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

Abstract

This involves registering skills using AI that generates them from natural language input, such as speech. [Solution] The information processing system includes: an acquisition unit that acquires speech data including the content of speech spoken by a person to be identified as a skill; a generation unit that generates first instruction information that instructs the system to output information for identifying a skill related to the speech content from among a plurality of predefined skills based on the content of speech included in the speech data; a transmission unit that transmits the speech data and the first instruction information to a generation AI; a receiving unit that receives a first response from the generation AI to the first instruction information; an identification unit that identifies one or more skills from among the plurality of skills based on the information for identifying the skills included in the first response; and a registration unit that associates the identified one or more skills with the person and registers them in a first storage unit.

Description

Technical Field

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

Background Art

[0002] Understanding what skills each individual belonging to an organization such as a company has is also important for realizing the placement of personnel in appropriate positions. It is conceivable to grasp skills by referring to resumes or conducting interviews, etc., but both impose a heavy burden on the parties and are not economical.

[0003] On the other hand, conventionally, a technique for analyzing an input natural language and registering an individual's skills based on skill mapping rules has been disclosed (for example, Patent Document 1).

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, it was not possible to register the skills of a target person using a generative AI from a natural language input by speech or the like.

[0005] The present invention has been made in view of the above points, and an object thereof is to register skills using a generative AI from a natural language input by speech or the like.

Means for Solving the Problems

[0006] To solve the above problems, the information processing system includes: an acquisition unit that acquires speech data including the speech content of a person to be identified as a target for skill identification; a generation unit that generates first instruction information that instructs the system to output information for identifying a skill related to the speech content from among a plurality of predefined skills based on the speech content included in the speech data; a transmission unit that transmits the speech data and the first instruction information to the generation AI; a receiving unit that receives a first response from the generation AI to the first instruction information; an identification unit that identifies one or more skills from among the plurality of skills based on the information for identifying the skills included in the first response; and a registration unit that associates the identified one or more skills with the target person and registers them in a first storage unit. [Effects of the Invention]

[0007] Skills can be registered using AI that generates data from natural language input, such as speech. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the configuration of the information processing system in the first embodiment. [Figure 2] This figure shows an example of the hardware configuration of the information processing device 10 in the first embodiment. [Figure 3] This figure shows an example of the functional configuration of the information processing system in the first embodiment. [Figure 4] This is a flowchart illustrating an example of the processing procedure for identifying the skills of a target person in the first embodiment. [Figure 5] This figure shows an example of the configuration of the determination condition storage unit 121 in the first embodiment. [Figure 6] This figure shows an example of the configuration of the skill list storage unit 122 in the first embodiment. [Figure 7] This figure shows an example of the configuration of the personnel master storage unit 21 in the first embodiment. [Figure 8]This is a flowchart illustrating an example of the processing procedure for updating corresponding information in the first embodiment. [Figure 9] This figure shows an example of the configuration of the determination condition storage unit 121 in the second embodiment. [Figure 10] This figure shows an example of the configuration of the determination condition storage unit 121 in the third embodiment. [Figure 11] This is a diagram illustrating a fourth embodiment. [Figure 12] This figure shows an example of the functional configuration of the information processing system in the fifth embodiment. [Figure 13] This is a flowchart illustrating an example of the processing procedure for the personnel search process in the fifth embodiment. [Figure 14] This figure shows an example of the search criteria input screen. [Figure 15] This figure shows an example of how the search results screen is displayed. [Figure 16] This figure shows an example of the configuration of the information processing system in the sixth embodiment. [Figure 17] This figure shows an example of the functional configuration of the information processing system in the sixth embodiment. [Figure 18] This figure shows an example of the display of the registration inquiry screen in the eighth embodiment. [Figure 19] This figure shows an example of the display of the skill update notification screen in the ninth embodiment. [Figure 20] This figure shows an example of the display of the HR portal screen in the tenth embodiment. [Figure 21] This figure shows an example of the display of the personal information screen in the tenth embodiment. [Figure 22] This figure shows an example of the display of the department information screen in the tenth embodiment. [Figure 23] This figure shows an example of the display of the personal information screen in the tenth embodiment. [Figure 24] This figure shows an example of the functional configuration of the information processing system in the eleventh embodiment. [Figure 25]It is a diagram showing an example of the display of the personal information screen in the 11th embodiment. [Figure 26] It is a diagram showing an example of the display of the department information screen in the 11th embodiment. [Figure 27] It is a diagram showing an example of the display of the personal information screen in the 11th embodiment. [Figure 28] It is a diagram showing an example of the functional configuration of the terminal 40 in the 12th embodiment. [Figure 29] It is a sequence diagram for explaining an example of the processing procedure regarding screen transition in the 12th embodiment.

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described based on the drawings. FIG. 1 is a diagram showing a configuration example of an information processing system in the first embodiment. In FIG. 1, the information processing system includes a personnel server 20, an information processing device 10, an AI server 30, and one or more terminals 40. The terminal 40 is connected to the personnel server 20 and the information processing device 10 via a network such as the Internet or a LAN. The information processing device 10 is connected to the personnel server 20 and the AI server 30 via a network such as the Internet or a LAN.

[0010] The personnel server 20 is one or more computers that manage information (hereinafter referred to as "skill information") indicating what skills each individual belonging to an organization such as a company (hereinafter referred to as "Organization X") has.

[0011] The terminal 40 is a device that uploads (transmits) data that is the extraction source of skill information to the information processing device 10. In the present embodiment, voice data in which the speech of a person (hereinafter simply referred to as the "subject") who identifies skills is recorded is the extraction source of skill information about the subject.

[0012] The information processing device 10 is one or more computers that register skill information about the subject in the personnel server 20 based on voice data received from the terminal 40. The information processing device 10 converts the voice data into text data including the content of the utterances in the voice data (hereinafter referred to as "utterance data"), and identifies the subject's skills related to the voice data from the utterance data. "Subject's skills" refers to the skills that the subject is presumed to possess.

[0013] In this embodiment, we will describe an example where organization X is a company that sells cosmetics, and the target is a cosmetics salesperson. The speech data is text data that shows the content of speech recorded from audio data, such as speeches made by a cosmetics salesperson when serving customers or during internal meetings regarding product explanations. Any method can be used to record the audio data. By automatically registering each salesperson's skill information based on their speech data, the information processing device 10 can efficiently collect skill information for each salesperson, even if organization X has thousands of salespeople nationwide.

[0014] The AI ​​server 30 is one or more computers that have a generating AI. The generating AI is used to identify the skills of a target person from speech data. Note that the AI ​​server 30 does not have to be a component specific to the information processing system. For example, the AI ​​server 30 may be a cloud server that makes the generating AI publicly available.

[0015] Figure 2 shows an example of the hardware configuration of the information processing device 10 in the first embodiment. As shown in Figure 2, the information processing device 10 is built by a computer and includes a CPU 101, ROM 102, RAM 103, HD 104, HDD (Hard Disk Drive) controller 105, display 106, external device connection I / F (Interface) 108, network I / F 109, data bus 110, keyboard 111, pointing device 112, DVD-RW (Digital Versatile Disk Rewritable) drive 114, and media I / F 116.

[0016] Of these, the CPU 101 controls the operation of the entire information processing device 10. The ROM 102 stores programs used to drive the CPU 101, such as IPL. The RAM 103 is used as the work area for the CPU 101. The HD 104 stores various data such as programs. The HDD controller 105 controls the reading or writing of various data to the HD 104 according to the control of the CPU 101. The display 106 displays various information such as cursors, menus, windows, characters, or images. The external device connection I / F 108 is an interface for connecting various external devices. In this case, external devices include, for example, USB (Universal Serial Bus) memory and printers. The network I / F 109 is an interface for data communication using the communication network 100. The data bus 110 is an address bus and data bus, etc., for electrically connecting each component such as the CPU 101 shown in Figure 2.

[0017] The keyboard 111 is a type of input means equipped with multiple keys for inputting characters, numbers, and various instructions. The pointing device 112 is a type of input means for selecting and executing various instructions, selecting processing targets, and moving the cursor. The DVD-RW drive 114 controls the reading or writing of various data to the DVD-RW 113, which is an example of a removable recording medium. Note that it is not limited to DVD-RW, but may also be DVD-R, etc. The media I / F 116 controls the reading or writing (storage) of data to the recording medium 115, such as flash memory.

[0018] Figure 3 shows an example of the functional configuration of the information processing system in the first embodiment. In Figure 3, the AI ​​server 30 has a generating AI 31. The generating AI 31 is a generating AI. A generating AI refers to, for example, a machine learning model (e.g., a neural network) that has acquired the ability to generate various types of content through machine learning. In this embodiment, a machine learning model that can take text as input and generate text corresponding to that text may be used as the generating AI. As an example of such a machine learning model, a large-scale language model (LLM) may be used. An LLM is a machine learning model that has learned natural language processing using a large amount of text data. LLMs are used in many NLP tasks such as generating responses to specific questions, automatic text generation, text summarization, translation, and sentiment analysis. They can also be used in a variety of applications such as education, entertainment, customer service, and product development.

[0019] Machine learning is a technique that enables computers to acquire human-like learning abilities. It refers to a technique in which a computer autonomously generates algorithms necessary for data identification and other judgments from pre-inputted training data, and applies these algorithms to new data to make predictions. The learning method for machine learning can be supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or deep learning, or a combination of these learning methods; there are no restrictions on the learning method used for machine learning.

[0020] The personnel server 20 includes a personnel master storage unit 21 and a skills list storage unit 22. Each of these storage units can be implemented using an auxiliary storage device of the personnel server 20 or a storage device that can be connected to the personnel server 20 via a network.

[0021] The skill list storage unit 22 stores information on a list of predefined skills. This skill list information includes the name of each skill. The skill list storage unit 22 also stores the identification information (hereinafter referred to as "employee ID") of the individual (salesperson) who is determined to possess each of the predefined skills.

[0022] The personnel master memory unit 21 stores information indicating the skills that each salesperson belonging to organization X is determined to possess (identified to that salesperson).

[0023] The information processing device 10 includes an acquisition unit 11, a generation unit 12, a transmission unit 13, a reception unit 14, a specification unit 15, a registration unit 16, and an update unit 17. Each of these units is realized by processing that one or more programs installed in the information processing device 10 cause the CPU 101 to execute. The information processing device 10 also utilizes a judgment condition storage unit 121 and a skill list storage unit 122. Each of these storage units can be realized using, for example, an HD 104 or a storage device that can be connected to the information processing device 10 via a network.

[0024] The acquisition unit 11 acquires speech data from the audio data uploaded from the terminal 40. Acquisition of speech data from the audio data can be performed using known speech recognition technology. Furthermore, if the audio data contains speech from multiple speakers, the acquisition unit 11 may use known speaker separation technology to acquire only the speech data of the target speaker. When collecting the target speaker's speech, a bone conduction microphone or the like may be used to prevent ambient sounds (i.e., speech from speakers other than the target speaker) from being mixed into the same audio data.

[0025] The generation unit 12 generates a first prompt that instructs the generation AI 31 to output information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data acquired by the acquisition unit 11. The first prompt includes the utterance content and information instructing the generation AI 31 to output information for identifying a skill related to the utterance content. In other words, the generation unit 12 generates information that instructs the generation AI 31 to output information for identifying a skill related to the utterance content. In the first embodiment, the generation unit 12 generates the first prompt by referring to the judgment condition storage unit 121. The judgment condition storage unit 121 stores judgment conditions for each of a plurality of predefined skills, for determining whether a subject possesses that skill. In the first embodiment, the judgment condition for each skill consists of one or more terms related to the skill (hereinafter referred to as "tags") and a pass criterion indicating how many or more of those terms must be included in the utterance data. Among the judgment conditions, the information showing the correspondence between a skill and a set of one or more tags is hereinafter referred to as "correspondence information". The generation unit 12 generates a first prompt that instructs the generation unit 12 to extract tags from the set of tags included in the correspondence information (i.e., the set of tags associated with any skill) that contain words in the speech data that have the same or similar meaning as the tag in question. A word that has the same or similar meaning as a tag refers to a string that is identical to the tag in question, or a word that is different as a string from the tag in question but has the same or similar meaning. The criteria for determining semantic identity and similarity depend on the generation AI 31.

[0026] The transmitting unit 13 transmits the prompt (such as the first prompt) generated by the generating unit 12 to the generating AI 31, thereby transmitting information to the generating AI 31 instructing it to output information for identifying the utterance content and the skills related to that utterance content.

[0027] The receiving unit 14 receives a response to the first prompt from the generating AI. The response to the first prompt is hereinafter referred to as the "first response".

[0028] The identification unit 15 identifies one or more skills from among multiple skills, based on information for identifying the skills included in the first response. In this embodiment, the identification unit 15 is an example of an identification unit.

[0029] The registration unit 16 associates one or more skills identified by the identification unit 15 with the target person and registers them in the first storage unit. More specifically, the registration unit 16 associates skill identification information (skill ID described later) that identifies one or more skills and target person identification information (target person ID described later) that identifies the target person and registers them in the first storage unit. In this embodiment, the skill list storage unit 122, the skill list storage unit 22 and the personnel master storage unit 21 are examples of the first storage units. The same information is stored in the skill list storage unit 122 in synchronization with the skill list storage unit 22. The information processing device 10 has a skill list storage unit 122 in order to enable, for example, a high-speed determination (without querying the personnel server 20) of whether or not a skill identified by the identification unit 15 has already been registered for the target person. This is because there is no need to register skills that have already been registered.

[0030] The update unit 17 updates the correspondence information stored in the judgment condition storage unit 121. More specifically, the update unit 17 updates the list of tags corresponding to each skill. This is because the terminology associated with a particular skill may change over time. The correspondence information is updated using the generation AI 31. In this case, the generation unit 12 generates a second prompt that instructs the generation of one or more tags associated with each of the multiple skills, based on one or more document information (hereinafter referred to as "source document information") related to a predefined set of skills and the correspondence information. The transmission unit 13 sends the second prompt to the generation AI 31, and the reception unit 14 receives a second response from the generation AI 31 that received the second prompt. The update unit 17 updates the correspondence information for each of the multiple skills based on the one or more terms included in the second response. In this embodiment, the document information is an example of the latest information.

[0031] Here, the source document information refers to, for example, the latest information on Organization X's own products (new product information, discontinued product information, renewed product information), sales strategy information (target customer information, sales target information, branding information), and the latest trend information in Organization X's business field.

[0032] The following describes the processing procedures performed in the information processing system. Figure 4 is a flowchart illustrating an example of the processing procedure for identifying the skills of a target person in the first embodiment.

[0033] In step S101, the acquisition unit 11 receives the voice data transmitted from the terminal 40 and the employee ID of the subject (hereinafter referred to as "subject ID"). The transmission of the voice data and subject ID from the terminal 40 may be at any time after the recording of the voice data, or it may be while the subject is speaking (in real time).

[0034] Next, the acquisition unit 11 acquires speech data in text format from the received audio data (S102). For example, speech data may be acquired by applying speech recognition to the audio data.

[0035] Next, the generation unit 12 obtains the determination condition from the determination condition storage unit 121 (S103).

[0036] Figure 5 shows an example of the configuration of the judgment condition storage unit 121 in the first embodiment. As shown in Figure 5, the judgment condition storage unit 121 stores judgment conditions, including a skill ID, tag information, and passing criteria, for each predefined skill. The judgment conditions are conditions related to the content of speech that define the criteria by which it can be estimated that the person being judged for a skill possesses that skill. The judgment condition storage unit 121 is also an example of a second storage unit.

[0037] The skill ID is the identification information for a skill. The definition (meaning) of the skill corresponding to the skill ID is stored in the skill list storage unit 122 and the skill list storage unit 22, as described later.

[0038] Tag information is a list of tags (terms) related to the skill associated with the skill ID. Skill-related tags can also be described as terms that are likely to be spoken by someone who possesses that skill. The correspondence between the skill ID and tag information in the judgment criteria is an example of correspondence information.

[0039] The passing criteria are conditions related to the utterance content used to determine whether the user possesses the skill associated with the skill ID. Here, the conditions are set based on the number of unique tags included in the utterance data. For skills marked "N or more," the user is determined to possess that skill if the utterance data contains N or more different types of tags from the list of tags corresponding to that skill.

[0040] Next, the generation unit 12 generates a first prompt (S104) that instructs the system to extract tags from the set of tags included in the correspondence information that constitutes each judgment condition (i.e., the set of tags associated with any of the skills) that contain words in the speech data that have the same or similar meaning as the tag in question. Here, the set of tags included in the correspondence information refers to the set of all tags stored in the tag information column of the judgment condition storage unit 121 (Figure 5), and is an example of information for identifying a skill. For example, the content of the first prompt may be as follows.

[0041] <Example of the first prompt starts here> The following is the speech data.

[0042] {Speech data} The following is a collection of tags.

[0043] {tag information} Extract tags from the set of tags that contain words with the same or similar meanings in the speech data, and output those tags.

[0044] <This is an example of the first prompt.> In the above, {speech data} is the complete text of the speech data. {tag information} is a list of all tags included in the tag information of the corresponding information. According to the first prompt as described above, "tags in the speech data that contain words with the same or similar meaning" are indicated. Therefore, even if a word does not exactly match a tag as a string, if a word with the same or similar meaning as that tag is included in the speech data, that tag will be extracted.

[0045] Next, the transmission unit 13 sends the first prompt generated by the generation unit 12 to the generation AI 31 (S105). When the generation AI 31 receives the first prompt, it outputs text corresponding to the first prompt based on the learned parameters and sends the first response containing the text to the information processing device 10.

[0046] Next, the receiving unit 14 receives the first response (S106).

[0047] Next, the identification unit 15 identifies a skill ID to be registered as a candidate for the subject based on the first response and the judgment conditions (Figure 5) (S107). Specifically, for each skill ID, the identification unit 15 determines whether the set of tags included in the first response satisfies the passing criteria set in the judgment conditions (Figure 5) for that skill ID. For example, for a skill whose skill ID is "1" in Figure 5 (hereinafter referred to as "skill 1," and other skills are identified using the same naming convention), the identification unit 15 determines that the subject has skill 1 if four or more tags from {moisturizing, dry skin, texture, inner dryness} are included in the first response. The identification unit 15 identifies the skill ID of the subject's skills by performing such a determination for all skills. In other words, the identification unit 15 identifies the subject's skills based on information for identifying skills.

[0048] Next, the registration unit 16 refers to the skill list storage unit 122 to identify the skills already registered for the target person (S108).

[0049] Figure 6 shows an example of the configuration of the skill list storage unit 122 in the first embodiment. As shown in Figure 6, the skill list storage unit 122 stores the skill ID, skill name, and owner ID for each predefined skill.

[0050] The skill ID is the identification information for a skill. The skill ID assigned to a skill in the skill list storage unit 122 is the same as the skill ID stored for that skill in the judgment condition storage unit 121 (Figure 5).

[0051] The skill name is the name of the skill. The skill name may be a string that concisely describes the skill's content, or it may simply be an identifier.

[0052] The holder ID is the employee ID of the salesperson who has been determined to possess the skill related to the skill ID.

[0053] Furthermore, the skill list storage unit 22 has the same configuration as in Figure 6 and stores the same data as the skill list storage unit 122.

[0054] The registration unit 16 can identify skills already registered for a target person (hereinafter referred to as "existing skills") by identifying the skill ID in which the target person ID is recorded in the holder ID. However, there may be cases where there are no existing skills, such as when the process in Figure 4 is executed for the target person for the first time.

[0055] Next, the registration unit 16 identifies the set of skill IDs of skills to be registered by excluding the skill IDs of existing skills from the set of skills of the target person that are candidates for registration (the set of skill IDs identified by the identification unit 15) (S109).

[0056] Next, the registration unit 16 performs a registration process to associate the target person with the set of skill IDs to be registered (S110). Specifically, the registration unit 16 adds the target person ID to the "Owner ID" column of the record corresponding to the skill ID to be registered in the skill list storage unit 122 and the skill list storage unit 22. The registration unit 16 also updates the personnel master storage unit 21.

[0057] Figure 7 shows an example of the configuration of the personnel master storage unit 21 in the first embodiment. As shown in Figure 7, the personnel master storage unit 21 stores skill information for each salesperson (individual) belonging to organization X, including the skill ID and skill name of each skill that the salesperson is determined to possess.

[0058] The registration unit 16 registers the skill ID and skill name of the skill to be registered in the personnel master storage unit 21, associating them with the target person ID.

[0059] Next, we will explain how to update the correspondence information that constitutes the judgment conditions (Figure 5).

[0060] Figure 8 is a flowchart illustrating an example of the processing procedure for updating corresponding information in the first embodiment. The processing procedure in Figure 8 is executed, for example, at regular intervals. This regular interval may be, for example, a period during which terminology in the business field of organization X may change. Alternatively, the processing procedure in Figure 8 may be executed in response to user input. The user may be one of the salespeople, or a specific employee of organization X (for example, the administrator of the information processing system).

[0061] In step S201, the generation unit 12 reads the source document information in response to the second prompt generation request from the update unit 17. The contents of the source document information are as described above. The source document information may be stored in advance on, for example, HD104.

[0062] Next, the generation unit 12 reads the corresponding information for all the judgment conditions from the judgment condition storage unit 121 (Figure 5) (S202).

[0063] Next, the generation unit 12 reads the skill name corresponding to each skill ID from the skill list storage unit 122 (Figure 6) (S203).

[0064] Next, the generation unit 12 generates a second prompt based on the information read in steps S201 to S203 (S204). For example, the content of the second prompt may be as follows.

[0065] <Example of the second prompt starts here> Currently, the correspondence between each skill and term is defined as follows:

[0066] {List of correspondences between skill names and tag information} On the other hand, the following information is needed to review the above correspondences.

[0067] {Source Document Information} Based on this information, please review the above correspondences. If, as a result, any skills need to have their correspondences changed, please output the correspondence information between the skill name and the term.

[0068] <This is an example of the second prompt.> In the above, {List of correspondences between skill names and tag information} is text that shows the correspondence between the skill name and the corresponding tag information (list of tags) for each skill. Such text can be generated based on the correspondence between the skill ID and tag information in the correspondence information (Figure 5) and the skill name corresponding to each skill ID obtained from the skill list storage unit (Figure 6). Also, {Extraction source document information} is, for example, text that shows the full text of the extraction source document information.

[0069] Next, the transmission unit 13 sends the second prompt generated by the generation unit 12 to the generation AI 31 (S205). When the generation AI 31 receives the second prompt, it outputs text corresponding to the second prompt based on the learned parameters and sends the second response containing the text to the information processing device 10.

[0070] Next, the receiving unit 14 receives the second response (S206).

[0071] Next, the update unit 17 generates new correspondence information (hereinafter referred to as "modified correspondence information") by modifying the correspondence information stored in the determination condition storage unit 121 (Figure 5) based on the second response (S207). Specifically, according to the second prompt exemplified above, the skill name and modified tag information of the skill whose tag information has been changed are included in the second response. For example, the update unit 17 generates information (i.e., a set of skill ID, current tag information, and modified tag information) as change information, which includes the skill ID corresponding to the skill name included in the second response, the tag information in the current correspondence information related to the skill ID (hereinafter referred to as "current tag information"), and the tag information obtained by changing the current tag information based on the tag information included for the skill name in the second response (hereinafter referred to as "new tag information") (hereinafter referred to as "modified tag information"). Note that change information is generated for each skill name included in the second response.

[0072] For example, the modified tag information may be the result of adding tags included in the new tag information that are not included in the current tag information to the current tag information. Alternatively, the modified tag information may be the result of deleting tags included in the current tag information that are not included in the new tag information from the current tag information. Alternatively, the modified tag information may be the new tag information as is.

[0073] Next, the update unit 17 inquires with the user, such as an administrator, whether or not to allow the current tag information to be updated with the modified tag information (S208). For example, the update unit 17 sends information for inquiring about such permission (hereinafter referred to as "inquiry information") to the user's terminal 40. The inquiry information may be information that inquires about permission for all change information at once, or it may be information that inquires about permission for updating the current tag information to the modified tag information for each change information. The user's terminal 40 displays a screen for inquiring about such permission based on the information. When the user enters permission or denial for the update via the screen, the terminal 40 sends the user's input result to the update unit 17. In this case, if it is possible to select permission or denial for each change information, the terminal 40 may send the current tag information for which the user has permitted the update to the update unit 17.

[0074] If there is change information for which the user has entered permission to update (Yes in S209), the update unit 17 updates (replaces) the current tag information contained in the change information with the changed tag information contained in the change information in the determination condition storage unit 121 (S210). If no input indicating permission to update is given for any of the change information (No in S209), the current tag information is not updated.

[0075] The update unit 17 may forcibly execute step S210 without executing steps S208 and S209. In other words, the update unit 17 may update the current tag information to the modified tag information without inquiring with the user about whether or not to permit the update.

[0076] As described above, according to the first embodiment, the subject's skills can be identified using the generating AI 31 based on the subject's speech data. Here, the speech data is data that represents the content of the subject's natural language utterances. Therefore, skills can be registered using the generating AI from natural language input such as speech.

[0077] While it is conceivable to have subjects self-report their skills through resumes or other means, even if a subject self-reports possessing a certain skill, it is unclear whether the level of that skill is at the level required by the evaluator (organization X). In this embodiment, since the subject's skills are identified based on the content of their actual speech, depending on the definition of the judgment criteria, it is possible to increase the likelihood of more accurately identifying skills compared to self-reporting, while also reducing the workload on the subject.

[0078] Next, a second embodiment will be described. The differences between the second embodiment and the first embodiment will be described. Therefore, points not specifically mentioned may be the same as in the first embodiment.

[0079] In the second embodiment, the configuration of the determination condition storage unit 121 differs from that of the first embodiment. Figure 9 shows an example of the configuration of the determination condition storage unit 121 in the second embodiment.

[0080] As shown in Figure 9, the judgment condition storage unit 121 in the second embodiment stores judgment conditions associated with a skill ID and passing criteria for each predefined skill. In other words, the judgment conditions in the second embodiment do not include tag information. Therefore, in the second embodiment, the passing criteria are not based on tag information, and conditions related to the speech content for determining whether a person possesses the skill related to the skill ID are set in a free form. Free form means any format as long as the content is understandable to the generating AI 31. In the second embodiment, the skill ID is an example of information for identifying a skill.

[0081] In the second embodiment, the processing procedure for registering the subject's skills is the same as in Figure 4. However, in step S103, the generation unit 12 acquires the judgment conditions shown in Figure 9. Subsequently, the generation unit 12 generates a first prompt (S104) that instructs the output of information for identifying the skill related to the utterance content based on the passing criteria for each skill and the utterance content included in the utterance data. Specifically, the generation unit 12 generates a first prompt (S104) that instructs the extraction of the skill ID related to the judgment condition in which the utterance content satisfies the passing criteria among the acquired judgment conditions. For example, the content of the first prompt may be as follows.

[0082] <Example of the first prompt starts here> The following is the speech data.

[0083] {Speech data} The following is a list of evaluation criteria, including skill IDs and passing standards.

[0084] {List of judgment conditions} From the list of evaluation criteria, please extract and output the skill IDs for the evaluation criteria where the speech data meets the passing criteria.

[0085] <This is an example of the first prompt.> In the above, {List of Judgment Criteria} is a text that shows a list of pairs of Skill IDs and passing criteria.

[0086] Next, the transmission unit 13 sends the first prompt generated by the generation unit 12 to the generation AI 31 (S105). When the generation AI 31 receives the first prompt, it outputs text corresponding to the first prompt based on the learned parameters and sends the first response containing the text to the information processing device 10.

[0087] Next, the receiving unit 14 receives the first response (S106). In the second embodiment, the first response includes the skill ID of the skill that the subject has been determined to possess. In other words, in the second embodiment, the generating AI 31 performs the task of identifying the skills that the subject possesses. Therefore, in step S107, the identification unit 15 identifies the skill (skill ID) included in the second response as a skill that the subject possesses. Steps S108 onward may be the same as in the first embodiment. In other words, the identification unit 15 identifies the subject's skills based on information for identifying skills.

[0088] Furthermore, since the determination conditions in the second embodiment do not include correspondence information (association between skills and tag information), updating of the correspondence information is not required. Therefore, the information processing device 10 in the second embodiment does not need to have an update unit 17.

[0089] As described above, according to the second embodiment, the skills of the subject can be identified by different determination criteria than those in the first embodiment. Since the determination criteria in the second embodiment have fewer structural constraints compared to the determination criteria in the first embodiment, it is possible to set determination criteria with a relatively high degree of flexibility.

[0090] Next, a third embodiment will be described. The differences between the third embodiment and the first embodiment will be described. Therefore, points not specifically mentioned may be the same as in the first embodiment.

[0091] In the third embodiment, the configuration of the determination condition storage unit 121 differs from that of the first embodiment. Figure 10 shows an example of the configuration of the determination condition storage unit 121 in the third embodiment.

[0092] As shown in Figure 10, the judgment condition storage unit 121 in the third embodiment stores judgment conditions, including required words, for each predefined skill.

[0093] A required word for a particular skill is a keyword (string of characters) that must be included in the speech data in order to be determined to possess that skill. A required word may be any one of the tag information, or it may be a term different from the tag information.

[0094] In the third embodiment, the processing procedure for registering the subject's skills is the same as in Figure 4. However, in step S103, the generation unit 12 obtains the judgment conditions shown in Figure 9. Subsequently, the generation unit 12 generates a first prompt (S104) that instructs the extraction of tags from the set of tags included in the corresponding information constituting each judgment condition, which are tags that correspond to the skills related to the essential words included in the utterance data and which have a common meaning in the utterance data. For example, the content of the first prompt may be as follows.

[0095] <Example of the first prompt starts here> The following is the speech data.

[0096] {Speech data} The following shows the correspondence between required words and the set of tags.

[0097] {Required keywords and tag information for each skill} Extract tags from the set of tags that correspond to essential words included in the speech data and have the same or similar meaning, and output those tags.

[0098] <This is an example of the first prompt.> In the above, {Required words and tag information for each skill} is a text that shows a list of pairs of skill IDs, required words, and tag information.

[0099] Steps S105 onward are the same as in the first embodiment.

[0100] As described above, according to the third embodiment, in order to determine whether or not a subject possesses a certain skill, it is required that a specific keyword be included in the speech data, and if this requirement is met, it is determined whether or not the subject possesses that skill based on the tag information and the passing criteria. For example, in the case of skill 1 in Figure 10, if "beauty serum" is included in the speech data, the determination is made based on the tag information and the passing criteria. Therefore, by setting a term related to a specific field as a required word, it is possible to avoid being mistakenly determined to possess a skill in that specific field based on speech data related to other fields.

[0101] Next, a fourth embodiment will be described. The differences between the fourth embodiment and the above embodiments will be described. Therefore, points that are not specifically mentioned may be the same as in the above embodiments.

[0102] Figure 11 is a diagram illustrating a fourth embodiment. In the fourth embodiment, a judgment condition storage unit 121, a skill list storage unit 122, and a skill list storage unit 22 (i.e., multiple skills and corresponding information) are defined (prepared) for each attribute possessed by the individual (salesperson) whose skills are to be evaluated. Attributes may be classified (distinguished) by, for example, job type or role (role, position), or by other criteria that may result in different required skills. Figure 11 shows an example where, for each attribute, the judgment condition storage unit 121, the skill list storage unit 122, and the skill list storage unit 22 are defined (prepared), such as when the attributes are a salesperson, a sales manager, a researcher, and a research manager.

[0103] The attributes to which each individual belongs may, for example, be stored in the personnel master memory unit 21 in association with the employee ID. The generation unit 12 and the identification unit 15 may use the judgment condition memory unit 121 corresponding to the attributes to which the target person belongs. The registration unit 16 may use the skill list memory unit 122 and the skill list memory unit 22 corresponding to the attributes to which the target person belongs as the registration targets.

[0104] As described above, according to the fourth embodiment, for example, when the meaning of terms used in the judgment criteria differs depending on the job type, even if the same term is used, the skills of the subject can be identified more accurately.

[0105] Next, a fifth embodiment will be described. The differences between the fifth embodiment and the first embodiment will be described. Therefore, points not specifically mentioned may be the same as in the first embodiment.

[0106] Figure 12 shows an example of the functional configuration of the information processing system in the fifth embodiment. In Figure 12, the same reference numerals are used for parts that are the same as those in Figure 3, and their descriptions are omitted.

[0107] In Figure 12, the information processing device 10 further includes a receiving unit 18 and an output unit 19. Each of these units is realized by processing that one or more programs installed in the information processing device 10 cause the CPU 101 to execute.

[0108] The reception unit 18 accepts search conditions written in natural language.

[0109] The output unit 19 outputs a list of salespeople that match the search criteria. Hereinafter, the process of searching for salespeople that match the search criteria will be referred to as the "personnel search process".

[0110] Figure 13 is a flowchart illustrating an example of the processing procedure for the personnel search process in the fifth embodiment.

[0111] In step S301, the reception unit 18 receives the search conditions entered in the terminal 40 from the terminal 40. The reception unit 18 requests the generation unit 12 to generate a third prompt for the generation AI 31 to execute a search based on the search conditions.

[0112] On terminal 40, for example, search conditions written in natural language may be entered via a search condition input screen 510, as shown in Figure 14. Figure 14 shows an example where the search condition "Who is knowledgeable about dryness countermeasures?" is entered.

[0113] Next, the generation unit 12 executes a process to generate a third prompt in response to a request from the reception unit 18. First, the generation unit 12 obtains skill information for each salesperson from the personnel master storage unit 21 (Figure 7) (S302). Next, the generation unit 12 obtains the corresponding information (skill ID and tag information) included in each judgment condition from the judgment condition storage unit 121 (Figure 5) (S303). Next, the generation unit 12 generates a third prompt, which instructs the system to search for individuals (salespeople) associated with skills that match the search conditions, based on the search conditions, skill information, and corresponding information received by the reception unit 18 (S304). For example, the content of the third prompt may be as follows.

[0114] <Example of the third prompt starts here> Currently, each salesperson possesses the following skills:

[0115] {Skill information for each salesperson} Additionally, the terms associated with each skill ID are as follows:

[0116] {Correspondence Information} Based on the above, please extract and output salespeople who possess the skills that match the following search criteria.

[0117] {search criteria} <This is an example of the third prompt.> In the above, {skill information for each salesperson} is text that shows the skill information (employee ID, skill ID, skill name) obtained in step S302 for each salesperson. {correspondence information} is text that shows the correspondence information obtained in step S303. {search criteria} is text that shows the search criteria.

[0118] Next, the transmission unit 13 sends the third prompt generated by the generation unit 12 to the generation AI 31 (S305). When the generation AI 31 receives the third prompt, it outputs text corresponding to the third prompt based on the learned parameters and sends the third response containing the text to the information processing device 10.

[0119] Next, the receiving unit 14 receives the third response (S306).

[0120] Next, the output unit 19 outputs (sends) the search results included in the third response (i.e., a list of employee IDs that match the search criteria) to the terminal 40 that sent the search criteria (S307). For example, the output unit 19 may display a search results screen 520 on the terminal 40, as shown in Figure 15.

[0121] As described above, according to the fifth embodiment, the user can identify personnel with specific skills by inputting them in natural language. As a result, for example, when allocating personnel (assigning sales staff to each store) or transferring personnel, it is possible to distribute sales staff with specific skills to each store.

[0122] The fifth embodiment may be combined with the third or fourth embodiment.

[0123] Next, a sixth embodiment will be described. The differences between the sixth embodiment and the first embodiment will be described. Therefore, points not specifically mentioned may be the same as in the first embodiment.

[0124] Figure 16 shows an example of the configuration of the information processing system in the sixth embodiment. In Figure 16, the same reference numerals are used for parts that are the same as or corresponding to parts in Figure 1, and their descriptions are omitted.

[0125] As shown in Figure 16, the information processing system in the sixth embodiment does not necessarily have an AI server 30.

[0126] Figure 17 shows an example of the functional configuration of the information processing system in the sixth embodiment. In Figure 17, the same reference numerals are used for parts that are the same as those in Figure 3, and their descriptions are omitted as appropriate.

[0127] In Figure 17, the information processing device 10 further includes a generating AI 31. That is, in the sixth embodiment, the generating AI 31 is located inside the information processing device 10, not outside of it. Therefore, in the sixth embodiment, an external AI server 30 does not need to exist.

[0128] The processing procedure performed in the sixth embodiment may be the same as in the first embodiment.

[0129] The sixth embodiment may be combined with one or more of the second to fifth embodiments.

[0130] Next, a seventh embodiment will be described. The seventh embodiment will be described in terms of how it differs from the first embodiment. Therefore, unless otherwise specified, it may be the same as the first embodiment.

[0131] The seventh embodiment describes an example in which the generating AI 31 is a multimodal AI. For example, although the above embodiments described an example in which the speech data is text data, voice data may be used directly as speech data and input to the generating AI 31. Alternatively, instead of voice data, video data (including audio) of the subject speaking may be used as speech data and input to the generating AI 31. Furthermore, the speech data from the subject does not necessarily have to be data based on the voice spoken by the subject. For example, presentation materials (projected materials) used by the subject in explanations at meetings, the name of the meeting, the date and time of the meeting, the subject's work chat history, invitation information, etc., may be input to the generating AI 31. By inputting multimodal information into the generating AI 31, it is possible to expect an improvement in the accuracy of skill identification.

[0132] Furthermore, when inputting audio or video data to the generating AI 31, the prompt to the generating AI 31 may also include instructions for outputting a numerical value indicating the degree of certainty (likelihood) of the constituent elements (tags or skills) included in the output text from the generating AI 31, according to the way the subject speaks (volume, speed, etc.). Specifically, tags or skills extracted from parts of the speech data that correspond to a speaking style that suggests confidence in the content of the utterance may be assigned a relatively high degree of certainty, while tags or skills extracted from parts that do not correspond to this may be assigned a relatively low degree of certainty. In this case, the personnel master memory unit 21 (Figure 7) may register the degree of certainty for each skill determined to be possessed by each salesperson. The user may specify a threshold for the degree of certainty to identify salespeople who possess a particular skill.

[0133] Next, an eighth embodiment will be described. The eighth embodiment will be described in terms of its differences from the above embodiments. Therefore, unless otherwise specified, it may be the same as in the above embodiments.

[0134] Following step S109 in Figure 4, the registration unit 16 indicates the skills to be registered to the subject and sends information to the subject's terminal 40 to inquire whether registration of those skills is necessary.

[0135] The user's device 40 displays a screen (hereinafter referred to as the "registration inquiry screen") to inquire with the user whether or not they need to register their skills, based on the information provided.

[0136] Figure 18 shows an example of the display of the registration inquiry screen in the eighth embodiment. As shown in Figure 18, the registration inquiry screen 530 includes a message 531 and buttons 532 to 534. Message 531 includes information such as that there is a newly acquired skill that meets the passing criteria, the name of the skill, and a recommendation to register the skill as a skill possessed by the user.

[0137] Button 532 is for receiving instructions to register the skill. Button 533 is for receiving instructions not to register the skill. Button 534 is for receiving instructions to display the detailed information of the skill.

[0138] When the user presses any of the buttons 532 to 534, the terminal 40 sends information corresponding to the pressed button to the registration unit 16. If the information is an instruction to register a skill, the registration unit 16 executes step S110. If the information is an instruction not to register a skill, the registration unit 16 does not execute step S110. If the information is an instruction to display detailed information about a skill, the registration unit 16 sends detailed information about the skill to be registered to the user's terminal 40. This detailed information is stored for each skill, for example, in the skill list storage unit 122 and the skill list storage unit 22.

[0139] As described above, according to the eighth embodiment, before the registration of the subject's possession of automatically identified skills is made, the subject is asked whether or not registration of those skills is necessary. Therefore, the subject's own awareness (such as their awareness of possessing those skills) can be reflected in the skill list storage unit 122 and the skill list storage unit 22, as well as the personnel master storage unit 21.

[0140] Furthermore, the user can be aware of which skills are registered as their own.

[0141] Next, the ninth embodiment will be described. The differences between the ninth embodiment and the first to seventh embodiments will be described. Therefore, points not specifically mentioned may be the same as those in the first to seventh embodiments.

[0142] Following step S110 in Figure 4, the registration unit 16 reads from the skill list storage unit 122 a list of skills associated with the subject (skills possessed by the subject), skill update information including information indicating skills newly associated with the subject in step S110, and the subject's career information, and notifies the subject's terminal 40. The subject's career information refers to information indicating the subject's work activities (e.g., sales activities) within organization X. For example, career information is stored in the personnel master storage unit 21 for each salesperson belonging to organization X.

[0143] The user's terminal 40 displays a screen (hereinafter referred to as the "skill update notification screen") to notify the user of updates to their skills, based on the skill information notified from the registration unit 16.

[0144] Figure 19 shows an example of the display of the owned skills update notification screen in the ninth embodiment. As shown in Figure 19, the owned skills update notification screen 540 includes area 541, area 542, and button 543.

[0145] Area 541 is the area containing the list of skills among the skill update information. Skills included in Area 5411 within Area 541 correspond to newly registered skills. Area 542 is the area containing the subject's career information. Button 543 is a button for receiving instructions to edit the subject's possessed skills (association of subject and skills in Skill List Storage Unit 122, Skill List Storage Unit 22, and Personnel Master Storage Unit 21) or the subject's career information. When button 543 is pressed, the editing screen for possessed skills and career information is displayed. The subject can edit their possessed skills or career information through this editing screen.

[0146] As described above, according to the ninth embodiment, the subject can be notified that their skills have been automatically updated.

[0147] Furthermore, the ninth embodiment may be combined with the eighth embodiment. For example, the owned skill update notification screen 540 may be displayed when button 532 on the registration inquiry screen 530 is pressed. In this case, the owned skill update notification screen 540 will serve to notify the user that their owned skills have indeed been updated following the press of button 532 on the registration inquiry screen 530.

[0148] Next, the tenth embodiment will be described. The differences between the tenth embodiment and the fifth embodiment will be described. Therefore, points not specifically mentioned may be the same as those in the fifth embodiment.

[0149] In the tenth embodiment, terminal 40 displays the personnel portal screen in response to a predetermined operation by the user before step S301 in Figure 13.

[0150] Figure 20 shows an example of the display of the HR portal screen in the tenth embodiment. The HR portal screen 550 is a screen that serves as a portal for services provided by the information processing device 10, and includes buttons 551 to 553.

[0151] For example, the HR portal screen 550 is displayed on the terminal 40 in response to a user logging into the information processing device 10. Therefore, at the time the HR portal screen 550 is displayed, the employee ID of the user on terminal 40 (hereinafter referred to as the "logged-in user") is identified by the information processing device 10.

[0152] When button 551 is pressed, terminal 40 displays the search criteria input screen 510 (Figure 14). In this case, the processing procedure described in Figure 13 is executed in response to the input of search criteria on the search criteria input screen 510.

[0153] When button 552 is pressed, terminal 40 sends a request to information processing device 10 to retrieve the personal information of the logged-in user. When the receiving unit 18 of the information processing device 10 receives the retrieval request, the output unit 19 retrieves skill list information, which shows a list of skills associated with the employee ID of the logged-in user, and the logged-in user's career information from the personnel master storage unit 21. In the tenth embodiment as well, career information for each salesperson belonging to organization X is stored in the personnel master storage unit 21. The output unit 19 sends the skill list information and career information to terminal 40. Terminal 40 displays a personal information screen that includes the skill list information and career information.

[0154] Figure 21 shows an example of the display of the personal information screen in the tenth embodiment. As shown in Figure 21, the personal information screen 560a includes area 561, area 562, and button 563. Area 561 is an area containing the logged-in user's skill list information. Area 562 is an area containing the logged-in user's career information. Button 563 is a button for receiving instructions to edit the logged-in user's owned skills (association of logged-in users with skills in the skill list storage unit 122, skill list storage unit 22, and personnel master storage unit 21) or the logged-in user's career information. When button 563 is pressed, the editing screen for owned skills and career information is displayed. The logged-in user can edit owned skills or career information through this editing screen. The edited results are stored in the skill list storage unit 122, skill list storage unit 22, personnel master storage unit 21, etc.

[0155] When button 553 is pressed on the HR portal screen 550, terminal 40 sends a request to information processing device 10 to acquire skill information for the department to which the logged-in user belongs (hereinafter referred to as the "target department"). When the receiving unit 18 of the information processing device 10 receives the acquisition request, the output unit 19 acquires skill list information from the HR master storage unit 21, showing a list of skills associated with each salesperson belonging to the target department. In the tenth embodiment, the HR master storage unit 21 stores information indicating the department and team to which each salesperson belongs. A team is a group composed of some employees within a department. Therefore, by referring to the HR master storage unit 21, the target department and each salesperson belonging to the target department can be identified. The output unit 19 sends the acquired information to terminal 40. Terminal 40 displays a department information screen containing the acquired information.

[0156] Figure 22 shows an example of the display of the department information screen in the tenth embodiment. As shown in Figure 22, the department information screen 570a includes a radar chart 571 and a table 572.

[0157] The radar chart 571 is a radar chart in which skill categories are assigned to each axis, and graph g1 corresponding to the target department and graph g2 corresponding to the entire organization X are drawn. A skill category is a category for skills stored in the skill list storage unit 122 (Figure 6). One or more skills belong to one skill category. Information indicating which skill each skill belongs to may be stored in the skill list storage unit 122 or in another storage unit.

[0158] The value of graph g1 on a certain axis of the radar chart 571 represents the percentage of salespeople in the target department who possess skills belonging to the skill category corresponding to that axis. Alternatively, points may be calculated for each salesperson belonging to the target department according to the skills they possess, and the average value of each salesperson's points for each skill category may be used as the value of graph g1. The value of graph g2 on a certain axis of the radar chart 571 represents the percentage of salespeople in organization X who possess skills belonging to the skill category corresponding to that axis. However, other indicators may be assigned to each axis of the radar chart 571. The output unit 19 of the information processing device 10 calculates the values ​​of each axis of graphs g1 and g2 by referring to the skill list storage unit 122 (Figure 6) and generates the radar chart 571. The output unit 19 transmits the radar chart 571 along with the skill list information for each salesperson belonging to the target department to the terminal 40. As a result, the terminal 40 can display the radar chart 571. Furthermore, the items assigned to each axis of the radar chart 571 are not limited to skill categories. For example, other items such as the rate of women's participation or work experience may also be assigned.

[0159] Table 572 contains the names, skill lists, and team affiliations of each salesperson in the target department. In Table 572, each salesperson's name is linked to their personal information.

[0160] When a user clicks on any name in table 572, terminal 40 sends a request to information processing device 10 to retrieve personal information, including the employee ID of the salesperson associated with that name (hereinafter referred to as the "target salesperson"). When the receiving unit 18 of the information processing device 10 receives the retrieval request, the output unit 19 retrieves skill list information showing a list of skills associated with the employee ID and career information associated with the employee ID from the personnel master storage unit 21. The output unit 19 sends the skill list information and career information to terminal 40. Terminal 40 displays a personal information screen including the skill list information and career information.

[0161] Figure 23 shows an example of the display of the personal information screen in the tenth embodiment. As shown in Figure 23, the personal information screen 580a includes areas 581 and 582. Area 581 is an area containing the skill list information of the target salesperson. Area 582 is an area containing the career information of the target salesperson.

[0162] Users can refer to the personal information screen 580a to check the skills and other information of the salesperson in question.

[0163] Furthermore, on the HR portal screen 550 (Figure 20), button 533 may be limited to being pressable only by employees in management positions. In this case, the department information screen 570a and the personal information screen 580a can be displayed only if the user is in a management position.

[0164] As described above, according to the tenth embodiment, it is possible to check the salespersons who possess specific skills, their own skill information, and the department's skill information from the HR portal screen 550 (Figure 20). Therefore, the burden of operations required to check this information can be reduced.

[0165] Next, the eleventh embodiment will be described. The differences between the eleventh embodiment and the tenth embodiment will be described. Therefore, points not specifically mentioned may be the same as those of the tenth embodiment.

[0166] Figure 24 shows an example of the functional configuration of the information processing system in the eleventh embodiment. In Figure 24, the same reference numerals are used for parts that are the same as those in Figure 12, and their descriptions are omitted.

[0167] In Figure 24, the information processing device 10 further includes an estimation unit 131. The estimation unit 131 is realized by a process that one or more programs installed on the information processing device 10 cause the CPU 101 to execute.

[0168] In the eleventh embodiment, terminal 40 uploads data based on the subject's biometric information for the period corresponding to the voice data to information processing device 10. The acquisition unit 11 of the information processing device 10 acquires the data. The estimation unit 131 estimates the subject's well-being level based on the data. Well-being level is a numerical value indicating the degree of well-being. Well-being refers to being in a good physical, mental, and social state. Therefore, well-being level is a numerical value indicating the degree of a good physical, mental, and social state.

[0169] The data based on the subject's biometric information during the period corresponding to the audio data is, for example, data indicating the subject's emotions (hereinafter referred to as "emotional data") estimated based on the subject's biometric information during the period from the start time to the end time of the audio data (hereinafter referred to as the "target period").

[0170] The subject's biological information during the target period can be measured using a vital sensor (biosensor). For example, with Ecomoai (registered trademark) (https: / / www.fcl-components.com / products / sensors / viral-sensor.html), biological information (pulse information) can be measured and emotional data such as "concentration level," "sleepiness level (boredom, laziness)," "activity level (tension, energy)," and "fatigue level" can be generated in time series. Terminal 40 uploads this time-series emotional data to the information processing device 10 as data based on biological information. Alternatively, Terminal 40 may upload data containing time-series biological information measured by other vital sensors (hereinafter referred to as "biological data") to the information processing device 10 as data based on biological information. Emotional data or biological information is uploaded together with the audio data. Alternatively, emotional data or biological data may be uploaded separately from the audio data.

[0171] The estimation unit 131 estimates emotion data from biometric data when biometric data is uploaded. The estimation of emotion data from biometric data can be performed using publicly known techniques.

[0172] Machine learning can be used to estimate the degree of well-being based on emotional data by the estimation unit 131. A machine learning model (e.g., a neural network) that takes emotional data as input and outputs the degree of well-being is trained using training data. The training data is a pair of emotional data as input data and the degree of well-being as the correct label (correct value) for the output. The input data may also include information such as the average working hours and the skills possessed. The machine learning model can be trained by updating the learning parameters of the machine learning model so that the output from the machine learning model, which is input with the input data of the training data, approaches the correct label of the training data. The estimation unit 131 inputs the subject's emotional data, etc., into the trained machine learning model and obtains the output from the machine learning model as the subject's degree of well-being. Alternatively, the estimation unit 131 may instruct the generating AI 31 to estimate the degree of well-being based on emotional data. In this case, the estimation unit 131 obtains the degree of well-being from the response from the generating AI 31. Alternatively, the estimation unit 131 may calculate the well-being level from the emotional data using other known methods.

[0173] The registration unit 16 associates the emotional data and the well-being score estimated by the estimation unit 131 from the emotional data with the target person and registers them in the personnel master memory unit 21. In other words, in the eleventh embodiment, the personnel master memory unit 21 further stores the history of emotional data and well-being score for each salesperson. The history of emotional data and well-being score refers to the history of uploaded (or estimated from biometric information) emotional data and the history of well-being score estimated based on each emotional data.

[0174] In the 11th embodiment, the configuration of the personal information screen displayed when button 552 is pressed and the configuration of the department information screen displayed when button 553 is pressed on the personnel portal screen 550 (Figure 20) differ from those of the 10th embodiment.

[0175] Figure 25 shows an example of the display of the personal information screen in the eleventh embodiment. In Figure 25, the same reference numerals are used for parts that are the same as in Figure 21, and their descriptions are omitted.

[0176] As shown in Figure 25, the personal information screen 560b includes area 564 instead of area 562. Area 564 includes the subject's latest well-being percentage and the emotional information for the most recent K times (2 times in the example in Figure 25). The emotional information displayed in area 546 shows the percentage of the most dominant emotion during the period in the time-series emotional data for the period. However, emotional information may be represented in other ways. To enable such a display, the output unit 19 obtains the subject's well-being percentage and emotional data history from the personnel master storage unit 21, rather than career information, and transmits it to the terminal 40.

[0177] Figure 26 shows an example of the display of the department information screen in the eleventh embodiment. In Figure 26, the same reference numerals are used for parts that are the same as in Figure 22, and their descriptions are omitted. As shown in Figure 26, the department information screen 570b further includes a radar chart 573. It also includes a table 574 instead of a table 572.

[0178] The radar chart 573 is a radar chart in which well-being levels or emotional data (concentration level, fatigue level, drowsiness level, activity level) are assigned to each axis, and graph g3 corresponding to the target department and graph g4 corresponding to the entire organization X are drawn. The value of graph g3 for a certain axis of radar chart 573 is the average value of the corresponding value for that axis stored in the personnel master storage unit 21 for each salesperson belonging to the target department. The value of graph g4 for a certain axis of radar chart 573 is the average value of the corresponding value for that axis stored in the personnel master storage unit 21 for each salesperson belonging to organization X.

[0179] Table 574 contains the names, skill lists, and well-being scores of each salesperson in the target department. In Table 574, each salesperson's name is linked to their personal information. Therefore, when any name is clicked, the personal information screen for that salesperson is displayed on terminal 40.

[0180] Figure 27 shows an example of the display of the personal information screen in the eleventh embodiment. In Figure 27, the same reference numerals are used for parts identical to those in Figure 23, and their descriptions are omitted. As shown in Figure 27, the personal information screen 580a includes area 583 instead of area 582. Area 583 contains the same information as the personal information screen 564b with respect to the target salesperson.

[0181] As described above, according to the 11th embodiment, it is possible to check not only employee skills but also information on well-being. Furthermore, information on well-being (well-being level) can be included in personnel information, not just information on skills. In the prior art, managing information on employee skills and well-being in a single system was not considered. The purpose of this embodiment is to visualize information on skills and well-being. It also aims to centrally manage information on skills and well-being.

[0182] Next, the twelfth embodiment will be described. The twelfth embodiment will describe the differences (or points not explicitly described) from the tenth or eleventh embodiment. Therefore, points not specifically mentioned may be the same as those in the tenth or eleventh embodiment.

[0183] In the twelfth embodiment, we will describe an example in which the terminal 40 displays various screens using a web browser 41, and the information processing device 10 functions as a web server that executes web applications.

[0184] Figure 28 shows an example of the functional configuration of terminal 40 in the twelfth embodiment. In Figure 28, terminal 40 has a web browser 41. The web browser 41 is a general web browser and includes a browser engine 411, a scripting engine 412, and a network engine 413.

[0185] Browser engine 411 interprets HTML (HyperText Markup Language) data and CSS (Cascading Style Sheets) data that make up a web page and displays the web page.

[0186] Script engine 412 executes scripts that make up a web page (for example, JavaScript®).

[0187] The network engine 413 sends HTTP requests and receives HTTP responses.

[0188] Figure 29 is a sequence diagram illustrating an example of a screen transition process in the twelfth embodiment. The sequence diagram in Figure 29 shows the initial state where the HR portal screen 550 (Figure 20) is displayed on terminal 40, and illustrates the process of screen transitions from the HR portal screen 550.

[0189] When a user clicks any button on the HR portal screen 550 (S401), the browser engine 411 inputs the URL associated with that button into the network engine 413 (S402). The network engine 413 then sends an HTTP request to that URL (S403).

[0190] The output unit 19 of the information processing device 10 generates an HTTP response in response to the HTTP request, which includes Web content data (HTML data, CSS data, and scripts (hereinafter referred to as "JS")) corresponding to the URL to which the HTTP request is headed (S403). The Web content is Web content for displaying two Web pages, a Web page which is the first screen and a Web page which is the second screen. The JS also includes a first JS that performs processing in response to operations on the first screen and a second JS that performs table processing on the second screen.

[0191] If button 551 is pressed in step S401, the search criteria input screen 510 (Figure 14) is the first screen, and the search results screen 520 (Figure 15) is the second screen. If button 553 is pressed, the department information screen 570a (Figure 22) or department information screen 570b (Figure 26) is the first screen, and the personal information screen 580a (Figure 23) or personal information screen 580b (Figure 27) is the second screen.

[0192] Next, the output unit 19 sends the HTTP response generated in step S404 to the terminal 40 (S405).

[0193] When the network engine 413 of terminal 40 receives the HTTP response, it inputs the HTML data, CSS data, and JS contained in the HTTP response into the browser engine 411 (S406). The browser engine 411 inputs the JS input from the network engine 413 into the script engine 412 (S407). The script engine 412 loads the JS (S408) and requests the browser engine 411 to update the screen (S409). The screen update includes displaying a new screen.

[0194] Here, the HTTP response generated in step S404 may contain the filename of the JS file rather than the actual JS file itself. In this case, in step S408, the script engine 412 accesses the external file based on the filename and downloads the JS file. This method is a method of loading the JS file as an external file.

[0195] Next, the browser engine 411 displays the first screen based on the HTML data and CSS data (S410).

[0196] When a user performs a predetermined operation on the first screen (S411), the browser engine 411 notifies the script engine 412 of the execution of the predetermined operation and the input data associated with the predetermined operation (S412).

[0197] If the first screen is the search criteria input screen 510 (Figure 14), then inputting search criteria constitutes the execution of a predetermined operation, and the search criteria are the input data. If the first screen is the department information screen 570a (Figure 22) or the department information screen 570b (Figure 26), then clicking on any name in table 572 or table 524 constitutes the execution of a predetermined operation, and the employee ID corresponding to the clicked name is the input data.

[0198] The script engine 412, in response to a notification from the browser engine 411, executes the first JS (S413) and inputs a request to send an HTTP request and input data corresponding to the predetermined operation to the network engine 413 (S414). The network engine 413 sends the HTTP request, including the input data, to the information processing device 10 (S415).

[0199] When the reception unit 18 of the information processing device 10 receives the HTTP request, the information processing device 10 executes the processing requested by the HTTP request (S416). If the first screen is the search condition input screen 510 (Figure 14), steps S302 to S306 in Figure 13 are executed. If the first screen is the department information screen 570a (Figure 22), the information processing device 10 obtains from the personnel master storage unit 21 a list of skills information showing a list of skills associated with the employee ID included in the HTTP request (the employee ID of the target salesperson whose name was clicked in table 572), and career information associated with that employee ID. If the first screen is the department information screen 570b (Figure 26), the information processing device 10 obtains from the personnel master storage unit 21 a list of skills information showing a list of skills associated with the employee ID included in the HTTP request (the employee ID of the target salesperson whose name was clicked in table 574), the latest well-being score (%) associated with that employee ID, and the most recent K emotion data.

[0200] Next, the output unit 19 generates an HTTP response containing JSON (JavaScript® Object Notation) describing the data obtained from the processing result (hereinafter simply referred to as "processing result") (S417). Subsequently, the output unit 19 sends the HTTP response to the terminal 40 (S418).

[0201] When the network engine 413 of terminal 40 receives the HTTP response, it inputs the JSON contained in the HTTP response into the script engine 412 (S419). The script engine 412 executes a second JS (S420) and requests the browser engine 411 to update the display content of the web page based on the JSON (S421). The browser engine 411 displays a second screen (search results screen 520 (Figure 15), personal information screen 580a (Figure 23), or personal information screen 580b (Figure 27)) based on the HTML data and CSS data obtained in step S406 and the JSON (S422).

[0202] As described above, in the twelfth embodiment, the first screen and the second screen, and the execution of processing in response to operations on each of these screens, are realized by a single-page application. Specifically, when displaying the first screen, the terminal 40 is delivered not just Web content data for displaying the first screen, but Web content data for displaying both the first and second screens, including JavaScript that executes processing such as screen transitions in response to operations on the first screen. Therefore, since the screen transition from the first screen to the second screen is executed by JavaScript, the terminal 40 does not need to download the Web content data for the second screen. As a result, it is possible to solve technical issues such as improving the display speed of the second screen and reducing the communication load during screen transitions.

[0203] In the above example, Organization X is a company that sells cosmetics, and the skills of each salesperson were identified. However, the technology of this embodiment can be applied to other fields as long as skills can be estimated from conversation. In other words, the technology of this embodiment may be applied to other fields as long as the skills of the subject can be identified based on the content of their speech when they communicate something to others.

[0204] For example, a business designer's skills (presentation skills, facilitation skills, planning ability, proficiency in AI, etc.) may be identified based on the content of their speech. Similarly, a teacher's skills (whether they can recite the open lesson scenario, whether they can teach the teaching materials and units, etc.) may be identified based on the content of their speech during a lesson. Furthermore, a construction site supervisor's skills may be identified based on the content of their speech at the construction site. In fields where the skills required may change depending on the site, such as for a construction site supervisor, location information corresponding to the site may be associated with each judgment condition in the judgment condition storage unit 121. In this case, the subject's skills may be identified using judgment conditions corresponding to the location where the subject (site supervisor) made their speech.

[0205] In any field, the skills identified for each target group may be used in their respective training programs. For example, a certification system based on the skills possessed may be established.

[0206] Furthermore, skills are not limited to those required for specific tasks, but may also be defined in terms of personality, character, and general job performance abilities (such as time management skills). Time management skills may be estimated from the length of the audio data.

[0207] Furthermore, speech data, which records the content of utterances, may be used for purposes other than skill identification. For example, it may be used as evidence that a certain matter was spoken.

[0208] Furthermore, the information processing device 10 is not limited to a general-purpose server computer, as long as it is a device equipped with information processing functions. The information processing device 10 may be, for example, an output device such as a PJ (Projector), IWB (Interactive White Board: an electronic whiteboard with the ability to communicate with each other), or digital signage, a HUD (Head Up Display) device, industrial machinery, imaging devices, sound collection devices, medical equipment, networked home appliances, a notebook PC (Personal Computer), a mobile phone, a smartphone, a tablet device, a game console, a PDA (Personal Digital Assistant), a digital camera, a wearable PC, or a desktop PC.

[0209] Furthermore, each function of each embodiment can be realized by one or more processing circuits. Hereinafter, "processing circuit" as used herein includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), FPGAs (field programmable gate arrays), and conventional circuit modules designed to execute the functions described above.

[0210] Furthermore, the apparatus of each embodiment represents only one of several computing environments for carrying out the embodiments disclosed herein.

[0211] In one embodiment, the information processing device 10 includes a plurality of computing devices, such as a server cluster. The plurality of computing devices are configured to communicate with each other via any type of communication link, including a network or shared memory, and perform the processing disclosed herein. Similarly, the personnel server 20 may include a plurality of computing devices configured to communicate with each other.

[0212] Although embodiments of the present invention have been described in detail above, the present invention is not limited to these specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention as described in the claims.

[0213] Examples of the present invention are as follows:

[0214] <1> An acquisition unit that acquires speech data including the content of speech spoken by the target person for skill identification, A generation unit generates first instruction information that instructs the output of information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data. A transmission unit that transmits the aforementioned speech data and the first instruction information to a generating AI, A receiving unit that receives a first response to the first instruction information from the generating AI, An identification unit identifies one or more skills from among the plurality of skills, based on information for identifying the skills included in the first response, A registration unit that associates the identified one or more skills with the subject and registers them in a first memory unit, An information processing system characterized by having the following features.

[0215] <2> Each of the aforementioned multiple skills has a second memory unit that stores correspondence information with one or more related terms, The generation unit generates, as the first instruction information which instructs the output of information for identifying skills related to the utterance content, the instruction to extract from the set of terms included in the correspondence information the term whose meaning is the same as or similar to the term included in the utterance data. Characterized by <1> The information processing system described above.

[0216] <3> The generation unit further generates a second prompt that instructs the generation of one or more terms related to each of the multiple skills, based on one or more latest information related to the multiple skills and the corresponding information. The transmitting unit further transmits the second prompt to the generating AI, The receiving unit further receives a second response from the generating AI that has input the second prompt, An update unit updates the corresponding information for each of the multiple skills based on the one or more terms included in the second response. Having, Characterized by <2> The information processing system described above.

[0217] <4> The generation unit generates, as the first instruction information, an instruction that instructs the output of information for identifying the skill related to the utterance content, based on the conditions related to the utterance content for determining whether a person possesses the skill, which are set for each of the plurality of skills, and the utterance content included in the utterance data. Characterized by <1> The information processing system described above.

[0218] <5> For each attribute possessed by the aforementioned subject, the multiple skills and corresponding information are defined in advance. The generation unit and the identification unit use the corresponding information that corresponds to the attribute to which the target person belongs. Characterized by <2> or <3> The information processing system described above.

[0219] <6> The second memory unit stores keywords associated with the corresponding information for each skill, The generation unit generates, as the first instruction information, instruction information that instructs the extraction of terms from the set of terms included in the correspondence information that correspond to the skills related to the keywords included in the utterance data, and that have a common meaning with the words included in the utterance data. Characterized by <2> or <3> The information processing system described above.

[0220] <7> The update unit updates the corresponding information when the user provides input indicating permission to update the corresponding information. Characterized by <3> The information processing system described above.

[0221] <8> It has a reception section that accepts search conditions written in natural language, The generation unit further generates a third prompt that instructs the search to search for individuals associated with skills that match the search conditions, based on the search conditions and the information stored in the first storage unit. The transmitting unit further transmits the third prompt to the generating AI, The receiving unit further receives a third response from the generating AI that has received the third prompt, The device has an output unit that outputs the search result indicated by the third response, Characterized by <1> ~ <7> The information processing system described in any of the following.

[0222] <9> The registration unit registers in the storage unit skill identification information that identifies one or more skills and subject identification information that identifies the subject, in association with each other. Characterized by <1> ~ <8> The information processing system described in any of the following.

[0223] <10> The generation unit generates a first prompt which includes the first instruction information that instructs the output of information for identifying skills related to the utterance content, and the utterance data. The transmitting unit transmits the first instruction information and the speech data to the generating AI by transmitting the generated first prompt to the generating AI. Characterized by <1> ~ <9> The information processing system described in any of the following.

[0224] <11> An acquisition unit that acquires speech data including the content of speech spoken by the target person for skill identification, A generation unit generates first instruction information that instructs the output of information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data. A transmission unit that transmits the aforementioned speech data and the first instruction information to a generating AI, A receiving unit that receives a first response to the first instruction information from the generating AI, An identification unit identifies one or more skills from among the plurality of skills, based on information for identifying the skills included in the first response, A registration unit that associates the identified one or more skills with the subject and registers them in a first memory unit, An information processing device characterized by having the following features.

[0225] <12> A procedure for acquiring speech data that includes the content of the speech of the person whose skills are to be identified, A generation procedure that generates a first prompt that instructs the output of information for identifying a skill related to the utterance content from among a predefined group of skills, based on the utterance content contained in the utterance data, A transmission procedure for sending the aforementioned first prompt to the generating AI, A receiving procedure for receiving a first response from the generating AI that has entered the first prompt, A receiving procedure for receiving a first response to the first instruction information from the generating AI, An identification procedure for identifying one or more skills from among the aforementioned multiple skills based on information for identifying the skills included in the first response, A registration procedure for associating the identified one or more skills with the subject and registering them in the first memory unit, An information processing method characterized by a computer executing the following.

[0226] <13> A procedure for acquiring speech data that includes the content of the speech of the person whose skills are to be identified, A generation procedure that generates a first prompt that instructs the output of information for identifying a skill related to the utterance content from among a predefined group of skills, based on the utterance content contained in the utterance data, A transmission procedure for sending the aforementioned first prompt to the generating AI, A receiving procedure for receiving a first response to the first instruction information from the generating AI, A receiving procedure for receiving a first response to the first prompt from the generating AI, An identification procedure for identifying one or more skills from among the aforementioned multiple skills based on information for identifying the skills included in the first response, A registration procedure for associating the identified one or more skills with the subject and registering them in the first memory unit, A program that causes a computer to execute something.

[0227] <14> The acquisition unit acquires data based on the subject's biometric information during the period corresponding to the speech data. Based on the aforementioned data, an estimation unit 131 estimates the degree of well-being of the subject. It has, The registration unit associates the estimated well-being level with the subject and registers it in the first storage unit. Characterized by <1> The information processing system described above. [Explanation of symbols]

[0228] 10 Information Processing Devices 11 Acquisition Department 12 Generation part 13 Transmitter 14 Receiving Unit 15 Specific section 16 Registration Department 17 Update section 18 Reception Department 19 Output section 20 HR Server 21. Human Resources Master Memory Unit 22 Skill List Memory 30 AI Servers 31 Generation AI 40 devices 41 Web Browsers 121 Judgment condition storage section 122 Skill List Memory 131 Estimation Department 411 Browser Engines 412 Script Engine 413 Network Engine [Prior art documents] [Patent Documents]

[0229] [Patent Document 1] International Publication No. 2005 / 010789

Claims

1. An acquisition unit that acquires speech data including the content of the speech of the person whose skill is to be identified, A generation unit generates first instruction information that instructs the output of information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data. A transmission unit that transmits the aforementioned speech data and the first instruction information to the generating AI, A receiving unit that receives a first response to the first instruction information from the generating AI, An identification unit identifies one or more skills from among the plurality of skills, based on information for identifying the skills included in the first response, A registration unit that associates the identified one or more skills with the subject and registers them in a first memory unit, An information processing system characterized by having the following features.

2. Each of the aforementioned multiple skills has a second memory unit that stores correspondence information with one or more related terms, The generation unit generates, as the first instruction information for outputting information to identify skills related to the utterance content, instruction information for extracting from the set of terms included in the correspondence information the terms that are identical or similar in meaning to the term included in the utterance data. The information processing system according to feature 1.

3. The generation unit further generates a second prompt that instructs the generation of one or more terms related to each of the multiple skills, based on one or more latest information related to the multiple skills and the corresponding information. The transmitting unit further transmits the second prompt to the generating AI. The receiving unit further receives a second response from the generating AI that has input the second prompt, Based on the one or more terms included in the second response, an update unit updates the corresponding information for each of the multiple skills. Having, The information processing system according to feature 2.

4. The generation unit generates, as the first instruction information, an instruction to output information for identifying the skill related to the utterance content, based on the conditions for the utterance content used to determine whether a person possesses the skill, which are set for each of the plurality of skills, and the utterance content included in the utterance data. The information processing system according to feature 1.

5. For each attribute possessed by the aforementioned subject, the multiple skills and corresponding information are defined in advance. The generation unit and the identification unit use the corresponding information that corresponds to the attribute to which the target person belongs. The information processing system according to feature 2.

6. The second memory unit stores keywords associated with the corresponding information for each skill, The generation unit generates, as the first instruction information, instruction information that instructs the extraction of terms from the set of terms included in the correspondence information that correspond to the skills related to the keywords included in the utterance data, and that have a common meaning with the words included in the utterance data. The information processing system according to feature 2.

7. The update unit updates the corresponding information when the user provides input indicating permission to update the corresponding information. The information processing system according to feature 3.

8. It has a reception section that accepts search conditions written in natural language, The generation unit further generates a third prompt that instructs the search to search for individuals associated with skills that match the search conditions, based on the search conditions and the information stored in the first storage unit. The transmitting unit further transmits the third prompt to the generating AI, The receiving unit further receives a third response from the generating AI that has input the third prompt, The device has an output unit that outputs the search result indicated by the third response, The information processing system according to feature 1.

9. The registration unit registers in the storage unit skill identification information that identifies one or more skills and subject identification information that identifies the subject, in association with each other. The information processing system according to feature 1.

10. The generation unit generates a first prompt which includes the first instruction information that instructs the output of information for identifying skills related to the utterance content, and the utterance data. The transmitting unit transmits the first instruction information and the speech data to the generating AI by transmitting the generated first prompt to the generating AI. The information processing system according to feature 1.

11. An acquisition unit that acquires speech data including the content of the speech of the person whose skill is to be identified, A generation unit generates first instruction information that instructs the output of information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data. A transmission unit that transmits the aforementioned speech data and the first instruction information to the generating AI, A receiving unit that receives a first response to the first instruction information from the generating AI, An identification unit identifies one or more skills from among the plurality of skills, based on information for identifying the skills included in the first response, A registration unit that associates the identified one or more skills with the subject and registers them in a first memory unit, An information processing device characterized by having the following features.

12. A procedure for acquiring speech data that includes the content of the speech of the person whose skills are to be identified, A generation procedure for generating first instruction information that instructs the output of information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data, A transmission procedure for transmitting the aforementioned speech data and the first instruction information to the generating AI, A receiving procedure for receiving a first response to the first instruction information from the generating AI, A receiving procedure for receiving a first response to the first instruction information from the generating AI, An identification procedure for identifying one or more skills from among the plurality of skills, based on information for identifying the skills included in the first response, A registration procedure for associating the identified one or more skills with the subject and registering them in the first memory unit, An information processing method characterized by a computer executing the following.

13. A procedure for acquiring speech data that includes the content of the speech of the person whose skills are to be identified, A generation procedure for generating first instruction information that instructs the output of information for identifying a skill related to the utterance content from among a plurality of predefined skills, based on the utterance content contained in the utterance data, A transmission procedure for transmitting the aforementioned speech data and the first instruction information to the generating AI, A receiving procedure for receiving a first response to the first instruction information from the generating AI, A receiving procedure for receiving a first response to the first instruction information from the generating AI, An identification procedure for identifying one or more skills from among the plurality of skills, based on information for identifying the skills included in the first response, A registration procedure for associating the identified one or more skills with the subject and registering them in the first memory unit, A program that causes a computer to execute something.

14. The acquisition unit acquires data based on the subject's biometric information during the period corresponding to the speech data. An estimation unit that estimates the degree of well-being of the subject based on the aforementioned data. It has, The registration unit associates the estimated well-being level with the subject and registers it in the first storage unit. The information processing system according to feature 1.

Images