Information processing system, information processing method, and program

Abstract

Provided is an information processing system and the like that can generate a sentence tailored to a job seeker. 【Solution means】According to one aspect of the present invention, there is provided an information processing system including at least one processor configured to execute the following steps by reading a program. In a reception step, first job seeker information including information regarding the attributes of a job seeker is received. In a question information extraction step, question information corresponding to the first job seeker information is extracted from reference information. The question information includes questions for the job seeker and information regarding answer examples corresponding to the questions. The reference information includes a plurality of question information candidates that are candidates for question information generated in advance based on the accumulated job content. In an acquisition step, an answer from the job seeker to the question information is acquired. In a job content generation step, a sentence regarding the job content of the job seeker is generated based on second job seeker information. The second job seeker information includes the first job seeker information and the answer acquired in the acquisition step. An information processing system is provided.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a technique for assisting in creating a sentence using a template.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is preferable to generate a sentence tailored to a job seeker.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like capable of generating a sentence tailored to a job seeker.

Means for Solving the Problems

[0006] According to one aspect of the present invention, there is provided an information processing system including at least one processor. The processor is configured to execute the following steps by reading a program. In the reception step, the information processing system receives first job applicant information including information regarding the attributes of a job applicant. In the question information extraction step, the information processing system extracts question information corresponding to the first job applicant information from reference information. The question information includes questions for the job applicant and information regarding answer examples corresponding to the questions. The reference information includes a plurality of question information candidates which are candidates for the question information generated in advance based on the accumulated job duties. In the acquisition step, the information processing system acquires answers from the job applicant to the question information. In the job duty generation step, the information processing system generates a text regarding the job duties of the job applicant based on the second job applicant information. The second job applicant information includes the first job applicant information and the answers acquired in the acquisition step.

[0007] According to such an aspect, it is possible to provide a document creation support system or the like that can generate a document more tailored to each job applicant.

[0008] Hereinafter, embodiments of the present invention will be described. Note that the various characteristic matters shown in the following embodiments can be combined with each other.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various characteristic matters shown in the following embodiments can be combined with each other.

[0011] By the way, a program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium that can be read by a computer, may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its function is realized on a client terminal (so-called cloud computing).

[0012] Also, in various information processes according to one embodiment, input and output corresponding to the input can be realized. Here, if an output is obtained as a result of the input, the mode of information (hereinafter referred to as reference information) referred to in such information processing is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, a predetermined function (including a judgment formula such as a regression formula constructed by a statistical method), a learned model in which the correlation between input and output is learned in advance, or a large language model capable of outputting a desired result by inputting a prompt.

[0013] In addition, in one embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various types of information are handled. These types of information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0014] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, and the like. Also, 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 (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), and the like.

[0015] 1. Hardware Configuration In this section, the hardware configuration of the information processing system according to this embodiment will be described.

[0016] FIG. 1 is a diagram showing the overall configuration of the information processing system 1. In FIG. 1, each device included in the information processing system 1 and an overview of the users who use these devices are shown. Regarding each overview, it will be described as needed with reference to other figures.

[0017] The information processing system 1 is an information processing system that executes text generation processing, which is information processing for assisting in creating text related to job duties included in text about job seekers, such as a resume. A resume, also called a curriculum vitae, is text that a job seeker conveys to a job applicant regarding their past job experience, skills, qualifications, etc. In the present embodiment, the information processing system 1 assists the job seeker U1 in creating text related to job duties. The text related to job duties may be any text that describes the jobs and tasks that the job seeker has experienced so far, and includes, for example, text that summarizes job duties (job summary). Note that, as an example of the text to be created, a resume is used for explanation, but it is not limited to this, and any text that includes text related to job duties, such as a job summary, is not limited to this.

[0018] The information processing system 1 includes a communication line 2, a server device 10, and a job seeker terminal 20. The communication line 2 is not particularly limited, but may be configured by the Internet network. Further, the communication line 2 may include a local area network, may include a mobile communication network, or may include a VPN (Virtual Private Network), etc. The communication line 2 mediates the exchange of data between devices connected to its own line. The server device 10 is connected to the communication line 2 by wire, and the job seeker terminal 20 is connected to the communication line 2 wirelessly. Note that the connection of each device to the communication line 2 may be wired or wireless.

[0019] The server device 10 is an information processing device that executes sentence generation processing while exchanging data with the job seeker terminal 20 via the communication line 2. The server device 10 stores a word database DB1 and a job seeker database DB2. The word database DB1 stores words used in the sentence generation processing. The job seeker database DB2 stores job seeker information used by the job seeker U1 in job hunting activities. The job seeker information is information about the job seeker, including the job seeker information (registration information) input on the registration screen and previously registered, and the job seeker information (input information) input on the input screen for creating a sentence related to the job content, and includes all information related to the registered or input job seeker. Here, the registration information and the input information may be stored in separate databases. The server device 10 has a function of artificial intelligence (AI: Artificial Intelligence), and generates and outputs a sentence related to the job content using the information stored in the word database DB1 and the job seeker database DB2.

[0020] The word database DB1 may store templates used in the sentence generation processing. Further, the word database DB1 may store question information regarding questions for collecting words corresponding to the templates. The question information includes information regarding the questions and the answers corresponding to the questions. The information regarding the answers is information for reference of the answers, and includes answer examples, answer options, etc. The answer options are at least one option for presenting to the job seeker U1. The number of options can be set as appropriate, but as an example, the number of options is 2 to 5. The answer examples and answer options may be words or sentences. The word database DB1 may store question information corresponding to the templates for each template. The word database DB1 may be a vector database (vector DB) including vector information of the templates and the question information.

[0021] The job seeker terminal 20 is a terminal with the job seeker U1 as the user. The job seeker terminal 20 is a smartphone, a tablet terminal, a personal computer, etc. The job seeker terminal 20 receives inputs necessary for text generation processing and displays texts related to the generated job content, etc.

[0022] Figure 2 is a diagram showing the hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a bus 14. The bus 14 electrically connects each part included in the server device 10.

[0023] (Control unit 11) The control unit 11 may include at least one processor. The at least one processor may be constituted by, for example, a Central Processing Unit (CPU), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), one or more Integrated Circuits, one or more Discrete Circuits, which are not shown, and combinations thereof. The control unit 11 is a computer that realizes various functions related to the information processing system 1 by reading a predetermined program stored in the storage unit 12. That is, the 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 may be implemented to have a plurality of control units 11 for each function. Or combinations thereof may also be possible.

[0024] (Storage unit 12) The storage unit 12 stores various information defined by the foregoing description. This can be implemented, for example, as a storage device such as a Solid State Drive (SSD) or a Hard Disk Drive (HDD) that stores various programs and the like related to the information processing system 1 executed by the control unit 11, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the calculation of programs. The storage unit 12 stores various programs, variables, etc. related to the information processing system 1 executed by the control unit 11.

[0025] (Communication unit 13) The communication unit 13 is composed of a communication module. The communication module may be a wireless communication module compliant with standards such as IEEE802.11a / b / g / n / ac / ax, LTE, 5G, 6G, etc., or may be a wired communication module compliant with standards such as IEEE802.3. The communication unit 13 is configured to be able to transmit various electrical signals from the server device 10 to external components. Also, the communication unit 13 is configured to be able to receive various electrical signals from external components to the server device 10. More preferably, the communication unit 13 has a network communication function, and thereby various information may be communicatively implemented between the server device 10 and external devices via the communication line 2.

[0026] FIG. 3 is a diagram showing the hardware configuration of the job seeker terminal 20. The job seeker terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a bus 26. The bus 26 electrically connects each part included in the job seeker terminal 20. The control unit 21, the storage unit 22, and the communication unit 23 may have different specifications, models, etc. from the control unit 11, the storage unit 12, and the communication unit 13 shown in FIG. 2, but are the same hardware.

[0027] (Input unit 24) The input unit 24 receives operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the bus 26. The control unit 21 can execute predetermined controls and calculations as necessary based on the transferred command signals. The input unit 24 may be included in the housing of the job seeker terminal 20, or may be externally attached. For example, the input unit 24 may be integrated with the output unit 25 and implemented as a touch panel. 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. As the input unit 24, instead of a touch panel, a switch button, a mouse, a track pad, a QWERTY keyboard, etc. can be adopted.

[0028] (Output unit 25) The output unit 25 displays a screen of a graphical user interface (GUI) operable by the user. The output unit 25 may be included in the housing of the job seeker terminal 20, or may be externally attached. Specifically, the output unit 25 can be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. These display devices are preferably selectively implemented according to the type of the job seeker terminal 20.

[0029] 2. Functional configuration In this section, the functional configuration of this embodiment will be described. The 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 thus can be executed as each functional unit included in the control unit 11 (the processor included in the information processing system 1).

[0030] FIG. 4 is a block diagram showing the functions realized by the server device 10 (control unit 11) and the job seeker terminal 20 (control unit 21).

[0031] As shown in FIG. 4A, the server device 10 (control unit 11) includes a reception unit 111, a memory control unit 112, an artificial intelligence unit 113, a generation unit 118, an extraction unit 115, a presentation unit 116, an acquisition unit 117, a generation unit 118, a conversion unit 119, and a memory control unit 112. As shown in FIG. 4B, the job seeker terminal 20 (control unit 21) includes a user display unit 211 and an operation reception unit 212.

[0032] <Reception unit 111> The reception unit 111 is configured to be able to receive information from the job seeker terminal 20 or other information processing terminals. Further, the reception unit 111 is configured to be able to receive various information by reading out various information stored in at least a part of the storage area, which is at least a part of the memory unit 12, and writing the read information into the work area, which is at least a part of the memory unit 12. The storage area is, for example, an area implemented as a storage device such as an SSD in the memory unit 12. The work area is, for example, an area implemented as a memory such as a RAM. For example, the reception unit 111 is configured to be able to receive an input based on the terminal operation of the job seeker U1 on the job seeker terminal 20. Specifically, the reception unit 111 is configured to be able to receive an input by the job seeker U1. Further, the reception unit 111 may be configured to be able to receive the editing of the text by the job seeker U1. The reception unit 111 may receive the editing of the text based on the terminal operation of the job seeker. The reception unit 111 is configured to be able to receive the job seeker information of the job seeker U1. The reception unit 111 may receive the job seeker information of the job seeker U1 via the job seeker terminal 20. The reception unit 111 may acquire the job seeker information of the job seeker U1 stored in the memory unit 12 from the job seeker database.

[0033] <Memory control unit 112> The memory control unit 112 controls the memory unit 12 of the own device and writes and reads data to and from the memory unit 12. The memory control unit 112 stores, for example, applicant information (input information) regarding the applicant U1 input on the input screen. The memory control unit 112 may register in the applicant database the applicant information (registration information) of the applicant U1 generated or updated according to the input of the applicant U1 and the applicant information (input information) input on the input screen for creating a sentence regarding the job content.

[0034] In the applicant database, applicant information used by the applicant U1 in the job hunting activity is registered. The applicant information is information regarding the applicant and includes the applicant information (registration information) input and pre-registered on the registration screen and the applicant information (input information) input on the input screen for creating a sentence regarding the job content, and includes all information regarding the registered or input applicant. The applicant information includes information related to a resume, a work history resume, etc. Note that the "resume" is a sentence mainly describing the applicant's profile, current situation, academic background, work history, desired working conditions, etc., and the "work history resume", also called a resume, is a sentence in which the applicant conveys his / her previous work history, experience, skills, qualifications, etc. to the employer. Note that the employer also includes a personnel agency that mediates between the applicant and the organization as an agent of the organization. The personnel agency is also called a headhunter, an agent, etc.

[0035] The registration information registered in the job seeker database includes the basic information of job seeker U1, information regarding the work history of job seeker U1, skill information regarding the skills of job seeker U1, a job summary (summary text) which is an outline of the work history document, etc. The basic information of job seeker U1 includes, for example, the name, age, address, previous annual income, educational background, work history, etc. of job seeker U1. Further, the basic information of job seeker U1 may include the industry and occupation the job seeker hopes for and the desired conditions for the applying organization. The information regarding job content includes information about the organizations job seeker U1 has experienced so far, information describing the jobs and tasks engaged in within the organization, etc. The job content may include, for example, the previous affiliated organizations of the job seeker, department names, job titles, affiliated periods, experienced job titles, experienced projects, business periods, the job seeker's management experience, language ability, awards, etc.

[0036] The registration information registered in the job seeker database may include the achievements of the job seeker's job hunting activities. The achievements of the job seeker's job hunting activities include the actions of job seeker U1 towards job offers and the actions in the job seeker information processing system 1 of job seeker U1. The actions of job seeker U1 towards job offers include, for example, viewing job offers, applying for job offers, registering in the bookmark list of job offers, replying to scout messages sent based on job offers, passing the screening (document screening, interview screening, etc.) in job offers, etc. The actions of job seeker U1 towards job offers are composed of information indicating the job offers that were the target or starting point of the job hunting activities and the content of the job hunting activities. The actions in the job seeker information processing system 1 of job seeker U1 include the number of updates and update frequency of the job seeker information (registration information) of job seeker U1, the number of display times and display frequency of the registration screen of the job seeker information, the number of confirmation times and confirmation frequency of messages, etc. The achievements of the job seeker's job hunting activities are recorded, for example, in the job seeker database for each job seeker (i.e., linked to the job seeker information).

[0037] The memory control unit 112 may store by associating a template candidate vector obtained by vectorizing a template candidate with a question information candidate vector which is a vector of question information candidates corresponding to the template candidate. FIG. 5 is a diagram showing an example of the configuration of the vector DB. The vector DB includes a template T1, a template T2, a template vector TV1, a template vector TV2, a question information vector QAV1-1, a question information vector QAV1-2, a question information vector QAV2-1, and a question information vector QAV2-2. The template T1 is, for example, a template defined in advance for generating a resume which is an example of a document related to job duties. Also, the template T1 may be called a document structure or a resume structure, and for example, the structure and keywords of a document related to job duties are defined. In the template of the resume structure, the format and font of the document may be defined. The template includes, for example, as necessary configurations for a document related to job duties, item names such as job type, industry type, job content, and appeal points, and a document template for each item. The template vector TV1 is obtained by converting the template T1 into a vector, and the template vector TV2 is obtained by converting the template T2 into a vector. The question information vectors QAV1-1 and QAV1-2 are obtained by converting the question information corresponding to the template T1 into a vector, and the question information vectors QAV2-1 and QAV2-2 are obtained by converting the question information corresponding to the template T2 into a vector.

[0038] The vector database stores by associating a template T1 with a template vector TV1 obtained by vectorizing the template. The vector database may store by associating the template vector TV1 with a question information vector QAV1-1 corresponding to the template vector TV1 and a question information vector QAV1-2. The vector database stores by associating a template T2 with a template vector TV2 obtained by vectorizing the template. The vector database may store by associating the template vector TV2 with a question information vector QAV2-1 corresponding to the template vector TV2 and a question information vector QAV2-2.

[0039] <Artificial intelligence unit 113> The artificial intelligence unit 113 is configured to receive an input from each functional unit and return an instructed output. Note that the artificial intelligence used by the server device 10 in each functional unit may be common or may be individually prepared for each functional unit. Note that hereinafter, the artificial intelligence unit 113 may also be referred to as an "artificial intelligence module".

[0040] The artificial intelligence unit 113 is an AI (Artificial Intelligence) equipped with a language model such as a Transformer (including GPT (Generative Pretrained Transformer, GPT-1, GPT-2, GPT-3, GPT-4), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer)), a Recurrent Neural Network (RNN), etc., and includes a generative AI.

[0041] A language model is an example of a learning model by a machine learning algorithm. Specific algorithms for machine learning include the nearest neighbor method, the naive Bayes method, decision trees, support vector machines, deep learning (deep neural networks) using neural networks, and the like. The artificial intelligence unit 113 can appropriately apply the above algorithms.

[0042] The artificial intelligence unit 113 has a trained model constructed by a learning method such as supervised learning, unsupervised learning, or semi-supervised learning. In supervised learning, machine learning is performed using teacher data (learning data). The teacher data is composed of a pair of input data for learning and output data (correct data). Also, the language model may be a general-purpose model that can be used generally for a wide range of tasks, not just trained for a specific task.

[0043] The artificial intelligence unit 113 includes, as artificial intelligence, a general-purpose natural language processing learning model such as a large language model (Large Language Models (LLM)) that has learned a lot of data. Such a general-purpose learning model includes language models that can handle various tasks without fine-tuning by One-shot Learning, Few-shot Learning, etc. Also, the general-purpose learning model can handle various tasks by Zero-shot Learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model or a common general-purpose learning model.

[0044] The learning model included in the artificial intelligence unit 113 is capable of performing additional learning. For example, the artificial intelligence unit 113 learns whether the text related to the job content of the job seeker U1 created has been corrected by the job seeker U1 or the like. That is, the artificial intelligence unit 113 performs additional learning and fine-tuning using, as teacher data, the text related to the actually corrected job content corrected by the job seeker U1 as feedback on the text related to the job content of the job seeker U1 created by the learning model. Thereby, the text related to the job content of the job seeker U1 output from the learning model is optimized.

[0045] The artificial intelligence unit 113 may include a component extraction model, a template candidate generation model, a question information candidate generation model, a question information extraction model, a template extraction model, a job content generation model, and the like.

[0046] The component extraction model may be a large language model or a learning model trained to input text related to the learning job content and output common components in the text related to the job content. When the template candidate generation model is a large language model, the generation unit 118 may input, as a component extraction step, an instruction to input text related to the job content and output common components in the input text related to the job content to the model.

[0047] The template candidate generation model may be a large language model, or a learning model that takes as input texts related to job content for learning and is trained to output template candidates for texts related to job content. When the template candidate generation model is a large language model, in the template candidate generation step, the generation unit 118 may input, as an instruction for the model to output a template candidate, a text related to job content. Also, the template candidate generation model may be a learning model that takes as input a specific text satisfying a predetermined condition for learning and is trained to output template candidates for texts related to job content. When the template candidate generation model is a large language model, in the template candidate generation step, the generation unit 118 may input, as an instruction for the model to output a template candidate, a specific text satisfying a predetermined condition. Also, the template candidate generation model may be a learning model that takes as input common components for learning and is trained to output template candidates for texts related to job content. When the template candidate generation model is a large language model, in the template candidate generation step, the generation unit 118 may input, as an instruction for the model to output a template candidate, common components.

[0048] The component extraction model and the template candidate generation model may be the same model, and the template candidate generation model may execute the component extraction step and the template candidate generation step. In that case, the template candidate generation model may be a learning model that takes as input texts related to job content for learning, extracts common components, and outputs template candidates based on the extracted components. In the case of a large language model, as an instruction for the model to output a template candidate based on the common components extracted from the input text related to job content, a text related to job content may be input.

[0049] The question information candidate generation model may be a large language model or a learning model trained to input texts related to job content for learning and output candidate question information for generating texts related to job content. When the question information candidate generation model is a large language model, in the question information candidate generation step, the generation unit 118 may input an instruction to input a text related to job content and output candidate question information for generating a text related to job content to the model. Also, the question information candidate generation model may be a learning model trained to input a specific text that meets a predetermined condition for learning and output candidate question information for generating a text related to job content. When the question information candidate generation model is a large language model, in the question information candidate generation step, the generation unit 118 may input an instruction to input a specific text that meets a predetermined condition and output candidate question information for generating a text related to job content to the model. Also, the question information candidate generation model may be a learning model trained to input a template candidate for a text related to job content and output candidate question information for generating a text related to job content. When the question information candidate generation model is a large language model, in the question information candidate generation step, the generation unit 118 may input an instruction to input a template candidate for a text related to job content and output candidate question information for generating a text related to job content to the model. Also, the question information candidate generation model may be a learning model trained to generate candidate question information necessary for generating a text related to job content along with a template candidate, or when it is a large language model, an instruction may be given to output the question information required for generating a text related to job content along with the input template candidate.

[0050] The template extraction model may use a learning model (machine learning or fine-tuning) that is trained to take the first job seeker information or the second job seeker information as input and output a template of the text related to the job content. For example, the template extraction model is a learning model that is trained using the first job seeker information or the second job seeker information and the corresponding template as teacher data. The extraction unit 115 inputs the first job seeker information and the template candidates into the template extraction model of the artificial intelligence unit 113, and causes the template extraction model to output a template from among the template candidates. Further, the template extraction model may be a generative AI including a large language model. In this case, the extraction unit 115 inputs a prompt in which an instruction to extract a template based on the first job seeker information and the first job seeker information are inserted into the template extraction model, and causes the template extraction model to output a template. Further, in addition to the extraction instruction of the template and the first job seeker information, the extraction unit 115 may input, for example, a prompt in which one or more samples of the first job seeker information and one or more corresponding samples of the template are inserted into the template extraction model.

[0051] The question information extraction model may use a learning model (machine learning or fine-tuning) that is trained to take the first job seeker information or the second job seeker information as input and output question information. For example, the question information extraction model is a learning model trained using the first job seeker information or the second job seeker information and the corresponding question information as teacher data. The extraction unit 115 inputs the first job seeker information into the question information extraction model of the artificial intelligence unit 113 and causes the question information extraction model to output the first question information. Also, the question information extraction model may be a generative AI including a large language model. In this case, the extraction unit 115 inputs a prompt in which an instruction to extract the first question information based on the first job seeker information and the first job seeker information are inserted into the question information extraction model, and causes the question information extraction model to output the first question information. Also, in addition to the extraction instruction for the first question information and the first job seeker information, the extraction unit 115 may input a prompt in which, for example, one or more samples of the first job seeker information and one or more samples of the corresponding first question information are inserted into the question information extraction model. When the extraction unit 115 obtains an answer to the first question, the storage control unit 112 stores the obtained answer in the job seeker database DB2 as job seeker information. The extraction unit 115 inputs the second job seeker information into the question information extraction model of the artificial intelligence unit 113 and causes the question information extraction model to output the second question information. Also, the question information extraction model may be a generative AI including a large language model. In this case, the extraction unit 115 inputs a prompt in which an instruction to extract the second question information based on the second job seeker information and the second job seeker information are inserted into the question information extraction model, and causes the question information extraction model to output the second question information. Also, in addition to the extraction instruction for the second question information and the second job seeker information, the extraction unit 115 may input a prompt in which, for example, one or more samples of the second job seeker information and one or more samples of the corresponding second question information are inserted into the question information extraction model.

[0052] In addition, in this embodiment, the artificial intelligence module may include a learning model. The learning model is a model that is trained to take large language models or second job seeker information as input and output text related to the job content of the job seeker. When the learning model is a large language model, the learning model inputs the second job seeker information and an instruction to output text related to the job content of the job seeker into the large language model. The generation of text related to the job content is performed by referring to a job content generation model that includes the correlation between the first job seeker information or the second job seeker information and the text related to the job content. As the job content generation model, for example, a job content generation model that is a learning model trained to take the first job seeker information or the second job seeker information as input and output text related to the job content is used. The generation unit 118 inputs the first job seeker information or the second job seeker information into the job content generation model of the artificial intelligence unit 113 and causes the job content generation model to output text related to the job content. Further, the job content generation model may be a generative AI including a large language model. In this case, the generation unit 118 inputs a prompt in which an instruction to generate text related to the job content based on the first job seeker information or the second job seeker information and the first job seeker information or the second job seeker information are inserted into the job content generation model, and causes the job content generation model to output text related to the job content. In addition to the instruction to generate text related to the job content and the first job seeker information or the second job seeker information, the generation unit 118 may input, for example, a prompt in which one or more samples of the first job seeker information or the second job seeker information and one or more corresponding samples of text related to the job content are inserted into the job content generation model. When inputting into the job content generation model, the generation unit 118 may input a template extracted based on the job seeker information into the learning model as reference information.

[0053] This learning model is a trained model that has machine-learned job seeker information for learning. The text related to the job content for learning is text related to the job content used as learning data for training the learning model. The text related to the job content for learning is information about job seekers other than the job seeker U1 who is a user of the information processing system 1, but may include the registration information and input information of the job seeker U1.

[0054] Further, this learning model may be a model generated by performing machine learning with teacher data in which, for example, job seeker information of job seekers who have previously conducted job hunting activities is used as input data (explanatory variables) for learning, and sentences related to job content such as resumes submitted to companies or the like where the job seekers actually found employment (i.e., sentences related to job content that had an effect) are paired with output data (objective variables) for learning.

[0055] Also, the learning model may be generated by learning a corpus (a database in which natural language sentences are structured and accumulated on a large scale), and job seeker information or the like may be included as one of a large number of corpora. The artificial intelligence unit 113 creates a sentence related to job content derived from the information about the input job seeker using this learning model, and outputs the created sentence. The display control unit 114 also functions as an example of a display unit that displays the sentence related to job content output by the artificial intelligence unit 113 based on an instruction from the generation unit 118 in this way.

[0056] <display control unit 114> The display control unit 114 executes processing for displaying a system screen related to the information processing system 1 on each terminal. The display control unit 114 performs processing such as generation and transmission of an HTML (Hyper Text Markup Language) file, for example, and causes a web page showing the system screen to be displayed on the job seeker terminal 20. Note that the display control unit 114 may perform processing such as generation and transmission of display data for an application for using the information processing system 1. For example, the display control unit 114 can cause a registration screen, an input screen, a reception screen, etc. of job seeker information related to the job seeker U1 to be displayed on the job seeker terminal.

[0057] <extraction unit 115> The extraction unit 115 is configured to be able to extract various information from the reference information. For example, as a specific sentence extraction step, the extraction unit 115 can extract a specific sentence that satisfies a predetermined condition from the sentences related to the accumulated job content. As a component extraction step, the extraction unit 115 can extract common components common to a plurality of specific sentences from the plurality of specific sentences. As a template extraction step, the extraction unit 115 can extract a template corresponding to the first job seeker information from the reference information. As a question information extraction step, the extraction unit 115 extracts question information corresponding to the first job seeker information from the reference information.

[0058] <Presentation unit 116> The presentation unit 116 executes processing for presenting a system screen related to the information processing system 1 to each terminal. The presentation unit 116 is configured to be able to present the question information extracted by the extraction unit 115 to the job seeker U1.

[0059] <Acquisition unit 117> The acquisition unit 117 is configured to be able to acquire various information. The acquisition unit 117 can acquire the information input to the job seeker terminal 20 as an answer.

[0060] <Generation unit 118> The generation unit 118 is configured to be able to generate various sentences based on the job seeker information related to the job seeking activities of the job seeker U1.

[0061] The generation unit 118 may be configured to be able to generate a sentence related to the job content of the job seeker U1 as a job content generation step. For example, as a job content generation step, the generation unit 118 may give an instruction to the learning model to generate a sentence related to the job content based on the job seeker information, and cause the learning model to generate a sentence related to the job content. Here, the sentence related to the job content may be, for example, a sentence explaining the job content of the job seeker U1 or a sentence summarizing the job content of the job seeker U1.

[0062] The generation unit 118 controls the input to the artificial intelligence unit 113. For example, the generation unit 118 is configured to generate a prompt that instructs to output information regarding the job content of the job seeker U1, using, as input, the information input by the job seeker U1 on the input screen for job seeker information or the information input and registered on the registration screen. Further, the generation unit 118 may be configured to generate a prompt that instructs to output a sentence regarding the job content, using, as input, for example, the job seeker information of the job seeker U1. Further, the generation unit 118 may generate a prompt by inserting, for example, the job seeker information of the job seeker U1 into a preset prompt template.

[0063] Also, the generation unit 118 is configured to be able to instruct the artificial intelligence unit 113 to create a sentence regarding the job content of the job seeker based on the job seeker information including the registration information and the input information. The job seeker information referred to here includes the input input information and the pre-registered registration information.

[0064] <Conversion unit 119> The conversion unit 119 can convert the generated question information candidates into vector data. The conversion unit 119 can convert the template candidates and the job seeker information into vector data. Note that the vector data is a vector value obtained by quantifying text data by known methods such as natural language processing by morphological analysis or encoding of categorical variables. The vector data may be a dense vector or a sparse vector.

[0065] <User display unit 211> The user display unit 211 of the job seeker terminal 20 displays the screen indicated by the screen data transmitted from the server device 10. The user display unit 211 of the job seeker terminal 20 displays a system screen regarding the information processing system 1 indicated by the screen data transmitted from the server device 10.

[0066] <Operation reception unit 212> The operation reception unit 212 of the job seeker terminal 20 is configured to be able to receive operations by a user (job seeker) who uses the job seeker terminal 20. When the job seeker U1 operates the job seeker terminal 20 as a user to use the information processing system 1, a user ID (Identification) and a password are input for login. As a result, the user ID is associated with the information generated or updated in the job seeker terminal 20, and it becomes possible to know which user the information is about.

[0067] 3. Outline of the information processing method In this section, the information processing method of the server device 10 will be described. In this information processing method, each part of the server device 10 is executed by a computer as each step. As shown below, the information processing method includes each step executed by the information processing system. The program of the present embodiment causes the computer to execute each step of the information processing system 1. Note that the order of processing can be appropriately changed, a plurality of processes can be executed simultaneously, or some processes can be omitted.

[0068] 3.1 Outline FIG. 6 is a flowchart showing an outline of the information processing executed by the information processing system 1. In such processing, first, the reception unit 111 receives first job seeker information including information regarding the attributes of the job seeker (step S001). Subsequently, the extraction unit 115 extracts question information corresponding to the first job seeker information from the reference information as a question information extraction step (step S002). Here, the question information includes a question for the job seeker and information regarding an example answer corresponding to the question, and the reference information includes a plurality of question information candidates that are candidates for the question information generated in advance based on the accumulated texts regarding the job content. Subsequently, the acquisition unit 117 acquires an answer from the job seeker to the question information (step S003). Subsequently, the generation unit 118 generates a text regarding the job content of the job seeker based on the second job seeker information as a job content generation step (step S004). The second job seeker information includes the first job seeker information and the answer acquired by the acquisition unit 117.

[0069] Summarizing the above, an information processing system according to an embodiment includes at least one processor. By reading a program, the processor includes the following components. A reception unit 111 receives first job seeker information including information regarding the attributes of a job seeker. An extraction unit 115 extracts, as a question information extraction step, question information corresponding to the first job seeker information from reference information. The question information includes a question for the job seeker and information regarding an answer example corresponding to the question. The reference information includes a plurality of question information candidates that are candidates for the question information generated in advance based on the accumulated job content-related texts. An acquisition unit 117 acquires an answer from the job seeker to the question information. A generation unit 118 generates, as a job content generation step, a text regarding the job content of the job seeker based on the second job seeker information. The second job seeker information includes the first job seeker information and the answer acquired by the acquisition unit 117. In such a manner, a question corresponding to the job seeker information can be presented.

[0070] 4. Details of the Information Processing Method In this section, in the present embodiment, the information processing for causing a computer that controls the information processing system 1 to execute a program will be described in more detail. The information processing system 1 includes at least one processor. By reading a program, the processor is configured such that each step shown in FIG. 7, FIG. 9, etc. is performed.

[0071] FIG. 7 is an activity diagram showing the flow of information processing for constructing a vector DB executed by the information processing system 1. An example of the flow may be included within the scope defined in the above-mentioned overview. FIG. 8 is an explanatory diagram for explaining an example of the relationship between a specific text and a question information vector. The explanatory diagram includes a specific text, components, templates, question information, and question information vectors. Hereinafter, the following will be described along each activity of this activity diagram using the explanatory diagram. Note that the information processing may include any exception processing not shown. The exception processing includes interruption of the information processing and omission of each process. The selection or input performed in the information processing may be based on the operation by the job seeker U1 or may be automatically performed without depending on the operation of the job seeker U1.

[0072] First, the acquisition unit 117 acquires the text related to the accumulated job content (Activity A001). The text related to the accumulated job content is the text related to the job content of a plurality of job seekers. The acquisition unit 117 can acquire the text related to the job content stored in the job seeker database DB2.

[0073] Subsequently, as a specific text extraction step, the extraction unit 115 extracts specific texts that meet predetermined conditions from the texts related to the accumulated job content (Activity A002). The texts related to the accumulated job content may be those stored in the job seeker database DB2. The predetermined conditions may be conditions that enable extraction of high-quality specific texts from the texts related to the accumulated job content.

[0074] Specifically, as a specific text extraction step, the extraction unit 115 may extract specific texts that meet predetermined conditions regarding the achievements of job seeking activities corresponding to the texts related to the accumulated job content. The achievements of job seeking activities may be stored in the job seeker database DB2 in association with the texts related to the job content. The achievements of job seeking activities are, for example, the number of received scout emails, the presence or absence of received scout emails, the number of replied scout emails, the presence or absence of replied scout emails, the number of passed document screenings, the presence or absence of passed document screenings, the number of job offers, the presence or absence of job offers, the presence or absence of employment decisions, etc. The predetermined conditions may include that the number of received scout emails is equal to or more than a predetermined number.

[0075] In addition, the predetermined conditions may include that the text contains predetermined components. The predetermined components are, for example, 5W1H. 5W1H is "Who" (who), "What" (what), "When" (when), "Where" (where), "Why" (why), "How" (how). It can be said that a text related to job content containing 5W1H is a high-quality text.

[0076] In Activity A002, as a specific text extraction unit, the extraction unit 115 may extract specific texts from the texts related to the accumulated job content for each attribute of the job seeker. Specifically, as a specific text extraction step, the extraction unit 115 may extract specific texts from the texts related to the accumulated job content for each attribute of the job seeker, such as for each industry type, job type, age, place of residence, place of work, etc. When the extraction unit 115 extracts specific texts for each attribute, the memory control unit 112 may save the extracted specific texts in association with the attributes of the job seeker used for the extraction.

[0077] Subsequently, in the component extraction step, the extraction unit 115 extracts common components common to a plurality of specific texts by means of an artificial intelligence module (Activity A003). In the example of the explanatory diagram, as a component extraction step, the extraction unit 115 extracts components A, B, C, etc. as common components common to the specific texts by means of the artificial intelligence module M1 (for example, a component extraction model). Thereby, for example, components commonly included in texts related to high-quality job content (for example, appeal points, presence or absence of management experience, specific achievements, quantitative results, etc.) can be extracted. In other words, the common components relate to at least one of the achievements, skills, qualifications, and appeal points of the job seeker.

[0078] Here, as a component extraction step, the extraction unit 115 may extract common components common to each attribute of the job seeker. For example, as a component extraction step, the extraction unit 115 may extract common components common to the texts related to the accumulated job content for each attribute of the job seeker, such as for each industry type, job type, age, place of residence, place of work, etc. Specifically, as a component extraction step, the extraction unit 115 may extract common components common to the specific texts extracted for each attribute. When the extraction unit 115 extracts common components for each attribute, the memory control unit 112 may save the extracted common components in association with the attributes.

[0079] For example, as a template candidate generation step, the generation unit 118 generates a template candidate including common components (Activity A004). In the example of the explanatory diagram, as a template candidate generation step, the extraction unit 115 can generate a template candidate for a text related to job content based on common components by an artificial intelligence module M2 (for example, a template candidate generation model). The template candidate may be referred to as a set of components composed of a plurality of common components. A plurality of template candidates may be generated (for example, template T1, template T2, etc.). Thereby, for example, a template candidate including components commonly included in high-quality texts related to job content can be generated.

[0080] Here, as a template candidate generation step, the generation unit 118 may generate a template candidate for each attribute of the job seeker. For example, as a template candidate generation step, the generation unit 118 may generate a template candidate based on the accumulated texts related to job content for each attribute of the job seeker, such as for each industry type, job type, age, place of residence, place of work, etc. Specifically, as a template candidate generation step, the generation unit 118 may generate a template candidate based on specific texts extracted for each attribute. Further, as a template candidate generation step, the generation unit 118 may generate a template candidate including common components extracted for each attribute. Thereby, a template candidate corresponding to the attribute of the job seeker can be generated. When the generation unit 118 generates a template candidate for each attribute, the memory control unit 112 may store the template candidate in association with the attribute.

[0081] Subsequently, as a question information candidate generation step, the generation unit 118 generates question information candidates by an artificial intelligence module based on the accumulated sentences related to job content (Activity A005). Specifically, as a question information candidate generation step, the extraction unit 115 may generate question information candidates for generating sentences related to the job content of job seekers according to template candidates by an artificial intelligence module. Here, as a question information candidate generation step, the generation unit 118 may generate question information candidates for each attribute of the job seeker. For example, as a question information candidate generation step, the generation unit 118 may generate question information candidates for each industry type, job type, age, place of residence, and place of work. Specifically, the generation unit 118 may generate question information candidates according to the template candidates generated for each attribute. When generating question information candidates for each attribute, the memory control unit 112 may store the question information candidates in association with the attributes. Thereby, question information candidates corresponding to the attributes of the job seeker can be generated. In the example of the explanatory diagram, as a question information candidate generation step, the extraction unit 115 can generate question information candidates according to template candidates by the artificial intelligence module M3 (for example, a question information candidate generation model). That is, question information candidates for obtaining information of job seekers required for generating sentences according to the template are generated to obtain answers from the job seekers. As a question information candidate generation step, the extraction unit 115 may generate a plurality of question information candidates for each template. For example, the extraction unit 115 can generate question information candidate QA1-1 and question information candidate QA1-2 for template T1, and generate question information candidate QA2-1 and question information candidate QA2-2 for template T2. The question information candidates may include one question and information regarding a plurality of answer options corresponding to the question. Here, the answer options are candidates for answers to the corresponding questions.For example, the question information candidate QA1-1 may include the question Q1-1, and the answers A1-1-1 and A1-1-2 corresponding to the question Q1-1. The question information candidate QA1-2 may include the question Q1-2, and the answers A1-2-1 and A1-2-2 corresponding to the question Q1-2. The question information candidate QA2-1 may include the question Q2-1, and the answers A2-1-1 and A2-1-2 corresponding to the question Q2-1. The question information candidate QA2-2 may include the question Q2-2, and the answers A2-2-1 and A2-2-2 corresponding to the question Q2-2.

[0082] Subsequently, the conversion unit 119 converts the generated question information candidates into vectors (activity A006). In the example of the explanatory diagram, the conversion unit 119 converts the template T1 into the template vector TV1, and the template T2 into the template vector TV2. Also, the conversion unit 119 converts the question information candidate QA1-1 into the question information vector QAV1-1, the question information candidate QA1-2 into the question information vector QAV1-2, the question information candidate QA2-1 into the question information vector QAV2-1, and the question information candidate QA2-2 into the question information vector QAV2-2. Further, when the generation unit 118 generates template candidates and question information candidates for each attribute of the job seeker, the conversion unit 119 may convert the associated attributes of the job seeker into vectors together with the template candidates and question information candidates.

[0083] Subsequently, the memory control unit 112 stores the question information candidates in the vector DB (Activity A007). Specifically, the memory control unit 112 can store the template candidate vector obtained by vectorizing the template candidate and the question information candidate vector which is the vector of the question information candidate corresponding to the template candidate in association with each other. The reference information (e.g., vector DB) includes the question information candidates and the question information candidate vectors which are the vectors of the question information candidates. Thereby, a vector DB in which the template candidates and the question information candidates are stored in association with each other is constructed. Also, when the conversion unit 119 converts the associated attributes into vectors together with the template candidates and the question information candidates, the memory control unit 112 may store the vector corresponding to the attributes of the job seeker corresponding to the template candidate or the question information candidate in association with the template candidate vector and the question information candidate vector.

[0084] Subsequently, with reference to FIGS. 9 and 10, the information processing for generating the text related to the job content will be described. FIG. 9 is an activity diagram showing the flow of the information processing for constructing the vector DB executed by the information processing system 1. FIG. 10 is a diagram showing an input screen G3 which is an example of the information input screen. The input screen G3 includes areas 31 to 40. Areas 31, 33, 35, 37, and 39 are areas for presenting questions generated based on the question information extracted by the extraction unit 115 as the question information extraction step. Areas 32, 34, 36, 38, and 40 are areas where the answers of the job seeker U1 to the questions are displayed.

[0085] First, the server device 10 receives the first job seeker information by the reception unit 111 (Activity A101). The first job seeker information includes information regarding the attributes of the job seeker. Specifically, the job seeker terminal 20 may receive the first job seeker information from the job seeker U1 via the operation reception unit 212, and the reception unit 111 may receive the first job seeker information from the job seeker terminal 20. Also, the reception unit 111 may receive the first job seeker information from the job seeker database DB2 stored in the storage unit 12.

[0086] Subsequently, the server device 10 converts the first job seeker information into a vector (job seeker information vector) by the conversion unit 119 (Activity A102). For example, the conversion unit 119 can convert the first job seeker information into an embedding vector.

[0087] Also, the conversion unit 119 may vectorize the job seeker information using a vectorization API. The vectorization API is an API for converting data into a vector (an array of numerical values). The conversion unit 119 may use a vectorization API outside the information processing system 1 as the API.

[0088] Subsequently, the extraction unit 115 searches the vector DB (Activity A103) and extracts a template corresponding to the first job seeker information (Activity A104). For example, the extraction unit 115 can extract a template vector from the vector DB based on a search query based on the first job seeker information and extract the template corresponding to the template vector.

[0089] Specifically, as a template extraction step, the extraction unit 115 can extract a template corresponding to the first job seeker information based on the similarity between the first job seeker information vector obtained by vectorizing the first job seeker information and the template candidate vector obtained by vectorizing the template candidate. For example, the extraction unit 115 can calculate the similarity between the first job seeker information vector and each template vector in the vector DB to extract high-similarity question information. As an index for calculating the similarity, cosine similarity or Euclidean distance can be used. Thereby, a template that matches the job seeker information can be extracted.

[0090] Here, as a template extraction step, the extraction unit 115 may extract a template according to the attributes of the job seeker included in the first job seeker information. That is, as a template extraction step, the extraction unit 115 may extract a template according to the industry, occupation, age, place of residence, place of work, etc. included in the first job seeker information. Specifically, the extraction unit 115 may extract a template according to the first job seeker information based on the similarity between the first job seeker information vector and the vector obtained by vectorizing the template candidate and the attribute associated with the template candidate. Also, the extraction unit 115 first determines whether the attribute included in the first job seeker information is a template candidate corresponding to a similar attribute, and extracts a template based on the similarity between the attribute included in the first job seeker information, the template candidate vector of the template candidate corresponding to the similar attribute, and the first job seeker information vector. Thereby, a template according to the attributes of the job seeker can be extracted.

[0091] Subsequently, as a question information extraction step, the extraction unit 115 extracts question information according to the first job seeker information from the reference information (Activity A105).

[0092] For example, as a question information extraction step, the extraction unit 115 may extract the first question information according to the first job seeker information based on the similarity between the first job seeker information vector obtained by vectorizing the first job seeker information and the question information candidate vector obtained by vectorizing the question information candidate. For example, the extraction unit 115 can calculate the similarity between the first job seeker information vector and each question information candidate vector in the vector DB to extract question information with a high similarity. As an index for calculating the similarity, cosine similarity or Euclidean distance can be used.

[0093] As a question information extraction step, the extraction unit 115 may extract question information corresponding to the template. The extraction unit 115 may extract the question information corresponding to the extracted template from the reference information. The extraction unit 115 may extract the question information stored in association with the extracted template from the word database DB1, and the word database DB1 may be a vector DB.

[0094] Also, as a question information extraction step, the extraction unit 115 may extract question information according to the attributes of the job seeker included in the first job seeker information. In activity A104, when the extraction unit 115 extracts a template according to the attributes of the job seeker as a template extraction step, the extraction unit 115 can extract question information according to the attributes of the job seeker as a question information extraction step in activity A105.

[0095] Subsequently, the presentation unit 116 presents the extracted question information on the user display unit 211 of the job seeker terminal 20 (activity A106). The extraction unit 115 may directly present the extracted question information to the presentation unit 116, or may edit the extracted question information according to the job seeker U1 and then present it to the presentation unit 116. For example, the extraction unit 115 may extract question information by a learning model, and the learning model may be a large language model. Based on the extracted question information, the extraction unit 115 may edit it according to the job seeker U1 by a large language model and then have it presented by the presentation unit 116.

[0096] The prompting unit 116 transmits the data of the extracted question information to the job seeker terminal 20. The job seeker terminal 20 presents, via the user display unit 211, an input screen G3 including the data of the transmitted question information. The input screen G3 includes an input field in which an answer to the question information can be input. In area 31 of the input screen G3, the first question information is presented. Area 31 includes the question "Automatically generate job content from 3 to 10 questions. First, please tell us in the following format what kind of job you have had in which company. Summarize one job in one line. Employment period Company name Job type Example of entry 2020 - 2021 Company A Job B".

[0097] Subsequently, the job seeker U1 inputs an answer to the question presented in area 31 into area 32. The job seeker terminal 20 receives, via the operation reception unit 212, the input operation of the job seeker U1. The job seeker terminal 20 transmits the answer data to the server device 10. The acquisition unit 117 acquires the answer from the job seeker terminal 20 (Activity A107).

[0098] Subsequently, the control unit 11 adds the answer to the first job seeker information to obtain second job seeker information (Activity A108). Specifically, the storage control unit 112 stores the answer acquired from the job seeker U1 in the job seeker database in association with the first job seeker information of the job seeker U1.

[0099] Subsequently, the control unit 11 determines whether additional questions are necessary based on the second job seeker information to which the answer has been added in Activity A108 (Activity A109).

[0100] If it is determined in Activity A109 that additional questions are necessary, the process returns to Activity A105.

[0101] The extraction unit 115 extracts second question information according to the second job seeker information. In other words, as a question information extraction step, the extraction unit 115 can extract first question information and second question information. The second question information may be extracted from the reference information according to the second job seeker information after obtaining an answer to the first question information. For example, when the reference information includes a vector DB, as a question information extraction step, the extraction unit 115 may extract second question information according to the second job seeker information based on the similarity between a second job seeker information vector obtained by vectorizing the second job seeker information and a question information candidate vector.

[0102] Subsequently, in activity A106, the presentation unit 116 presents the second question information to the job seeker terminal 20. Note that the control unit 11 may determine, by means of an artificial intelligence module, whether the answer of the job seeker U1 input to area 32 meets the requirements of the question in area 31. For example, area 32 includes an answer of "Company C from 2015 to 2023". The control unit 11 determines that the answer in area 32 does not include information on "job type" and causes it to be presented in area 33 as the next question. Area 33 includes a question of "Insufficient information. Please fill in 'working period company name job type' in the following format. Example of filling: 2020 - 2021 Company A Job type B".

[0103] Area 34 includes the answer "Responsible person of C company's store from 2015 to 2023". Subsequently, the control unit 11 determines whether additional questions are necessary based on the second job seeker information with the answer input to area 34. After the input of the job type, if the control unit 11 determines that additional questions are necessary, the extraction unit 115 extracts the next question information, and the generation unit 118 generates a question based on the extracted question information. Area 35 includes the question "Question: What was the size of the team? Answer example: 6 people". Area 36 includes the answer "80 people". Area 37 presents three answer examples along with the question "Question: What roles did you play?". Area 38 includes the answer "Executed ○○". Area 39 presents three answer examples along with the question "Question: What were the specific achievements?". Area 40 includes the answer "Increased ○○". In this way, the control unit 11 may repeat the extraction and presentation of question information to generate a text regarding the job content. The question information is extracted with the information necessary to generate a text regarding the job content of the job seeker, such as the job type, business area, specific role, and achievements.

[0104] The presentation unit 116 may present the question information to the job seeker U1 through the chat system and receive an answer from the job seeker U1. The chat system is a system that performs responses in real time, such as when the presentation unit 116 displays the question information on the user display unit 211 and receives an answer from the job seeker U1, the extraction unit 115 extracts the question information for the received answer. Specifically, when the presentation unit 116 presents the question information and receives an answer from the job seeker U1, the extraction unit 115 extracts the next question information corresponding to the second job seeker information using natural language processing technology and the presentation unit 116 presents it. Here, the presentation unit 116 may display a list of the sending and receiving of messages with the job seeker U1.

[0105] When the control unit 11 determines that no additional questions are necessary to generate a text regarding the job duties, the presentation unit 116 may present a question to the job seeker U1 asking for an instruction to generate a text regarding the job duties. Subsequently, the acquisition unit 117 acquires an instruction to generate a text regarding the job duties from the job seeker terminal 20. Subsequently, as a job duty generation step, the generation unit 118 can generate a text regarding the job duties of the job seeker by using the artificial intelligence module with the second job seeker information as the input (Activity A110). In such a manner, by extracting question information that matches the job seeker information, personalized questions can be presented for each job seeker, and based on that, a more personalized text can be generated by generating a text.

[0106] In the above embodiment, in Activity A002, the extraction unit 115 extracts a specific text that satisfies a predetermined condition from the accumulated texts regarding the job duties, and the generation unit 118 generates a template candidate and a question information candidate based on the specific text. By using the template candidate and the question information candidate generated based on the specific text in this way, the generation unit 118 can generate a high-quality (highly likely to satisfy a predetermined condition) text.

[0107] Also, as a job duty generation step, the generation unit 118 may generate a text regarding the job duties of the job seeker by using the artificial intelligence module based on the specific text. The artificial intelligence module is a learning model, and the learning model may be a model that is learned to output a text regarding the job duties of the job seeker with the specific text and the second job seeker information as the inputs. Also, the artificial intelligence module is a learning model, and the learning model is a large language model, and the specific text, the second job seeker information, and an instruction to output a text regarding the job duties of the job seeker based on the specific text and the second job seeker information may be input to the large language model. In such a manner, a text regarding the job duties of the job seeker U1 can be generated with reference to a text regarding the job duties that satisfies a predetermined condition.

[0108] Further, as a job content generation step, the generation unit 118 may generate a text related to the job content of the job seeker by an artificial intelligence module based on the answer from the job seeker U1 to the question. The artificial intelligence module is a learning model, and the learning model may be a model learned to input the answer from the job seeker U1 as the second job seeker information and output a text related to the job content of the job seeker. Also, the artificial intelligence module is a learning model, and the learning model is a large language model. The answer from the job seeker U1 to the question and an instruction to output a text related to the job content of the job seeker based on the answer may be input to the large language model. In such a manner, a text related to the job content of the job seeker U1 can be generated based on the answer from the job seeker U1 to the question.

[0109] Further, as a job content generation step, the generation unit 118 can generate a text related to the job content of the job seeker by an artificial intelligence module based on the second job seeker information and the template extracted in the template extraction step. The artificial intelligence module is a learning model, and the learning model may be a model learned to input the extracted template and the second job seeker information and output a text related to the job content of the job seeker. Also, the artificial intelligence module is a learning model, and the learning model is a large language model. The template, the second job seeker information, and an instruction to output a text related to the job content of the job seeker based on the template and the second job seeker information may be input to the large language model. In such a manner, a text related to the job content of the job seeker U1 can be generated based on the template. That is, for example, a text related to the job content of the job seeker U1 can be generated in a configuration along a template generated based on a text related to high-quality job content and similar to the job seeker information.

[0110] Further, the generation unit 118 may input a template as reference information into the learning model, and as a job content generation step, input the second job seeker information, and generate a text related to the job content of the job seeker by an artificial intelligence module. Here, as a job content generation step, the artificial intelligence module included in the generation unit 118 may include a learning model. The learning model may be a large language model or a model trained to input the second job seeker information and output a text related to the job content of the job seeker. By inputting the reference information in this way, the learning model can generate a text related to the job content of the job seeker U1 based on the reference information.

[0111] In addition, in the activity A104, when the template extraction step extracts a template according to the attributes of the job seeker, the generation unit 118 can, as a job content generation step, generate a text related to the job content of the job seeker by an artificial intelligence module based on the second job seeker information and the template extracted according to the attributes. Thereby, a text related to the job content more suitable for the job seeker can be generated.

[0112] The embodiments of the present invention have been described above, but the present invention is not limited thereto and can be appropriately changed without departing from the technical idea of the invention.

[0113] 5. Others In the above-described embodiment, the server device 10 performs various storage and control operations. However, instead of the server device 10, a plurality of external devices may be used. That is, various information and programs may be distributed and stored in a plurality of external devices using blockchain technology or the like. In particular, the artificial intelligence unit 113 may be an external component of the server device 10. In that case, the artificial intelligence unit 113 as an external component is provided, for example, by an artificial intelligence service server, receives inputs from each functional unit of the server device 10, receives a request to execute an artificial intelligence service, and is configured to return the output instructed as a processing result to the server device 10. The artificial intelligence service server may be a server that provides a service using a language model as a learning model, or a server that executes a language processing task using a language model. The artificial intelligence service server may be constructed by a large language model. The artificial intelligence service server receives inputs of prompts by text, image, voice, etc., generates an answer to the prompt, and responds.

[0114] In the above-described embodiment, after extracting the constituent elements common to the specific text, a template was generated based on the common constituent elements. However, as a template candidate generation step, the generation unit 118 may generate a template candidate for the text structure by an artificial intelligence module based on the specific text. In this case, the artificial intelligence module may include a learning model. The learning model is a model that is trained to output a template of a text related to the job content of a job seeker with the specific text as an input, which may be a large language model. When the learning model is a large language model, the learning model inputs the specific text and an instruction to output a template of the text structure based on the specific text to the large language model.

[0115] <Variations of the configuration> The configurations shown in FIG. 1 etc. are examples, and other modes may be adopted as long as there is no inconvenience in implementation. For example, one device may be distributed among two or more devices, or may be replaced by a cloud computing system. Also, the functions of one device may be realized by being distributed among two or more devices, or the functions of two or more devices may be concentrated and realized by one device. Further, the operations performed by one function may be distributed among two or more functions, or two or more functions may be integrated into one function. In short, as long as each function necessary for the entire information processing system 1 is realized, the devices realizing those functions may have any configuration. In particular, the artificial intelligence unit 113 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 113 which is an external configuration is provided by, for example, an artificial intelligence service server, receives an input from each functional unit of the server device 10, receives a request to execute an artificial intelligence service, and is configured to return an output instructed as a processing result to the server device 10. The artificial intelligence service server may be a server that provides a service using a language model as a learning model, or may be a server that executes a language processing task using a language model. The artificial intelligence service server may be constructed by an LLM. The artificial intelligence service server receives an input of a prompt by text, image, voice, etc., and generates and responds with an answer to the prompt.

[0116] <Other variations> The output destination of information or data (hereinafter referred to as "information etc.") may be another device, a display, a storage unit (including a built-in storage unit and an external storage unit), etc. The acquisition of information etc. includes, in addition to the mode of acquiring information etc. transmitted from another device, the mode of acquiring information etc. generated by the own device. The table associating parameters is not limited to the illustrated table, and the number of parameters may be reduced or increased. Also, instead of using a table, information etc. corresponding to the parameters may be obtained by a mathematical formula or a conditional expression, etc.

[0117] <Supplementary note> Furthermore, it may be provided in each of the aspects described below.

[0118] (1) An information processing system, comprising at least one processor, wherein the processor is configured to execute the following steps by reading a program. In the reception step, it receives first job seeker information including information regarding the attributes of a job seeker. In the question information extraction step, it extracts question information corresponding to the first job seeker information from reference information, where the question information includes questions for the job seeker and information regarding answer examples corresponding to the questions, and the reference information includes a plurality of question information candidates which are candidates for the question information generated in advance based on the accumulated job content. In the acquisition step, it acquires answers from the job seeker to the question information. In the job content generation step, it generates a text regarding the job content of the job seeker based on second job seeker information, where the second job seeker information includes the first job seeker information and the answers acquired in the acquisition step.

[0119] In such a manner, questions corresponding to the job seeker information can be presented.

[0120] (2) In the information processing system according to (1) above, further, in the question information candidate generation step, based on the text regarding the accumulated job content, an artificial intelligence module generates the question information candidates. Further, in the conversion step, the generated question information candidates are converted into vectors, and the reference information includes the question information candidates and question information candidate vectors which are vectors of the question information candidates.

[0121] In such a manner, based on the text regarding the accumulated job content, question information candidates can be accumulated.

[0122] (3) In the information processing system according to (1) or (2) above, in the question information extraction step, it extracts first question information and second question information, where the second question information is extracted from the reference information according to the second job seeker information after acquiring the answer to the first question information.

[0123] In such a manner, job seeker information and question information corresponding to the answers can be extracted.

[0124] (4) In the information processing system according to (3) above, in the question information extraction step, based on the similarity between the vector of the first job seeker information obtained by vectorizing the first job seeker information and the vector of the question information candidates obtained by vectorizing the question information candidates, the first question information corresponding to the first job seeker information is extracted, and based on the similarity between the vector of the second job seeker information obtained by vectorizing the second job seeker information and the vector of the question information candidates, the second question information corresponding to the second job seeker information is extracted.

[0125] In such a manner, question information whose vector is similar to the job seeker information can be extracted.

[0126] (5) In the information processing system according to any one of (1) to (4) above, in the job content generation step, using the second job seeker information as input, an artificial intelligence module generates a text related to the job content of the job seeker. Here, the artificial intelligence module includes a learning model, and the learning model is a large language model or a model trained to take the second job seeker information as input and output a text related to the job content of the job seeker. When the learning model is the large language model, the second job seeker information and an instruction to output a text related to the job content of the job seeker are input to the large language model.

[0127] In such a manner, a text related to the job content of the job seeker can be generated using a large language model.

[0128] (6) In the information processing system according to any one of (1) to (5) above, further, in the specific sentence extraction step, a specific sentence that satisfies a predetermined condition is extracted from the sentences related to the accumulated job content, and in the job content generation step, based on the specific sentence, an artificial intelligence module generates a sentence related to the job content of the job seeker.

[0129] In such a manner, a high-quality sentence can be extracted from the accumulated sentences related to the job content, and the high-quality sentence can be utilized to generate a sentence related to the job content of the job seeker.

[0130] (7) In the information processing system according to (6) above, the predetermined condition includes that the number of received scouts is equal to or more than a predetermined number.

[0131] In such a manner, a sentence with the number of received scouts equal to or more than a predetermined number can be extracted from the accumulated sentences related to the job content, and the sentence can be utilized to generate a sentence related to the job content of the job seeker.

[0132] (8) In the information processing system according to (6) or (7) above, the predetermined condition includes that the sentence contains a predetermined component.

[0133] In such a manner, a sentence containing a predetermined component can be extracted from the accumulated sentences related to the job content, and the sentence can be utilized to generate a sentence related to the job content of the job seeker.

[0134] (9) In the information processing system according to any one of (6) to (8) above, further, in the template candidate generation step, based on the specific sentence, an artificial intelligence module generates a template candidate for the sentence structure, and further, in the question information candidate generation step, the artificial intelligence module generates the question information candidate for generating a sentence related to the job content of the job seeker according to the template candidate.

[0135] (10) In the information processing system according to (9) above, further, in the component extraction step, the artificial intelligence module extracts common components common to the plurality of specific sentences, and in the template candidate generation step, the template candidate including the common components is generated. Information processing system.

[0136] (11) In the information processing system according to (10) above, the common component is information processing system related to at least one of the achievements, skills, qualifications, and appeal points of the job seeker.

[0137] (12) In the information processing system according to any one of (9) to (11) above, in the specific sentence extraction step, the specific sentence is extracted for each industry type or each job type, and in the template candidate generation step, the template candidate is generated for each industry type or each job type. Information processing system.

[0138] (13) In the information processing system according to any one of (9) to (12) above, further, in the storage step, the template candidate vector obtained by vectorizing the template candidate and the question information candidate vector which is the vector of the question information candidate corresponding to the template candidate are associated and stored. Information processing system.

[0139] (14) In the information processing system according to any one of (9) to (13) above, further, in the template extraction step, based on the similarity between the first job seeker information vector obtained by vectorizing the first job seeker information and the template candidate vector obtained by vectorizing the template candidate, a template corresponding to the first job seeker information is extracted, and in the question information extraction step, the question information corresponding to the template is extracted. Information processing system.

[0140] (15) In the information processing system described in (14) above, in the job content generation step, based on the second job seeker information and the template extracted in the template extraction step, the artificial intelligence module generates a text related to the job content of the job seeker. An information processing system.

[0141] (16) In the information processing system described in (15) above, in the job content generation step, using the second job seeker information as an input, the artificial intelligence module generates a text related to the job content of the job seeker. Here, the artificial intelligence module includes a learning model, and the learning model is a large language model or a model trained to take the second job seeker information as an input and output a text related to the job content of the job seeker. The template is input into the learning model as reference information. An information processing system.

[0142] (17) An information processing method comprising each step executed by the information processing system according to any one of (1) to (16) above.

[0143] (18) A program that causes a computer to execute each step of the information processing system according to any one of (1) to (16) above. Of course, this is not all-inclusive. Also, the above-described embodiments and modifications may be arbitrarily combined and implemented.

[0144] Finally, although various embodiments of the present invention have been described, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The embodiments and their modifications are included in the scope and gist of the invention and are also included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0145] 1: Information Processing System 2: Communication Line 10: Server Device 11: Control Unit 111: Reception Unit 112: Memory Control Unit 113: Artificial Intelligence Unit 114: Display Control Unit 115: Extraction Unit 116: Presentation Unit 117: Acquisition Unit 118: Generation Unit 119: Conversion Unit 12: Memory Unit 13: Communication Unit 14: Bus 2: Communication Line 20: Job Seeker Terminal 21: Control Unit 211: User Display Unit 212: Operation Reception Unit 22: Memory Unit 23: Communication Unit 24: Input Unit 25: Output Unit 26: Bus 31: Area 32: Area 33: Area 34: Area 35: Area 36: Area 37: Area 38: Area 39: Area 40: Area A1-1-1: Answer A1-1-2: Answer A1-2-1: Answer A1-2-2: Answer A2-1-1: Answer A2-1-2: Answer A2-2-1: Answer A2-2-2: Answer DB: Vector DB1: Sentence Database DB2: Job Seeker Database G3: Input Screen M1: Artificial Intelligence Module M2: Artificial Intelligence Module M3: Artificial Intelligence Module Q1-1: Question Q1-2: Question Q2-1: Question Q2-2: Question QA1-1: Question Information Candidate QA1-2: Question Information Candidate QA2-1: Question Information Candidate QA2-2: Question Information Candidate QAV1-1: Question Information Vector QAV1-2: Question Information Vector QAV2-1: Question Information Vector QAV2-2: Question Information Vector T1: Template T2: Template TV1: Template Vector TV2: Template Vector U1: Job Seeker

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 receiving step, first job seeker information including information on attributes of the job seeker is received; In the question information extraction step, question information corresponding to the first job seeker information is extracted from the reference information; the question information includes questions for the job seeker and information regarding example answers corresponding to the questions; the reference information includes a plurality of question information candidates that are candidates for the question information, wherein the question information candidates are generated in advance based on accumulated sentences related to job content, and are associated with information on attributes of the job seekers that correspond to the accumulated sentences related to job content that serve as the basis; In the presenting step, the extracted question information is presented to the job seeker; In the acquisition step, an answer to the question information is acquired from the job seeker, In the job content generation step, second job seeker information obtained by adding the answer to the first job seeker information is input, and an artificial intelligence module is used to generate a sentence regarding the job content of the job seeker, The artificial intelligence module includes a job content generation model; The job content generation model is either a large-scale language model or a model trained to generate sentences related to job content from job seeker information; inputting the second job seeker information into the job content generation model, and executing a process of outputting a sentence regarding the job content of the job seeker by the job content generation model; When the job content generation model is the large-scale language model, an information processing system executes a process of inputting an instruction to generate sentences related to the job content of the job seeker based on the second job seeker information and the second job seeker information into the large-scale language model, and outputting the sentences related to the job content of the job seeker using the large-scale language model.

2. 2. The information processing system according to claim 1, Furthermore, in the question information candidate generating step, the question information candidates are generated by the artificial intelligence module based on the accumulated sentences related to the job content, Furthermore, in the conversion step, the generated question information candidates are converted into vectors; An information processing system, wherein the reference information includes the question information candidates and a question information candidate vector that is a vector of the question information candidates.

3. 2. The information processing system according to claim 1, In the question information extraction step, first question information and second question information are extracted, the second question information is extracted from the reference information according to the second job seeker information after the answer to the first question information is obtained.

4. 4. The information processing system according to claim 3, In the question information extraction step, extracting the first question information corresponding to the first job seeker information based on a similarity between a first job seeker information vector obtained by vectorizing the first job seeker information and a question information candidate vector obtained by vectorizing the question information candidate; an information processing system that extracts the second question information corresponding to the second job applicant information based on a similarity between a second job applicant information vector obtained by vectorizing the second job applicant information and the question information candidate vector.

5. 2. The information processing system according to claim 1, Furthermore, in the specific sentence extraction step, specific sentences that satisfy a predetermined condition are extracted from the accumulated sentences related to the job content, In the job content generating step, the artificial intelligence module generates a sentence regarding the job content of the job seeker based on the specific sentence and the second job seeker information.

6. 6. The information processing system according to claim 5, The information processing system, wherein the specified condition includes the number of scouts received being equal to or greater than a specified number.

7. 6. The information processing system according to claim 5, The information processing system, wherein the specified condition includes that a sentence contains a specified component.

8. 6. The information processing system according to claim 5, Furthermore, in the template candidate generating step, a template candidate of a sentence structure is generated by the artificial intelligence module based on the specific sentence, wherein: the artificial intelligence module includes a template candidate generation model; the template candidate generation model is either the large-scale language model or a model trained to generate template candidates from specific sentences; executing a process of inputting the specific sentence into the template candidate generation model and outputting the template candidate from the template candidate generation model; When the template candidate generation model is the large-scale language model, an instruction to generate the template candidate based on the specific sentence and the specific sentence are input to the large-scale language model, and the template candidate is output by the large-scale language model, and processing is executed; Furthermore, in the question information candidate generating step, the artificial intelligence module generates the question information candidates for generating sentences related to the job content of the job seeker corresponding to the template candidates, wherein: The artificial intelligence module includes a question information candidate generation model; the question information candidate generation model is either the large-scale language model or a model trained to generate question information candidates from template candidates; inputting the template candidate into the question information candidate generation model, and executing a process of outputting the question information candidate from the question information candidate generation model; and, when the question information candidate generation model is the large-scale language model, inputting an instruction to generate the question information candidate based on the template candidate and the template candidate into the large-scale language model, and executing a process of outputting the question information candidate from the large-scale language model.

9. 9. The information processing system according to claim 8, Furthermore, in the component extraction step, the artificial intelligence module extracts common components common to a plurality of the specific sentences, the artificial intelligence module includes a component extraction model; the component extraction model is either the large-scale language model or a model trained to extract common components that are common in training job content sentences; A process is executed in which the plurality of specific sentences are input to the component extraction model, and the common components common to the plurality of specific sentences are output by the component extraction model; When the component extraction model is the large-scale language model, an instruction to extract the common components common to the plurality of specific sentences based on the plurality of specific sentences and the plurality of specific sentences are input to the large-scale language model, and a process of outputting the common components by the large-scale language model is executed; In the template candidate generating step, the template candidates including the common components are generated.

10. 10. The information processing system according to claim 9, An information processing system, wherein the component extraction step extracts at least one of the job seeker's achievements, skills, qualifications, and appealing points as the common components.

11. 9. The information processing system according to claim 8, In the specific sentence extraction step, the specific sentence is extracted for each industry or each job type, In the template candidate generating step, the template candidates are generated for each of the business categories or each of the job categories.

12. 9. The information processing system according to claim 8, Furthermore, in the storing step, a template candidate vector obtained by vectorizing the template candidate and a question information candidate vector which is a vector of the question information candidate corresponding to the template candidate are stored in association with each other.

13. 9. The information processing system according to claim 8, Furthermore, in the template extraction step, a template corresponding to the first job applicant information is extracted based on a similarity between a first job applicant information vector obtained by vectorizing the first job applicant information and a template candidate vector obtained by vectorizing the template candidate; In the question information extraction step, the question information corresponding to the template is extracted.

14. 14. The information processing system according to claim 13, an information processing system, in which in the job content generation step, the artificial intelligence module generates text regarding the job content of the job seeker based on the second job seeker information and the template extracted in the template extraction step.

15. 15. The information processing system according to claim 14, An information processing system, wherein in the job content generating step, the template is input to the job content generation model as reference information.

16. 1. An information processing method, comprising: An information processing method comprising the steps executed by the information processing system according to any one of claims 1 to 15.

17. 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 15.

Images