning model that has previously trained a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). It can perform various language processing tasks when given a task, and can perform a wide range of natural language processing tasks, such as understanding sentence patterns and context, answering questions, and generating sentences, according to given prompts. Such a general-purpose learning model includes a language model that can handle various tasks without fine-tuning, using one-shot learning, few-shot learning, etc. Furthermore, a general-purpose learning model may also be configured to handle various tasks using zero-shot learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

[0113] The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as the correction policy creation model) can undergo additional learning using techniques such as transfer learning and fine tuning. For example, each time new data is registered, the artificial intelligence unit 120 may perform additional learning and fine tuning using the new data as new training data. This improves the accuracy of the information output from the learning model.

[0114] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using an original learning model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby learning the student model, which becomes the distilled model. Alternatively, the student model may be learned to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model). Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the learning model. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0115] For example, the learning model used in each functional unit may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the learning model used in each functional unit, and when training data from the large-scale language model is accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the learning model used in each functional unit.

[0116] AI agents may also be called autonomous agents. An "AI agent" is a model that, when given a goal (purpose, objective, etc.) such as "teach me XX" or a task such as "output XX," breaks down the processing required to reach the goal or accomplish the task into subtasks, actions, etc., and performs tasks such as collecting and analyzing necessary data, generating and executing programs, etc. AI agents target information and instructions input by a user, autonomously select and execute tasks and actions according to the goal, and output information according to the goal, without requiring user intervention (operational input). AI agents may also autonomously learn to achieve their goals by autonomously creating and executing plans and evaluating the results. For example, an AI agent may be autonomously updated based on the results of subtask execution (e.g., collected information, information analysis results, etc.).

[0117] <Display section> The display unit 211 of the recruiting party terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen (information) indicated by the data transmitted from the server device 10.

[0118] <Operation acquisition part> The operation acquisition unit 212 of the recruiting party terminal 20 accepts operations by the recruiter using the recruiting party terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by the job seeker using the job seeker terminal 30.

[0119] 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.

[0120] This information processing includes an acquisition step, a selection receiving step, a correction suggestion step, and a correction step. In the acquisition step, a document related to the job seeker is acquired. In the selection receiving step, a selection of correction portions in the document is accepted from the job seeker. In the correction suggestion step, at least one correction policy for the correction portions is presented to the job seeker based on information about the correction portions and the first reference information, and a confirmation of the correction policy is accepted from the job seeker. In the correction step, the correction portions are corrected based on the selected correction policy.

[0121] 11 is an activity diagram showing an example of the flow of information processing (document correction processing) executed by the information processing system 1. Below, the information processing will be described along with each activity in this activity diagram.

[0122] The document correction process begins when the job seeker specifies the document to be corrected. The job seeker specifies the document to be corrected by selecting or uploading the document on the job seeker terminal 30 (activity A101). The server device 10 acquires the specified document from the job seeker terminal 30 (activity A102). Next, the server device 10 outputs to the job seeker terminal 30 a correction screen (a screen that displays the contents of the document) that accepts input of corrections (activity A103). As a result, the correction screen is displayed on the job seeker terminal 30 (activity A104).

[0123] The job seeker selects the part to be corrected on the correction screen displayed on the job seeker terminal 30 (activity A105). The server device 10 accepts the selection of the part to be corrected on the job seeker terminal 30 (activity A106). Next, the server device 10 creates a correction policy (correction options) based on the content of the accepted part to be corrected, and outputs the correction policy to the job seeker terminal 30 (activity A107). As a result, the correction policy is displayed on the job seeker terminal 30 (activity A108).

[0124] The job seeker confirms the displayed revision policy (selects a revision option) (activity A109). The server device 10 accepts the confirmation of the revision policy at the job seeker terminal 30 (activity A110). Next, the server device 10 creates a revision result based on the confirmed revision policy and outputs the revision result to the job seeker terminal 30 (activity A111). As a result, the revision result is displayed on the job seeker terminal 30 (activity A112). The job seeker then confirms the displayed revision result (selects a revision result) (activity A113). As a result, the revision part is corrected using the revision result (activity A114).

[0125] 4. Effect The operation of this embodiment can be summarized as follows: That is, by correcting the part to be corrected by presenting correction options for the part to be corrected and accepting the selection, it is possible to support the creation of documents related to job seekers.

[0126] 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 within the scope of the technical idea of ​​the invention.

[0127] 5.Other In the above embodiment, the server device 10 performs various storage and control functions. However, 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 blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external component of the server device 10. In this case, the external artificial intelligence unit 120 may be provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using LLM. The artificial intelligence service server receives inputs of prompts such as text, images, and voice, and generates and responds to the prompts.

[0128] At least one of the devices included in the information processing system 1 may be installed outside the country in which the functions of the information processing system 1 are performed.

[0129] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes steps executed by the information processing system 1. The program causes a computer to execute the steps of the information processing system 1.

[0130] The information processing system 1 can also be applied to the application of correcting documents (documents to be corrected) related to a recruiter (a person hiring human resources). When the user is a recruiter, documents to be corrected include, for example, a job posting, a scouting document to be sent to a job seeker, etc. In this case, the term "job seeker" in the above-mentioned acquisition unit 112, selection receiving unit 113, correction suggestion unit 114, correction unit 115, etc. may be replaced with "recruiter." For example, the acquisition unit 112 may acquire a document related to the user, who is a recruiter, as a document to be corrected.

[0131] It may be provided in the following manner.

[0132] (1) An information processing system comprising at least one processor, the processor being configured to execute the following steps by reading a program: an acquisition step of acquiring a document relating to a user who is a job seeker or an employer; a selection acceptance step of accepting a selection of corrections in the document from the user; a correction suggestion step of presenting to the user at least one correction policy for the corrections based on information about the corrections and first reference information, and accepting confirmation of the correction policy from the user; wherein the first reference information includes a correlation between information about the corrections and the correction policy; and a correction step of correcting the corrections based on the selected correction policy.

[0133] (2) In the information processing system described in (1) above, the first reference information includes a learning model that has been machine-learned to be able to input information about the correction location and output the correction policy, or a correction policy creation model that is a generative AI, and in the correction suggestion step, the information about the correction location is input to the correction policy creation model, and the correction policy creation model is caused to output at least one of the correction policies.

[0134] (3) In the information processing system described in (1) or (2) above, in the modification suggestion step, a plurality of modification options indicating the modification policy are presented, and a selection of the modification option is accepted as a confirmation of the modification policy.

[0135] (4) In the information processing system described in (3) above, in the correction suggestion step, at least one fixed option that does not change depending on the correction location and at least one variable option that changes depending on the correction location are presented as the correction options.

[0136] (5) In the information processing system described in (4) above, in the correction suggestion step, the variable option is created based on the information on the correction location and the first reference information, or the variable option is selected from pre-prepared option candidates.

[0137] (6) In the information processing system described in any one of (1) to (5) above, in the correction suggestion step, if the correction part contains a numerical value, the correction policy indicating the correction of the numerical value is presented.

[0138] (7) In the information processing system described in any one of (1) to (6) above, in the correction step, a correction result in which the correction part is corrected is created based on the correction policy and second reference information, and the correction result is presented to the user, wherein the second reference information includes information on the correction part and a correlation between the correction policy and the correction result.

[0139] (8) In the information processing system described in (7) above, the second reference information includes a correction model that is a learning model or a generative AI that has been machine-learned to be able to input information about the correction location and the correction policy and output the correction result, and in the correction step, the information about the correction location and the correction policy are input into the correction model, and the correction model is caused to output the correction result.

[0140] (9) In the information processing system described in (8) above, in the correction step, a portion of the document other than the corrected portion or other information about the user is further input to the correction model.

[0141] (10) In the information processing system described in any one of (7) to (9) above, in the correction step, a plurality of correction results different from each other are created, the plurality of correction results are presented to the user, and further, a selection of the correction result is accepted from the user.

[0142] (11) In the information processing system described in any one of (7) to (10) above, in the correction step, when the selected correction policy is to detail the correction portion, the information processing system creates the correction result including keywords or numerical values ​​contained in parts of the document other than the correction portion or other information related to the user.

[0143] (12) In the information processing system described in any one of (1) to (11) above, the correction policy includes a first option indicating a category of correction and a second option indicating a policy content in the category indicated by the first option, and in the correction suggestion step, the first option is presented to the user and a selection of the first option is accepted from the user, and further, based on the selected first option, at least one second option is presented to the user and a selection of the second option is accepted from the user, and in the correction step, the correction part is corrected based on the policy content indicated by the selected second option.

[0144] (13) In the information processing system described in (12) above, in the correction suggestion step, if the selected first option indicates a correction to the content of the correction part, the second option indicating the part to be corrected or a correction suggestion for the part to be corrected is presented to the user.

[0145] (14) In the information processing system described in (12) or (13) above, in the correction suggestion step, if the selected first option indicates a request for a question about the part to be corrected, a question about the part to be corrected and the second option indicating an answer to the question are presented to the user.

[0146] (15) In the information processing system described in any one of (1) to (14) above, in the correction suggestion step, a free input field is presented that accepts input of any text from the user and is displayed in combination with the correction policy, and in the correction step, the correction part is corrected based on the correction policy and the text entered in the free input field.

[0147] (16) In the information processing system described in (15) above, in the correction suggestion step, the free input field is displayed in response to the user's selection of the correction policy that has been set in combination with the free input field.

[0148] (17) In the information processing system described in (15) or (16) above, in the correction suggestion step, the correction policy indicating the direct correction by the user is presented in combination with the free input field, and in the correction step, the correction part is corrected based on the information entered in the free input field.

[0149] (18) In the information processing system described in any one of (1) to (17) above, the processor is configured to further execute the following steps: in the reference information update step, the first reference information is updated using a combination of information on the selected correction location and the selected correction policy.

[0150] (19) An information processing method, comprising steps executed by the information processing system according to any one of (1) to (18) above.

[0151] (20) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (18) above. Of course, this is not the case.

[0152] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0153] 1: Information processing system 2: Communication line 10: Server device 11: Control section 111: Basic display control section 112: Acquisition Department 113: Selection reception section 114: Revision proposal department 115: Correction section 116: Reference information update section 120: Artificial Intelligence Department 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter terminal 21: Control unit 211:Display section 212: Operation acquisition section 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job seeker terminal 31: Control unit 311: Display section 312: Operation acquisition section 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus B11: Execute button B12: Cancel button B21: First choice button B22: Second option button B23: Third option button B24: 4th option button B25: 5th option button B31: Decision button B32: Re-edit button B33: Cancel button BF: Send button CD: Document Editing Screen CR: Correction result DG1: Initial Dialog DG2: Correction Strategy Dialog DG3: Modify Operation Dialog FF: Free entry field RD: Document to be corrected SK: Software keyboard SP: Correction

Claims

1. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the acquisition step, documents relating to the user, a job seeker or an employer, are acquired, In the selection receiving step, a selection of a portion to be corrected in the document is received from the user; In the correction suggestion step, correction part information including the content expressed by the natural language included in the correction part or the context of the correction part is input to a correction policy creation model, the correction policy creation model is caused to output at least one correction policy for the correction part, the correction policy is presented to the user, and confirmation of the correction policy from the user is accepted, wherein the correction policy creation model is a learning model that has been machine-trained so as to be able to input the correction part information and output the correction policy based on information including the content expressed by the natural language included in the correction part in a document related to a job seeker or an employer that has been recorded in advance, or the context of the correction part, and the correction policy for that information, In the correction step, the information about the correction area and the selected correction policy are input into a correction model, and the correction model is caused to output a correction result obtained by correcting the correction area, and the correction result is presented to the user, wherein the correction model is a machine-learned learning model that is capable of inputting the information about the correction area and the correction policy and outputting the correction result based on a combination of pre-recorded information expressed in natural language contained in the correction area in a document related to a job seeker or an employer, or information including the context of the correction area, a correction policy for that information, and the correction result for that combination.

2. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the acquisition step, documents relating to the user, a job seeker or an employer, are acquired, In the selection receiving step, a selection of a portion to be corrected in the document is received from the user; In the correction suggestion step, a prompt including correction part information including the content expressed by the natural language included in the correction part or the context of the correction part and an instruction to output a correction policy for the correction part is input to a correction policy creation model, the correction policy creation model is caused to output at least one correction policy, the correction policy is presented to the user, and confirmation of the correction policy from the user is accepted, wherein the correction policy creation model is a generative AI, In the correction step, the information about the correction area and the selected correction policy are input into a correction model, and the correction model is caused to output a correction result obtained by correcting the correction area, and the correction result is presented to the user, wherein the correction model is a machine-learned learning model that is capable of inputting the information about the correction area and the correction policy and outputting the correction result based on a combination of pre-recorded information expressed in natural language contained in the correction area in a document related to a job seeker or an employer, or information including the context of the correction area, a correction policy for that information, and the correction result for that combination.

3. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the acquisition step, documents relating to the user, a job seeker or an employer, are acquired, In the selection receiving step, a selection of a portion to be corrected in the document is received from the user; In the correction suggestion step, correction part information including the content expressed by the natural language included in the correction part or the context of the correction part is input to a correction policy creation model, the correction policy creation model is caused to output at least one correction policy for the correction part, the correction policy is presented to the user, and confirmation of the correction policy from the user is accepted, wherein the correction policy creation model is a learning model that has been machine-trained so as to be able to input the correction part information and output the correction policy based on information including the content expressed by the natural language included in the correction part in a document related to a job seeker or an employer that has been recorded in advance, or the context of the correction part, and the correction policy for that information, In the correction step, a prompt including the correction location information, the selected correction policy, and an instruction to output a correction result obtained by correcting the correction location corresponding to the correction location information and the correction policy is input to a correction model, and the correction result is output by the correction model and presented to the user, wherein the correction model is a generative AI.

4. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the acquisition step, documents relating to the user, a job seeker or an employer, are acquired, In the selection receiving step, a selection of a portion to be corrected in the document is received from the user; In the correction suggestion step, a prompt including correction part information including the content expressed by the natural language included in the correction part or the context of the correction part and an instruction to output a correction policy for the correction part is input to a correction policy creation model, the correction policy creation model is caused to output at least one correction policy, the correction policy is presented to the user, and confirmation of the correction policy from the user is accepted, wherein the correction policy creation model is a generative AI, In the correction step, a prompt including the correction location information, the selected correction policy, and an instruction to output a correction result obtained by correcting the correction location corresponding to the correction location information and the correction policy is input to a correction model, and the correction result is output by the correction model and presented to the user, wherein the correction model is a generative AI.

5. 2. The information processing system according to claim 1, In the modification suggestion step, a plurality of modification options indicating the modification policy are presented, and a selection of the modification option is accepted as a confirmation of the modification policy.

6. 6. The information processing system according to claim 5, In the correction suggestion step, the information processing system presents, as the correction options, at least one fixed option that does not change depending on the correction location, and at least one variable option that changes depending on the correction location.

7. 7. The information processing system according to claim 6, In the modification suggestion step, the information processing system creates the variation option using the modification location information and the modification policy creation model, or selects the variation option from option candidates prepared in advance.

8. 2. The information processing system according to claim 1, In the correction suggestion step, if the part to be corrected includes a numerical value, the information processing system presents the correction policy indicating how to correct the numerical value.

9. 2. The information processing system according to claim 1, In the correction step, other information about the portion of the document other than the corrected portion or the user is further input to the correction model.

10. 2. The information processing system according to claim 1, In the correction step, the information processing system creates a plurality of correction results that are different from each other, presents the plurality of correction results to the user, and further accepts selection of the correction result from the user.

11. 2. The information processing system according to claim 1, In the correction step, when the selected correction policy is to detail the correction portion, an information processing system creates the correction result including keywords or numerical values ​​contained in parts of the document other than the correction portion or other information related to the user.

12. 2. The information processing system according to claim 1, the modification policy includes a first option indicating a category of modification and a second option indicating a policy content in the category indicated by the first option; the correction suggestion step presents the first option to the user and accepts selection of the first option from the user; and further presents at least one second option to the user based on the selected first option and accepts selection of the second option from the user; In the modifying step, the part to be modified is modified based on the policy content indicated by the selected second option.

13. 13. The information processing system according to claim 12, In the correction suggestion step, if the selected first option indicates a correction to the content of the correction part, the information processing system presents the second option, which indicates the part to be corrected or a correction suggestion for the part to be corrected, to the user.

14. 13. The information processing system according to claim 12, In the correction suggestion step, if the selected first option indicates a request for a question about the correction part, the information processing system presents the user with a question about the correction part and the second option indicating an answer to the question.

15. 2. The information processing system according to claim 1, In the correction suggestion step, a free input field is presented that is displayed in combination with the correction policy and that accepts input of any text from the user; In the correction step, the correction part is corrected based on the correction policy and the text entered in the free input field.

16. 16. The information processing system according to claim 15, In the correction suggestion step, the information processing system displays the free input field in response to the user's selection of the correction policy that has been set to be combined with the free input field.

17. 16. The information processing system according to claim 15, In the correction suggestion step, the correction policy indicating a direct correction by the user is presented in combination with the free input field; In the correcting step, the correction part is corrected based on information input in the free input field.

18. 2. The information processing system according to claim 1, The processor is further configured to perform the steps of: In the reference information updating step, the information processing system updates the modification policy creation model using a combination of the selected modification location information and the selected modification policy.

19. An information processing method, comprising: An information processing method, wherein an information processing device executes each step of the information processing system according to claim 4.

20. A program, A program for causing a computer to execute each step of the information processing system according to claim 4.

Images