Device and method
The apparatus enhances skill visibility by extracting and naming common factors using generative AI, addressing the challenge of fine-grained skill measurement visibility in existing systems, facilitating effective personnel decisions.
Patent Information
- Application Number
- PCT/JP2025/017242
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-12
- Publication Date
- 2026-11-19
AI Technical Summary
Existing systems struggle to provide clear visibility into fine-grained skill measurements, making it difficult for human resources departments and managers to understand the overall skills of transfer candidates.
An apparatus and method that utilizes a factor information acquisition unit to extract common factors from skill check information, a response instruction generation unit to generate visible information using generative AI, and a response information acquisition unit to display meta-skills, enhancing understanding of employee skills through exploratory factor analysis and generative AI naming.
Improves the visibility of common factors by providing clear meta-skill names, allowing for better personnel decisions and reducing implementation costs by leveraging existing skill check systems.
Smart Images

Figure JP2025017242_19112026_PF_FP_ABST
Abstract
Description
Apparatus and Method
[0001] The present invention relates to an apparatus and a method for managing employee skills.
[0002] Patent Document 1 describes a question item selection method for questionnaire data analysis that enables questionnaire data obtained from questionnaires conducted for the same survey purpose at different times and locations to be used as questionnaire data for evaluating the same characteristics. The invention of Patent Document 1 collects a large amount of questionnaire data from a plurality of question items and performs factor analysis to extract common factors.
[0003] Japanese Unexamined Patent Application Publication No. 2012-79297
[0004] However, Patent Document 1 is limited to extracting common factors from questionnaire data, and it is difficult to understand what the common factors mean. For example, there are cases where skill measurement is performed at a very fine granularity in questionnaire items for skill checks, and in such cases, a problem remains regarding human visibility. Specifically, the granularity of skills measured by the questionnaire is too fine, so that the human resources department or on-site managers who make decisions on personnel transfers cannot grasp the overall picture of the skills possessed by transfer candidates.
[0005] Accordingly, an object of the present disclosure is to provide an apparatus and a method capable of improving the visibility of common factors.
[0006] The apparatus of the present disclosure includes a factor information acquisition unit that acquires common factor information based on skill check information for inquiring about a user's skills, a response instruction generation unit that generates response instruction information for causing a generative AI to generate visible information of the common factor information, and a response information acquisition unit that transmits the response instruction information to the generative AI and acquires response information including the visible information.
[0007] According to the present disclosure, the visibility of common factors can be improved.
[0008] Figure 1 is a diagram showing the system configuration including the analysis device 100 of this disclosure. Figure 2 is a diagram showing a part of a specific example of a skill check sheet. Figure 3 is a block diagram showing the functional configuration of the analysis device 100 of this disclosure. Figure 4 is a diagram showing skill information stored in the storage unit 102. Figure 5 is a diagram showing categories and corresponding question item numbers. Figure 6 is a diagram showing prompts. Figure 7 is a flowchart showing the operation of the analysis device 100 of this disclosure. Figure 8 is a schematic diagram showing the overall operation. Figure 9 is an example of the configuration when the analysis device 100 does not have a prompt generation function and when it has a built-in generation AI. Figure 10 is a diagram showing an example of the hardware configuration of the analysis device 100 according to one embodiment of this disclosure.
[0009] Embodiments of this disclosure will be described with reference to the attached drawings. Where possible, the same parts will be denoted by the same reference numerals, and redundant descriptions will be omitted.
[0010] Figure 1 is a diagram showing the system configuration including the analysis device 100 of this disclosure. As shown in the diagram, this system includes the analysis device 100 and a user terminal 200. The analysis device 100 acquires skill information (questionnaire items and their answers) indicated on a skill check sheet filled out on the user terminal 200. The user terminal 200 is a terminal used by users such as the human resources department and employees being evaluated by field managers. Users operate this user terminal 200 to fill in skill information on the skill check sheet. Figure 2 is a diagram showing a part of a specific example of a skill check sheet. In this disclosure, information for checking the user's skills is acquired in the form of a questionnaire. For example, this skill check sheet asks the user whether or not they possess skills such as "...can they organize and clarify the issues that need to be solved?". This skill check sheet includes multiple items that ask the user to answer about the skills they believe they possess in their self-assessment.
[0011] The analysis device 100 identifies common categories based on skill information. These categories represent the user's meta-skills. The analysis device 100 provides these categories (meta-skills) to management users such as the human resources department or field managers. These management users use the provided categories (meta-skills) to make decisions such as personnel changes. Hereafter, in this disclosure, meta-skills will be referred to as categories.
[0012] Figure 3 is a block diagram showing the functional configuration of the analysis device 100 of this disclosure. As shown in the figure, the analysis device 100 is composed of a skill information acquisition unit 101, a storage unit 102, a factor information acquisition unit 103, a response instruction generation unit 104, a response information acquisition unit 105, and a display unit 106.
[0013] The skill information acquisition unit 101 is responsible for acquiring skill information indicated on the skill check sheet filled out on the user terminal 200. The skill check sheet is, for example, a questionnaire about skills (questions and their answers). Users who are to fill out the sheet indicate whether they possess the skills indicated on the skill check sheet using a YES / NO format. For example, a user might answer YES / NO to the question, "1. Can you organize and clarify the data that customers want to collect and store, its purpose, and the problems that should be solved by utilizing that data?" The skill check sheet consists of multiple questions.
[0014] The memory unit 102 is the part that stores the skill information answered on the user terminal 200 for each user. Figure 4 shows the skill information stored in the memory unit 102. The memory unit 102 stores the user ID and the question item and answer in association with each other as skill information. As shown in the figure, YES / NO is indicated for each question item number.
[0015] The factor information acquisition unit 103 is responsible for acquiring common factors (factor information) of users based on skill information. Specifically, the factor information acquisition unit 103 uses exploratory factor analysis to discover the structure of categories (meta-skills) (how many categories (meta-skills) there are and which questionnaire questions should be associated with which categories (meta-skills)) from the response results of all users (employees being evaluated). This exploratory factor analysis makes it possible to clarify the number of categories (meta-skills) and the association between questionnaire items and categories (meta-skills).
[0016] Specifically, the following processing is performed. In this disclosure, the question items among the skill information are represented by x_1, ..., x_m, and the answers by user n (n=1, ..., N) are represented by x_11, ..., x_mn. In addition, the categories to be estimated (meta-skills) are represented by η_1 ..., η_d. At this time, the structural equation model M is expressed by the following mathematical formula. however, That is the case.
[0017] At this time, This determines the number of categories (meta-skills). However, The parameter vector θ, whose elements include all of the elements, is: It is determined by [the following].
[0018] Here, S is the sample covariance matrix, and Σ is the covariance structure. Matrix A_11 shows the relationships between common factors, and matrix A_12 shows the relationships between common factors and observed variables. When prompts are created, as described later, common factors and observed variables are assigned based on the relationship (influence coefficient or factor loading) between the common factors and observed variables (questionnaire items) shown in A_12. Matrix A_21 and matrix A_22 show the relationships between observed variables. If the influence coefficient (factor loading) in matrix A_12 is above a threshold, that observed variable (questionnaire item) is assigned to a common factor.
[0019] Figure 5(a) shows categories η_1, η_2, etc., and their corresponding question item numbers. As shown in the figure, the factor information acquisition unit 103 acquires factor information indicating the category number (which is unknown at this point) that will be a common factor and the question item associated with it. As described above, the factor information acquisition unit 103 exploratoryally analyzes the factors using a structural equation model and adopts a model whose model fit d^ is above a certain threshold. This discovers a common factor for each question item.
[0020] The response instruction generation unit 104 generates a prompt that instructs the generation AI 300 to generate a response based on factor information including common factors and assigned question items, and transmits the prompt to the generation AI 300.
[0021] Figure 6 shows the prompt. As shown in the figure, the prompt includes the following text: "You will be given a set of questions divided into the following three categories. For each category, please create a category name from the perspective of 'what skills can be measured.'" # Rules: Category names must not be duplicated, and category names must be expressed concisely as single words. # Output format: {eta1: Category name}, {eta2: Category name}, {eta_3: Category name} # Categories and questions (influence coefficient on the overall category): Category 1: Question 1 (a_(1,1)) Question 2 (a_(1,2)) Question 3 (a_(1,3)) Question 4 (a_(1,4)) Question 14 (a_(1,14)) Question 17 (a_(1,17)) Category 2: Question 4 (a_(2,4)) Question 5 (a_(2,5)) Question 6 (a_(2,6)) Question 7 (a_(2,7)) Question 16 (a_(2,16)) Category 3: Question 4 (a_(3,4)) Question 10 (a_(3,10)) Question 11 (a_(3,11)) ...Category 4: ..." This prompt instructs the system to generate text and parameters such as "Question 1" for each category. For example, "Question 1" will be replaced with the text of an actual skill check sheet question. Also, values (influence coefficients) estimated by the structural equation model will be replaced with values such as a_(1,d+1). Here, prompts are generated for questions 1 to 4, corresponding to the number of question items and their corresponding numbers that are assigned to common factors in each category. In the above prompt example, for category 1, since the influence coefficient (factor loading) a(a_(1,1)) for question 1 is above the threshold, category 1 is treated as a common factor for question 1.
[0022] The response information acquisition unit 105 is responsible for acquiring the response information generated by the generation AI 300. The response information consists of the category name for each η (category) indicated in the prompt output format field.
[0023] The display unit 106 is the part that displays the category name (meta-skill name) for each category. For example, the display unit 106 displays the category name (meta-skill name) in association with the skill information (question item number and its answer).
[0024] Figure 5(b) shows a specific example. As shown in the figure, the display unit 106 displays the category name (meta-skill name) in association with the corresponding question item number. As shown in the figure, the generation AI 300 names the category names (meta-skill names) such as problem identification and design / environment construction.
[0025] Figure 7 is a flowchart showing the operation of the analysis apparatus 100 of this disclosure. As shown in the figure, the skill information acquisition unit 101 acquires skill information for each user from a plurality of user terminals 200 (S101). The storage unit 102 stores the skill information for each user. The factor information acquisition unit 103 performs exploratory factorization using a structural equation model (S103). Then, the factor information acquisition unit 103 acquires factor information indicating common factors (skill information for each category η) (S104).
[0026] The response instruction generation unit 104 generates a prompt to instruct the generation AI 300 to generate names for each category η using the factor information (S105). Then, the response instruction generation unit 104 sends the prompt to the generation AI 300 (S106).
[0027] The generating AI 300 generates answers including names for each category according to the prompt, and the answer information acquisition unit 105 acquires those answers (S107). The storage unit 102 stores the answers (S108).
[0028] In accordance with the operation by a user such as the Human Resources Department or a field manager, the display unit 106 displays the name of each category and its skill information (S109).
[0029] Figure 8 is a schematic diagram showing the overall operation. As shown in the figure, in the analysis device 100, the database stored in the memory unit 102 stores the answers to the skill check sheet. Then, exploratory factor analysis using a structural equation model is performed on these answers to the skill check sheet. Then, a structural equation model is obtained in which the meta-skills η_1...η_d, which were described as categories above, and the parameters (a_11, ... a_dd, ... a_d+m, dm) are determined. In the analysis device 100, prompts are created from the relationship between η, A_11, and A_12 in this structural equation model and sent to the generating AI 300 (for example, LLM (Large Language Model)). The generating AI 300 generates meta-skill names for each category η and provides them to the analysis device 100.
[0030] Next, the operation and effects of the analytical apparatus 100 of this disclosure will be described. In the analytical apparatus 100 of this disclosure, the factor information acquisition unit 103 acquires common factor information based on a skill check sheet (skill check information) that inquires about the user's skills. For example, this skill check information is information based on the skill check sheet, such as the answered questions and their answers. Common factor information is information that indicates common factors based on the skill check information. In this disclosure, common factor information means categories, and each category is associated with multiple question items.
[0031] The response instruction generation unit 104 then generates a prompt, which is response instruction information, that causes the generating AI 300 to respond with visible information of common factor information. Visible information refers to the name of the category of common factor information. General common factor derivation processes derive common factors in some form, but it is difficult to understand what they are. In this disclosure, the generating AI 300 is used to give a name to these common factors. The response information acquisition unit 105 then transmits the response instruction information to the generating AI 300 and acquires response information including visible information. This visible information is, for example, a name, and the managing user can determine the user's meta-skills by looking at that name.
[0032] Furthermore, while conventional structural equation models could identify common factors, the naming of those factors was done manually.
[0033] Furthermore, while it is expected that the generation AI300 can discover common factors from the question items to some extent by devising prompts, there is no guarantee regarding its validity.
[0034] This disclosure makes it possible to measure meta-skills common to multiple skills while guaranteeing a mathematical and statistical structure (guaranteeing the existence of common factors, i.e., the existence of some kind of abstracted meta-skill).
[0035] Furthermore, when this is used to understand skills in the course of business operations within a company, the following additional benefits can be obtained. For example, by effectively utilizing existing skill check sheets and other questionnaires already used by each company, it is possible to understand the meta-skills of the employees being evaluated. Therefore, it can be implemented more cheaply and simply than introducing a new skill check system. In other words, it only involves analyzing existing questionnaires, which reduces implementation costs. Therefore, it is possible to easily understand the skills of users and facilitate personnel placement that takes skills into account.
[0036] In this disclosure, the factor information acquisition unit 103 acquires common factor information based on the information of each question item and its answer in the skill check sheet. Furthermore, the factor information acquisition unit 103 may acquire common factor information including an influence coefficient for the common factor. This allows the generating AI to determine the degree of influence of each question item on the common factor and to assign a name based on that determination.
[0037] The response instruction generation unit 104 generates response instruction information as visible information, which causes the generating AI 300 to respond with a name for the common factor information. The response instruction information also includes an influence coefficient for the common factor.
[0038] In this disclosure, common factor information is information obtained by factor analysis using a structural equation model, and consists of multiple common factors (multiple categories) and influence coefficients for those common factors.
[0039] Furthermore, the number of common factors is determined by the structural equation model, and the response instruction information specifies the number of common factors as the number of visible information items and instructs the corresponding output format. The generating AI 300 may be installed in the analysis device 100. Some generating AI models, like Tsuzumi, have the generating AI model located inside the device. In this type, the RAG application is also provided in the device. However, the information (knowledge DB) accessed by RAG may be located inside the device or on the network. There are also types, like ChatGPT, where the generating AI model is located on the network. In this type, the RAG application is provided in the device. However, the information (knowledge DB) accessed by RAG is on the network.
[0040] By the way, the generative AI model 300 represented by LLM is a model that can generate content in accordance with the instructions, context, questions, and output format indicated by a prompt in response to the input of the prompt including input information, and return the content as response information. In addition, the prompt can include input information, and in this case, the generative AI model 300 generates response information targeting the input information. The generative AI model 300 is configured to include, for example, a Large Language Model (LLM) and a user interface (UI) for interaction with a user, and may be an interactive AI model that enables text-based chat or voice-based chat with the user. Examples of such generative AI model 300 include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, and the like. In the present embodiment, the analysis device 100 is enabled to provide a content providing function by interactive AI models which are a plurality of types of models. These interactive AI models may be stored in the analysis device 100, or may be stored in another device connected to the analysis device 100 via a network, and configured to enable information exchange with the user via the analysis device 100.
[0041] Note that, in the present disclosure, the prompt is information indicating an instruction or a question input by a user in an interactive system such as an interaction with a generative AI model or a command line interface (CLI).
[0042] Here, the configuration of the analysis device 100 or the device in which the generative AI 300 is disposed will be described. FIG. 9(a) is a configuration example when the analysis device 100 does not have a prompt generation function. In this case, the analysis device 100 can access an external prompt generation device and an external knowledge DB, generate a prompt using them, transmit the prompt to the generative AI 300, and obtain the result.
[0043] FIG. 9(b) is a configuration example when the analysis device 100 is provided with a prompt generation function and generative AI 300. As shown in the figure, the analysis device 100 can access an external knowledge DB, generate a prompt using it, output the prompt to the built-in generative AI 300, and obtain the result.
[0044] The apparatus and method of the present disclosure have the following configurations.
[0045] [1] An apparatus comprising: a factor information acquisition unit that acquires common factor information based on skill check information for inquiring about a user's skill; a response instruction generation unit that generates response instruction information for causing generative AI to generate visible information of the common factor information; and a response information acquisition unit that transmits the response instruction information to the generative AI to acquire response information including the visible information.
[0046] [2] The apparatus according to [1], wherein the factor information acquisition unit acquires the common factor information based on each piece of question item information of the skill check information and a response thereto.
[0047] [3] The apparatus according to [1] or [2], wherein the factor information acquisition unit acquires the common factor information including an influence degree coefficient for the common factor.
[0048] [4] The apparatus according to any one of [1] to [3], wherein the response instruction generation unit generates the response instruction information for causing the generative AI to output a name for the common factor information as the visible information.
[0049] [5] The apparatus according to [3], wherein the response instruction information further includes the influence degree coefficient for the common factor.
[0050] [6] The apparatus according to any one of [1] to [5], wherein the common factor information is information obtained by factor analysis using a structural equation model, and is composed of a plurality of common factors and influence degree coefficients for the common factors.
[0051] [7] The apparatus according to [6], wherein the number of common factors is determined by the structural equation model, and the response instruction information specifies the number of common factors as the number of visible information items and instructs the output format accordingly.
[0052] [8] A method in a device comprising: a factor information acquisition step of acquiring common factor information based on skill check information that inquires about the user's skills; a response instruction generation step of generating response instruction information that causes a generating AI to respond with visible information of the common factor information; and a response information acquisition step of transmitting the response instruction information to the generating AI to acquire response information including the visible information.
[0053] The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may be realized by combining the one or more devices with software.
[0054] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.
[0055] For example, the analysis apparatus 100 in one embodiment of the present disclosure may function as a computer that processes the analysis method of the present disclosure. Figure 10 is a diagram showing an example of the hardware configuration of the analysis apparatus 100 according to one embodiment of the present disclosure. The analysis apparatus 100 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.
[0056] In the following explanation, the term "apparatus" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the analytical apparatus 100 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.
[0057] Each function in the analysis device 100 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.
[0058] The processor 1001 controls the entire computer, for example, by running the operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the factor information acquisition unit 103 and the response instruction generation unit 104 described above may be implemented by the processor 1001.
[0059] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the factor information acquisition unit 103 and the response instruction generation unit 104 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.
[0060] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out the analysis method according to one embodiment of the present disclosure.
[0061] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.
[0062] The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the skill information acquisition unit 101 described above may be implemented by the communication device 1004. The communication device 1004 may be implemented with physically or logically separated transmitting and receiving units.
[0063] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).
[0064] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.
[0065] Furthermore, the analysis device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.
[0066] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.
[0067] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.
[0068] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.
[0069] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).
[0070] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).
[0071] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.
[0072] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.
[0073] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.
[0074] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.
[0075] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc.
[0076] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values from a given value, or other corresponding information. For example, wireless resources may be indicated by an index.
[0077] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way.
[0078] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.
[0079] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term.
[0080] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."
[0081] The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.
[0082] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."
[0083] Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.
[0084] Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR.
[0085] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.
[0086] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."
[0087] 100...Analyzer, 200...User terminal, 101...Skill information acquisition unit, 102...Storage unit, 103...Factor information acquisition unit, 104...Answer instruction generation unit, 105...Answer information acquisition unit, 106...Display unit.
Claims
1. A device comprising: a factor information acquisition unit that acquires common factor information based on skill check information that inquires about the user's skills; a response instruction generation unit that generates response instruction information that causes a generating AI to respond with visible information of the common factor information; and a response information acquisition unit that transmits the response instruction information to the generating AI and acquires response information including the visible information.
2. The apparatus according to claim 1, wherein the factor information acquisition unit acquires common factor information based on the question item information and the answers to the skill check information.
3. The apparatus according to claim 1, wherein the factor information acquisition unit acquires common factor information including an influence coefficient for the common factor.
4. The apparatus according to claim 1, wherein the response instruction generation unit generates response instruction information to cause the generating AI to respond with a name for the common factor information as the visible information.
5. The apparatus according to claim 3, wherein the response instruction information further includes an influence coefficient on the common factor.
6. The apparatus according to claim 1, wherein the common factor information is information obtained by factor analysis using a structural equation model, and consists of a plurality of common factors and an influence coefficient for said common factors.
7. The apparatus according to claim 6, wherein the number of common factors is determined by the structural equation model, and the response instruction information specifies the number of common factors as the number of visible information items and instructs the output format accordingly.
8. A method in a device comprising: a factor information acquisition step of acquiring common factor information based on skill check information that inquires about the user's skills; a response instruction generation step of generating response instruction information that causes a generating AI to respond with visible information of the common factor information; and a response information acquisition step of transmitting the response instruction information to the generating AI to acquire response information including the visible information.
