Information processing system, information processing method, and information processing program

Abstract

This invention provides an information processing system, information processing method, and information processing program that enable the efficient provision of diverse and high-quality self-promotion data to job seekers. [Solution] In an information processing system in which multiple evaluated self-PR data are stored in a predetermined storage unit, the PR data are evaluated based on specificity, fluency, cultural relevance, and objectivity from different evaluation perspectives, for multiple self-PR data that have been pre-generated by combining user-selectable conditions and diversification variables. The specific method involves receiving a request for conditions that combine at least job type, industry, and strengths as selectable conditions, input by the user through a selection operation, extracting the self-PR data that matches the conditions from the multiple evaluated self-PR data in the storage unit based on the received conditions, and displaying the extracted self-PR data on a predetermined terminal corresponding to the user.

Description

Technical Field

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

Background Art

[0002] Conventionally, there has been a technology related to the creation of job applicant manuscripts.

[0003] For example, there is a technology related to obtaining information useful for the employment of job applicants using a natural language model (see Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] As described in Patent Document 1, it is disclosed to obtain resume information of job applicants generated by a natural language model from job applicant information. However, conventionally, information such as catchphrases generated as part of resume information can have constraints determined during generation, but no evaluation for quality improvement has been performed, and content that is necessarily tailored to the user has not always been provided. Also, it takes time for input of constraints and execution time, etc., and there have been cases where the comfortable user experience is impaired.

[0006] An object of the present disclosure is to provide an information processing system, an information processing method, and an information processing program that can efficiently provide diverse and high-quality self-promotion data to job applicants.

Means for Solving the Problems

[0007] An information processing system according to the first aspect of this disclosure comprises a processor, in which a plurality of evaluated self-PR data are stored in a predetermined storage unit, the evaluated plurality of self-PR data being pre-generated by multiplying user-selectable conditions and diversification variables, and the content generated as the self-PR data is evaluated based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation axis perspectives, the processor receiving as a request conditions that combine at least job type, industry, and strengths as input by the user in a selection operation, extracts the self-PR data that matches the conditions from the plurality of evaluated self-PR data in the storage unit based on the received conditions, and displays the extracted self-PR data on a predetermined terminal corresponding to the user.

[0008] According to the information processing system of the first embodiment, it is possible to efficiently provide diverse and high-quality self-promotion data to job seekers.

[0009] In the second aspect of this disclosure, the information processing system, in the first aspect, includes a processor that, as a process for assigning evaluations to the plurality of self-PR data, performs evaluations using a combination of evaluations based on a generative model from the perspective of predefined evaluation axes, evaluations using language analysis, and evaluations of structure based on format, as evaluation methods. The information processing system in the second aspect enables multifaceted and highly accurate evaluations of self-PRs.

[0010] In the third aspect of this disclosure, the information processing system, in the first or second aspect, the processor evaluates fluency on the evaluation axis in the evaluation using the generative model, evaluating linguistic usage, structural correctness, and contextual consistency. According to the information processing system of the third aspect, it is possible to create a self-introduction that comprehensively evaluates linguistic accuracy.

[0011] In the fourth aspect of the information processing system of this disclosure, in any of the first to third aspects, the processor randomly extracts the evaluated self-PR data that matches the conditions from the storage unit as part of the extraction process, and if the user determines that the self-PR data displayed after the extraction is unsuitable, the processor accepts a re-request from the user with the same conditions, and extracts and displays different self-PR data with the same conditions through the random extraction. According to the information processing system of the fourth aspect, a self-PR corresponding to the content requested by the user can be easily extracted.

[0012] Furthermore, the information processing method of the fifth aspect of this disclosure includes a plurality of evaluated self-PR data stored in a predetermined storage unit, wherein the plurality of evaluated self-PR data are pre-generated by multiplying user-selectable conditions and diversification variables, and the content generated as the self-PR data is evaluated based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation axis perspectives, and the computer receives as a request conditions that combine at least job type, industry type, and strengths as input by the user in the selection operation, extracts the evaluated self-PR data from the storage unit based on the received conditions, and displays the extracted self-PR data on a predetermined terminal corresponding to the user.

[0013] Furthermore, the information processing program in the sixth aspect of this disclosure stores a plurality of evaluated self-PR data in a predetermined storage unit, and the plurality of evaluated self-PR data are pre-generated by multiplying user-selectable conditions and diversification variables, and the content generated as the self-PR data is evaluated based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation axis perspectives, and the computer is made to receive as a request conditions that combine at least job type, industry type, and strengths as input by the user's selection operation as the selectable conditions, extract the evaluated self-PR data from the storage unit based on the received conditions, and execute a process that displays the extracted self-PR data on a predetermined terminal corresponding to the user. [Effects of the Invention]

[0014] The information processing system, information processing method, and information processing program disclosed herein have the effect of enabling the efficient provision of diverse and high-quality self-promotion data to job seekers. [Brief explanation of the drawing]

[0015] [Figure 1] Figure 1 is a block diagram showing the functional configuration of the information processing system in this embodiment. [Figure 2] Figure 2 is a block diagram showing the hardware configuration of the information processing system. [Figure 3] Figure 3 is a schematic diagram showing the flow of the process for providing self-introduction data. [Figure 4] Figure 4 is a flowchart showing the flow of pre-processing by the information processing system. [Figure 5] Figure 5 is a flowchart showing the flow of presentation processing by the information processing system. [Figure 6] Figure 6 shows an example of a WebUI screen, specifically the job selection screen. [Figure 7] Figure 7 shows an example of a WebUI screen, specifically the industry selection screen. [Figure 8] FIG. 8 is an example of a WebUI screen, and is a screen of a chat bar and a screen for selecting strengths. [Figure 9] FIG. 9 is an example of a WebUI screen, and is a screen of a chat bar and a screen for displaying extraction results.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the disclosed technology will be described with reference to the drawings. In each of the drawings, the same or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may be different from the actual ratios.

[0017] First, an overview of the embodiment of the present disclosure will be described. The system provided in this embodiment relates to a system that provides sample sentences (hereinafter referred to as samples) regarding self-promotion in job hunting support. The problems in providing sentences regarding self-promotion will be described. For example, although various job hunting sites may provide samples of self-promotion as part of job hunting support content, the samples of self-promotion were manually created by the content providers. Also, users of the site created self-promotions for the companies they wanted to apply to referring to the samples.

[0018] However, in the current provision of self-promotion samples, there were major issues as follows: (1) Manual creation of content provision on job hunting websites was inefficient. It was impossible to create a large number of self-promotion samples manually, and there was a tendency to be limited to common job types and industries. (2) It was difficult to find self-promotion samples suitable for one's own job type or industry. As a result of the situation in (1), users could not find samples suitable for themselves, and ultimately had to think on their own. (3) There were concerns about the inaccessibility of AI for those unfamiliar with its use and usability. Although the development and popularization of AI has made it relatively easy for users to create self-promotions by using interactive AI tools such as ChatGPT, the users who can utilize them are limited to a certain extent. Also, when using existing AI tools, hallucinations may occur depending on the input content. In addition, using existing AI tools takes a long time for output, which may reduce the convenience for the user experience.

[0019] Therefore, in the information processing system of this embodiment, pre-generated self-promotion samples are assigned and provided. This realizes a job hunting support experience that does not make job seekers feel the time lag caused by AI generation. In addition, by evaluating self-promotion samples of products based on evaluation AI based on manual evaluation and providing the evaluated self-promotion samples, hallucinations can be prevented and the quality of self-promotion provided to users can be improved. Note that, as described below, the self-promotion samples provided in this embodiment are composite data in which evaluation has been performed and evaluation information has been added as metadata to the self-promotion samples. When the system is referenced, extraction is performed based on the evaluation information, and the self-promotion sample is provided to the user at the time of provision. Therefore, it is distinguished from the existing self-promotion samples described above and is described as evaluated self-promotion data.

[0020] (Configuration) Figure 1 is a block diagram showing the functional configuration of the information processing system 100 in this embodiment. The information processing system 100 is connected via a network N to a management terminal 140 that can be operated by an administrator and a user terminal 150 that can be operated by a job seeker. The management terminal 140 accepts operations related to setting the generation model and prompts and pre-evaluation of self-PR data. The user terminal 150 accepts various operations related to requesting and obtaining self-PR data.

[0021] Figure 2 is a block diagram showing the hardware configuration of the information processing system 100. As shown in Figure 2, the information processing system 100 includes a CPU (Central Processing Unit) 11, ROM (Read Only Memory) 12, RAM (Random Access Memory) 13, storage 14, input unit 15, display unit 16, and communication interface (I / F) 17. Each component is connected to the others via a bus 19 so that they can communicate with each other.

[0022] The CPU 11 is a central processing unit that executes various programs and controls various components. Specifically, the CPU 11 reads a program from the ROM 12 or storage 14 and executes the program using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various calculations according to the program stored in the ROM 12 or storage 14. In this embodiment, the ROM 12 or storage 14 stores an information processing program.

[0023] ROM12 stores various programs and data. RAM13 temporarily stores programs or data as a working area. Storage14 consists of a storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs, including the operating system, and various data.

[0024] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used for various types of input. The display unit 16 is, for example, a liquid crystal display and displays various types of information. The display unit 16 may also function as the input unit 15 by employing a touch panel system.

[0025] The communication interface 17 is an interface for communicating with other devices such as terminals. For such communication, a wired communication standard such as Ethernet® or FDDI, or a wireless communication standard such as 4G, 5G, or Wi-Fi® may be used.

[0026] The functional configuration of the information processing system 100 will be described. The information processing system 100 is composed of a storage unit 102, a reception unit 104, a generation unit 110, a pre-evaluation unit 112, an extraction unit 120, and an output unit 122. The generation unit 110 and the pre-evaluation unit 112 perform pre-processing to generate and evaluate self-PR data in advance. The extraction unit 120 and the output unit 122 perform the processing to provide self-PR data to the user. The storage unit 102 includes a setting information storage unit 102A, an evaluation information storage unit 102B, and a generated data storage unit 102C. The functional configuration of each part of the information processing system 100 will be described. Note that the information processing system 100 may also be configured to include a user terminal 150 and a management terminal 140 as a hard disk.

[0027] The configuration information storage unit 102A stores user conditions and diversification variable settings for generation received from the management terminal 140. The evaluation information storage unit 102B stores various models for assigning evaluations and settings for evaluation. The generated data storage unit 102C stores multiple evaluated self-PR data in database format.

[0028] In the pre-processing stage, the reception unit 104 receives user-selectable conditions and diversification variables from the management terminal 140. In the provisioning stage, the reception unit 104 receives conditions as requests from the user terminal 150, based on user selection inputs. The conditions are combinations of selected job type, industry, and strengths. Furthermore, in the provisioning stage, the reception unit 104 provides the user terminal 150 with a dedicated WebUI page that allows interaction for providing self-PR data, in response to access from the user terminal 150. The dedicated WebUI page will be described later.

[0029] The conditions that users can select refer to the respective categories of job type, industry, and strengths, as explained below. Diversification variables are variables used to express the characteristics of job seekers from various perspectives, such as variables that express in- and out-of-work experience, skills, and preferences as parameters.

[0030] The preprocessing will now be explained. The generation unit 110 pre-generates self-PR data by multiplying the user-selectable conditions and diversification variables received from the management terminal 140. Here, a generation model for self-PR generation is used to generate the self-PR data. A prompt that combines the conditions and diversification variables is input to the generation model for self-PR generation. For example, the prompt generates a predetermined quantity of self-PR data where the XXX part is a variable determined by the conditions and diversification variables, as shown in the following example prompt. An example prompt is: "Please output a self-PR statement within XXX characters that matches the following conditions. Job title: XXX, Industry: XXX, Strengths: XXX, Work experience: XXX, Aspirations: XXX, Achievements: XXX / Please structure it in a way that is easy for the reader to understand (introduction → experience → results → conclusion), and ensure it is logical and specific. Please use natural Japanese, avoid excessive self-assertion, and adapt it to a business context."

[0031] The pre-evaluation unit 112 assigns an evaluation to the content generated as self-PR data. The evaluated self-PR data is stored in the generated data storage unit 102C. The evaluation is based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation axes, but the evaluation method will be described later.

[0032] Next, the provision process will be described. The information processing system 100 provides a dedicated WebUI page to the user terminal 150. The dedicated WebUI page provides a series of functions for the provision process described below. For the sake of explanation, the information processing system 100 will be simply referred to as the system, and the user terminal 150 and the user operating the terminal will be simply referred to as the user.

[0033] Figure 3 is a schematic diagram showing the flow of the process for providing self-PR data. (A1) The user accesses a dedicated WebUI page for providing this function and first selects a job type. It is assumed that when selecting a job type and industry, a major category is selected, followed by a more detailed subcategory. It is also possible to select classifications set as appropriate. (A2) The system presents selectable industries based on the selected job type. (A3) The user selects from the presented industries. (A4) The system presents strengths to the user. (A5) The user selects one strength from the presented strengths. (A6) The system requests the conditions of the selected job type, industry, and strengths. (A7) The system randomly selects matching data from the evaluated self-PR data based on the requested combination of job type, industry, and strengths. The request is sent, for example, via API to the database of the generated data storage unit 102C, and a response of the extraction results is received. (A8) The system outputs the extraction results to the screen of the dedicated page. (A9) If the output is not appropriate, the user will make another request under the same conditions. (A10) The user will retrieve the output and reflect it in the input fields of the self-introduction section of the job search site or other relevant platform. The criteria for random selection is to assign a score to each condition when generating the self-introduction data, and then randomly select from a group of self-introduction data where the scores for each condition (job type, industry, and strengths) meet predetermined thresholds.

[0034] The extraction unit 120 receives a request for conditions that combine at least job type, industry, and strengths, and extracts self-PR data that matches the conditions from among multiple evaluated self-PR data in the generated data storage unit 102C based on the received conditions.

[0035] The output unit 122 outputs the extracted self-PR data as extraction results to the user terminal 150 and displays the extraction results on a dedicated page.

[0036] (Process flow) Next, the processing flow of the information processing system 100 will be explained. Figure 4 is a flowchart showing the pre-processing flow by the information processing system 100. Figure 5 is a flowchart showing the presentation processing flow by the information processing system 100. The CPU 11 functions as a part of the information processing system 100 to execute the following processes.

[0037] The preprocessing will be explained with reference to Figure 4. In step S100, the CPU 11, acting as a reception unit 104, receives user-selectable conditions and diversification variables from the management terminal 140 and stores them in the setting information storage unit 102A.

[0038] In step S102, the CPU 11, acting as a generation unit 110, pre-generates self-PR data by multiplying the conditions that the user can select and the diversification variables.

[0039] In step S104, the CPU 11, acting as a pre-evaluation unit 112, evaluates the content generated as self-PR data and stores the evaluated self-PR data in the generated data storage unit 102C.

[0040] The evaluation methods will be explained. Evaluation will be performed using a combination of the following evaluation methods: (B1) evaluation using a generative model based on predefined evaluation axes, (B2) evaluation using language analysis, and (B3) evaluation of structure using format. In the evaluation using the generative model in (B1), a dedicated model may be trained for each evaluation criterion, and the evaluation may be performed by this dedicated model. Similarly, in the evaluation methods of (B2) and (B3), a dedicated model may be used for evaluation for each evaluation method.

[0041] This section explains what is evaluated for each of the evaluation criteria (specificity, fluency, cultural relevance, and objectivity). Specificity assesses, for example, whether it is clear what was done and how. It evaluates whether the description includes specific actions / situations / results rather than abstract expressions, and whether it is quantitative and includes concrete examples. Fluency assesses, for example, whether the language is natural and easy to read. Cultural relevance assesses whether it aligns with the corporate culture and the business context of the Japanese-speaking world. It evaluates whether self-assertion is avoided and humility is maintained, and whether the tone and expression are appropriate to the common sense and context of the industry / job. Objectivity assesses, for example, whether it is based on facts and evidence rather than being biased by subjectivity. It evaluates whether it is supported by achievements, data, and third-party evaluations, and whether it touches not only on self-evaluation but also on the reactions and results of those around you.

[0042] The evaluation methods will be explained below. (B1) In the evaluation using a generative model, specific evaluation criteria are trained on the generative model, and by inputting a self-introduction text, the model determines whether the text is OK or NG by comparing it with predefined evaluation axes and outputs the reason for the result. Furthermore, in the evaluation using the generative model, fluency is evaluated based on linguistic usage, structural correctness, and contextual consistency. Self-introduction data that is deemed OK in each evaluation of (B1) to (B3) will be saved as evaluated self-introduction data.

[0043] The following is an example of a prompt for fluency, which is input into a generative model for evaluation. An example prompt is: "Please evaluate the fluency (readability as natural Japanese) of the following sentence. Please check the following points: linguistic usage (use of Japanese, grammatical correctness, naturalness of word order), structural correctness (smoothness of conjunctions and expressions, accuracy and plausibility of sentence structure), and contextual consistency (consistency in logical development, absence of unrelated sentences). Output the evaluation as a score and briefly state the reason."

[0044] (B2) In the evaluation using language analysis, morphological analysis is performed on the self-introduction text, and the number of repetitions of sentence-ending expressions, etc., is measured. A threshold is set for the number of repetitions that would cause a human to feel unnatural, and if the number of repetitions exceeds this threshold, it will be deemed unacceptable.

[0045] (B3) In the evaluation of structure by format, a specific format is specified in advance, and if the output content does not adhere to the format, it is evaluated as NG through static analysis.

[0046] As described above, the evaluated self-PR data is assigned scores and reasons for each aspect of the evaluation axis based on evaluation using a generative model, scores and reasons for the evaluation of language analysis, and scores and reasons for the evaluation of structure.

[0047] Next, the presentation process will be explained with reference to Figure 5.

[0048] In step S200, the CPU 11, acting as a reception unit 104, displays a dedicated WebUI page in response to user access from the user terminal 150.

[0049] In step S202, the CPU 11, acting as an extraction unit 120, receives a request from the user terminal 150, based on the user's input of selections on a dedicated page of the WebUI, specifying conditions that combine at least job type, industry, and strengths.

[0050] In step S204, the CPU 11, acting as an extraction unit 120, extracts evaluated self-PR data based on the received conditions. The extraction process involves randomly extracting evaluated self-PR data that matches the conditions from the generated data storage unit 102C.

[0051] In step S206, the CPU 11 displays the extracted self-PR data on the user terminal 150 as an output unit 122.

[0052] In step S208, the CPU 11, acting as a reception unit 104, determines whether the self-introduction data displayed after extraction is unsuitable for the user. To determine if the displayed self-introduction data is unsuitable for the user, the CPU 11 can present the user with options for suitability on a dedicated page and accept their selection. If it is unsuitable, the process proceeds to step S208; otherwise, the process ends.

[0053] In step S210, the CPU 11, acting as an extraction unit 120, receives a re-request from the user under the same conditions, and extracts and displays different self-PR data under the same conditions through random extraction.

[0054] (Screen example) Figures 6 to 9 show examples of WebUI screens. On the dedicated WebUI page displayed on user terminal 150, a chat field with an interactive AI is displayed before and after the selection screen, allowing the user to proceed with the display of the selection screen and the selection of conditions through the chat. The selection screen should be displayed overlaid on the chat field. This allows the user to select conditions while confirming their selections in the chat field.

[0055] Figure 6 shows the job selection screen. An example of operation is explained below. (X1) is the screen for selecting the major job category, and (X2) is the screen for selecting the detailed (minor) category. On the (X1) selection screen, a list of job category options (50B) is displayed. Selecting "Sales" from the list of options (50B) will take you to the (X2) detailed selection screen. On the (X2) detailed selection screen, you can select the details (minor) of the job category selected on the previous (X1) selection screen. Pressing the "Finish Selection" button (50D) will return you to the chat field with the selections reflected (the same applies to the subsequent industry selection screen and strengths selection screen).

[0056] Figure 7 shows the industry selection screen. (X3) is the screen for selecting the major industry category, and (X4) is the screen for selecting the detailed (minor) category. The selection screen (X3) displays a list of industry options (50E). The process for selecting details is the same as for the job selection screen. On the detailed selection screen (X4), you can select the details of the industry selected on the previous selection screen (X3).

[0057] Figure 8 shows the chat screen and the strengths selection screen. (X5) is the chat screen after the industry selection stage, and (X6) is the strengths selection screen. On the chat screen of (X5), a progress button (50F) to move to the strengths selection screen, a re-select button (50G), and a reset button (50N) to start over are displayed. Pressing the re-select button (50G) returns you to the previous selection screen (X3) where you can change your selection. The re-select button (50G) is also displayed in the chat screen after selecting a job, allowing you to re-select your job. Pressing the progress button (50F) moves you to the next selection screen. (X6) is the strengths selection screen. A list of strengths options (50H) and a selection completion button (50D) are displayed. Pressing the reset button (50N) resets the selection in (X1) and returns you to the initial chat screen or selection screen.

[0058] Figure 9 shows the chat screen and the screen displaying the extraction results. (X7) is the chat screen after the selection of strengths has been completed, and (X8) is the screen displaying the extraction results. On the chat screen (X7), a Create button (50I) to proceed to creating a self-introduction (system extraction), a Re-select Strengths button (50J), and a Re-select Button (50G) are displayed. When the Create button (50I) is pressed, the user proceeds through a waiting screen during extraction (displaying tips, etc.) to the extraction results screen (X8). On the extraction results screen (X8), the extracted self-introduction (50K), an Acquire button (50L) to copy the self-introduction, a Re-request button (50M) to create another self-introduction text with the selected content (same conditions), and a Reset button (50N) to start over are displayed. The Re-request button (50M) is an example of the "No" option in the "Suitable / Not Suitable" option in step S208 above, and serves as the trigger for the Re-request.

[0059] (modified version) Examples of modifications of the above-described embodiment are given below.

[0060] The above embodiment illustrates the case where one self-introduction data that matches the conditions is randomly extracted, but it is not limited to this. For example, multi-stage extraction / narrowing may be possible. In the initial extraction, multiple self-introduction data may be presented, and the user may be allowed to select one through A / B testing, or the user may be allowed to further select conditions they want to narrow down or expressive styles they want to emphasize. In this way, an interactive extraction process may be provided so that the user can arrive at the optimal self-introduction data step by step. Furthermore, in a re-request, the user may be allowed to select / input the closeness (similarity) to the currently displayed self-introduction data, and when re-extracting, random extraction may be performed using weights based on the similarity to the currently displayed self-introduction data.

[0061] Furthermore, while examples of how to obtain and re-request the extracted self-PR (50K) data have been provided, the system is not limited to these examples. For instance, the system may have a function that allows the user to select specific parts of the extracted self-PR (50K) data that they wish to change, and then re-output the self-PR data with the requested changes corrected.

[0062] Furthermore, the selection of strengths is not limited to one; multiple strengths may be selected. Additionally, the selected strengths may be ordered and weighted according to their priority to extract self-promotion data.

[0063] Furthermore, while specificity, fluency, cultural relevance, and objectivity were given as examples of evaluation criteria, the evaluation is not limited to these, and other criteria may be added. For example, suitability for a specific occupation or corporate culture, or originality of the argument, may be considered in the evaluation.

[0064] As described above, the information processing system 100 according to this embodiment can efficiently provide diverse and high-quality self-promotion data to job seekers.

[0065] Furthermore, this method ensures quality. By providing self-introduction data that has been checked through evaluation, hallucination can be prevented, encouraging users to use the service with confidence, and ensuring accuracy. Evaluation allows for the provision of more accurate texts. It also makes recruitment activities more efficient. Because users can easily pick out self-introductions that are suitable or similar to themselves, the time required to create a self-introduction can be reduced. Moreover, since it does not depend on the user's AI tool literacy, a wide range of users can benefit from the use of AI.

[0066] Furthermore, the technology disclosed herein is not limited to the embodiments described above, and various modifications and applications are possible without departing from the spirit of this invention.

[0067] Furthermore, although the present specification describes an embodiment in which the program is pre-installed, it is also possible to provide the program stored on a computer-readable recording medium. [Explanation of symbols]

[0068] 100 Information Processing Systems 102 Storage section 104 Reception Department 110 Generation part 112 Pre-evaluation Department 120 Extraction part 122 Output section 140 Management terminals 150 user terminals

Claims

1. Equipped with a processor, Multiple evaluated self-PR data are stored in a designated storage unit. The aforementioned evaluated multiple self-PR data are generated in advance by combining user-selectable conditions and diversification variables, and the content generated as the self-PR data is evaluated based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation perspectives. The aforementioned processor, As for the selectable conditions, the system accepts requests that combine at least the job title, industry, and strengths entered by the user through a selection process. Based on the received conditions, the storage unit extracts the self-PR data that matches the conditions from among the evaluated plurality of self-PR data. The extracted self-PR data is displayed on a predetermined terminal corresponding to the user. Information processing system.

2. The aforementioned processor, As a process for assigning evaluations to the aforementioned multiple self-PR data, The evaluation method involves a combination of evaluation using a generative model based on predefined evaluation axes, evaluation using language analysis, and evaluation of structure based on format. The information processing system according to claim 1.

3. The aforementioned processor, In the evaluation using the generative model, the evaluation of fluency on the evaluation axis includes evaluation of linguistic usage, structural correctness, and contextual consistency. The information processing system according to claim 2.

4. The aforementioned processor, As part of the extraction process, the evaluated self-PR data that matches the conditions is randomly extracted from the storage unit. If the user determines that the self-PR data displayed after the extraction is unsuitable, the system accepts a re-request from the user under the same conditions, and then extracts and displays different self-PR data under the same conditions through random extraction. The information processing system according to claim 1.

5. Multiple evaluated self-PR data are stored in a designated storage unit. The aforementioned evaluated multiple self-PR data are generated in advance by combining user-selectable conditions and diversification variables, and the content generated as the self-PR data is evaluated based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation perspectives. Computers As for the selectable conditions, the system accepts requests that combine at least the job title, industry, and strengths entered by the user through a selection process. Based on the accepted conditions, the evaluated self-PR data is extracted from the storage unit. The extracted self-PR data is displayed on a predetermined terminal corresponding to the user. An information processing method that performs a process.

6. Multiple evaluated self-PR data are stored in a designated storage unit. The aforementioned evaluated multiple self-PR data are generated in advance by combining user-selectable conditions and diversification variables, and the content generated as the self-PR data is evaluated based at least on specificity, fluency, cultural relevance, and objectivity from different evaluation perspectives. On the computer, As for the selectable conditions, the system accepts requests that combine at least the job title, industry, and strengths entered by the user through a selection process. Based on the accepted conditions, the evaluated self-PR data is extracted from the storage unit. The extracted self-PR data is displayed on a predetermined terminal corresponding to the user. An information processing program used to execute a process.

Images