Information processing system, information processing method and program

Abstract

We provide an information processing system that can support the creation of documents related to job seekers. [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: a document acquisition step acquiring a document containing information about a job seeker; a proposed information creation step creating at least one piece of proposed revision information for each of a plurality of revision perspectives for at least one item contained in the document based on the document and first reference information, the first reference information being information regarding the correlation between the combination of the document and the proposed revision information and the proposed revision information; a priority determination step determining the priority of each of the plurality of proposed revision information created in the proposed information creation step based on the proposed revision information and second reference information, the second reference information being information regarding the correlation between the proposed revision information and the priority; and an information presentation step presenting the proposed revision information extracted based on the priority from the plurality of proposed revision information created in the proposed information creation step to the job seeker.

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 related to job applicants.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can support the creation of documents related to job seekers. [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, the processor being configured to execute the following steps by reading a program: in a document acquisition step, a document containing information about a job seeker is acquired; in a proposed information creation step, at least one piece of suggested revision information is created for at least one item contained in the document for each of a plurality of revision perspectives based on the document and first reference information, the first reference information being information regarding the correlation between the combination of the document and the revision perspective and the suggested revision information; in a priority determination step, the priority of each piece of suggested revision information created in the proposed information creation step is determined based on the suggested revision information and second reference information, the second reference information being information regarding the correlation between the suggested revision information and the priority; and in an information presentation step, suggested revision information extracted based on the priority from the plurality of pieces of suggested revision information created in the suggested information creation step is presented to the job seeker.

[0007] According to this embodiment, it is possible to support the creation of documents relating to job seekers. [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] FIG. 10 is a diagram showing an example of a proposed information display screen SD displayed on the job seeker terminal 30. [Figure 6] 10 is a diagram showing an example of an improvement target document editing screen ED displayed on the job seeker terminal 30. FIG. [Figure 7]FIG. 10 is a diagram showing an example of an improvement target document edit screen ED in edit mode. [Figure 8] 1 is an activity diagram showing an example of the flow of information processing (processing for displaying correction suggestion information) 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 learned the correlation between input and output, or a generative AI such as a large-scale language model (these models include parameters that establish the correlation between input and output) or a visual language model that can output a desired result in response to a prompt.

[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 includes 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 terminal 20, and the job seeker terminal 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 terminal 20, and the job seeker terminal 30 may be wired or wireless. Furthermore, the server device 10, the recruiter terminal 20, and the job seeker terminal 30 are each an example of an information processing device.

[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), which is an example of a processor. 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 single, 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), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as necessary. That is, the communication unit 13 may be implemented as a collection of these multiple communication means. Furthermore, the server device 10 may communicate various information with 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> 3 is a block diagram showing the hardware configuration of the recruiting party terminal 20 and the job seeker terminal 30. The recruiting party terminal 20 is an information processing terminal used by the recruiter, and is capable of accessing the server device 10.

[0023] "Recruiters" include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, foundations), and public corporations (e.g., local governments), as well as their personnel. Personnel at recruiters may also be called hiring managers, and may include personnel in the organization's human resources department or personnel in the department that hires personnel. Recruiters may also include headhunters. A headhunter is an organization or its personnel that acts as an agent for the organization (recruiter) to mediate between job seekers and recruiters (organizations). Headhunters are also called recruitment agencies, recruitment agencies, agents, etc.

[0024] 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.

[0025] <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.

[0026] <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.

[0027] <Job Seeker Terminal 30> The job seeker terminal 30 is an information processing terminal used by a job seeker, and can access the server device 10. "Job seekers" include, for example, people who are looking to change jobs or find employment (for example, employed people (people looking to change jobs), prospective new graduates (job seekers), students, etc.), and people who are interested in changing jobs or finding employment.

[0028] 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.

[0029] 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).

[0030] 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).

[0031] As shown in FIG. 4A, the server device 10 (control unit 11) includes a basic display control unit 111, a document acquisition unit 112, a proposal information creation unit 113, a priority determination unit 114, an information presentation unit 115, a document editing unit 116, and an artificial intelligence unit 120.

[0032] 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.

[0033] <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 registration information of job seekers 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).

[0034] <Document Acquisition Unit 112> The document acquisition unit 112 is configured to acquire a document that includes information about a job seeker (hereinafter, "improvement target document").

[0035] "Information about the job seeker" includes, for example, basic information about the job seeker (name, age, gender, address, etc.), current employment information (organization, industry, department, job type, duties, job content, position, annual income, etc.), and historical information (educational background, work history, etc.).

[0036] Documents to be improved include, for example, resumes, which are documents related to a job seeker's work history (work history documents) that inform employers of their work history, experience, skills, qualifications, etc. 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 mainly describes the job seeker's profile, current situation, educational background, work history, desired working conditions, etc.

[0037] The document to be improved may be automatically generated by artificial intelligence such as a generation AI, or may be created by the job seeker himself / herself. Furthermore, the document to be improved may be, for example, registered in a job seeker database stored in the storage unit 12, uploaded by the job seeker from the job seeker terminal 30, or stored in external storage designated by the job seeker. In other words, the document acquisition unit 112 may accept the designation of the document to be improved by uploading the document to be improved from the job seeker terminal 30, inputting the network address of the document to be improved from the job seeker terminal 30, or the like. Furthermore, the document to be improved may be, for example, part of the registration information of the job seeker registered in the job seeker database.

[0038] The document to be improved includes multiple items. Each item includes a title (item name) and information to be written (e.g., text written by the job seeker, keywords, numerical values, etc.). The document to be improved may also include a summary item that summarizes the contents of other items.

[0039] Specific items included in the document to be improved include, for example, work history items, work summary items, skill items, qualification items, and self-promotion items.

[0040] The "work history items" include organizational information (e.g., industry, organization name, department name, job title, etc.), project details, job content, work content, achievements, etc. in the job seeker's career. If the job seeker has multiple experience elements (e.g., experience organization, experience department, experience position, experience project, etc.), details for each of the multiple experience elements are entered.

[0041] The "job summary item" includes a summary of the items in the work experience item as a description item. In other words, the document to be improved may include a work experience item that includes multiple experience elements and a job summary item that summarizes the multiple experience elements.

[0042] The "skills section" includes the skills possessed by the job seeker. The "qualifications section" includes the qualifications possessed by the job seeker. The "self-promotion section" includes the points that the job seeker wants to appeal to employers.

[0043] <Proposal Information Creation Unit 113> The proposed information creating unit 113 is configured to create at least one piece of proposed modification information for each of a plurality of modification viewpoints for at least one item included in the improvement target document, based on the improvement target document and the first reference information.

[0044] The "correction perspective" is a perspective (criteria) for evaluating the content of the current item and making improvements to improve that evaluation. The "correction proposal information" is information that includes improvements for each item in line with the correction perspective (i.e., evaluation based on the correction perspective).

[0045] The multiple revision perspectives may include at least a first perspective on matters that are required to be described in the item and a second perspective on the specificity of the content of the item. This allows revision suggestions to be made from two perspectives (for example, sufficiency and specificity), allowing the job seeker to revise the document to be improved to have content that is advantageous for job hunting.

[0046] The "items required to be described in each item" may be set or determined for each item. For example, the work history item requires descriptions of roles, achievements, etc., and the work summary item requires descriptions of clear experience, chronological information, etc.

[0047] The number and content of revision perspectives may vary for each item. For example, in the work history item, revision suggestion information may be created for each of the two first perspectives, "Is the role described?" and "Are achievements described?", and the second perspective, "Is there specificity?" (a total of three revision suggestion information). Also, for example, in the job summary item, revision suggestion information may be created for each of the two first perspectives, "Is there a chronological description?" and "Is the experience clearly described?", and the second perspective, "Is there specificity?" (a total of three revision suggestion information).

[0048] The proposal information creating unit 113 may create at least one piece of proposed modification information for each of a plurality of modification viewpoints for a plurality of items included in the document to be improved, based on the document to be improved and the first reference information.

[0049] The proposal information creating unit 113 may create one or more pieces of proposal information for one revision perspective or one item (one combination of an item and a revision perspective). Furthermore, the number of pieces of proposal information for each revision perspective or each item may not be the same for each revision perspective or each item. In other words, the number of pieces of proposal information for revision created may differ depending on the combination of an item and a revision perspective.

[0050] The total number of pieces of correction proposal information created by the proposal information creation unit 113 is the sum of the number of correction perspectives for each item for which correction proposal information is created. For example, if there is one item for which correction proposal information is created and the correction perspective for that item is two, the proposal information creation unit 113 creates at least two pieces of correction proposal information. Also, if there are two items for which correction proposal information is created and the correction perspectives for each item are two and three, respectively, the proposal information creation unit 113 creates at least five pieces of correction proposal information. In this case, if three pieces of correction proposal information are created for each correction perspective, the total number of pieces of correction proposal information will be 15.

[0051] The proposed information creating unit 113 may create proposed revision information for all items included in the document to be improved, or may create proposed revision information for only pre-set items (for example, work history items and job summary items) out of multiple items included in the document to be improved. The proposed information creating unit 113 may also accept a selection of items for which proposed revision information is to be created from the job seeker terminal 30, and create proposed revision information for the selected items.

[0052] The proposal information creating unit 113 may determine items for which correction proposal information is to be created, for example, according to the content of the document to be improved. For example, the proposal information creating unit 113 may evaluate the content of each item of the document to be improved based on viewpoints such as the degree of satisfaction of a correction viewpoint using a classifier such as a trained model, and determine items for which correction proposal information is to be created based on the evaluation results.

[0053] The first reference information (reference information for revision suggestions) is information regarding the correlation between the combination of the improvement target document and the revision viewpoint and the revision suggestion information. 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 the combination of the improvement target document and the revision viewpoint and the revision suggestion information. The correlation included in the first reference information can be constructed, for example, by statistically analyzing data recording the combination of the improvement target document and the revision viewpoint and the corresponding revision suggestion information.

[0054] The first reference information may include a set of parameters for generating suggested revision information from a combination of the improvement target document and the revision viewpoint. For example, the first reference information may be various types of trained models. For example, the first reference information may include a dedicated learning model that has been machine-learned so as to be able to input the combination of the improvement target document and the revision viewpoint and output suggested revision information, or a suggested information creation model that is a general-purpose learning model. In this case, the suggested information creation unit 113 inputs the combination of the improvement target document and the revision viewpoint into the suggested information creation model and causes the suggested information creation model to output suggested revision information.

[0055] The proposal information creation model is included in the artificial intelligence unit 120. The proposal information creation model, which is a dedicated learning model, may be constructed by performing learning using, for example, data on combinations of documents to be improved and revision viewpoints and data on corresponding revision proposal information as training data. In such a proposal information creation model, parameters calculated, tuned, etc. through learning construct a correlation between combinations of documents to be improved and revision viewpoints and revision proposal information. Note that the dedicated learning model may include a generation AI capable of generating answers not included in the training data. The generation AI of the dedicated learning model is a limited-purpose generation AI that does not require input of instructions such as the content of the output information to be generated or the content of the task to be executed.

[0056] When the proposal information creation model is a general-purpose learning model (e.g., a language model such as a large-scale language model), the proposal information creation unit 113 inputs a prompt including a combination of a document to be improved and a revision perspective and an instruction to input the combination and output revision proposal information corresponding to the combination to the proposal information creation model, and causes the proposal information creation model to output the revision proposal information. The proposal information creation unit 113 may generate a prompt that instructs the proposal information creation model to create revision proposal information and input the prompt to the proposal information creation model. Furthermore, the proposal information creation unit 113 may input a prompt including, in addition to the combination of the document to be improved and a revision perspective and the instruction to create and output the revision proposal information, examples, or training data of input and output pairs, for example, one or more samples of combinations of the document to be improved and a revision perspective and one or more corresponding samples of revision proposal information to the proposal information creation model. Here, the parameters for constructing the proposal information creation model and the prompt including an instruction to output revision proposal information corresponding to the combination of the document to be improved and a revision perspective construct a correlation between the combination of the document to be improved and the revision proposal information. The general-purpose learning model may include a generation AI that can generate any output information based on input information. The generation AI of the general-purpose learning model is a general-purpose generation AI that requires input of instructions such as the content of the output information to be generated and the content of the task to be executed.

[0057] The first reference information may include multiple proposed information creation models, which are trained models prepared for multiple revision perspectives. In this case, the proposed information creation unit 113 may input the document to be improved into multiple proposed information creation models and cause each proposed information creation model to output proposed revision information for each of the multiple revision perspectives. This allows proposed revision information to be created by a proposed information creation model specialized for each revision perspective, thereby improving the quality of the proposed revision information. Furthermore, parallel processing by multiple proposed information creation models can shorten the processing time until the proposed revision information is presented.

[0058] The proposed information creation model prepared for each of the multiple correction perspectives may be a dedicated learning model or a general-purpose learning model. In the case of a dedicated learning model, the proposed information creation model for each correction perspective is constructed by performing learning using, as training data, a combination of data on the document to be improved and data on correction proposal information based on a specific correction perspective for the document to be improved (e.g., "Is a role described?").

[0059] In the case of a general-purpose learning model, the proposal information creation model for each correction viewpoint is, for example, a trained model in which parameters constituting a neural network or the like are different from each other. In other words, the proposal information creation model for each correction viewpoint is different from each other in at least one of, for example, the vendor of the trained model, the number of parameters, the network structure, the learning algorithm, etc. Furthermore, the proposal information creation model for each correction viewpoint may be a fine-tuned model (derived model) in which different fine-tuning (additional learning for each correction viewpoint) is performed on a common base model.

[0060] The correction perspective does not necessarily have to be input to the proposed information creation model (dedicated learning model or general-purpose learning model) prepared for each of the multiple correction perspectives. In other words, the proposed information creation unit 113 may input only the improvement target document to each proposed information creation model for each correction perspective, and output the correction proposal information for each correction perspective to each proposed information creation model. In this case, the correspondence between the correction perspective and the proposed information creation model for each correction perspective forms part of the correlation between the combination of the improvement target document and the correction perspective and the correction proposal information.

[0061] The first reference information may include multiple proposal information creation models, which are trained models prepared for multiple items. In this case, the proposal information creation unit 113 may input the document to be improved into multiple proposal information creation models and cause each proposal information creation model to output revision proposal information for each revision perspective for each of the multiple items. This allows revision proposal information to be created by a proposal information creation model specialized for each item, thereby improving the quality of the revision proposal information. Furthermore, parallel processing by multiple proposal information creation models can shorten the processing time until the revision proposal information is presented.

[0062] The proposed information creation model prepared for each of the multiple items may be a dedicated learning model or a general-purpose learning model. In the case of a dedicated learning model, the proposed information creation model for each item is constructed by performing learning using, as training data, a combination of data on a combination of a document to be improved and a correction perspective, and data on correction proposal information from the correction perspective for a specific item of the document to be improved (e.g., a work history item).

[0063] When the model is a general-purpose learning model, the model for creating proposal information for each item is a trained model in which, like the model for creating proposal information for each correction viewpoint, parameters constituting a neural network or the like are different from each other. In addition, the model for creating proposal information for each item may be a fine-tuning model (derived model) in which different fine-tuning (additional learning for each item) is performed on a common base model.

[0064] The first reference information may include multiple proposed information creation models, which are trained models prepared for multiple combinations of correction perspectives and items. The proposed information creation models prepared for multiple combinations may be dedicated learning models or general-purpose learning models. The proposed information creation models (dedicated learning models or general-purpose learning models) prepared for multiple combinations do not necessarily require input of correction perspectives. In other words, the proposed information creation unit 113 may input only the improvement target document to each proposed information creation model for each combination, and output the proposed correction information for each combination to each proposed information creation model.

[0065] The proposal information creating unit 113 may create correction proposal information including a correction example for an item of the document to be improved. The "correction example" may be, for example, a sentence or keyword obtained by correcting a sentence or keyword included in the current item, a sentence or keyword that replaces a sentence or keyword included in the current item, a sentence or keyword that is added to the current item, or a combination thereof.

[0066] Furthermore, the proposal information creating unit 113 may create correction proposal information including a correction policy for an item and an example of a correction for the item in accordance with the correction policy. The "correction policy" is information that suggests, for example, a correction target, a correction purpose, a correction method, etc.

[0067] <Priority determination unit 114> The priority determination unit 114 is configured to determine the priority of each of the multiple pieces of suggested modification information created in the suggested information creation unit 113, based on the suggested modification information created by the suggested information creation unit 113 and the second reference information.

[0068] The "priority" is a parameter indicating the order of priority for determining the suggested revision information to be presented by the information presenting unit 115, which will be described later. The priority is assigned regardless of the revision perspective from which the suggested revision information was created. For example, if three pieces of suggested revision information are created by the suggested information creating unit 113 for each of the first and second revision perspectives, the absolute priority among the total of six pieces of suggested revision information is determined as the priority.

[0069] The priority determination unit 114 may assign an index indicating the magnitude of the priority to the modification suggestion information as a priority. The "index" may include, for example, a numerical value, a code indicating a rank or a grade (e.g., A, B, C, etc.), etc.

[0070] The second reference information is information relating to the correlation between the revision suggestion information and the priority. 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 revision suggestion information and the priority. The correlation included in the second reference information can be constructed, for example, by statistically analyzing data recording the revision suggestion information and the corresponding priority.

[0071] The second reference information may include a set of parameters for generating priorities from the revision proposal information. For example, the second reference information may be various types of trained models. For example, the second reference information may include a priority determination model, which is a dedicated learning model that has been machine-learned to use the revision proposal information as input and output priorities, or a general-purpose learning model. In this case, the priority determination unit 114 inputs the revision proposal information to the priority determination model and causes the priority determination model to output priorities.

[0072] The priority determination model is included in the artificial intelligence unit 120. The priority determination model, which is a dedicated learning model, may be constructed by performing learning using data on correction suggestion information and data on the corresponding priority as training data. In such a priority determination model, parameters calculated, tuned, etc. by learning construct a correlation between the correction suggestion information and the priority.

[0073] When the priority determination model is a general-purpose learning model (e.g., a language model such as a large-scale language model), the priority determination unit 114 inputs a prompt including correction suggestion information and an instruction to input the correction suggestion information and output a priority corresponding to the correction suggestion information to the priority determination model, and causes the priority determination model to output the priority.

[0074] The priority determination unit 114 may generate a prompt that provides an instruction to the priority determination model to determine the priority, and input the prompt to the priority determination model. Furthermore, the priority determination unit 114 may input a prompt that includes, for example, one or more samples of correction proposal information and one or more corresponding priority samples as examples, samples, or training data of input and output pairs, in addition to the correction proposal information and the priority determination / output instruction, to the priority determination model. Here, the parameters that construct the priority determination model and the prompt that includes an instruction to output the priority corresponding to the correction proposal information construct a correlation between the correction proposal information and the priority.

[0075] The priority determination unit 114 may input a prompt including the proposed revision information, the definition information of the priority, and an instruction to input the proposed revision information and output the priority corresponding to the proposed revision information to a priority determination model, which is a general-purpose learning model, and cause the priority determination model to output the priority. This allows the priority determination criteria to be flexibly adjusted by customizing the definition information.

[0076] The "priority definition information" is, for example, information linking the magnitude (index) of the priority with the content of the corresponding revision proposal information. For example, the priority determination unit 114 may input definition information, such as "an index of 4 for revision proposal information regarding an item that, if not corrected, is likely to result in the hiring manager not sending a scout, an index of 3 for revision proposal information that significantly changes the content of the target document or that addresses an oversight of an important point, an index of 2 for revision proposal information that improves the content of the target document but does not improve a critical part, and an index of 1 for revision proposal information that does not significantly affect the content of the target document or that involves minor corrections," into the priority determination model, along with a prompt including an instruction to determine the priority of the revision proposal information according to the definition information, and output the index to the priority determination model. Note that the definition information may be input to the priority determination model as part of the prompt.

[0077] When the proposal information creating unit 113 creates correction proposal information for a plurality of items, the priority determination unit 114 may determine, based on the correction proposal information and the second reference information, the priority of each of the plurality of correction proposal information for the plurality of items created by the proposal information creating unit 113. Here, the priority may be, for example, independent for each item (i.e., specifying the priority of the correction proposal information for each item), or may be common to a plurality of items (i.e., specifying the priority of all correction proposal information regardless of the item).

[0078] When the correction proposal information includes a correction example, the priority determination unit 114 may assign a first priority to one of the multiple pieces of correction proposal information created by the proposal information creation unit 113, whose correction example satisfies the description requirements for the corresponding item. Furthermore, the priority determination unit 114 may assign a second priority, which is lower than the first priority, to one of the multiple pieces of correction proposal information created by the proposal information creation unit 113, whose correction examples include consistent keywords. Furthermore, the priority determination unit 114 may assign a third priority, which is lower than the second priority, to one of the multiple pieces of correction proposal information created by the proposal information creation unit 113, whose correction examples include matters required for the corresponding item. This makes it possible to preferentially present correction proposal information that is highly likely to contribute to improving the document to be improved to the job seeker.

[0079] "Description requirements for each item" are, for example, the number of characters (minimum or maximum) set for each item. "Consistent keywords" means, for example, that there is no variation in keywords or the use of multiple synonyms that are different from each other. "Items required for each item" are, for example, keywords that are set for each item and must be written.

[0080] The priority determination unit 114 may, for example, input a prompt including correction suggestion information and instructions to determine the priority in accordance with the above-mentioned first priority, second priority, and third priority assignment rules to the priority determination model, and cause the priority determination model to output a priority (either the first priority, the second priority, or the third priority).

[0081] <Information presentation section 115> The information presentation unit 115 is configured to present to the job seeker the correction proposal information extracted from the multiple correction proposal information created by the proposal information creation unit 113 based on the priority determined by the priority determination unit 114.

[0082] The information presenting unit 115, for example, displays on the job seeker terminal 30 suggested revision information whose priority level is equal to or greater than a predetermined level. If an index is assigned as the priority level, the information presenting unit 115 may present suggested revision information whose index is equal to or greater than a predetermined threshold level to the job seeker. This ensures that suggested revision information with a high priority level is presented to the job seeker. The "threshold" may be set to, for example, "3" (for a numerical value) or "B" (for a sign).

[0083] The information presenting unit 115 may determine the proposed revision information to be presented to the job seeker based on, for example, the ranking of the priority levels of the plurality of proposed revision information. For example, the information presenting unit 115 may cause the job seeker terminal 30 to display the proposed revision information having a priority (index) that is within the top five. The information presenting unit 115 may also determine the proposed revision information to be presented to the job seeker by combining a threshold value and the ranking. For example, the information presenting unit 115 may cause the job seeker terminal 30 to display the proposed revision information having an index of 3 or more and within the top five in terms of index size.

[0084] The information presentation unit 115 may extract at least one piece of revision suggestion information for each of a plurality of revision perspectives, or may extract revision suggestion information based on priority regardless of the revision perspective. In the former case, for example, the information presentation unit 115 may extract revision suggestion information with the highest priority for each revision perspective, and then additionally extract the remaining revision suggestion information whose priority satisfies the extraction condition. In the latter case, for example, the information presentation unit 115 may extract revision suggestion information based only on the priority of the revision suggestion information without considering the revision perspective. In other words, there may be a revision perspective for which created revision suggestion information is not presented.

[0085] Furthermore, the information presenter 115 may weight the priority according to the revision perspective. For example, the information presenter 115 may multiply the priority of the revision suggestion information by a weighting coefficient that differs for each revision perspective. For example, the information presenter 115 may extract the revision suggestion information by comparing a value obtained by multiplying a priority index of the revision suggestion information created from a first perspective by a first weighting coefficient with a value obtained by multiplying a priority index of the revision suggestion information created from a second perspective by a second weighting coefficient that is smaller than the first weighting coefficient.

[0086] When the proposal information creating unit 113 creates correction proposal information for multiple items, the information presenting unit 115 may present to the job seeker correction proposal information extracted based on priority from the multiple correction proposal information created by the proposal information creating unit 113 for each of the multiple items. This makes it easier for the job seeker to correct the document to be improved, as high-priority correction proposal information is presented for each item of the document to be improved. Note that the number of correction proposal information presented for each item may be the same or different. Note that, depending on the extraction results, there may be items for which created correction proposal information is not presented.

[0087] The information presenting unit 115 may present at least one piece of correction proposal information for each of the plurality of items so that the total number of pieces of correction proposal information presented for each item across all of the plurality of items for which correction proposal information has been created is equal to or less than a predetermined upper limit. This makes it possible to present at least one piece of correction proposal information for each item while suppressing the total number of pieces of correction proposal information presented to the job seeker.

[0088] For example, when suggested correction information is created for a work history item and a work summary item and the total number of suggested correction information is limited to six, the information presenting unit 115 may present two suggested correction information for the work history item and four suggested correction information for the work summary item based on the priority of each suggested correction information. Such presentation is performed, for example, when the priority of the suggested correction information with the third and fourth highest priorities in the work summary item is higher than the priority of the suggested correction information with the third highest priority in the work history item.

[0089] When the correction suggestion information includes correction examples, the information presenting unit 115 may present a correction policy and a correction example for each piece of correction suggestion information. This enables the job seeker to edit the document to be improved by referring to the correction example while confirming the intention of the correction policy presented by the correction policy.

[0090] The information presentation unit 115 may highlight text in the revision example according to the degree of relevance to the revision policy. This makes it easier for job seekers to understand important parts of the revision example, thereby improving the efficiency of the work of revising documents to be improved.

[0091] "Relevance to the revision policy" refers to, for example, the relevance to keywords included in the revision policy (whether it embodies the keyword, etc.), the correspondence to instructions or commands included in the revision policy (whether it is a response to instructions or commands), etc.

[0092] "Highlighting" refers to, for example, displaying text (keywords, sentences, etc.) in a revision example that is more relevant to the revision policy than other parts in a way that makes it more noticeable than other parts. Examples of highlighting include coloring, bolding, enlarging the size, adding decoration, framing, and individual display (displaying in a position or area separate from the entire revision example).

[0093] The information presenter 115 may determine text to be highlighted (hereinafter, "highlighted text") based on the revision suggestion information including the revision policy and revision examples, and the third reference information. The third reference information is information regarding the correlation between the revision suggestion information and the highlighted text. The third reference information is stored, for example, in the storage unit 12. The third reference information may include, for example, a table, a function, a simple algorithm, or the like, which indicates the correlation between the revision suggestion information and the highlighted text. The correlation included in the third reference information can be constructed, for example, by statistically analyzing data recording the revision suggestion information and the corresponding highlighted text.

[0094] The third reference information may include a set of parameters for generating emphasized text from the suggested revision information. For example, the third reference information may be various types of trained models. For example, the third reference information may include an emphasized text determination model, which is a dedicated learning model trained by machine learning to use the suggested revision information as input and output emphasized text, or a general-purpose learning model. In this case, the information presenter 115 inputs the suggested revision information to the emphasized text determination model and causes the emphasized text determination model to output emphasized text.

[0095] The emphasized text determination model is included in the artificial intelligence unit 120. The emphasized text determination model, which is a dedicated learning model, may be constructed, for example, by learning using data on the suggested correction information and data on the corresponding emphasized text as training data. In such an emphasized text determination model, parameters calculated, tuned, etc., through learning establish a correlation between the suggested correction information and the emphasized text.

[0096] When the emphasized text determination model is a general-purpose learning model (e.g., a language model such as a large-scale language model), the information presentation unit 115 inputs a prompt including correction suggestion information and an instruction to input the correction suggestion information and output emphasized text corresponding to the correction suggestion information to the emphasized text determination model, and causes the emphasized text to be output from the emphasized text determination model. The information presentation unit 115 may generate a prompt that instructs the emphasized text determination model to determine emphasized text and input the prompt to the emphasized text determination model. Furthermore, in addition to the correction suggestion information and the instruction to determine and output the emphasized text, the information presentation unit 115 may input a prompt including, for example, one or more samples of the correction suggestion information and one or more samples of the corresponding emphasized text as examples, samples, or training data of input and output pairs to the emphasized text determination model. Here, the parameters for constructing the emphasized text determination model and the prompt including an instruction to output emphasized text corresponding to the correction suggestion information establish a correlation between the correction suggestion information and the emphasized text.

[0097] The information presenting unit 115 may present a plurality of pieces of proposed correction information to the job seeker, and may display confirmation status information indicating whether the proposed correction information has been confirmed based on the job seeker's operation on the proposed correction information. This prevents the job seeker from repeatedly confirming proposed correction information that the job seeker has already referenced, thereby improving the efficiency of the work of correcting the document to be improved.

[0098] "Operations on correction proposal information" include, for example, operations to display details of the correction proposal information (e.g., correction examples) on the job seeker terminal 30, operations to switch the correction proposal information whose details are displayed, operations to start correcting the document to be improved using the correction proposal information (to instruct the start of editing), operations to select or copy text included in the correction proposal information (e.g., sentences in the correction examples, etc.), operations to edit the contents of the document to be improved for which the correction proposal information has been created, etc.

[0099] The "confirmation status information" is displayed in the form of, for example, a keyword, a label, an icon, or the like. The confirmation status information may be assigned to each piece of suggested revision information, or may be assigned to an item for which suggested revision information has been created. In the latter case, the information presenter 115 may, for example, display confirmation status information indicating that the suggested revision information has not been confirmed for one item for which multiple pieces of suggested revision information have been created, and when an operation is performed on any of the suggested revision information included in the item, change the confirmation status information to content indicating that the information has been confirmed.

[0100] For example, the information presentation unit 115 may display on the job seeker terminal 30, for each item of the document to be improved, a proposed information display area that displays proposed correction information and a correction reception object that accepts corrections, and may display confirmation status information for the item indicating that it has been confirmed in response to a switching operation of the proposed correction information in the proposed information display area or an input operation into the correction reception object.

[0101] 5 is a diagram showing an example of the proposed information display screen SD displayed on the job seeker terminal 30. The proposed information display screen SD displays suggested correction information SI, a confirmation status label CL, and a correction reception object MO for each of a plurality of items IM.

[0102] The item IM is the name of the item for which the correction proposal information SI was created in the document to be improved. In the example of Figure 5, the job summary item ("Job Summary" in Figure 5) and the work history item ("Job Description" in Figure 5) are displayed.

[0103] The revision proposal information SI includes a revision policy MP ("Proposal Content" in FIG. 5) and a revision example ("Proposal Sample" in FIG. 5). In the example of FIG. 5, two revision proposal information SI are presented for the job summary, and one revision proposal information SI is presented for the job content. In the job summary, the two revision proposal information SI are displayed side by side, and the revision proposal information SI that displays the entire content can be switched by scrolling left and right on the job seeker terminal 30.

[0104] The confirmation status label CL is a label that displays the confirmation (view) status of the correction proposal information SI prepared for each item. In the example of Figure 5, the correction proposal information SI in the job summary displays a confirmation status label CL in the unconfirmed state, and the job content displays a confirmation status label CL in the confirmed state. For example, in the job summary of Figure 5, when the correction proposal information SI is scrolled or an input operation is performed on the correction reception object MO, the confirmation status label CL changes from the unconfirmed state to the confirmed state.

[0105] The correction reception object MO accepts corrections (edits) to the contents of the corresponding item. When an input operation is performed on the correction reception object MO, a screen for editing the contents of the item is displayed on the job seeker terminal 30.

[0106] <Document Editing Department 116> The document editing unit 116 is configured to accept edits to the document to be improved from the job seeker. For example, the document editing unit 116 displays the content of the item to be edited and suggested correction information for the item side by side on the job seeker terminal 30, and accepts edits to the content of the item (sentences or keywords) from the job seeker terminal 30.

[0107] The document editing unit 116 may accept edits for the entire document to be improved, or may accept edits for each item. For example, the document editing unit 116 may display the content of each item on the job seeker terminal 30 and accept edits to the content.

[0108] The document editing unit 116 may accept copying of any text of the correction example included in the correction suggestion information and pasting of the copied text into an item of the document to be improved. Furthermore, the document editing unit 116 may display a copy reception object that accepts selection of a copy range of the correction example on the job seeker terminal 30, and accept an operation to copy the text of the correction example in response to an input operation on the copy reception object.

[0109] The document editing unit 116 may display, on the job seeker terminal 30, a redisplay reception object that accepts the redisplay of the correction proposal information while the contents of the document to be improved are being edited on the job seeker terminal 30, and may redisplay the correction proposal information on the job seeker terminal 30 in response to an input operation on the redisplay reception object. For example, when the document editing unit 116 accepts an edit of the document to be improved (for example, when text in the document to be improved is selected and the mode is switched to edit mode), it may display a software keyboard on the job seeker terminal 30 instead of the correction proposal information and accept text input from the software keyboard. Furthermore, the document editing unit 116 may redisplay the correction proposal information instead of the software keyboard in response to an input operation on the redisplay reception object.

[0110] Fig. 6 is a diagram showing an example of the improvement target document editing screen ED displayed on the job seeker terminal 30. The improvement target document editing screen ED is displayed, for example, when an input operation is performed on the correction reception object MO on the proposed information display screen SD of Fig. 5. In Fig. 6, as an example of an input operation being performed on the job summary correction reception object MO, the edit target text ET, which is the content of the job summary item of the improvement target document, is displayed on the improvement target document editing screen ED.

[0111] Below the text to be edited ET, correction proposal information SI created for the job summary item (two correction proposal information SI in the example of Figure 6) is displayed. The number and content of correction proposal information SI displayed on the improvement target document editing screen ED are the same as the correction proposal information SI for the job summary item displayed on the proposal information display screen SD. Also, like the proposal information display screen SD, the correction proposal information SI displayed on the improvement target document editing screen ED can be switched by scrolling left and right.

[0112] On the screen ED for editing the document to be improved, in the example correction ME of the correction proposal information SI, text that is highly relevant to the correction policy MP (in the example of Figure 6, the part describing the "improvement points" included in the correction policy MP) is highlighted in bold. In addition, the example correction ME has a copy reception object CO attached. When an input operation is performed on the copy reception object CO, the entire text of the example correction ME is selected as the copy range, and a copy execution object that accepts the execution of the copy is displayed. The copy range can be adjusted to any part (text) of the example correction ME by the job seeker's operation. When an input operation is performed on the copy execution object, the text included in the copy range is copied to the clipboard.

[0113] Fig. 7 is a diagram showing an example of the improvement target document editing screen ED in edit mode. When the text to be edited ET is selected (an input operation is performed on any part) on the improvement target document editing screen ED in Fig. 6, an edit cursor CS is displayed on the text to be edited ET as shown in Fig. 7, and the text to be edited ET becomes editable (edit mode).

[0114] On the improvement target document editing screen ED in edit mode, a software keyboard SK is displayed below the text to be edited ET in place of the correction suggestion information SI. Also, a redisplay reception object RO is displayed above the software keyboard SK. When an input operation is performed on the redisplay reception object RO, the correction suggestion information SI is redisplayed below the text to be edited ET in place of the software keyboard SK.

[0115] <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.

[0116] The artificial intelligence unit 120 may be an AI (Artificial Intelligence) having a trained model such as a language model, such as a Transformer (including GPT (Generative Pretrained Transformer, including GPT-1 to GPT-5)), 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, various language models, large-scale language models, general-purpose learning models including generative AI, or AI agents, and may include specific models such as OpenAI's GPT, Google's Gemini, and models provided through services or platforms such as Microsoft's Azure AI Studio. The generative AI may be, for example, a text generation AI, an image generation AI, a multimodal generation AI, or the like. The trained model may be referred to as an artificial intelligence model, a machine learning model, or a deep learning model. Alternatively, the artificial intelligence unit 120 may include any trained model.

[0117] Specific examples of machine learning algorithms for constructing trained models include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, deep learning using neural networks, etc. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0118] 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 trained model may not only be one trained for a specific task, but also a general-purpose learning model that can be used for a wide range of tasks.

[0119] The artificial intelligence unit 120 may include a natural language model as its artificial intelligence, or a general-purpose learning 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). Given a task, the LLM can perform various tasks, such as language processing. Following given prompts, the LLM can perform a wide range of natural language processing tasks, such as grasping sentence patterns and contexts, answering questions, and generating sentences. Such a general-purpose learning model includes a trained model that can handle various tasks without fine-tuning, using one-shot learning or few-shot learning. The 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 trained model, or a common general-purpose trained model. The artificial intelligence unit 120 may also include a small-scale language model or a medium-scale language model, which are smaller in scale than a large-scale language model, as a trained model. Small-scale language models and medium-scale language models are natural language processing models trained based on less data than large-scale language models (constructed with fewer parameters than large-scale language models).

[0120] The trained models included in the artificial intelligence unit 120 (trained models used in each functional unit, such as the proposal information creation model) can be additionally trained 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 trained models.

[0121] The trained model included in the artificial intelligence unit 120 may be a trained model (distilled model) obtained by knowledge distillation using an original trained 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 training the student model, which becomes a distilled model. Alternatively, the student model may be trained 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 training model). Compared to the original training model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the trained model. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0122] For example, the trained 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 trained 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 trained model used in each functional unit.

[0123] An AI agent (which may also be called an autonomous 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 the necessary data collection and analysis, program generation, and execution. The AI ​​agent targets information and instructions input by a user, autonomously selects and executes tasks and actions according to the goal, and outputs information according to the goal, without requiring user intervention (operational input). The AI ​​agent may also autonomously learn to achieve its goal by autonomously creating and executing plans and evaluating the execution results. For example, the AI ​​agent may be autonomously updated based on the results of subtask execution (e.g., collected information, information analysis results, etc.).

[0124] <Display section> The display unit 211 of the recruiting party terminal 20 shown in FIG. 4B and the display unit 311 of the job seeker terminal 30 shown in FIG. 4C each display a screen (information) indicated by the data transmitted from the server device 10.

[0125] <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.

[0126] 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.

[0127] The information processing method described above includes a document acquisition step, a proposed information creation step, a priority determination step, and an information presentation step. In the document acquisition step, a document to be improved that includes information about the job seeker is acquired. In the proposed information creation step, at least one piece of proposed correction information is created for each of a plurality of points of correction for at least one item included in the document to be improved, based on the document to be improved and first reference information. In the priority determination step, the priority of each piece of proposed correction information created in the proposed information creation step is determined based on the proposed correction information and second reference information. In the information presentation step, proposed correction information extracted based on priority from the plurality of proposed correction information created in the proposed information creation step is presented to the job seeker.

[0128] 8 is an activity diagram showing an example of the flow of information processing (processing for displaying suggested correction information) executed by the information processing system 1. The information processing will be described below along with each activity in this activity diagram.

[0129] The process of displaying correction suggestion information begins with the job seeker selecting a document to be improved. The job seeker specifies the document to be improved (inputs information about the document to be improved) on the job seeker terminal 30 (activity A101). The server device 10 acquires the document to be improved based on the information about the document to be improved input from the job seeker terminal 30 (activity A102). Next, the server device 10 creates multiple pieces of correction suggestion information for the document to be improved (activity A103).

[0130] After creating the correction proposal information, the server device 10 determines the priority of each piece of created correction proposal information (activity A104). Next, the server device 10 extracts correction proposal information to be presented to the job seeker terminal 30 based on the priority of each piece of correction proposal information (activity A105). Furthermore, the server device 10 outputs the extracted correction proposal information to the job seeker terminal 30 (activity A106). As a result, the correction proposal information with the highest priority is displayed on the job seeker terminal 30 (activity A107).

[0131] 4. Effect The operation of this embodiment can be summarized as follows. That is, it is possible to support the creation of documents related to job seekers. In particular, by presenting high-priority correction proposal information created for each of multiple correction perspectives to the job seeker, it is possible to make correction proposals that will improve the quality of the document to be improved while reducing the time and effort required for the job seeker to select and discard information.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. In the information processing method, an information processing device executes each step of the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0136] It may be provided in the following manner.

[0137] (1) An information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: a document acquisition step of acquiring a document containing information about a job seeker; a proposed information creation step of creating at least one correction suggestion information for each of a plurality of correction perspectives for at least one item included in the document based on the document and first reference information, wherein the first reference information is information regarding the correlation between the combination of the document and the correction perspective and the correction suggestion information; a priority determination step of determining the priority of each of the plurality of correction suggestion information created in the proposed information creation step based on the correction suggestion information and second reference information, wherein the second reference information is information regarding the correlation between the correction suggestion information and the priority; and an information presentation step of presenting the correction suggestion information extracted based on the priority from the plurality of correction suggestion information created in the proposed information creation step to the job seeker.

[0138] (2) In the information processing system described in (1) above, the multiple correction perspectives include at least a first perspective on the matters that need to be described in the item and a second perspective on the specificity of the content of the item.

[0139] (3) In the information processing system described in (2) above, the first reference information includes a plurality of proposed information creation models, which are trained models prepared for each of the plurality of correction perspectives, and in the proposed information creation step, the document is input into the plurality of proposed information creation models, and the proposed correction information for each of the plurality of correction perspectives is output to each of the proposed information creation models.

[0140] (4) In the information processing system described in any one of (1) to (3) above, in the proposed information creating step, at least one piece of proposed correction information is created for each of a plurality of aspects of correction for a plurality of items included in the document based on the document and the first reference information; in the priority determining step, the priority of each piece of proposed correction information for a plurality of items created in the proposed information creating step is determined based on the proposed correction information and the second reference information; and in the information presenting step, the proposed correction information extracted based on the priority from the plurality of proposed correction information created in the proposed information creating step for each of the plurality of items is presented to the job seeker.

[0141] (5) In the information processing system described in (4) above, in the information presentation step, at least one piece of revision suggestion information is presented for each of the plurality of items for which the revision suggestion information was created, so that the total number of pieces of revision suggestion information presented for each of the plurality of items for which the revision suggestion information was created is equal to or less than a predetermined upper limit.

[0142] (6) In the information processing system described in (4) or (5) above, the first reference information includes a plurality of proposed information creation models, which are trained models prepared for each of the plurality of items, and in the proposed information creation step, the document is input into the plurality of proposed information creation models, and the correction proposed information for each of the correction perspectives is output to each of the proposed information creation models for each of the plurality of items.

[0143] (7) In the information processing system described in any one of (1) to (6) above, the second reference information includes a priority determination model which is a general-purpose learning model, and in the priority determination step, a prompt including the correction suggestion information, definition information of the priority, and an instruction to input the correction suggestion information and output the priority corresponding to the correction suggestion information is input to the priority determination model, and the priority is output to the priority determination model.

[0144] (8) In the information processing system described in any one of (1) to (7) above, in the priority determination step, an index indicating the magnitude of the priority is assigned to the revision suggestion information, and in the information presentation step, the revision suggestion information whose index is equal to or greater than a predetermined threshold is presented to the job seeker.

[0145] (9) In the information processing system described in any one of (1) to (8) above, in the proposed information creating step, the correction proposal information including correction examples for the item is created, and in the priority determining step, a first priority is assigned to one of the multiple correction proposal information created in the proposed information creating step, the correction example satisfying the description requirements for the corresponding item, a second priority lower than the first priority is assigned to one of the multiple correction proposal information created in the proposed information creating step, the correction example including consistent keywords is assigned to one of the multiple correction proposal information created in the proposed information creating step, and a third priority lower than the second priority is assigned to one of the multiple correction proposal information created in the proposed information creating step, the correction example including matters required for the corresponding item is assigned to one of the multiple correction proposal information created in the proposed information creating step.

[0146] (10) In the information processing system described in any one of (1) to (9) above, in the proposed information creation step, the correction proposal information is created, which includes a correction policy for the item and an example of a correction for the item in accordance with the correction policy, and in the information presentation step, the correction policy and the example of a correction are presented for each piece of proposed correction information.

[0147] (11) In the information processing system according to (10) above, in the information presenting step, text in the correction example is highlighted according to the degree of relevance to the correction principle.

[0148] (12) In the information processing system described in any one of (1) to (11) above, in the information presentation step, a plurality of pieces of suggested revision information are presented to the job seeker, and information indicating whether the suggested revision information has been confirmed is displayed based on the job seeker's operation on the suggested revision information.

[0149] (13) The information processing system according to any one of (1) to (12) above, further comprising: a server device having the processor; and a terminal that can access the server device.

[0150] (14) An information processing method, in which an information processing device executes each step of the information processing system described in any one of (1) to (13) above.

[0151] (15) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (13) 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: Document Acquisition Unit 113: Proposal Information Creation Department 114:Priority determination section 115: Information presentation section 116: Document Editing Department 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 CL: Confirmation status label CO: Copy Reception Object CS: Edit cursor ED: Editing screen for document to be improved ET: Text to be edited IM:Item ME: Correction example MO: Modification Receipt Object MP: Correction Policy RO: Redisplay reception object SD: Proposal information display screen SI: Correction Suggestion Information SK: Software keyboard

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 document acquisition step, a document containing information about the job seeker is acquired, In the proposed information creation step, at least one piece of proposed revision information is created for each of a plurality of revision viewpoints for at least one item included in the document based on the document and first reference information, wherein the first reference information is information regarding a correlation between a combination of the document and the revision viewpoint and the proposed revision information; In the priority determination step, a priority of each of the plurality of pieces of suggested revision information created in the suggested information creation step is determined based on the suggested revision information and second reference information, wherein the second reference information is information relating to a correlation between the suggested revision information and the priority; In the information presenting step, the correction proposal information extracted based on the priority from the plurality of pieces of correction proposal information created in the proposal information creating step is presented to the job seeker.

2. 2. The information processing system according to claim 1, An information processing system, wherein the multiple revision perspectives include at least a first perspective regarding matters that need to be described in the item and a second perspective regarding the specificity of the content of the item.

3. 3. The information processing system according to claim 2, The first reference information includes a plurality of proposed information creation models, which are trained models prepared for each of the plurality of correction perspectives, In the proposed information creation step, the document is input to a plurality of proposed information creation models, and the revision proposal information for each of the plurality of revision perspectives is output to each of the proposed information creation models.

4. 2. The information processing system according to claim 1, In the proposed information creating step, at least one piece of proposed revision information is created for each of a plurality of the items included in the document based on the document and the first reference information, and In the priority determination step, the priority of each of the plurality of pieces of suggested revision information for the plurality of items created in the suggested information creation step is determined based on the suggested revision information and the second reference information; In the information presenting step, the correction proposal information extracted based on the priority from the plurality of pieces of correction proposal information created in the proposal information creating step is presented to the job seeker for each of the plurality of items.

5. 5. The information processing system according to claim 4, In the information presentation step, at least one piece of revision suggestion information is presented for each of the plurality of items so that the total number of pieces of revision suggestion information presented for each of the plurality of items for which the revision suggestion information was created is less than or equal to a predetermined upper limit.

6. 5. The information processing system according to claim 4, The first reference information includes a plurality of proposal information generation models, which are trained models prepared for each of the plurality of items, In the proposed information creation step, the document is input into a plurality of proposed information creation models, and the proposed revision information for each of the plurality of items and each of the proposed information creation models is output.

7. 2. The information processing system according to claim 1, the second reference information includes a priority determination model that is a general-purpose learning model; In the priority determination step, a prompt including the modification proposal information, definition information of the priority, and an instruction to input the modification proposal information and output the priority corresponding to the modification proposal information is input to a priority determination model, and the priority is output to the priority determination model.

8. 2. The information processing system according to claim 1, In the priority determination step, an index indicating a degree of priority is assigned to the modification suggestion information as the priority; In the information presenting step, the correction suggestion information in which the index is equal to or greater than a predetermined threshold is presented to the job seeker.

9. 2. The information processing system according to claim 1, In the proposed information creation step, the correction proposed information including a correction example of the item is created, In the priority determination step, assigning a first priority as the priority to one of the plurality of pieces of suggested correction information created in the suggested information creating step, the piece of suggested correction information whose suggested correction information satisfies the description requirements for the corresponding item; assigning a second priority, which is smaller than the first priority, to the plurality of pieces of suggested correction information created in the suggested information creating step, the pieces of suggested correction information having the same keywords included in the suggested correction examples; An information processing system in which, among the multiple pieces of proposed correction information created in the proposed information creation step, those pieces of proposed correction information in which the items required for the corresponding items are included in the proposed correction examples are assigned a third priority, which is lower than the second priority.

10. 2. The information processing system according to claim 1, In the proposal information creation step, the modification proposal information is created, which includes a modification policy for the item and a modification example for the item in accordance with the modification policy; In the information presenting step, the information processing system presents the modification policy and the modification example for each of the modification suggestion information.

11. 11. The information processing system according to claim 10, In the information presenting step, text in the correction example is highlighted according to a degree of relevance to the correction principle.

12. 2. The information processing system according to claim 1, In the information presentation step, a plurality of pieces of suggested revision information are presented to the job seeker, and information indicating whether the suggested revision information has been confirmed is displayed based on the job seeker's operation on the suggested revision information.

13. 2. The information processing system according to claim 1, a server device having the processor; a terminal that can access the server device; An information processing system comprising:

14. An information processing method, comprising: An information processing method, wherein an information processing device executes each step of the information processing system according to any one of claims 1 to 13.

15. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 13.

Images