system

Abstract

We provide the system. [Solution] A data analysis means for collecting and preprocessing surveys, emails, chats, and meeting records, A personality trait evaluation means that uses a generative AI model to perform a process that objectively evaluates the user's personality traits and skills, A personnel placement recommendation tool that calculates the optimal team structure and staffing based on evaluation results and creates a specific placement plan, A feedback analysis tool that analyzes user-provided feedback to evaluate actual performance and team harmony, A database update mechanism that updates personality profiles and skill maps based on feedback and newly collected data, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the personnel allocation in conventional organizations, the skill set was evaluated as the main criterion, but this did not consider the personality characteristics of employees and their compatibility with existing members, resulting in problems such as inappropriate team compositions and early departures. Also, even if there was a mechanism to consider personality characteristics, many of them were based on subjective evaluations and lacked objectivity and consistency. To solve this, a system that accurately understands the personalities, strengths, and weaknesses of employees and realizes effective and sustainable personnel allocation has been demanded.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, and database update means. First, the data analysis means collects and preprocesses data such as questionnaires, past emails, chats, and meeting records. Next, the personality trait evaluation means using a generative AI model evaluates the personality traits and skills of employees from the data. Based on the evaluation results, the personnel placement recommendation means calculates the optimal team composition and provides a specific personnel placement plan. Furthermore, the feedback analysis means evaluates actual performance, and the database update means updates personality profiles and skill maps, enabling personnel placement that always reflects the latest information.

[0006] "Data analysis methods" refer to methods for collecting data such as survey results, past emails, chats, and meeting records, and organizing and pre-processing it using natural language processing technology.

[0007] A "generative AI model" refers to artificial intelligence technology used to evaluate a user's personality traits and skills based on collected data.

[0008] A "personality trait evaluation method" is a means of performing a process that objectively evaluates a user's personality traits and skills using a generative AI model.

[0009] A "personnel placement recommendation method" is a means of calculating the optimal team composition and personnel placement based on evaluation results, and creating a specific placement plan.

[0010] A "feedback analysis method" is a means of analyzing feedback provided by users to evaluate actual performance and team cohesion.

[0011] A "database update method" is a means of updating personality profiles and skill maps based on feedback and newly collected data. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0034] Program Processing Description

[0035] Data Acquisition and Preprocessing

[0036] Users access the system and answer questionnaires. These questionnaires include self-assessment and job-related questions, revealing the user's personality traits and skill set. With the user's permission, the server also collects past emails, chat messages, meeting records, etc. The server preprocesses this data and extracts only meaningful information.

[0037] Analysis of personality and abilities

[0038] The server analyzes the collected data using natural language processing techniques. Specifically, it performs sentiment analysis, topic modeling, and keyword extraction to visualize the user's personality traits and skills. Subsequently, a generative AI model is used to evaluate the user's personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile.

[0039] Team formation and recommendations

[0040] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This includes required skill sets, personality traits, and roles. Based on these project requirements, the server calculates the optimal team composition. In doing so, it compares the user's personality profile and skill set to propose a well-balanced team structure.

[0041] Feedback and updates

[0042] After team formation, users provide feedback on project progress and team cohesion. This feedback is periodically sent to and analyzed by the server. The server analyzes the feedback and updates the user's profile based on the results. This update allows for more accurate personnel allocation in future team formations.

[0043] Specific example

[0044] Data Acquisition and Preprocessing

[0045] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0046] Analysis of personality and abilities

[0047] The server analyzes user A's data and assesses that they possess advanced skills in "task management ability" and "leadership." A generative AI model confirms this and stores it in the database as user A's personality profile.

[0048] Team formation and recommendations

[0049] Next, the company enters into the system that a "leader with strong task management skills" is required as a project requirement for launching a new project. Based on this, the server recommends User A as the most suitable member for the project.

[0050] Feedback and updates

[0051] As the project progresses, User A and other team members provide feedback. This feedback includes information about User A's leadership and team cohesion. The server analyzes this and updates User A's profile. This update allows for appropriate placement in future projects.

[0052] Thus, the present invention precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0056] Step 2:

[0057] The server receives user survey responses and stores them in a database. Simultaneously, it collects the user's past emails, chat logs, and meeting records. Prior user consent is required for this collection.

[0058] Step 3:

[0059] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0060] Step 4:

[0061] The server uses natural language processing (NLP) techniques to analyze the organized data. Specifically, it performs sentiment analysis, extracts keywords and topics from the text, and assesses the user's characteristics and skills.

[0062] Step 5:

[0063] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but low cooperativeness. The evaluation results are stored in a database.

[0064] Step 6:

[0065] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, and role. For example, "data scientist" or "highly collaborative leader."

[0066] Step 7:

[0067] The server analyzes project requirements and calculates the optimal staffing based on user personality profiles and skill sets. Multiple filtering algorithms are used to recommend the most suitable members.

[0068] Step 8:

[0069] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics and skills.

[0070] Step 9:

[0071] Users provide feedback during the project. This feedback includes information about team cohesion and the performance of each member. This feedback is collected regularly.

[0072] Step 10:

[0073] The server analyzes the feedback data and updates the user's personality profile. NLP techniques are used again for the feedback analysis, and actual performance evaluation is performed.

[0074] Step 11:

[0075] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[0076] Through the steps described above, the present invention enables effective staffing and improves overall organizational performance and satisfaction.

[0077] (Example 1)

[0078] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0079] Currently, many companies and organizations are attempting to effectively staff based on employee personality traits and skills. However, traditional methods are time-consuming to collect and analyze data, and their accuracy is low, making it difficult to achieve optimal placement. Furthermore, updating employee profiles as projects progress is not easy. This makes it difficult to form teams that fully utilize the potential of employees.

[0080] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0081] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, and database update means. This makes it possible to precisely evaluate the personality traits and skills of employees and to achieve optimal personnel placement based on the evaluation results. Furthermore, by analyzing project feedback and updating profiles, appropriate placement becomes possible for future projects as well, maximizing the capabilities of employees.

[0082] "Data analysis means" refers to devices or software that collect and preprocess data such as questionnaires answered by users when they access the system, past emails, chat messages, and meeting records. Preprocessing includes noise removal and extraction of meaningful information.

[0083] "Personality trait evaluation method using generative AI models" refers to a device or software that analyzes data collected using natural language processing technology to evaluate the user's personality traits and skills, and the evaluation results are stored as a profile in a database.

[0084] A "personnel placement recommendation tool" is a device or software that, based on project requirements, matches the personality traits and skill profiles of evaluated users to recommend the most suitable team members.

[0085] A "feedback analysis tool" is a device or software that collects user feedback regarding project progress and team harmony, and updates the user's profile based on the analysis results.

[0086] A "database update method" refers to a device or software that updates user profiles based on feedback and analysis results, reflecting the latest information in the database.

[0087] "Natural language processing technology" is a technique that analyzes text data and performs sentiment analysis, topic modeling, keyword extraction, etc., and is mainly used to evaluate users' personality traits and skills.

[0088] A "profile" is data that records evaluation results regarding a user's personality traits and skills, and is stored in a database.

[0089] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0090] Data Acquisition and Preprocessing

[0091] Users first access the system and answer a questionnaire. This questionnaire includes questions about self-assessment and job-related matters, revealing the user's personality traits and skill set. With the user's permission, the server also collects data such as past emails, chat messages, and meeting records. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes, for example, titles, signatures, and automated messages, and extracts keywords related to task management.

[0092] Analysis of personality and abilities

[0093] The server analyzes the collected data using natural language processing techniques. It performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. Subsequently, it uses a generative AI model to evaluate personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile. For example, if "User A's leadership skills are high" is evaluated, this result will be recorded in the profile.

[0094] Team formation and recommendations

[0095] When a company or organization launches a new project, HR personnel use a terminal to input project requirements into the system. This includes necessary skill sets, personality traits, and roles. Based on these requirements, the server matches user profiles to calculate the optimal team composition and proposes a balanced team structure. For example, if the input states, "New Project X requires a leader with strong task management skills," the server will recommend user A as the leader.

[0096] Feedback and updates

[0097] As the project progresses, users provide feedback on the project's progress and the team's cohesion. This feedback is periodically sent to the server for analysis. The server updates user profiles based on the feedback, enabling more accurate personnel allocation for future projects. For example, if User B provides feedback stating, "I am satisfied with User A's leadership," this information will be reflected in User A's profile.

[0098] Example of a prompt

[0099] The following are examples of specific prompt statements used by the system.

[0100] "Please recommend a leader with strong task management skills for our new project."

[0101] "Analyze User A's leadership and task management skills and evaluate whether they meet the project requirements."

[0102] Thus, the present invention is a system that precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0103] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0104] Step 1:

[0105] Users access the system and answer questionnaires. These questionnaire responses become input data. The server collects this data for later analysis. Specifically, users input data in the form of self-assessments and questions about their work. For example, a user might answer the question, "How do you feel about working in a team?"

[0106] Step 2:

[0107] With the user's permission, the server collects past emails, chat messages, and meeting records. The collected text data becomes the input data. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes honorifics, signatures, and auto-generated messages, and extracts keywords related to task management. For example, "Extract important keywords from User A's email communication records for the past year."

[0108] Step 3:

[0109] The server analyzes the data collected in Steps 1 and 2 using natural language processing techniques. The results of this analysis are output as intermediate data. Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. For example, "extract keywords related to 'cooperativeness' and 'leadership' from User A's emails."

[0110] Step 4:

[0111] The server uses a generative AI model to perform a detailed evaluation of the user's personality traits and skills based on the analysis results from step 3. This evaluation result is saved as profile data. Specifically, it might be evaluated as "User A has high leadership skills." This data is stored in the database.

[0112] Step 5:

[0113] An HR representative uses a terminal to input project requirements into the system. This requirements data becomes the input data. The server matches the requirements data with user profiles and calculates the optimal team composition. This result is output as team member recommendation data. Specifically, it might input something like, "New Project X requires a leader with strong task management skills."

[0114] Step 6:

[0115] The server recommends the most suitable user based on the requirements data from Step 5. The recommendation result is output data and displayed on the terminal. Specifically, the data displayed will say, "We recommend User A as the leader of Project X."

[0116] Step 7:

[0117] During project progress, users provide feedback on the progress and team harmony. This feedback data becomes input data. The server collects and analyzes this feedback. Specifically, the input might be, "User B is satisfied with User A's leadership."

[0118] Step 8:

[0119] The server analyzes the feedback data and updates the user's profile based on the results. This updated data becomes the output data and is used for future personnel assignments. For example, "Update User A's profile to 'Leadership skills rated higher based on feedback'."

[0120] Thus, the system of the present invention processes and analyzes data at each step to achieve optimal personnel allocation.

[0121] (Application Example 1)

[0122] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0123] Traditional factory management methods made it difficult to optimize staffing and team formation, hindering efficient production and effective utilization of human resources. Furthermore, dynamic updates to profiles based on feedback were not implemented, potentially leading to similar problems recurring in subsequent projects.

[0124] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0125] In this invention, the server includes functions for data collection and preprocessing, personality and ability analysis, team composition recommendation, and profile updating based on feedback. This enables optimal team formation based on the skills and personality traits of individual factory employees, and by sequentially updating profiles based on feedback, highly accurate personnel allocation becomes possible in subsequent projects as well.

[0126] "Data analysis methods" refer to methods for collecting data such as questionnaires, communication records, and work records, and extracting detailed information through preprocessing.

[0127] "Personality trait evaluation method using generative AI models" refers to a method that uses natural language processing technology to evaluate a user's personality traits and abilities.

[0128] A "personnel placement recommendation system" is a method of recommending the most suitable personnel for a specific project or task based on collected data and evaluation results from a generated AI model.

[0129] A "feedback analysis method" is a means of analyzing feedback data collected after the project is completed and updating the user profile.

[0130] A "database update method" is a means of saving and updating user profiles in a database based on analyzed data and feedback.

[0131] The "data collection and preprocessing function" refers to a function that collects data such as questionnaires, communication records, and work records, extracts the necessary information, and performs preprocessing.

[0132] The "personality and ability analysis function" is a function that uses collected data to evaluate the user's personality traits and skills.

[0133] The "team composition recommendation function" is a function that recommends the optimal personnel allocation and team composition based on project requirements.

[0134] The "feedback-based profile update function" is a function that analyzes user feedback and updates the user's profile based on that feedback.

[0135] To implement this invention, the following basic system configuration and processing flow are used.

[0136] System Configuration

[0137] The system consists of a data collection server, a GPU server for personality and ability analysis, a database server, and client terminals. The entire system includes various hardware and software components, such as:

[0138] Hardware:

[0139] Data collection server: This server collects and preprocesses data such as surveys, communication records, and business records. It is equipped with a CPU and adequate memory.

[0140] GPU Server for Personality and Ability Analysis: This server is equipped with a high-performance graphics processor (GPU) to evaluate personality traits and abilities using natural language processing technology.

[0141] Database Server: This server is used to store and update evaluation results and feedback data. It is equipped with data storage that has high I / O performance.

[0142] Client terminals: These are terminals used by HR personnel and employees to access the system. This includes desktop PCs and mobile devices.

[0143] software:

[0144] Data analysis libraries: These are libraries used for data preprocessing and analysis, such as Pandas and NumPy.

[0145] Natural language processing libraries: These include libraries such as Transformers and BERT, which are used for personality trait evaluation.

[0146] Database management system: This refers to database software such as MySQL or PostgreSQL used to store and manage evaluation results and feedback.

[0147] Processing details for each means

[0148] Data acquisition and preprocessing means

[0149] Users access the system and periodically answer questionnaires. These questionnaires include self-assessment and job-related questions and are provided through web forms and mobile apps. With user permission, past emails, chat messages, and work records are also collected. The data collection server preprocesses this data, performing keyword extraction and data cleansing.

[0150] Methods for analyzing personality and abilities

[0151] The preprocessed data is analyzed using natural language processing techniques. Specifically, the BERT model is used for sentiment analysis, topic modeling, and keyword extraction to evaluate the user's personality traits and skills. These analyses are performed at high speed on a GPU server, and a generative AI model generates the evaluation results.

[0152] Team formation recommendation methods

[0153] The terminal used to input project requirements allows users to enter information such as required skill sets, personality traits, and roles. The server calculates the optimal team composition based on the entered requirements. To ensure a balanced team, it compares the user's personality profile with their skill set. This recommendation is displayed on the client terminal.

[0154] Feedback and profile update methods

[0155] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications. This feedback data is stored on a database server and analyzed periodically. The analysis results are reflected in the user's profile and accumulated as information useful for future team formations.

[0156] Specific example

[0157] For example, suppose a "leader with strong task management skills" is needed to set up a new production line in a factory. In this case, the system would input "leader with strong task management skills" and "worker skilled in machine operation" as project requirements. The system would then analyze past data and recommend the most suitable personnel.

[0158] Example of a prompt

[0159] Project Requirements: "Leaders with strong task management skills" and "Workers skilled in machine operation"

[0160] Evaluation profile:

[0161] [

[0162] {"Name": "A", "Task Management": 9, "Leadership": 8, "Machine Operation": 7}

[0163] {"Name": "B", "Task Management": 7, "Leadership": 9, "Machine Operation": 8}

[0164] {"Name": "C", "Task Management": 6, "Leadership": 9, "Machine Operation": 5}

[0165] ]

[0166] Based on the prompt, the system recommends "A" as the leader and "B" as the assistant. In this way, optimal personnel allocation and team formation are achieved.

[0167] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0168] Step 1:

[0169] Users access the system and answer questionnaires, which include questions about self-assessment and job-related matters. The questionnaire data entered by users is collected. This data includes information about the user's personality traits and skill set. The server receives this data and performs cleaning and initial preprocessing.

[0170] Step 2:

[0171] The server collects user survey data, past emails, chat messages, and work records. This data is also pre-processed. Specific pre-processing steps include deleting unnecessary data, normalizing text, and extracting keywords. The pre-processed data is then stored on the database server.

[0172] Step 3:

[0173] The server analyzes pre-processed data using natural language processing techniques. This analysis utilizes the BERT model for sentiment analysis, topic modeling, and keyword extraction. Using pre-processed text data as input, the output provides results that evaluate the user's personality traits and skills. These results are stored in a database as the user's personality profile.

[0174] Step 4:

[0175] Using a terminal, HR personnel enter project requirements into the system. This includes information such as required skill sets, personality traits, and roles. The server receives these project requirements and compares them with the user's personality profile stored in the database.

[0176] Step 5:

[0177] The server performs calculations to recommend the optimal team composition based on project requirements and the user's personality profile. Specifically, it generates prompt statements and provides them as input to a generative AI model. The generative AI model selects the most suitable team members based on the input and outputs the recommendation results. These recommendation results are displayed on the terminal.

[0178] Step 6:

[0179] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications and sent to the server. The feedback data includes information such as the project's progress, team cohesion, and the contributions of individual members.

[0180] Step 7:

[0181] The server analyzes the collected feedback data and updates the user's personality profile. The analysis again utilizes natural language processing techniques such as sentiment analysis and topic modeling. Feedback is used as input data, and the updated personality profile is obtained as output and stored in the database.

[0182] Step 8:

[0183] After a project is completed, the updated personality profiles will be used for future projects. These profiles will be compared to new project requirements to aid in future team building. This will enable continuously improving and optimized personnel allocation.

[0184] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0185] The present invention provides a system that includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, database update means, and an emotion engine that recognizes user emotions.

[0186] Program Processing Description

[0187] Data Acquisition and Preprocessing

[0188] Users log into the system and answer an online questionnaire. This questionnaire includes questions about personality assessment and job-related matters, such as "Are you good at demonstrating leadership?" or "How do you perform in stressful environments?". The server also collects data such as past emails, chat messages, and meeting records with the user's permission.

[0189] Extraction and analysis of emotional information

[0190] The server preprocesses the collected data using an emotion engine to analyze the user's emotional information. The emotion engine uses natural language processing techniques to extract emotions such as positive, negative, and neutral from the text. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion.

[0191] Analysis of personality and abilities

[0192] The server uses a generative AI model to evaluate the user's personality traits based on the results of emotional information extraction by the emotion engine. Because emotional information is also incorporated into this evaluation, a more refined personality profile is created. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The evaluation results are stored in a database.

[0193] Team formation and recommendations

[0194] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these project requirements, taking into account user personality profiles, skill sets, and emotional information.

[0195] Feedback and updates

[0196] After team formation, users provide feedback on project progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to the server for analysis.

[0197] The server analyzes the feedback and updates the user's profile. This update uses the sentiment engine again to re-extract sentiment information from the feedback. The updated profile is saved in the database and used to improve the accuracy of future staffing decisions.

[0198] Specific example

[0199] Data Acquisition and Preprocessing

[0200] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0201] Extraction and analysis of emotional information

[0202] The server uses an emotion engine to extract emotional information from user A's data. For example, a message like "This project is fun" is recognized as a positive emotion.

[0203] Analysis of personality and abilities

[0204] The server analyzes user A's data, including emotional information, using a generating AI model to evaluate personality traits in detail. For example, it might be assessed that user A has high task management skills and a positive mindset, but occasionally experiences emotional fluctuations.

[0205] Team formation and recommendations

[0206] When an HR representative enters the requirements for a new project into the system—specifically, "a leader with strong task management skills and a positive attitude"—the server recommends User A as the most suitable member.

[0207] Feedback and updates

[0208] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This allows for optimal placement in future projects as well.

[0209] As described above, the present invention, by combining an emotion engine, takes into account the user's emotional information, thereby achieving more precise and effective personnel allocation.

[0210] The following describes the processing flow.

[0211] Step 1:

[0212] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0213] Step 2:

[0214] The server receives user survey responses and stores them in a database. Simultaneously, with the user's permission, it collects work-related data such as past emails, chat messages, and meeting records.

[0215] Step 3:

[0216] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0217] Step 4:

[0218] The server extracts emotional information from pre-processed data using an emotion engine. The emotion engine leverages natural language processing techniques to identify and classify emotional expressions within text. For example, the message "I'm really looking forward to it!" in a chat log is recognized as a positive emotion.

[0219] Step 5:

[0220] The server uses natural language processing (NLP) techniques to analyze the organized data (including sentiment information). Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to assess user characteristics and skills.

[0221] Step 6:

[0222] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but also experiencing intense emotional fluctuations. The evaluation results are stored in a database.

[0223] Step 7:

[0224] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, role, and emotional stability. For example, "data scientist" or "highly collaborative leader."

[0225] Step 8:

[0226] Based on project requirements, the server calculates the optimal team composition, taking into account user personality profiles, skill sets, and emotional information. Multiple filtering algorithms are used to recommend the most suitable members.

[0227] Step 9:

[0228] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics, skills, and emotional stability.

[0229] Step 10:

[0230] Users provide feedback during the project. This feedback includes aspects such as the level of harmony among team members, the progress of work, and emotional fluctuations. This feedback is sent to the server periodically.

[0231] Step 11:

[0232] The server analyzes the feedback data and updates the user's personality profile. NLP techniques and an emotion engine are again used for the feedback analysis, reflecting actual performance evaluations and emotional changes.

[0233] Step 12:

[0234] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[0235] Through the steps described above, the present invention, by including an emotion engine, takes into account the user's emotional information and achieves more precise and effective personnel allocation.

[0236] (Example 2)

[0237] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0238] In modern companies and organizations, optimal staffing is a critical issue directly linked to project success and improved efficiency. However, traditional staffing methods often rely solely on skill sets and experience, making it difficult to consider individual members' personality traits and emotional states. This can easily lead to team disharmony and decreased work efficiency. Furthermore, insufficient real-time feedback-based profile updates meant a lack of adaptability to dynamic project environments.

[0239] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0240] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, and emotion analysis means using an emotion engine that recognizes the user's emotions. This enables precise evaluation that takes into account the user's personality traits and emotional information, allowing for optimal staffing and real-time profile updates.

[0241] "Data analysis methods" refer to methods for collecting information such as surveys, emails, chats, and meeting records, and extracting necessary keywords and data through preprocessing.

[0242] "Personality trait evaluation method using generative AI models" refers to a method that utilizes natural language processing technology to evaluate personality traits, including emotional information, from text in collected data.

[0243] A "personnel placement recommendation method" is a means of selecting and recommending members who are best suited to the requirements of a project or team, based on evaluated personality traits, skill sets, and emotional information.

[0244] A "feedback analysis method" is a means of analyzing feedback information provided by users and team members during the progress of a project to evaluate the team's harmony and the status of work execution.

[0245] A "database update method" refers to a method of periodically updating user profiles based on the results of feedback analysis, etc., and utilizing this information for future evaluations and personnel allocation.

[0246] "Emotional analysis means" refers to a method of extracting user emotional information from text collected using natural language processing technology and analyzing emotional states such as positive, negative, and neutral.

[0247] The present invention is a system that includes data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means. Specific embodiments of each means will be described below.

[0248] This system has the following configuration: Users first log in to the system and answer an online questionnaire. The questionnaire includes questions about personality assessment and job-related matters. For example, it includes questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" This collects the necessary personality information.

[0249] The server collects data such as past emails, chat messages, and meeting records with the user's permission. This data is preprocessed using data analysis tools to extract necessary keywords and data. This involves using software that employs natural language processing techniques (e.g., Apache OpenNLP or NLTK).

[0250] Next, the collected data is analyzed using sentiment analysis techniques. These techniques use natural language processing to classify emotions within the text as positive, negative, neutral, etc. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion. A sentiment analysis engine (e.g., IBM Watson Tone Analyzer) is used for this analysis.

[0251] The analyzed emotional information is incorporated into personality trait assessments by generative AI models (e.g., GPT-3 or BERT). The server then uses this information to evaluate the user's personality traits and create a more refined profile. For example, "User A" might be assessed as having strong leadership and analytical skills, but also experiencing significant emotional fluctuations. The assessment results are stored in a database and used for future personnel placement and evaluations.

[0252] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. Based on these requirements, the server calculates the optimal team composition. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended.

[0253] During project progress, users provide feedback on the project's progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to a server and analyzed using feedback analysis tools. The server updates the user's profile based on the analysis results and stores it in a database. This helps improve the accuracy of future personnel allocation.

[0254] Specific example

[0255] User A logs into the system and answers a "self-assessment questionnaire." The server collects User A's questionnaire responses and past email communication data, and extracts keywords related to task management. This data is analyzed using a sentiment analysis engine, and messages such as "This project is fun" are recognized as positive emotions.

[0256] Next, the data, including the analyzed emotional information, is analyzed using a generating AI model to evaluate User A's personality traits. The evaluation results indicate that User A has "high task management skills and a positive outlook, but occasionally experiences emotional fluctuations." When an HR person enters the requirements for a new project into the system, the server recommends User A as the most suitable member.

[0257] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This updated profile is then used for optimal placement in future projects.

[0258] As described above, the system of the present invention combines data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means to achieve precise evaluation and optimal personnel placement that takes into account the user's emotional information.

[0259] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0260] Step 1:

[0261] The user logs into the system and answers an online questionnaire. The user's login information and questionnaire responses are provided as input. The questionnaire includes questions about personality assessment and job-related matters. Specifically, the user answers questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" The user's response data is generated as output.

[0262] Step 2:

[0263] The server collects data such as past emails, chat messages, and meeting records with the user's permission. User consent data and access information are provided as input. APIs and log analysis tools are used for data collection. Specifically, the server accesses these data sources and retrieves the relevant communication content. As output, the collected data is stored in temporary storage.

[0264] Step 3:

[0265] The server preprocesses the collected data using data analysis tools. The raw data is provided as input. Specifically, irrelevant information is filtered out, and important keywords and phrases are extracted. For example, natural language processing techniques are used to extract keywords related to task management. The output is preprocessed, clean data.

[0266] Step 4:

[0267] The server extracts user emotional information using sentiment analysis tools. Pre-processed, clean data is provided as input. Specifically, the sentiment analysis engine extracts emotions from text and classifies them as positive, negative, or neutral. For example, the message "This project is fun" would be recognized as a positive emotion. Emotionally labeled data is generated as output.

[0268] Step 5:

[0269] The server uses a generative AI model to evaluate the user's personality traits. The input is emotion-labeled data. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to create a detailed personality profile that includes emotional information. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The output is the generated, evaluated personality profile.

[0270] Step 6:

[0271] HR personnel use a terminal to input project requirements into the system. The input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these requirements. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended. The output is a list of recommended team members.

[0272] Step 7:

[0273] During the project, users provide feedback. Input includes feedback on project progress and team harmony. Specifically, the server analyzes the feedback data using feedback analysis tools and updates the user's profile. For example, harmony among team members, work performance, and emotional fluctuations are analyzed. The updated user profile is generated and stored in the database.

[0274] The above outlines the specific processing flow of this system and details the actions performed at each step. This enables precise evaluation that takes user emotional information into account and optimal staffing.

[0275] (Application Example 2)

[0276] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0277] In modern factories, it is difficult to assign tasks optimally based on the skill sets and personality traits of workers and robots. Furthermore, detailed profiling that takes emotional information into account and improvements based on feedback are not sufficiently implemented. As a result, problems arise with decreased production efficiency and work harmony.

[0278] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is realized by the following means. In this invention, the server includes data analysis means, personality characteristic evaluation means using a generated AI model, sentiment analysis means, real-time data collection means, and task automatic allocation means. Thereby, based on the personality characteristics and sentiment information of workers and robots, optimal work allocation and team formation become possible.

[0279] The "data analysis means" is means for preprocessing and analyzing the collected data.

[0280] The "personality characteristic evaluation means using a generated AI model" is means for evaluating the personality characteristics and skill sets of users using a generated AI model.

[0281] The "personnel allocation recommendation means" is means for recommending optimal personnel allocation and team formation based on the collected data and evaluation results.

[0282] The "feedback analysis means" is means for collecting and analyzing feedback on the progress of projects or tasks.

[0283] The "database update means" is means for updating the database using the analysis results and feedback data.

[0284] The "sentiment analysis means" is means for analyzing the sentiment information of users from the data collected using natural language processing technology.

[0285] The "real-time data collection means" is means for collecting the operation data and text data of workers and robots in real time.

[0286] The "task automatic allocation means" is means for automatically allocating tasks to workers and robots based on the requirements of projects and the profiles of users.

[0287] This document describes a system for carrying out this invention. This system enables optimal placement and task allocation of workers and robots in a factory. The specific details are shown below.

[0288] Hardware and software

[0289] Hardware:

[0290] Factory robots

[0291] Sensors (camera, microphone, temperature sensor, etc.)

[0292] Server (for data analysis and AI model execution)

[0293] software:

[0294] Natural language processing tools (e.g., spaCy, NLTK)

[0295] Sentiment analysis engines (e.g., IBM Watson, Microsoft Cognitive Services)

[0296] Generative AI models (e.g., GPT-4)

[0297] Databases (e.g., MySQL, PostgreSQL)

[0298] Program processing details

[0299] The server first collects data in real time from factory workers and robots. The collected data includes work motion data and text data (conversation logs). Data from sensors and log files is sent to the server.

[0300] Next, the server uses natural language processing technology to analyze the data and extract sentiment information from the collected data. The sentiment analysis engine recognizes the user's sentiment state from the text data and obtains sentiment information such as positive, negative, and neutral. This sentiment information is stored in the database.

[0301] After that, the server uses a generative AI model to analyze the data containing sentiment information and evaluate in detail the personality characteristics and skill sets of the workers and robots. As a result, a personality profile for each worker and robot is generated. This profile is stored in the database.

[0302] When the requirements of the project are input, the server automatically assigns tasks to the optimal workers and robots based on the profiles stored in the database. This takes into account the skill sets and personality characteristics required for each task of the project. The results of the task assignment are also stored in the database.

[0303] Finally, the server collects feedback on the progress of the project and the harmony of the work and analyzes it. The results of the feedback are used to update the profiles of the workers and robots. The updated profiles are utilized for subsequent task assignments.

[0304] Specific example

[0305] For example, in Project A, workers and robots with high task management capabilities and stable emotions are required. Based on those requirements, the system automatically assigns the optimal members and updates the profiles based on feedback during the project.

[0306] Prompt sentence example

[0307] "In Project A, Task A1 requires high precision and a stable emotional state. Task A2 emphasizes task management capabilities, and appropriate workers and robots should be assigned."

[0308] Thus, the present invention is a system that takes into account the emotional information and personality traits of workers and robots, and significantly improves work efficiency and harmony within the factory.

[0309] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0310] Step 1:

[0311] The server collects data in real time from factory workers and robots. Inputs include motion data and conversation logs from sensors and log files. The server receives this data and preprocesses it using a data collection module. Specific operations include standardizing data formats and filtering out unnecessary data. The output is the preprocessed data.

[0312] Step 2:

[0313] The server analyzes the preprocessed data using natural language processing techniques. The input includes the preprocessed data obtained in step 1. Here, a natural language processing tool (e.g., spaCy) is used to analyze the text data. Specific operations include keyword extraction and contextual analysis from the text data. The output is the analyzed text data.

[0314] Step 3:

[0315] The server analyzes the parsed text data using a sentiment analysis engine and extracts sentiment information. The input includes the parsed text data obtained in step 2. Using a sentiment analysis engine (e.g., IBM Watson), it obtains sentiment information such as positive, negative, and neutral from the text data. Specifically, this involves sentiment tagging of the text data. The output is text data containing sentiment information.

[0316] Step 4:

[0317] The server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of workers and robots. The input includes emotionally charged text data obtained in step 3. A generative AI model (e.g., GPT-4) is used to evaluate personality profiles and skill sets. The specific operations involve inputting data into the model and extracting evaluation results. The output consists of personality profiles and skill sets.

[0318] Step 5:

[0319] The terminal inputs project requirements into the server. This input includes required skill sets, personality traits, roles, and emotional stability. This input then submits the specific project requirements to the server. The process involves the user inputting requirements into the terminal and sending data to the server. The output is the project requirements.

[0320] Step 6:

[0321] The server automatically assigns tasks to the most suitable workers or robots based on project requirements. Inputs include project requirements obtained in step 5 and personality profiles and skill sets obtained in step 4. An automated task assignment algorithm is used to calculate the optimal combination. Specific operations include data combination processing and generation of assignment results. The output is the optimal task assignment result.

[0322] Step 7:

[0323] The server collects and analyzes feedback on work progress and team cohesion throughout the project. Input includes feedback data. The server uses a feedback analysis engine to re-analyze sentiment information and work data. Specific operations include collecting and analyzing feedback data. Output includes evaluation results and updated profiles.

[0324] Step 8:

[0325] The server updates the database with worker and robot profiles based on the feedback analysis results. The input includes the evaluation results obtained in step 7. The server uses a database update module to update the profile information. Specifically, it updates and maintains the database. The output is the updated database.

[0326] The above describes the specific processing steps and their operation for implementing this invention.

[0327] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0328] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0329] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0330] [Second Embodiment]

[0331] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0332] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0333] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0334] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0335] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0336] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0337] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0338] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0339] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0340] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0341] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0342] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0344] Program Processing Description

[0345] Data Acquisition and Preprocessing

[0346] Users access the system and answer questionnaires. These questionnaires include self-assessment and job-related questions, revealing the user's personality traits and skill set. With the user's permission, the server also collects past emails, chat messages, meeting records, etc. The server preprocesses this data and extracts only meaningful information.

[0347] Analysis of personality and abilities

[0348] The server analyzes the collected data using natural language processing techniques. Specifically, it performs sentiment analysis, topic modeling, and keyword extraction to visualize the user's personality traits and skills. Subsequently, a generative AI model is used to evaluate the user's personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile.

[0349] Team formation and recommendations

[0350] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This includes required skill sets, personality traits, and roles. Based on these project requirements, the server calculates the optimal team composition. In doing so, it compares the user's personality profile and skill set to propose a well-balanced team structure.

[0351] Feedback and updates

[0352] After team formation, users provide feedback on project progress and team cohesion. This feedback is periodically sent to and analyzed by the server. The server analyzes the feedback and updates the user's profile based on the results. This update allows for more accurate personnel allocation in future team formations.

[0353] Specific example

[0354] Data Acquisition and Preprocessing

[0355] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0356] Analysis of personality and abilities

[0357] The server analyzes user A's data and assesses that they possess advanced skills in "task management ability" and "leadership." A generative AI model confirms this and stores it in the database as user A's personality profile.

[0358] Team formation and recommendations

[0359] Next, the company enters into the system that a "leader with strong task management skills" is required as a project requirement for launching a new project. Based on this, the server recommends User A as the most suitable member for the project.

[0360] Feedback and updates

[0361] As the project progresses, User A and other team members provide feedback. This feedback includes information about User A's leadership and team cohesion. The server analyzes this and updates User A's profile. This update allows for appropriate placement in future projects.

[0362] Thus, the present invention precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0366] Step 2:

[0367] The server receives user survey responses and stores them in a database. Simultaneously, it collects the user's past emails, chat logs, and meeting records. Prior user consent is required for this collection.

[0368] Step 3:

[0369] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0370] Step 4:

[0371] The server uses natural language processing (NLP) techniques to analyze the organized data. Specifically, it performs sentiment analysis, extracts keywords and topics from the text, and assesses the user's characteristics and skills.

[0372] Step 5:

[0373] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but low cooperativeness. The evaluation results are stored in a database.

[0374] Step 6:

[0375] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, and role. For example, "data scientist" or "highly collaborative leader."

[0376] Step 7:

[0377] The server analyzes project requirements and calculates the optimal staffing based on user personality profiles and skill sets. Multiple filtering algorithms are used to recommend the most suitable members.

[0378] Step 8:

[0379] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics and skills.

[0380] Step 9:

[0381] Users provide feedback during the project. This feedback includes information about team cohesion and the performance of each member. This feedback is collected regularly.

[0382] Step 10:

[0383] The server analyzes the feedback data and updates the user's personality profile. NLP techniques are used again for the feedback analysis, and actual performance evaluation is performed.

[0384] Step 11:

[0385] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[0386] Through the steps described above, the present invention enables effective staffing and improves overall organizational performance and satisfaction.

[0387] (Example 1)

[0388] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0389] Currently, many companies and organizations are attempting to effectively staff based on employee personality traits and skills. However, traditional methods are time-consuming to collect and analyze data, and their accuracy is low, making it difficult to achieve optimal placement. Furthermore, updating employee profiles as projects progress is not easy. This makes it difficult to form teams that fully utilize the potential of employees.

[0390] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0391] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, and database update means. This makes it possible to precisely evaluate the personality traits and skills of employees and to achieve optimal personnel placement based on the evaluation results. Furthermore, by analyzing project feedback and updating profiles, appropriate placement becomes possible for future projects as well, maximizing the capabilities of employees.

[0392] "Data analysis means" refers to devices or software that collect and preprocess data such as questionnaires answered by users when they access the system, past emails, chat messages, and meeting records. Preprocessing includes noise removal and extraction of meaningful information.

[0393] "Personality trait evaluation method using generative AI models" refers to a device or software that analyzes data collected using natural language processing technology to evaluate the user's personality traits and skills, and the evaluation results are stored as a profile in a database.

[0394] A "personnel placement recommendation tool" is a device or software that, based on project requirements, matches the personality traits and skill profiles of evaluated users to recommend the most suitable team members.

[0395] A "feedback analysis tool" is a device or software that collects user feedback regarding project progress and team harmony, and updates the user's profile based on the analysis results.

[0396] A "database update method" refers to a device or software that updates user profiles based on feedback and analysis results, reflecting the latest information in the database.

[0397] "Natural language processing technology" is a technique that analyzes text data and performs sentiment analysis, topic modeling, keyword extraction, etc., and is mainly used to evaluate users' personality traits and skills.

[0398] A "profile" is data that records evaluation results regarding a user's personality traits and skills, and is stored in a database.

[0399] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0400] Data Acquisition and Preprocessing

[0401] Users first access the system and answer a questionnaire. This questionnaire includes questions about self-assessment and job-related matters, revealing the user's personality traits and skill set. With the user's permission, the server also collects data such as past emails, chat messages, and meeting records. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes, for example, titles, signatures, and automated messages, and extracts keywords related to task management.

[0402] Analysis of personality and abilities

[0403] The server analyzes the collected data using natural language processing techniques. It performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. Subsequently, it uses a generative AI model to evaluate personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile. For example, if "User A's leadership skills are high" is evaluated, this result will be recorded in the profile.

[0404] Team formation and recommendations

[0405] When a company or organization launches a new project, HR personnel use a terminal to input project requirements into the system. This includes necessary skill sets, personality traits, and roles. Based on these requirements, the server matches user profiles to calculate the optimal team composition and proposes a balanced team structure. For example, if the input states, "New Project X requires a leader with strong task management skills," the server will recommend user A as the leader.

[0406] Feedback and updates

[0407] As the project progresses, users provide feedback on the project's progress and the team's cohesion. This feedback is periodically sent to the server for analysis. The server updates user profiles based on the feedback, enabling more accurate personnel allocation for future projects. For example, if User B provides feedback stating, "I am satisfied with User A's leadership," this information will be reflected in User A's profile.

[0408] Example of a prompt

[0409] The following are examples of specific prompt statements used by the system.

[0410] "Please recommend a leader with strong task management skills for our new project."

[0411] "Analyze User A's leadership and task management skills and evaluate whether they meet the project requirements."

[0412] Thus, the present invention is a system that precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0413] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0414] Step 1:

[0415] Users access the system and answer questionnaires. These questionnaire responses become input data. The server collects this data for later analysis. Specifically, users input data in the form of self-assessments and questions about their work. For example, a user might answer the question, "How do you feel about working in a team?"

[0416] Step 2:

[0417] With the user's permission, the server collects past emails, chat messages, and meeting records. The collected text data becomes the input data. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes honorifics, signatures, and auto-generated messages, and extracts keywords related to task management. For example, "Extract important keywords from User A's email communication records for the past year."

[0418] Step 3:

[0419] The server analyzes the data collected in Steps 1 and 2 using natural language processing techniques. The results of this analysis are output as intermediate data. Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. For example, "extract keywords related to 'cooperativeness' and 'leadership' from User A's emails."

[0420] Step 4:

[0421] The server uses a generative AI model to perform a detailed evaluation of the user's personality traits and skills based on the analysis results from step 3. This evaluation result is saved as profile data. Specifically, it might be evaluated as "User A has high leadership skills." This data is stored in the database.

[0422] Step 5:

[0423] An HR representative uses a terminal to input project requirements into the system. This requirements data becomes the input data. The server matches the requirements data with user profiles and calculates the optimal team composition. This result is output as team member recommendation data. Specifically, it might input something like, "New Project X requires a leader with strong task management skills."

[0424] Step 6:

[0425] The server recommends the most suitable user based on the requirements data from Step 5. The recommendation result is output data and displayed on the terminal. Specifically, the data displayed will say, "We recommend User A as the leader of Project X."

[0426] Step 7:

[0427] During project progress, users provide feedback on the progress and team harmony. This feedback data becomes input data. The server collects and analyzes this feedback. Specifically, the input might be, "User B is satisfied with User A's leadership."

[0428] Step 8:

[0429] The server analyzes the feedback data and updates the user's profile based on the results. This updated data becomes the output data and is used for future personnel assignments. For example, "Update User A's profile to 'Leadership skills rated higher based on feedback'."

[0430] Thus, the system of the present invention processes and analyzes data at each step to achieve optimal personnel allocation.

[0431] (Application Example 1)

[0432] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0433] Traditional factory management methods made it difficult to optimize staffing and team formation, hindering efficient production and effective utilization of human resources. Furthermore, dynamic updates to profiles based on feedback were not implemented, potentially leading to similar problems recurring in subsequent projects.

[0434] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0435] In this invention, the server includes functions for data collection and preprocessing, personality and ability analysis, team composition recommendation, and profile updating based on feedback. This enables optimal team formation based on the skills and personality traits of individual factory employees, and by sequentially updating profiles based on feedback, highly accurate personnel allocation becomes possible in subsequent projects as well.

[0436] "Data analysis methods" refer to methods for collecting data such as questionnaires, communication records, and work records, and extracting detailed information through preprocessing.

[0437] "Personality trait evaluation method using generative AI models" refers to a method that uses natural language processing technology to evaluate a user's personality traits and abilities.

[0438] A "personnel placement recommendation system" is a method of recommending the most suitable personnel for a specific project or task based on collected data and evaluation results from a generated AI model.

[0439] A "feedback analysis method" is a means of analyzing feedback data collected after the project is completed and updating the user profile.

[0440] A "database update method" is a means of saving and updating user profiles in a database based on analyzed data and feedback.

[0441] The "data collection and preprocessing function" refers to a function that collects data such as questionnaires, communication records, and work records, extracts the necessary information, and performs preprocessing.

[0442] The "personality and ability analysis function" is a function that uses collected data to evaluate the user's personality traits and skills.

[0443] The "team composition recommendation function" is a function that recommends the optimal personnel allocation and team composition based on project requirements.

[0444] The "feedback-based profile update function" is a function that analyzes user feedback and updates the user's profile based on that feedback.

[0445] To implement this invention, the following basic system configuration and processing flow are used.

[0446] System Configuration

[0447] The system consists of a data collection server, a GPU server for personality and ability analysis, a database server, and client terminals. The entire system includes various hardware and software components, such as:

[0448] Hardware:

[0449] Data collection server: This server collects and preprocesses data such as surveys, communication records, and business records. It is equipped with a CPU and adequate memory.

[0450] GPU Server for Personality and Ability Analysis: This server is equipped with a high-performance graphics processor (GPU) to evaluate personality traits and abilities using natural language processing technology.

[0451] Database Server: This server is used to store and update evaluation results and feedback data. It is equipped with data storage that has high I / O performance.

[0452] Client terminals: These are terminals used by HR personnel and employees to access the system. This includes desktop PCs and mobile devices.

[0453] software:

[0454] Data analysis libraries: These are libraries used for data preprocessing and analysis, such as Pandas and NumPy.

[0455] Natural language processing libraries: These include libraries such as Transformers and BERT, which are used for personality trait evaluation.

[0456] Database management system: This refers to database software such as MySQL or PostgreSQL used to store and manage evaluation results and feedback.

[0457] Processing details for each means

[0458] Data acquisition and preprocessing means

[0459] Users access the system and periodically answer questionnaires. These questionnaires include self-assessment and job-related questions and are provided through web forms and mobile apps. With user permission, past emails, chat messages, and work records are also collected. The data collection server preprocesses this data, performing keyword extraction and data cleansing.

[0460] Methods for analyzing personality and abilities

[0461] The preprocessed data is analyzed using natural language processing techniques. Specifically, the BERT model is used for sentiment analysis, topic modeling, and keyword extraction to evaluate the user's personality traits and skills. These analyses are performed at high speed on a GPU server, and a generative AI model generates the evaluation results.

[0462] Team formation recommendation methods

[0463] The terminal used to input project requirements allows users to enter information such as required skill sets, personality traits, and roles. The server calculates the optimal team composition based on the entered requirements. To ensure a balanced team, it compares the user's personality profile with their skill set. This recommendation is displayed on the client terminal.

[0464] Feedback and profile update methods

[0465] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications. This feedback data is stored on a database server and analyzed periodically. The analysis results are reflected in the user's profile and accumulated as information useful for future team formations.

[0466] Specific example

[0467] For example, suppose a "leader with strong task management skills" is needed to set up a new production line in a factory. In this case, the system would input "leader with strong task management skills" and "worker skilled in machine operation" as project requirements. The system would then analyze past data and recommend the most suitable personnel.

[0468] Example of a prompt

[0469] Project Requirements: "Leaders with strong task management skills" and "Workers skilled in machine operation"

[0470] Evaluation profile:

[0471] [

[0472] {"Name": "A", "Task Management": 9, "Leadership": 8, "Machine Operation": 7}

[0473] {"Name": "B", "Task Management": 7, "Leadership": 9, "Machine Operation": 8}

[0474] {"Name": "C", "Task Management": 6, "Leadership": 9, "Machine Operation": 5}

[0475] ]

[0476] Based on the prompt, the system recommends "A" as the leader and "B" as the assistant. In this way, optimal personnel allocation and team formation are achieved.

[0477] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0478] Step 1:

[0479] Users access the system and answer questionnaires, which include questions about self-assessment and job-related matters. The questionnaire data entered by users is collected. This data includes information about the user's personality traits and skill set. The server receives this data and performs cleaning and initial preprocessing.

[0480] Step 2:

[0481] The server collects user survey data, past emails, chat messages, and work records. This data is also pre-processed. Specific pre-processing steps include deleting unnecessary data, normalizing text, and extracting keywords. The pre-processed data is then stored on the database server.

[0482] Step 3:

[0483] The server analyzes pre-processed data using natural language processing techniques. This analysis utilizes the BERT model for sentiment analysis, topic modeling, and keyword extraction. Using pre-processed text data as input, the output provides results that evaluate the user's personality traits and skills. These results are stored in a database as the user's personality profile.

[0484] Step 4:

[0485] Using a terminal, HR personnel enter project requirements into the system. This includes information such as required skill sets, personality traits, and roles. The server receives these project requirements and compares them with the user's personality profile stored in the database.

[0486] Step 5:

[0487] The server performs calculations to recommend the optimal team composition based on project requirements and the user's personality profile. Specifically, it generates prompt statements and provides them as input to a generative AI model. The generative AI model selects the most suitable team members based on the input and outputs the recommendation results. These recommendation results are displayed on the terminal.

[0488] Step 6:

[0489] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications and sent to the server. The feedback data includes information such as the project's progress, team cohesion, and the contributions of individual members.

[0490] Step 7:

[0491] The server analyzes the collected feedback data and updates the user's personality profile. The analysis again utilizes natural language processing techniques such as sentiment analysis and topic modeling. Feedback is used as input data, and the updated personality profile is obtained as output and stored in the database.

[0492] Step 8:

[0493] After a project is completed, the updated personality profiles will be used for future projects. These profiles will be compared to new project requirements to aid in future team building. This will enable continuously improving and optimized personnel allocation.

[0494] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0495] The present invention provides a system that includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, database update means, and an emotion engine that recognizes user emotions.

[0496] Program Processing Description

[0497] Data Acquisition and Preprocessing

[0498] Users log into the system and answer an online questionnaire. This questionnaire includes questions about personality assessment and job-related matters, such as "Are you good at demonstrating leadership?" or "How do you perform in stressful environments?". The server also collects data such as past emails, chat messages, and meeting records with the user's permission.

[0499] Extraction and analysis of emotional information

[0500] The server preprocesses the collected data using an emotion engine to analyze the user's emotional information. The emotion engine uses natural language processing techniques to extract emotions such as positive, negative, and neutral from the text. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion.

[0501] Analysis of personality and abilities

[0502] The server uses a generative AI model to evaluate the user's personality traits based on the results of emotional information extraction by the emotion engine. Because emotional information is also incorporated into this evaluation, a more refined personality profile is created. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The evaluation results are stored in a database.

[0503] Team formation and recommendations

[0504] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these project requirements, taking into account user personality profiles, skill sets, and emotional information.

[0505] Feedback and updates

[0506] After team formation, users provide feedback on project progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to the server for analysis.

[0507] The server analyzes the feedback and updates the user's profile. This update uses the sentiment engine again to re-extract sentiment information from the feedback. The updated profile is saved in the database and used to improve the accuracy of future staffing decisions.

[0508] Specific example

[0509] Data Acquisition and Preprocessing

[0510] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0511] Extraction and analysis of emotional information

[0512] The server uses an emotion engine to extract emotional information from user A's data. For example, a message like "This project is fun" is recognized as a positive emotion.

[0513] Analysis of personality and abilities

[0514] The server analyzes user A's data, including emotional information, using a generating AI model to evaluate personality traits in detail. For example, it might be assessed that user A has high task management skills and a positive mindset, but occasionally experiences emotional fluctuations.

[0515] Team formation and recommendations

[0516] When an HR representative enters the requirements for a new project into the system—specifically, "a leader with strong task management skills and a positive attitude"—the server recommends User A as the most suitable member.

[0517] Feedback and updates

[0518] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This allows for optimal placement in future projects as well.

[0519] As described above, the present invention, by combining an emotion engine, takes into account the user's emotional information, thereby achieving more precise and effective personnel allocation.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0523] Step 2:

[0524] The server receives user survey responses and stores them in a database. Simultaneously, with the user's permission, it collects work-related data such as past emails, chat messages, and meeting records.

[0525] Step 3:

[0526] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0527] Step 4:

[0528] The server extracts emotional information from pre-processed data using an emotion engine. The emotion engine leverages natural language processing techniques to identify and classify emotional expressions within text. For example, the message "I'm really looking forward to it!" in a chat log is recognized as a positive emotion.

[0529] Step 5:

[0530] The server uses natural language processing (NLP) techniques to analyze the organized data (including sentiment information). Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to assess user characteristics and skills.

[0531] Step 6:

[0532] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but also experiencing intense emotional fluctuations. The evaluation results are stored in a database.

[0533] Step 7:

[0534] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, role, and emotional stability. For example, "data scientist" or "highly collaborative leader."

[0535] Step 8:

[0536] Based on project requirements, the server calculates the optimal team composition, taking into account user personality profiles, skill sets, and emotional information. Multiple filtering algorithms are used to recommend the most suitable members.

[0537] Step 9:

[0538] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics, skills, and emotional stability.

[0539] Step 10:

[0540] Users provide feedback during the project. This feedback includes aspects such as the level of harmony among team members, the progress of work, and emotional fluctuations. This feedback is sent to the server periodically.

[0541] Step 11:

[0542] The server analyzes the feedback data and updates the user's personality profile. NLP techniques and an emotion engine are again used for the feedback analysis, reflecting actual performance evaluations and emotional changes.

[0543] Step 12:

[0544] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[0545] Through the steps described above, the present invention, by including an emotion engine, takes into account the user's emotional information and achieves more precise and effective personnel allocation.

[0546] (Example 2)

[0547] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0548] In modern companies and organizations, optimal staffing is a critical issue directly linked to project success and improved efficiency. However, traditional staffing methods often rely solely on skill sets and experience, making it difficult to consider individual members' personality traits and emotional states. This can easily lead to team disharmony and decreased work efficiency. Furthermore, insufficient real-time feedback-based profile updates meant a lack of adaptability to dynamic project environments.

[0549] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0550] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, and emotion analysis means using an emotion engine that recognizes the user's emotions. This enables precise evaluation that takes into account the user's personality traits and emotional information, allowing for optimal staffing and real-time profile updates.

[0551] "Data analysis methods" refer to methods for collecting information such as surveys, emails, chats, and meeting records, and extracting necessary keywords and data through preprocessing.

[0552] "Personality trait evaluation method using generative AI models" refers to a method that utilizes natural language processing technology to evaluate personality traits, including emotional information, from text in collected data.

[0553] A "personnel placement recommendation method" is a means of selecting and recommending members who are best suited to the requirements of a project or team, based on evaluated personality traits, skill sets, and emotional information.

[0554] A "feedback analysis method" is a means of analyzing feedback information provided by users and team members during the progress of a project to evaluate the team's harmony and the status of work execution.

[0555] A "database update method" refers to a method of periodically updating user profiles based on the results of feedback analysis, etc., and utilizing this information for future evaluations and personnel allocation.

[0556] "Emotional analysis means" refers to a method of extracting user emotional information from text collected using natural language processing technology and analyzing emotional states such as positive, negative, and neutral.

[0557] The present invention is a system that includes data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means. Specific embodiments of each means will be described below.

[0558] This system has the following configuration: Users first log in to the system and answer an online questionnaire. The questionnaire includes questions about personality assessment and job-related matters. For example, it includes questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" This collects the necessary personality information.

[0559] The server collects data such as past emails, chat messages, and meeting records with the user's permission. This data is preprocessed using data analysis tools to extract necessary keywords and data. This involves using software that employs natural language processing techniques (e.g., Apache OpenNLP or NLTK).

[0560] Next, the collected data is analyzed using sentiment analysis techniques. These techniques use natural language processing to classify emotions within the text as positive, negative, neutral, etc. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion. A sentiment analysis engine (e.g., IBM Watson Tone Analyzer) is used for this analysis.

[0561] The analyzed emotional information is incorporated into personality trait assessments by generative AI models (e.g., GPT-3 or BERT). The server then uses this information to evaluate the user's personality traits and create a more refined profile. For example, "User A" might be assessed as having strong leadership and analytical skills, but also experiencing significant emotional fluctuations. The assessment results are stored in a database and used for future personnel placement and evaluations.

[0562] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. Based on these requirements, the server calculates the optimal team composition. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended.

[0563] During project progress, users provide feedback on the project's progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to a server and analyzed using feedback analysis tools. The server updates the user's profile based on the analysis results and stores it in a database. This helps improve the accuracy of future personnel allocation.

[0564] Specific example

[0565] User A logs into the system and answers a "self-assessment questionnaire." The server collects User A's questionnaire responses and past email communication data, and extracts keywords related to task management. This data is analyzed using a sentiment analysis engine, and messages such as "This project is fun" are recognized as positive emotions.

[0566] Next, the data, including the analyzed emotional information, is analyzed using a generating AI model to evaluate User A's personality traits. The evaluation results indicate that User A has "high task management skills and a positive outlook, but occasionally experiences emotional fluctuations." When an HR person enters the requirements for a new project into the system, the server recommends User A as the most suitable member.

[0567] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This updated profile is then used for optimal placement in future projects.

[0568] As described above, the system of the present invention combines data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means to achieve precise evaluation and optimal personnel placement that takes into account the user's emotional information.

[0569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0570] Step 1:

[0571] The user logs into the system and answers an online questionnaire. The user's login information and questionnaire responses are provided as input. The questionnaire includes questions about personality assessment and job-related matters. Specifically, the user answers questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" The user's response data is generated as output.

[0572] Step 2:

[0573] The server collects data such as past emails, chat messages, and meeting records with the user's permission. User consent data and access information are provided as input. APIs and log analysis tools are used for data collection. Specifically, the server accesses these data sources and retrieves the relevant communication content. As output, the collected data is stored in temporary storage.

[0574] Step 3:

[0575] The server preprocesses the collected data using data analysis tools. The raw data is provided as input. Specifically, irrelevant information is filtered out, and important keywords and phrases are extracted. For example, natural language processing techniques are used to extract keywords related to task management. The output is preprocessed, clean data.

[0576] Step 4:

[0577] The server extracts user emotional information using sentiment analysis tools. Pre-processed, clean data is provided as input. Specifically, the sentiment analysis engine extracts emotions from text and classifies them as positive, negative, or neutral. For example, the message "This project is fun" would be recognized as a positive emotion. Emotionally labeled data is generated as output.

[0578] Step 5:

[0579] The server uses a generative AI model to evaluate the user's personality traits. The input is emotion-labeled data. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to create a detailed personality profile that includes emotional information. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The output is the generated, evaluated personality profile.

[0580] Step 6:

[0581] HR personnel use a terminal to input project requirements into the system. The input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these requirements. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended. The output is a list of recommended team members.

[0582] Step 7:

[0583] During the project, users provide feedback. Input includes feedback on project progress and team harmony. Specifically, the server analyzes the feedback data using feedback analysis tools and updates the user's profile. For example, harmony among team members, work performance, and emotional fluctuations are analyzed. The updated user profile is generated and stored in the database.

[0584] The above outlines the specific processing flow of this system and details the actions performed at each step. This enables precise evaluation that takes user emotional information into account and optimal staffing.

[0585] (Application Example 2)

[0586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0587] In modern factories, it is difficult to assign tasks optimally based on the skill sets and personality traits of workers and robots. Furthermore, detailed profiling that takes emotional information into account and improvements based on feedback are not sufficiently implemented. As a result, problems arise with decreased production efficiency and work harmony.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data analysis means, personality trait evaluation means using a generated AI model, emotion analysis means, real-time data collection means, and task automatic assignment means. This makes it possible to assign tasks and form teams optimally based on the personality traits and emotion information of workers and robots.

[0589] "Data analysis means" refers to methods for preprocessing and analyzing collected data.

[0590] "Personality trait evaluation method using generative AI models" refers to a method of evaluating a user's personality traits and skill set using generative AI models.

[0591] A "personnel allocation recommendation method" is a means of recommending the optimal personnel allocation and team composition based on collected data and evaluation results.

[0592] A "feedback analysis method" is a means of collecting and analyzing feedback regarding the progress of a project or task.

[0593] A "database update method" is a means of updating a database using analysis results and feedback data.

[0594] "Emotional analysis methods" refer to methods for analyzing user emotional information from data collected using natural language processing technology.

[0595] A "real-time data collection method" is a means of collecting motion data and text data of workers and robots in real time.

[0596] A "task automation system" is a method for automatically assigning tasks to workers or robots based on project requirements and user profiles.

[0597] This document describes a system for carrying out this invention. This system enables optimal placement and task allocation of workers and robots in a factory. The specific details are shown below.

[0598] Hardware and software

[0599] Hardware:

[0600] Factory robots

[0601] Sensors (camera, microphone, temperature sensor, etc.)

[0602] Server (for data analysis and AI model execution)

[0603] software:

[0604] Natural language processing tools (e.g., spaCy, NLTK)

[0605] Sentiment analysis engines (e.g., IBM Watson, Microsoft Cognitive Services)

[0606] Generative AI models (e.g., GPT-4)

[0607] Databases (e.g., MySQL, PostgreSQL)

[0608] Program processing details

[0609] The server first collects data in real time from factory workers and robots. The collected data includes work motion data and text data (conversation logs). Data from sensors and log files is sent to the server.

[0610] Next, the server uses natural language processing techniques to analyze the data and extract sentiment information from the collected data. The sentiment analysis engine recognizes the user's emotional state from the text data and obtains sentiment information such as positive, negative, or neutral. This sentiment information is stored in a database.

[0611] Subsequently, the server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of the workers and robots in detail. This generates a personality profile for each worker and robot, which is then stored in a database.

[0612] Once project requirements are entered, the server automatically assigns tasks to the most suitable workers or robots based on profiles stored in the database. This takes into account the skill sets and personality traits required for each task in the project. The assignment results are also stored in the database.

[0613] Finally, the server collects and analyzes feedback on the project's progress and the harmony of the work. The results of the feedback are used to update the profiles of the workers and robots. The updated profiles are then used for future task assignments.

[0614] Specific example

[0615] For example, Project A requires workers and robots with strong task management skills and stable emotions. Based on these requirements, the system automatically assigns the most suitable members and updates their profiles based on feedback during the project.

[0616] Prompt example

[0617] "In Project A, Task A1 requires high precision and a stable emotional state. Task A2 emphasizes task management skills and the allocation of appropriate workers and robots."

[0618] Thus, the present invention is a system that takes into account the emotional information and personality traits of workers and robots, and significantly improves work efficiency and harmony within the factory.

[0619] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0620] Step 1:

[0621] The server collects data in real time from factory workers and robots. Inputs include motion data and conversation logs from sensors and log files. The server receives this data and preprocesses it using a data collection module. Specific operations include standardizing data formats and filtering out unnecessary data. The output is the preprocessed data.

[0622] Step 2:

[0623] The server analyzes the preprocessed data using natural language processing techniques. The input includes the preprocessed data obtained in step 1. Here, a natural language processing tool (e.g., spaCy) is used to analyze the text data. Specific operations include keyword extraction and contextual analysis from the text data. The output is the analyzed text data.

[0624] Step 3:

[0625] The server analyzes the parsed text data using a sentiment analysis engine and extracts sentiment information. The input includes the parsed text data obtained in step 2. Using a sentiment analysis engine (e.g., IBM Watson), it obtains sentiment information such as positive, negative, and neutral from the text data. Specifically, this involves sentiment tagging of the text data. The output is text data containing sentiment information.

[0626] Step 4:

[0627] The server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of workers and robots. The input includes emotionally charged text data obtained in step 3. A generative AI model (e.g., GPT-4) is used to evaluate personality profiles and skill sets. The specific operations involve inputting data into the model and extracting evaluation results. The output consists of personality profiles and skill sets.

[0628] Step 5:

[0629] The terminal inputs project requirements into the server. This input includes required skill sets, personality traits, roles, and emotional stability. This input then submits the specific project requirements to the server. The process involves the user inputting requirements into the terminal and sending data to the server. The output is the project requirements.

[0630] Step 6:

[0631] The server automatically assigns tasks to the most suitable workers or robots based on project requirements. Inputs include project requirements obtained in step 5 and personality profiles and skill sets obtained in step 4. An automated task assignment algorithm is used to calculate the optimal combination. Specific operations include data combination processing and generation of assignment results. The output is the optimal task assignment result.

[0632] Step 7:

[0633] The server collects and analyzes feedback on work progress and team cohesion throughout the project. Input includes feedback data. The server uses a feedback analysis engine to re-analyze sentiment information and work data. Specific operations include collecting and analyzing feedback data. Output includes evaluation results and updated profiles.

[0634] Step 8:

[0635] The server updates the database with worker and robot profiles based on the feedback analysis results. The input includes the evaluation results obtained in step 7. The server uses a database update module to update the profile information. Specifically, it updates and maintains the database. The output is the updated database.

[0636] The above describes the specific processing steps and their operation for implementing this invention.

[0637] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0638] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0639] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0640] [Third Embodiment]

[0641] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0642] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0643] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0644] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0645] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0646] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0647] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0648] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0649] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0650] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0651] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0652] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0653] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0654] Program Processing Description

[0655] Data Acquisition and Preprocessing

[0656] Users access the system and answer questionnaires. These questionnaires include self-assessment and job-related questions, revealing the user's personality traits and skill set. With the user's permission, the server also collects past emails, chat messages, meeting records, etc. The server preprocesses this data and extracts only meaningful information.

[0657] Analysis of personality and abilities

[0658] The server analyzes the collected data using natural language processing techniques. Specifically, it performs sentiment analysis, topic modeling, and keyword extraction to visualize the user's personality traits and skills. Subsequently, a generative AI model is used to evaluate the user's personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile.

[0659] Team formation and recommendations

[0660] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This includes required skill sets, personality traits, and roles. Based on these project requirements, the server calculates the optimal team composition. In doing so, it compares the user's personality profile and skill set to propose a well-balanced team structure.

[0661] Feedback and updates

[0662] After team formation, users provide feedback on project progress and team cohesion. This feedback is periodically sent to and analyzed by the server. The server analyzes the feedback and updates the user's profile based on the results. This update allows for more accurate personnel allocation in future team formations.

[0663] Specific example

[0664] Data Acquisition and Preprocessing

[0665] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0666] Analysis of personality and abilities

[0667] The server analyzes user A's data and assesses that they possess advanced skills in "task management ability" and "leadership." A generative AI model confirms this and stores it in the database as user A's personality profile.

[0668] Team formation and recommendations

[0669] Next, the company enters into the system that a "leader with strong task management skills" is required as a project requirement for launching a new project. Based on this, the server recommends User A as the most suitable member for the project.

[0670] Feedback and updates

[0671] As the project progresses, User A and other team members provide feedback. This feedback includes information about User A's leadership and team cohesion. The server analyzes this and updates User A's profile. This update allows for appropriate placement in future projects.

[0672] Thus, the present invention precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0676] Step 2:

[0677] The server receives user survey responses and stores them in a database. Simultaneously, it collects the user's past emails, chat logs, and meeting records. Prior user consent is required for this collection.

[0678] Step 3:

[0679] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0680] Step 4:

[0681] The server uses natural language processing (NLP) techniques to analyze the organized data. Specifically, it performs sentiment analysis, extracts keywords and topics from the text, and assesses the user's characteristics and skills.

[0682] Step 5:

[0683] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but low cooperativeness. The evaluation results are stored in a database.

[0684] Step 6:

[0685] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, and role. For example, "data scientist" or "highly collaborative leader."

[0686] Step 7:

[0687] The server analyzes project requirements and calculates the optimal staffing based on user personality profiles and skill sets. Multiple filtering algorithms are used to recommend the most suitable members.

[0688] Step 8:

[0689] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics and skills.

[0690] Step 9:

[0691] Users provide feedback during the project. This feedback includes information about team cohesion and the performance of each member. This feedback is collected regularly.

[0692] Step 10:

[0693] The server analyzes the feedback data and updates the user's personality profile. NLP techniques are used again for the feedback analysis, and actual performance evaluation is performed.

[0694] Step 11:

[0695] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[0696] Through the steps described above, the present invention enables effective staffing and improves overall organizational performance and satisfaction.

[0697] (Example 1)

[0698] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0699] Currently, many companies and organizations are attempting to effectively staff based on employee personality traits and skills. However, traditional methods are time-consuming to collect and analyze data, and their accuracy is low, making it difficult to achieve optimal placement. Furthermore, updating employee profiles as projects progress is not easy. This makes it difficult to form teams that fully utilize the potential of employees.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0701] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, and database update means. This makes it possible to precisely evaluate the personality traits and skills of employees and to achieve optimal personnel placement based on the evaluation results. Furthermore, by analyzing project feedback and updating profiles, appropriate placement becomes possible for future projects as well, maximizing the capabilities of employees.

[0702] "Data analysis means" refers to devices or software that collect and preprocess data such as questionnaires answered by users when they access the system, past emails, chat messages, and meeting records. Preprocessing includes noise removal and extraction of meaningful information.

[0703] "Personality trait evaluation method using generative AI models" refers to a device or software that analyzes data collected using natural language processing technology to evaluate the user's personality traits and skills, and the evaluation results are stored as a profile in a database.

[0704] A "personnel placement recommendation tool" is a device or software that, based on project requirements, matches the personality traits and skill profiles of evaluated users to recommend the most suitable team members.

[0705] A "feedback analysis tool" is a device or software that collects user feedback regarding project progress and team harmony, and updates the user's profile based on the analysis results.

[0706] A "database update method" refers to a device or software that updates user profiles based on feedback and analysis results, reflecting the latest information in the database.

[0707] "Natural language processing technology" is a technique that analyzes text data and performs sentiment analysis, topic modeling, keyword extraction, etc., and is mainly used to evaluate users' personality traits and skills.

[0708] A "profile" is data that records evaluation results regarding a user's personality traits and skills, and is stored in a database.

[0709] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0710] Data Acquisition and Preprocessing

[0711] Users first access the system and answer a questionnaire. This questionnaire includes questions about self-assessment and job-related matters, revealing the user's personality traits and skill set. With the user's permission, the server also collects data such as past emails, chat messages, and meeting records. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes, for example, titles, signatures, and automated messages, and extracts keywords related to task management.

[0712] Analysis of personality and abilities

[0713] The server analyzes the collected data using natural language processing techniques. It performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. Subsequently, it uses a generative AI model to evaluate personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile. For example, if "User A's leadership skills are high" is evaluated, this result will be recorded in the profile.

[0714] Team formation and recommendations

[0715] When a company or organization launches a new project, HR personnel use a terminal to input project requirements into the system. This includes necessary skill sets, personality traits, and roles. Based on these requirements, the server matches user profiles to calculate the optimal team composition and proposes a balanced team structure. For example, if the input states, "New Project X requires a leader with strong task management skills," the server will recommend user A as the leader.

[0716] Feedback and updates

[0717] As the project progresses, users provide feedback on the project's progress and the team's cohesion. This feedback is periodically sent to the server for analysis. The server updates user profiles based on the feedback, enabling more accurate personnel allocation for future projects. For example, if User B provides feedback stating, "I am satisfied with User A's leadership," this information will be reflected in User A's profile.

[0718] Example of a prompt

[0719] The following are examples of specific prompt statements used by the system.

[0720] "Please recommend a leader with strong task management skills for our new project."

[0721] "Analyze User A's leadership and task management skills and evaluate whether they meet the project requirements."

[0722] Thus, the present invention is a system that precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0723] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0724] Step 1:

[0725] Users access the system and answer questionnaires. These questionnaire responses become input data. The server collects this data for later analysis. Specifically, users input data in the form of self-assessments and questions about their work. For example, a user might answer the question, "How do you feel about working in a team?"

[0726] Step 2:

[0727] With the user's permission, the server collects past emails, chat messages, and meeting records. The collected text data becomes the input data. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes honorifics, signatures, and auto-generated messages, and extracts keywords related to task management. For example, "Extract important keywords from User A's email communication records for the past year."

[0728] Step 3:

[0729] The server analyzes the data collected in Steps 1 and 2 using natural language processing techniques. The results of this analysis are output as intermediate data. Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. For example, "extract keywords related to 'cooperativeness' and 'leadership' from User A's emails."

[0730] Step 4:

[0731] The server uses a generative AI model to perform a detailed evaluation of the user's personality traits and skills based on the analysis results from step 3. This evaluation result is saved as profile data. Specifically, it might be evaluated as "User A has high leadership skills." This data is stored in the database.

[0732] Step 5:

[0733] An HR representative uses a terminal to input project requirements into the system. This requirements data becomes the input data. The server matches the requirements data with user profiles and calculates the optimal team composition. This result is output as team member recommendation data. Specifically, it might input something like, "New Project X requires a leader with strong task management skills."

[0734] Step 6:

[0735] The server recommends the most suitable user based on the requirements data from Step 5. The recommendation result is output data and displayed on the terminal. Specifically, the data displayed will say, "We recommend User A as the leader of Project X."

[0736] Step 7:

[0737] During project progress, users provide feedback on the progress and team harmony. This feedback data becomes input data. The server collects and analyzes this feedback. Specifically, the input might be, "User B is satisfied with User A's leadership."

[0738] Step 8:

[0739] The server analyzes the feedback data and updates the user's profile based on the results. This updated data becomes the output data and is used for future personnel assignments. For example, "Update User A's profile to 'Leadership skills rated higher based on feedback'."

[0740] Thus, the system of the present invention processes and analyzes data at each step to achieve optimal personnel allocation.

[0741] (Application Example 1)

[0742] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0743] Traditional factory management methods made it difficult to optimize staffing and team formation, hindering efficient production and effective utilization of human resources. Furthermore, dynamic updates to profiles based on feedback were not implemented, potentially leading to similar problems recurring in subsequent projects.

[0744] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0745] In this invention, the server includes functions for data collection and preprocessing, personality and ability analysis, team composition recommendation, and profile updating based on feedback. This enables optimal team formation based on the skills and personality traits of individual factory employees, and by sequentially updating profiles based on feedback, highly accurate personnel allocation becomes possible in subsequent projects as well.

[0746] "Data analysis methods" refer to methods for collecting data such as questionnaires, communication records, and work records, and extracting detailed information through preprocessing.

[0747] "Personality trait evaluation method using generative AI models" refers to a method that uses natural language processing technology to evaluate a user's personality traits and abilities.

[0748] A "personnel placement recommendation system" is a method of recommending the most suitable personnel for a specific project or task based on collected data and evaluation results from a generated AI model.

[0749] A "feedback analysis method" is a means of analyzing feedback data collected after the project is completed and updating the user profile.

[0750] A "database update method" is a means of saving and updating user profiles in a database based on analyzed data and feedback.

[0751] The "data collection and preprocessing function" refers to a function that collects data such as questionnaires, communication records, and work records, extracts the necessary information, and performs preprocessing.

[0752] The "personality and ability analysis function" is a function that uses collected data to evaluate the user's personality traits and skills.

[0753] The "team composition recommendation function" is a function that recommends the optimal personnel allocation and team composition based on project requirements.

[0754] The "feedback-based profile update function" is a function that analyzes user feedback and updates the user's profile based on that feedback.

[0755] To implement this invention, the following basic system configuration and processing flow are used.

[0756] System Configuration

[0757] The system consists of a data collection server, a GPU server for personality and ability analysis, a database server, and client terminals. The entire system includes various hardware and software components, such as:

[0758] Hardware:

[0759] Data collection server: This server collects and preprocesses data such as surveys, communication records, and business records. It is equipped with a CPU and adequate memory.

[0760] GPU Server for Personality and Ability Analysis: This server is equipped with a high-performance graphics processor (GPU) to evaluate personality traits and abilities using natural language processing technology.

[0761] Database Server: This server is used to store and update evaluation results and feedback data. It is equipped with data storage that has high I / O performance.

[0762] Client terminals: These are terminals used by HR personnel and employees to access the system. This includes desktop PCs and mobile devices.

[0763] software:

[0764] Data analysis libraries: These are libraries used for data preprocessing and analysis, such as Pandas and NumPy.

[0765] Natural language processing libraries: These include libraries such as Transformers and BERT, which are used for personality trait evaluation.

[0766] Database management system: This refers to database software such as MySQL or PostgreSQL used to store and manage evaluation results and feedback.

[0767] Processing details for each means

[0768] Data acquisition and preprocessing means

[0769] Users access the system and periodically answer questionnaires. These questionnaires include self-assessment and job-related questions and are provided through web forms and mobile apps. With user permission, past emails, chat messages, and work records are also collected. The data collection server preprocesses this data, performing keyword extraction and data cleansing.

[0770] Methods for analyzing personality and abilities

[0771] The preprocessed data is analyzed using natural language processing techniques. Specifically, the BERT model is used for sentiment analysis, topic modeling, and keyword extraction to evaluate the user's personality traits and skills. These analyses are performed at high speed on a GPU server, and a generative AI model generates the evaluation results.

[0772] Team formation recommendation methods

[0773] The terminal used to input project requirements allows users to enter information such as required skill sets, personality traits, and roles. The server calculates the optimal team composition based on the entered requirements. To ensure a balanced team, it compares the user's personality profile with their skill set. This recommendation is displayed on the client terminal.

[0774] Feedback and profile update methods

[0775] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications. This feedback data is stored on a database server and analyzed periodically. The analysis results are reflected in the user's profile and accumulated as information useful for future team formations.

[0776] Specific example

[0777] For example, suppose a "leader with strong task management skills" is needed to set up a new production line in a factory. In this case, the system would input "leader with strong task management skills" and "worker skilled in machine operation" as project requirements. The system would then analyze past data and recommend the most suitable personnel.

[0778] Example of a prompt

[0779] Project Requirements: "Leaders with strong task management skills" and "Workers skilled in machine operation"

[0780] Evaluation profile:

[0781] [

[0782] {"Name": "A", "Task Management": 9, "Leadership": 8, "Machine Operation": 7}

[0783] {"Name": "B", "Task Management": 7, "Leadership": 9, "Machine Operation": 8}

[0784] {"Name": "C", "Task Management": 6, "Leadership": 9, "Machine Operation": 5}

[0785] ]

[0786] Based on the prompt, the system recommends "A" as the leader and "B" as the assistant. In this way, optimal personnel allocation and team formation are achieved.

[0787] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0788] Step 1:

[0789] Users access the system and answer questionnaires, which include questions about self-assessment and job-related matters. The questionnaire data entered by users is collected. This data includes information about the user's personality traits and skill set. The server receives this data and performs cleaning and initial preprocessing.

[0790] Step 2:

[0791] The server collects user survey data, past emails, chat messages, and work records. This data is also pre-processed. Specific pre-processing steps include deleting unnecessary data, normalizing text, and extracting keywords. The pre-processed data is then stored on the database server.

[0792] Step 3:

[0793] The server analyzes pre-processed data using natural language processing techniques. This analysis utilizes the BERT model for sentiment analysis, topic modeling, and keyword extraction. Using pre-processed text data as input, the output provides results that evaluate the user's personality traits and skills. These results are stored in a database as the user's personality profile.

[0794] Step 4:

[0795] Using a terminal, HR personnel enter project requirements into the system. This includes information such as required skill sets, personality traits, and roles. The server receives these project requirements and compares them with the user's personality profile stored in the database.

[0796] Step 5:

[0797] The server performs calculations to recommend the optimal team composition based on project requirements and the user's personality profile. Specifically, it generates prompt statements and provides them as input to a generative AI model. The generative AI model selects the most suitable team members based on the input and outputs the recommendation results. These recommendation results are displayed on the terminal.

[0798] Step 6:

[0799] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications and sent to the server. The feedback data includes information such as the project's progress, team cohesion, and the contributions of individual members.

[0800] Step 7:

[0801] The server analyzes the collected feedback data and updates the user's personality profile. The analysis again utilizes natural language processing techniques such as sentiment analysis and topic modeling. Feedback is used as input data, and the updated personality profile is obtained as output and stored in the database.

[0802] Step 8:

[0803] After a project is completed, the updated personality profiles will be used for future projects. These profiles will be compared to new project requirements to aid in future team building. This will enable continuously improving and optimized personnel allocation.

[0804] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0805] The present invention provides a system that includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, database update means, and an emotion engine that recognizes user emotions.

[0806] Program Processing Description

[0807] Data Acquisition and Preprocessing

[0808] Users log into the system and answer an online questionnaire. This questionnaire includes questions about personality assessment and job-related matters, such as "Are you good at demonstrating leadership?" or "How do you perform in stressful environments?". The server also collects data such as past emails, chat messages, and meeting records with the user's permission.

[0809] Extraction and analysis of emotional information

[0810] The server preprocesses the collected data using an emotion engine to analyze the user's emotional information. The emotion engine uses natural language processing techniques to extract emotions such as positive, negative, and neutral from the text. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion.

[0811] Analysis of personality and abilities

[0812] The server uses a generative AI model to evaluate the user's personality traits based on the results of emotional information extraction by the emotion engine. Because emotional information is also incorporated into this evaluation, a more refined personality profile is created. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The evaluation results are stored in a database.

[0813] Team formation and recommendations

[0814] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these project requirements, taking into account user personality profiles, skill sets, and emotional information.

[0815] Feedback and updates

[0816] After team formation, users provide feedback on project progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to the server for analysis.

[0817] The server analyzes the feedback and updates the user's profile. This update uses the sentiment engine again to re-extract sentiment information from the feedback. The updated profile is saved in the database and used to improve the accuracy of future staffing decisions.

[0818] Specific example

[0819] Data Acquisition and Preprocessing

[0820] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0821] Extraction and analysis of emotional information

[0822] The server uses an emotion engine to extract emotional information from user A's data. For example, a message like "This project is fun" is recognized as a positive emotion.

[0823] Analysis of personality and abilities

[0824] The server analyzes user A's data, including emotional information, using a generating AI model to evaluate personality traits in detail. For example, it might be assessed that user A has high task management skills and a positive mindset, but occasionally experiences emotional fluctuations.

[0825] Team formation and recommendations

[0826] When an HR representative enters the requirements for a new project into the system—specifically, "a leader with strong task management skills and a positive attitude"—the server recommends User A as the most suitable member.

[0827] Feedback and updates

[0828] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This allows for optimal placement in future projects as well.

[0829] As described above, the present invention, by combining an emotion engine, takes into account the user's emotional information, thereby achieving more precise and effective personnel allocation.

[0830] The following describes the processing flow.

[0831] Step 1:

[0832] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0833] Step 2:

[0834] The server receives user survey responses and stores them in a database. Simultaneously, with the user's permission, it collects work-related data such as past emails, chat messages, and meeting records.

[0835] Step 3:

[0836] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0837] Step 4:

[0838] The server extracts emotional information from pre-processed data using an emotion engine. The emotion engine leverages natural language processing techniques to identify and classify emotional expressions within text. For example, the message "I'm really looking forward to it!" in a chat log is recognized as a positive emotion.

[0839] Step 5:

[0840] The server uses natural language processing (NLP) techniques to analyze the organized data (including sentiment information). Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to assess user characteristics and skills.

[0841] Step 6:

[0842] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but also experiencing intense emotional fluctuations. The evaluation results are stored in a database.

[0843] Step 7:

[0844] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, role, and emotional stability. For example, "data scientist" or "highly collaborative leader."

[0845] Step 8:

[0846] Based on project requirements, the server calculates the optimal team composition, taking into account user personality profiles, skill sets, and emotional information. Multiple filtering algorithms are used to recommend the most suitable members.

[0847] Step 9:

[0848] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics, skills, and emotional stability.

[0849] Step 10:

[0850] Users provide feedback during the project. This feedback includes aspects such as the level of harmony among team members, the progress of work, and emotional fluctuations. This feedback is sent to the server periodically.

[0851] Step 11:

[0852] The server analyzes the feedback data and updates the user's personality profile. NLP techniques and an emotion engine are again used for the feedback analysis, reflecting actual performance evaluations and emotional changes.

[0853] Step 12:

[0854] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[0855] Through the steps described above, the present invention, by including an emotion engine, takes into account the user's emotional information and achieves more precise and effective personnel allocation.

[0856] (Example 2)

[0857] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0858] In modern companies and organizations, optimal staffing is a critical issue directly linked to project success and improved efficiency. However, traditional staffing methods often rely solely on skill sets and experience, making it difficult to consider individual members' personality traits and emotional states. This can easily lead to team disharmony and decreased work efficiency. Furthermore, insufficient real-time feedback-based profile updates meant a lack of adaptability to dynamic project environments.

[0859] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0860] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, and emotion analysis means using an emotion engine that recognizes the user's emotions. This enables precise evaluation that takes into account the user's personality traits and emotional information, allowing for optimal staffing and real-time profile updates.

[0861] "Data analysis methods" refer to methods for collecting information such as surveys, emails, chats, and meeting records, and extracting necessary keywords and data through preprocessing.

[0862] "Personality trait evaluation method using generative AI models" refers to a method that utilizes natural language processing technology to evaluate personality traits, including emotional information, from text in collected data.

[0863] A "personnel placement recommendation method" is a means of selecting and recommending members who are best suited to the requirements of a project or team, based on evaluated personality traits, skill sets, and emotional information.

[0864] A "feedback analysis method" is a means of analyzing feedback information provided by users and team members during the progress of a project to evaluate the team's harmony and the status of work execution.

[0865] A "database update method" refers to a method of periodically updating user profiles based on the results of feedback analysis, etc., and utilizing this information for future evaluations and personnel allocation.

[0866] "Emotional analysis means" refers to a method of extracting user emotional information from text collected using natural language processing technology and analyzing emotional states such as positive, negative, and neutral.

[0867] The present invention is a system that includes data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means. Specific embodiments of each means will be described below.

[0868] This system has the following configuration: Users first log in to the system and answer an online questionnaire. The questionnaire includes questions about personality assessment and job-related matters. For example, it includes questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" This collects the necessary personality information.

[0869] The server collects data such as past emails, chat messages, and meeting records with the user's permission. This data is preprocessed using data analysis tools to extract necessary keywords and data. This involves using software that employs natural language processing techniques (e.g., Apache OpenNLP or NLTK).

[0870] Next, the collected data is analyzed using sentiment analysis techniques. These techniques use natural language processing to classify emotions within the text as positive, negative, neutral, etc. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion. A sentiment analysis engine (e.g., IBM Watson Tone Analyzer) is used for this analysis.

[0871] The analyzed emotional information is incorporated into personality trait assessments by generative AI models (e.g., GPT-3 or BERT). The server then uses this information to evaluate the user's personality traits and create a more refined profile. For example, "User A" might be assessed as having strong leadership and analytical skills, but also experiencing significant emotional fluctuations. The assessment results are stored in a database and used for future personnel placement and evaluations.

[0872] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. Based on these requirements, the server calculates the optimal team composition. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended.

[0873] During project progress, users provide feedback on the project's progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to a server and analyzed using feedback analysis tools. The server updates the user's profile based on the analysis results and stores it in a database. This helps improve the accuracy of future personnel allocation.

[0874] Specific example

[0875] User A logs into the system and answers a "self-assessment questionnaire." The server collects User A's questionnaire responses and past email communication data, and extracts keywords related to task management. This data is analyzed using a sentiment analysis engine, and messages such as "This project is fun" are recognized as positive emotions.

[0876] Next, the data, including the analyzed emotional information, is analyzed using a generating AI model to evaluate User A's personality traits. The evaluation results indicate that User A has "high task management skills and a positive outlook, but occasionally experiences emotional fluctuations." When an HR person enters the requirements for a new project into the system, the server recommends User A as the most suitable member.

[0877] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This updated profile is then used for optimal placement in future projects.

[0878] As described above, the system of the present invention combines data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means to achieve precise evaluation and optimal personnel placement that takes into account the user's emotional information.

[0879] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0880] Step 1:

[0881] The user logs into the system and answers an online questionnaire. The user's login information and questionnaire responses are provided as input. The questionnaire includes questions about personality assessment and job-related matters. Specifically, the user answers questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" The user's response data is generated as output.

[0882] Step 2:

[0883] The server collects data such as past emails, chat messages, and meeting records with the user's permission. User consent data and access information are provided as input. APIs and log analysis tools are used for data collection. Specifically, the server accesses these data sources and retrieves the relevant communication content. As output, the collected data is stored in temporary storage.

[0884] Step 3:

[0885] The server preprocesses the collected data using data analysis tools. The raw data is provided as input. Specifically, irrelevant information is filtered out, and important keywords and phrases are extracted. For example, natural language processing techniques are used to extract keywords related to task management. The output is preprocessed, clean data.

[0886] Step 4:

[0887] The server extracts user emotional information using sentiment analysis tools. Pre-processed, clean data is provided as input. Specifically, the sentiment analysis engine extracts emotions from text and classifies them as positive, negative, or neutral. For example, the message "This project is fun" would be recognized as a positive emotion. Emotionally labeled data is generated as output.

[0888] Step 5:

[0889] The server uses a generative AI model to evaluate the user's personality traits. The input is emotion-labeled data. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to create a detailed personality profile that includes emotional information. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The output is the generated, evaluated personality profile.

[0890] Step 6:

[0891] HR personnel use a terminal to input project requirements into the system. The input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these requirements. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended. The output is a list of recommended team members.

[0892] Step 7:

[0893] During the project, users provide feedback. Input includes feedback on project progress and team harmony. Specifically, the server analyzes the feedback data using feedback analysis tools and updates the user's profile. For example, harmony among team members, work performance, and emotional fluctuations are analyzed. The updated user profile is generated and stored in the database.

[0894] The above outlines the specific processing flow of this system and details the actions performed at each step. This enables precise evaluation that takes user emotional information into account and optimal staffing.

[0895] (Application Example 2)

[0896] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0897] In modern factories, it is difficult to assign tasks optimally based on the skill sets and personality traits of workers and robots. Furthermore, detailed profiling that takes emotional information into account and improvements based on feedback are not sufficiently implemented. As a result, problems arise with decreased production efficiency and work harmony.

[0898] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data analysis means, personality trait evaluation means using a generated AI model, emotion analysis means, real-time data collection means, and task automatic assignment means. This makes it possible to assign tasks and form teams optimally based on the personality traits and emotion information of workers and robots.

[0899] "Data analysis means" refers to methods for preprocessing and analyzing collected data.

[0900] "Personality trait evaluation method using generative AI models" refers to a method of evaluating a user's personality traits and skill set using generative AI models.

[0901] A "personnel allocation recommendation method" is a means of recommending the optimal personnel allocation and team composition based on collected data and evaluation results.

[0902] A "feedback analysis method" is a means of collecting and analyzing feedback regarding the progress of a project or task.

[0903] A "database update method" is a means of updating a database using analysis results and feedback data.

[0904] "Emotional analysis methods" refer to methods for analyzing user emotional information from data collected using natural language processing technology.

[0905] A "real-time data collection method" is a means of collecting motion data and text data of workers and robots in real time.

[0906] A "task automation system" is a method for automatically assigning tasks to workers or robots based on project requirements and user profiles.

[0907] This document describes a system for carrying out this invention. This system enables optimal placement and task allocation of workers and robots in a factory. The specific details are shown below.

[0908] Hardware and software

[0909] Hardware:

[0910] Factory robots

[0911] Sensors (camera, microphone, temperature sensor, etc.)

[0912] Server (for data analysis and AI model execution)

[0913] software:

[0914] Natural language processing tools (e.g., spaCy, NLTK)

[0915] Sentiment analysis engines (e.g., IBM Watson, Microsoft Cognitive Services)

[0916] Generative AI models (e.g., GPT-4)

[0917] Databases (e.g., MySQL, PostgreSQL)

[0918] Program processing details

[0919] The server first collects data in real time from factory workers and robots. The collected data includes work motion data and text data (conversation logs). Data from sensors and log files is sent to the server.

[0920] Next, the server uses natural language processing techniques to analyze the data and extract sentiment information from the collected data. The sentiment analysis engine recognizes the user's emotional state from the text data and obtains sentiment information such as positive, negative, or neutral. This sentiment information is stored in a database.

[0921] Subsequently, the server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of the workers and robots in detail. This generates a personality profile for each worker and robot, which is then stored in a database.

[0922] Once project requirements are entered, the server automatically assigns tasks to the most suitable workers or robots based on profiles stored in the database. This takes into account the skill sets and personality traits required for each task in the project. The assignment results are also stored in the database.

[0923] Finally, the server collects and analyzes feedback on the project's progress and the harmony of the work. The results of the feedback are used to update the profiles of the workers and robots. The updated profiles are then used for future task assignments.

[0924] Specific example

[0925] For example, Project A requires workers and robots with strong task management skills and stable emotions. Based on these requirements, the system automatically assigns the most suitable members and updates their profiles based on feedback during the project.

[0926] Prompt example

[0927] "In Project A, Task A1 requires high precision and a stable emotional state. Task A2 emphasizes task management skills and the allocation of appropriate workers and robots."

[0928] Thus, the present invention is a system that takes into account the emotional information and personality traits of workers and robots, and significantly improves work efficiency and harmony within the factory.

[0929] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0930] Step 1:

[0931] The server collects data in real time from factory workers and robots. Inputs include motion data and conversation logs from sensors and log files. The server receives this data and preprocesses it using a data collection module. Specific operations include standardizing data formats and filtering out unnecessary data. The output is the preprocessed data.

[0932] Step 2:

[0933] The server analyzes the preprocessed data using natural language processing techniques. The input includes the preprocessed data obtained in step 1. Here, a natural language processing tool (e.g., spaCy) is used to analyze the text data. Specific operations include keyword extraction and contextual analysis from the text data. The output is the analyzed text data.

[0934] Step 3:

[0935] The server analyzes the parsed text data using a sentiment analysis engine and extracts sentiment information. The input includes the parsed text data obtained in step 2. Using a sentiment analysis engine (e.g., IBM Watson), it obtains sentiment information such as positive, negative, and neutral from the text data. Specifically, this involves sentiment tagging of the text data. The output is text data containing sentiment information.

[0936] Step 4:

[0937] The server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of workers and robots. The input includes emotionally charged text data obtained in step 3. A generative AI model (e.g., GPT-4) is used to evaluate personality profiles and skill sets. The specific operations involve inputting data into the model and extracting evaluation results. The output consists of personality profiles and skill sets.

[0938] Step 5:

[0939] The terminal inputs project requirements into the server. This input includes required skill sets, personality traits, roles, and emotional stability. This input then submits the specific project requirements to the server. The process involves the user inputting requirements into the terminal and sending data to the server. The output is the project requirements.

[0940] Step 6:

[0941] The server automatically assigns tasks to the most suitable workers or robots based on project requirements. Inputs include project requirements obtained in step 5 and personality profiles and skill sets obtained in step 4. An automated task assignment algorithm is used to calculate the optimal combination. Specific operations include data combination processing and generation of assignment results. The output is the optimal task assignment result.

[0942] Step 7:

[0943] The server collects and analyzes feedback on work progress and team cohesion throughout the project. Input includes feedback data. The server uses a feedback analysis engine to re-analyze sentiment information and work data. Specific operations include collecting and analyzing feedback data. Output includes evaluation results and updated profiles.

[0944] Step 8:

[0945] The server updates the database with worker and robot profiles based on the feedback analysis results. The input includes the evaluation results obtained in step 7. The server uses a database update module to update the profile information. Specifically, it updates and maintains the database. The output is the updated database.

[0946] The above describes the specific processing steps and their operation for implementing this invention.

[0947] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0948] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0949] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0950] [Fourth Embodiment]

[0951] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0952] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0953] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0954] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0955] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0956] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0957] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0958] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0959] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0960] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0961] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0962] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0963] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0964] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[0965] Program Processing Description

[0966] Data Acquisition and Preprocessing

[0967] Users access the system and answer questionnaires. These questionnaires include self-assessment and job-related questions, revealing the user's personality traits and skill set. With the user's permission, the server also collects past emails, chat messages, meeting records, etc. The server preprocesses this data and extracts only meaningful information.

[0968] Analysis of personality and abilities

[0969] The server analyzes the collected data using natural language processing techniques. Specifically, it performs sentiment analysis, topic modeling, and keyword extraction to visualize the user's personality traits and skills. Subsequently, a generative AI model is used to evaluate the user's personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile.

[0970] Team formation and recommendations

[0971] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This includes required skill sets, personality traits, and roles. Based on these project requirements, the server calculates the optimal team composition. In doing so, it compares the user's personality profile and skill set to propose a well-balanced team structure.

[0972] Feedback and updates

[0973] After team formation, users provide feedback on project progress and team cohesion. This feedback is periodically sent to and analyzed by the server. The server analyzes the feedback and updates the user's profile based on the results. This update allows for more accurate personnel allocation in future team formations.

[0974] Specific example

[0975] Data Acquisition and Preprocessing

[0976] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[0977] Analysis of personality and abilities

[0978] The server analyzes user A's data and assesses that they possess advanced skills in "task management ability" and "leadership." A generative AI model confirms this and stores it in the database as user A's personality profile.

[0979] Team formation and recommendations

[0980] Next, the company enters into the system that a "leader with strong task management skills" is required as a project requirement for launching a new project. Based on this, the server recommends User A as the most suitable member for the project.

[0981] Feedback and updates

[0982] As the project progresses, User A and other team members provide feedback. This feedback includes information about User A's leadership and team cohesion. The server analyzes this and updates User A's profile. This update allows for appropriate placement in future projects.

[0983] Thus, the present invention precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[0984] The following describes the processing flow.

[0985] Step 1:

[0986] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[0987] Step 2:

[0988] The server receives user survey responses and stores them in a database. Simultaneously, it collects the user's past emails, chat logs, and meeting records. Prior user consent is required for this collection.

[0989] Step 3:

[0990] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[0991] Step 4:

[0992] The server uses natural language processing (NLP) techniques to analyze the organized data. Specifically, it performs sentiment analysis, extracts keywords and topics from the text, and assesses the user's characteristics and skills.

[0993] Step 5:

[0994] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but low cooperativeness. The evaluation results are stored in a database.

[0995] Step 6:

[0996] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, and role. For example, "data scientist" or "highly collaborative leader."

[0997] Step 7:

[0998] The server analyzes project requirements and calculates the optimal staffing based on user personality profiles and skill sets. Multiple filtering algorithms are used to recommend the most suitable members.

[0999] Step 8:

[1000] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics and skills.

[1001] Step 9:

[1002] Users provide feedback during the project. This feedback includes information about team cohesion and the performance of each member. This feedback is collected regularly.

[1003] Step 10:

[1004] The server analyzes the feedback data and updates the user's personality profile. NLP techniques are used again for the feedback analysis, and actual performance evaluation is performed.

[1005] Step 11:

[1006] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[1007] Through the steps described above, the present invention enables effective staffing and improves overall organizational performance and satisfaction.

[1008] (Example 1)

[1009] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1010] Currently, many companies and organizations are attempting to effectively staff based on employee personality traits and skills. However, traditional methods are time-consuming to collect and analyze data, and their accuracy is low, making it difficult to achieve optimal placement. Furthermore, updating employee profiles as projects progress is not easy. This makes it difficult to form teams that fully utilize the potential of employees.

[1011] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1012] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, and database update means. This makes it possible to precisely evaluate the personality traits and skills of employees and to achieve optimal personnel placement based on the evaluation results. Furthermore, by analyzing project feedback and updating profiles, appropriate placement becomes possible for future projects as well, maximizing the capabilities of employees.

[1013] "Data analysis means" refers to devices or software that collect and preprocess data such as questionnaires answered by users when they access the system, past emails, chat messages, and meeting records. Preprocessing includes noise removal and extraction of meaningful information.

[1014] "Personality trait evaluation method using generative AI models" refers to a device or software that analyzes data collected using natural language processing technology to evaluate the user's personality traits and skills, and the evaluation results are stored as a profile in a database.

[1015] A "personnel placement recommendation tool" is a device or software that, based on project requirements, matches the personality traits and skill profiles of evaluated users to recommend the most suitable team members.

[1016] A "feedback analysis tool" is a device or software that collects user feedback regarding project progress and team harmony, and updates the user's profile based on the analysis results.

[1017] A "database update method" refers to a device or software that updates user profiles based on feedback and analysis results, reflecting the latest information in the database.

[1018] "Natural language processing technology" is a technique that analyzes text data and performs sentiment analysis, topic modeling, keyword extraction, etc., and is mainly used to evaluate users' personality traits and skills.

[1019] A "profile" is data that records evaluation results regarding a user's personality traits and skills, and is stored in a database.

[1020] This invention provides a system that includes data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means, thereby achieving effective personnel placement.

[1021] Data Acquisition and Preprocessing

[1022] Users first access the system and answer a questionnaire. This questionnaire includes questions about self-assessment and job-related matters, revealing the user's personality traits and skill set. With the user's permission, the server also collects data such as past emails, chat messages, and meeting records. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes, for example, titles, signatures, and automated messages, and extracts keywords related to task management.

[1023] Analysis of personality and abilities

[1024] The server analyzes the collected data using natural language processing techniques. It performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. Subsequently, it uses a generative AI model to evaluate personality traits, strengths, and weaknesses in detail. This evaluation result is stored in the server's database as a user profile. For example, if "User A's leadership skills are high" is evaluated, this result will be recorded in the profile.

[1025] Team formation and recommendations

[1026] When a company or organization launches a new project, HR personnel use a terminal to input project requirements into the system. This includes necessary skill sets, personality traits, and roles. Based on these requirements, the server matches user profiles to calculate the optimal team composition and proposes a balanced team structure. For example, if the input states, "New Project X requires a leader with strong task management skills," the server will recommend user A as the leader.

[1027] Feedback and updates

[1028] As the project progresses, users provide feedback on the project's progress and the team's cohesion. This feedback is periodically sent to the server for analysis. The server updates user profiles based on the feedback, enabling more accurate personnel allocation for future projects. For example, if User B provides feedback stating, "I am satisfied with User A's leadership," this information will be reflected in User A's profile.

[1029] Example of a prompt

[1030] The following are examples of specific prompt statements used by the system.

[1031] "Please recommend a leader with strong task management skills for our new project."

[1032] "Analyze User A's leadership and task management skills and evaluate whether they meet the project requirements."

[1033] Thus, the present invention is a system that precisely evaluates the personality and abilities of employees and achieves optimal personnel placement by using data analysis means, personality trait evaluation means using a generated AI model, personnel placement recommendation means, feedback analysis means, and database update means.

[1034] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1035] Step 1:

[1036] Users access the system and answer questionnaires. These questionnaire responses become input data. The server collects this data for later analysis. Specifically, users input data in the form of self-assessments and questions about their work. For example, a user might answer the question, "How do you feel about working in a team?"

[1037] Step 2:

[1038] With the user's permission, the server collects past emails, chat messages, and meeting records. The collected text data becomes the input data. The server preprocesses this data to remove noise and extract meaningful information. Specifically, it removes honorifics, signatures, and auto-generated messages, and extracts keywords related to task management. For example, "Extract important keywords from User A's email communication records for the past year."

[1039] Step 3:

[1040] The server analyzes the data collected in Steps 1 and 2 using natural language processing techniques. The results of this analysis are output as intermediate data. Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to visualize the user's personality traits and skills. For example, "extract keywords related to 'cooperativeness' and 'leadership' from User A's emails."

[1041] Step 4:

[1042] The server uses a generative AI model to perform a detailed evaluation of the user's personality traits and skills based on the analysis results from step 3. This evaluation result is saved as profile data. Specifically, it might be evaluated as "User A has high leadership skills." This data is stored in the database.

[1043] Step 5:

[1044] An HR representative uses a terminal to input project requirements into the system. This requirements data becomes the input data. The server matches the requirements data with user profiles and calculates the optimal team composition. This result is output as team member recommendation data. Specifically, it might input something like, "New Project X requires a leader with strong task management skills."

[1045] Step 6:

[1046] The server recommends the most suitable user based on the requirements data from Step 5. The recommendation result is output data and displayed on the terminal. Specifically, the data displayed will say, "We recommend User A as the leader of Project X."

[1047] Step 7:

[1048] During project progress, users provide feedback on the progress and team harmony. This feedback data becomes input data. The server collects and analyzes this feedback. Specifically, the input might be, "User B is satisfied with User A's leadership."

[1049] Step 8:

[1050] The server analyzes the feedback data and updates the user's profile based on the results. This updated data becomes the output data and is used for future personnel assignments. For example, "Update User A's profile to 'Leadership skills rated higher based on feedback'."

[1051] Thus, the system of the present invention processes and analyzes data at each step to achieve optimal personnel allocation.

[1052] (Application Example 1)

[1053] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1054] Traditional factory management methods made it difficult to optimize staffing and team formation, hindering efficient production and effective utilization of human resources. Furthermore, dynamic updates to profiles based on feedback were not implemented, potentially leading to similar problems recurring in subsequent projects.

[1055] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1056] In this invention, the server includes functions for data collection and preprocessing, personality and ability analysis, team composition recommendation, and profile updating based on feedback. This enables optimal team formation based on the skills and personality traits of individual factory employees, and by sequentially updating profiles based on feedback, highly accurate personnel allocation becomes possible in subsequent projects as well.

[1057] "Data analysis methods" refer to methods for collecting data such as questionnaires, communication records, and work records, and extracting detailed information through preprocessing.

[1058] "Personality trait evaluation method using generative AI models" refers to a method that uses natural language processing technology to evaluate a user's personality traits and abilities.

[1059] A "personnel placement recommendation system" is a method of recommending the most suitable personnel for a specific project or task based on collected data and evaluation results from a generated AI model.

[1060] A "feedback analysis method" is a means of analyzing feedback data collected after the project is completed and updating the user profile.

[1061] A "database update method" is a means of saving and updating user profiles in a database based on analyzed data and feedback.

[1062] The "data collection and preprocessing function" refers to a function that collects data such as questionnaires, communication records, and work records, extracts the necessary information, and performs preprocessing.

[1063] The "personality and ability analysis function" is a function that uses collected data to evaluate the user's personality traits and skills.

[1064] The "team composition recommendation function" is a function that recommends the optimal personnel allocation and team composition based on project requirements.

[1065] The "feedback-based profile update function" is a function that analyzes user feedback and updates the user's profile based on that feedback.

[1066] To implement this invention, the following basic system configuration and processing flow are used.

[1067] System Configuration

[1068] The system consists of a data collection server, a GPU server for personality and ability analysis, a database server, and client terminals. The entire system includes various hardware and software components, such as:

[1069] Hardware:

[1070] Data collection server: This server collects and preprocesses data such as surveys, communication records, and business records. It is equipped with a CPU and adequate memory.

[1071] GPU Server for Personality and Ability Analysis: This server is equipped with a high-performance graphics processor (GPU) to evaluate personality traits and abilities using natural language processing technology.

[1072] Database Server: This server is used to store and update evaluation results and feedback data. It is equipped with data storage that has high I / O performance.

[1073] Client terminals: These are terminals used by HR personnel and employees to access the system. This includes desktop PCs and mobile devices.

[1074] software:

[1075] Data analysis libraries: These are libraries used for data preprocessing and analysis, such as Pandas and NumPy.

[1076] Natural language processing libraries: These include libraries such as Transformers and BERT, which are used for personality trait evaluation.

[1077] Database management system: This refers to database software such as MySQL or PostgreSQL used to store and manage evaluation results and feedback.

[1078] Processing details for each means

[1079] Data acquisition and preprocessing means

[1080] Users access the system and periodically answer questionnaires. These questionnaires include self-assessment and job-related questions and are provided through web forms and mobile apps. With user permission, past emails, chat messages, and work records are also collected. The data collection server preprocesses this data, performing keyword extraction and data cleansing.

[1081] Methods for analyzing personality and abilities

[1082] The preprocessed data is analyzed using natural language processing techniques. Specifically, the BERT model is used for sentiment analysis, topic modeling, and keyword extraction to evaluate the user's personality traits and skills. These analyses are performed at high speed on a GPU server, and a generative AI model generates the evaluation results.

[1083] Team formation recommendation methods

[1084] The terminal used to input project requirements allows users to enter information such as required skill sets, personality traits, and roles. The server calculates the optimal team composition based on the entered requirements. To ensure a balanced team, it compares the user's personality profile with their skill set. This recommendation is displayed on the client terminal.

[1085] Feedback and profile update methods

[1086] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications. This feedback data is stored on a database server and analyzed periodically. The analysis results are reflected in the user's profile and accumulated as information useful for future team formations.

[1087] Specific example

[1088] For example, suppose a "leader with strong task management skills" is needed to set up a new production line in a factory. In this case, the system would input "leader with strong task management skills" and "worker skilled in machine operation" as project requirements. The system would then analyze past data and recommend the most suitable personnel.

[1089] Example of a prompt

[1090] Project Requirements: "Leaders with strong task management skills" and "Workers skilled in machine operation"

[1091] Evaluation profile:

[1092] [

[1093] {"Name": "A", "Task Management": 9, "Leadership": 8, "Machine Operation": 7}

[1094] {"Name": "B", "Task Management": 7, "Leadership": 9, "Machine Operation": 8}

[1095] {"Name": "C", "Task Management": 6, "Leadership": 9, "Machine Operation": 5}

[1096] ]

[1097] Based on the prompt, the system recommends "A" as the leader and "B" as the assistant. In this way, optimal personnel allocation and team formation are achieved.

[1098] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1099] Step 1:

[1100] Users access the system and answer questionnaires, which include questions about self-assessment and job-related matters. The questionnaire data entered by users is collected. This data includes information about the user's personality traits and skill set. The server receives this data and performs cleaning and initial preprocessing.

[1101] Step 2:

[1102] The server collects user survey data, past emails, chat messages, and work records. This data is also pre-processed. Specific pre-processing steps include deleting unnecessary data, normalizing text, and extracting keywords. The pre-processed data is then stored on the database server.

[1103] Step 3:

[1104] The server analyzes pre-processed data using natural language processing techniques. This analysis utilizes the BERT model for sentiment analysis, topic modeling, and keyword extraction. Using pre-processed text data as input, the output provides results that evaluate the user's personality traits and skills. These results are stored in a database as the user's personality profile.

[1105] Step 4:

[1106] Using a terminal, HR personnel enter project requirements into the system. This includes information such as required skill sets, personality traits, and roles. The server receives these project requirements and compares them with the user's personality profile stored in the database.

[1107] Step 5:

[1108] The server performs calculations to recommend the optimal team composition based on project requirements and the user's personality profile. Specifically, it generates prompt statements and provides them as input to a generative AI model. The generative AI model selects the most suitable team members based on the input and outputs the recommendation results. These recommendation results are displayed on the terminal.

[1109] Step 6:

[1110] As the project progresses, users provide feedback. This feedback is collected through dedicated forms and applications and sent to the server. The feedback data includes information such as the project's progress, team cohesion, and the contributions of individual members.

[1111] Step 7:

[1112] The server analyzes the collected feedback data and updates the user's personality profile. The analysis again utilizes natural language processing techniques such as sentiment analysis and topic modeling. Feedback is used as input data, and the updated personality profile is obtained as output and stored in the database.

[1113] Step 8:

[1114] After a project is completed, the updated personality profiles will be used for future projects. These profiles will be compared to new project requirements to aid in future team building. This will enable continuously improving and optimized personnel allocation.

[1115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1116] The present invention provides a system that includes data analysis means, personality trait evaluation means using a generative AI model, personnel placement recommendation means, feedback analysis means, database update means, and an emotion engine that recognizes user emotions.

[1117] Program Processing Description

[1118] Data Acquisition and Preprocessing

[1119] Users log into the system and answer an online questionnaire. This questionnaire includes questions about personality assessment and job-related matters, such as "Are you good at demonstrating leadership?" or "How do you perform in stressful environments?". The server also collects data such as past emails, chat messages, and meeting records with the user's permission.

[1120] Extraction and analysis of emotional information

[1121] The server preprocesses the collected data using an emotion engine to analyze the user's emotional information. The emotion engine uses natural language processing techniques to extract emotions such as positive, negative, and neutral from the text. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion.

[1122] Analysis of personality and abilities

[1123] The server uses a generative AI model to evaluate the user's personality traits based on the results of emotional information extraction by the emotion engine. Because emotional information is also incorporated into this evaluation, a more refined personality profile is created. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The evaluation results are stored in a database.

[1124] Team formation and recommendations

[1125] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these project requirements, taking into account user personality profiles, skill sets, and emotional information.

[1126] Feedback and updates

[1127] After team formation, users provide feedback on project progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to the server for analysis.

[1128] The server analyzes the feedback and updates the user's profile. This update uses the sentiment engine again to re-extract sentiment information from the feedback. The updated profile is saved in the database and used to improve the accuracy of future staffing decisions.

[1129] Specific example

[1130] Data Acquisition and Preprocessing

[1131] For example, User A has answered a "self-assessment questionnaire" and their past email communications have shown that they have strong task management skills. The server analyzes User A's questionnaire responses and past email communication data to extract keywords related to task management.

[1132] Extraction and analysis of emotional information

[1133] The server uses an emotion engine to extract emotional information from user A's data. For example, a message like "This project is fun" is recognized as a positive emotion.

[1134] Analysis of personality and abilities

[1135] The server analyzes user A's data, including emotional information, using a generating AI model to evaluate personality traits in detail. For example, it might be assessed that user A has high task management skills and a positive mindset, but occasionally experiences emotional fluctuations.

[1136] Team formation and recommendations

[1137] When an HR representative enters the requirements for a new project into the system—specifically, "a leader with strong task management skills and a positive attitude"—the server recommends User A as the most suitable member.

[1138] Feedback and updates

[1139] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This allows for optimal placement in future projects as well.

[1140] As described above, the present invention, by combining an emotion engine, takes into account the user's emotional information, thereby achieving more precise and effective personnel allocation.

[1141] The following describes the processing flow.

[1142] Step 1:

[1143] Users log into the system and answer an online questionnaire. The questionnaire includes questions about work and personality assessments. For example, "Are you good at demonstrating leadership?" or "Under what circumstances can you perform at your best?"

[1144] Step 2:

[1145] The server receives user survey responses and stores them in a database. Simultaneously, with the user's permission, it collects work-related data such as past emails, chat messages, and meeting records.

[1146] Step 3:

[1147] The server runs a text analysis algorithm to preprocess the collected historical data. It removes noisy data (e.g., spam emails, non-business-related messages, etc.) and extracts only meaningful information.

[1148] Step 4:

[1149] The server extracts emotional information from pre-processed data using an emotion engine. The emotion engine leverages natural language processing techniques to identify and classify emotional expressions within text. For example, the message "I'm really looking forward to it!" in a chat log is recognized as a positive emotion.

[1150] Step 5:

[1151] The server uses natural language processing (NLP) techniques to analyze the organized data (including sentiment information). Specifically, it performs sentiment analysis, topic modeling, keyword extraction, and other processes to assess user characteristics and skills.

[1152] Step 6:

[1153] The server uses a generative AI model to evaluate the user's personality traits based on the results of NLP analysis. For example, "User A" might be evaluated as having high leadership skills and analytical abilities, but also experiencing intense emotional fluctuations. The evaluation results are stored in a database.

[1154] Step 7:

[1155] The terminal (HR personnel) enters the requirements for new projects or teams into the system. This includes the required skill set, personality traits, role, and emotional stability. For example, "data scientist" or "highly collaborative leader."

[1156] Step 8:

[1157] Based on project requirements, the server calculates the optimal team composition, taking into account user personality profiles, skill sets, and emotional information. Multiple filtering algorithms are used to recommend the most suitable members.

[1158] Step 9:

[1159] The server presents the recommendation results to the HR department. For example, it provides specific placement suggestions such as, "User A is suitable for Project X." The reasons for the recommendation also clearly state User A's characteristics, skills, and emotional stability.

[1160] Step 10:

[1161] Users provide feedback during the project. This feedback includes aspects such as the level of harmony among team members, the progress of work, and emotional fluctuations. This feedback is sent to the server periodically.

[1162] Step 11:

[1163] The server analyzes the feedback data and updates the user's personality profile. NLP techniques and an emotion engine are again used for the feedback analysis, reflecting actual performance evaluations and emotional changes.

[1164] Step 12:

[1165] The server saves the updated profiles to the database, which is then used to improve the accuracy of future staffing decisions. This will enable optimal placement in subsequent projects as well.

[1166] Through the steps described above, the present invention, by including an emotion engine, takes into account the user's emotional information and achieves more precise and effective personnel allocation.

[1167] (Example 2)

[1168] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1169] In modern companies and organizations, optimal staffing is a critical issue directly linked to project success and improved efficiency. However, traditional staffing methods often rely solely on skill sets and experience, making it difficult to consider individual members' personality traits and emotional states. This can easily lead to team disharmony and decreased work efficiency. Furthermore, insufficient real-time feedback-based profile updates meant a lack of adaptability to dynamic project environments.

[1170] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1171] In this invention, the server includes data analysis means, personality trait evaluation means using a generative AI model, and emotion analysis means using an emotion engine that recognizes the user's emotions. This enables precise evaluation that takes into account the user's personality traits and emotional information, allowing for optimal staffing and real-time profile updates.

[1172] "Data analysis methods" refer to methods for collecting information such as surveys, emails, chats, and meeting records, and extracting necessary keywords and data through preprocessing.

[1173] "Personality trait evaluation method using generative AI models" refers to a method that utilizes natural language processing technology to evaluate personality traits, including emotional information, from text in collected data.

[1174] A "personnel placement recommendation method" is a means of selecting and recommending members who are best suited to the requirements of a project or team, based on evaluated personality traits, skill sets, and emotional information.

[1175] A "feedback analysis method" is a means of analyzing feedback information provided by users and team members during the progress of a project to evaluate the team's harmony and the status of work execution.

[1176] A "database update method" refers to a method of periodically updating user profiles based on the results of feedback analysis, etc., and utilizing this information for future evaluations and personnel allocation.

[1177] "Emotional analysis means" refers to a method of extracting user emotional information from text collected using natural language processing technology and analyzing emotional states such as positive, negative, and neutral.

[1178] The present invention is a system that includes data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means. Specific embodiments of each means will be described below.

[1179] This system has the following configuration: Users first log in to the system and answer an online questionnaire. The questionnaire includes questions about personality assessment and job-related matters. For example, it includes questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" This collects the necessary personality information.

[1180] The server collects data such as past emails, chat messages, and meeting records with the user's permission. This data is preprocessed using data analysis tools to extract necessary keywords and data. This involves using software that employs natural language processing techniques (e.g., Apache OpenNLP or NLTK).

[1181] Next, the collected data is analyzed using sentiment analysis techniques. These techniques use natural language processing to classify emotions within the text as positive, negative, neutral, etc. For example, in a chat log, the message "I'm really looking forward to it!" is recognized as a positive emotion. A sentiment analysis engine (e.g., IBM Watson Tone Analyzer) is used for this analysis.

[1182] The analyzed emotional information is incorporated into personality trait assessments by generative AI models (e.g., GPT-3 or BERT). The server then uses this information to evaluate the user's personality traits and create a more refined profile. For example, "User A" might be assessed as having strong leadership and analytical skills, but also experiencing significant emotional fluctuations. The assessment results are stored in a database and used for future personnel placement and evaluations.

[1183] When a company or organization launches a new project or team, HR personnel use a terminal to input project requirements into the system. This input includes required skill sets, personality traits, roles, and emotional stability. Based on these requirements, the server calculates the optimal team composition. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended.

[1184] During project progress, users provide feedback on the project's progress and team cohesion. This feedback includes aspects such as team cohesion, work performance, and emotional fluctuations. This feedback is periodically sent to a server and analyzed using feedback analysis tools. The server updates the user's profile based on the analysis results and stores it in a database. This helps improve the accuracy of future personnel allocation.

[1185] Specific example

[1186] User A logs into the system and answers a "self-assessment questionnaire." The server collects User A's questionnaire responses and past email communication data, and extracts keywords related to task management. This data is analyzed using a sentiment analysis engine, and messages such as "This project is fun" are recognized as positive emotions.

[1187] Next, the data, including the analyzed emotional information, is analyzed using a generating AI model to evaluate User A's personality traits. The evaluation results indicate that User A has "high task management skills and a positive outlook, but occasionally experiences emotional fluctuations." When an HR person enters the requirements for a new project into the system, the server recommends User A as the most suitable member.

[1188] During the project, User A and team members provide feedback, which the server analyzes and updates User A's profile. This updated profile is then used for optimal placement in future projects.

[1189] As described above, the system of the present invention combines data analysis means, personality trait evaluation means using a generative AI model, emotion analysis means, personnel placement recommendation means, feedback analysis means, and database update means to achieve precise evaluation and optimal personnel placement that takes into account the user's emotional information.

[1190] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1191] Step 1:

[1192] The user logs into the system and answers an online questionnaire. The user's login information and questionnaire responses are provided as input. The questionnaire includes questions about personality assessment and job-related matters. Specifically, the user answers questions such as, "Are you good at demonstrating leadership?" and "How do you perform in stressful environments?" The user's response data is generated as output.

[1193] Step 2:

[1194] The server collects data such as past emails, chat messages, and meeting records with the user's permission. User consent data and access information are provided as input. APIs and log analysis tools are used for data collection. Specifically, the server accesses these data sources and retrieves the relevant communication content. As output, the collected data is stored in temporary storage.

[1195] Step 3:

[1196] The server preprocesses the collected data using data analysis tools. The raw data is provided as input. Specifically, irrelevant information is filtered out, and important keywords and phrases are extracted. For example, natural language processing techniques are used to extract keywords related to task management. The output is preprocessed, clean data.

[1197] Step 4:

[1198] The server extracts user emotional information using sentiment analysis tools. Pre-processed, clean data is provided as input. Specifically, the sentiment analysis engine extracts emotions from text and classifies them as positive, negative, or neutral. For example, the message "This project is fun" would be recognized as a positive emotion. Emotionally labeled data is generated as output.

[1199] Step 5:

[1200] The server uses a generative AI model to evaluate the user's personality traits. The input is emotion-labeled data. Specifically, it uses a generative AI model (e.g., GPT-3 or BERT) to create a detailed personality profile that includes emotional information. For example, "User A" might be evaluated as having high leadership and analytical skills, but also experiencing significant emotional fluctuations. The output is the generated, evaluated personality profile.

[1201] Step 6:

[1202] HR personnel use a terminal to input project requirements into the system. The input includes required skill sets, personality traits, roles, and emotional stability. The server then calculates the optimal team composition based on these requirements. For example, if a "highly task-management-oriented, positive leader" is needed, a suitable user will be recommended. The output is a list of recommended team members.

[1203] Step 7:

[1204] During the project, users provide feedback. Input includes feedback on project progress and team harmony. Specifically, the server analyzes the feedback data using feedback analysis tools and updates the user's profile. For example, harmony among team members, work performance, and emotional fluctuations are analyzed. The updated user profile is generated and stored in the database.

[1205] The above outlines the specific processing flow of this system and details the actions performed at each step. This enables precise evaluation that takes user emotional information into account and optimal staffing.

[1206] (Application Example 2)

[1207] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1208] In modern factories, it is difficult to assign tasks optimally based on the skill sets and personality traits of workers and robots. Furthermore, detailed profiling that takes emotional information into account and improvements based on feedback are not sufficiently implemented. As a result, problems arise with decreased production efficiency and work harmony.

[1209] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes data analysis means, personality trait evaluation means using a generated AI model, emotion analysis means, real-time data collection means, and task automatic assignment means. This makes it possible to assign tasks and form teams optimally based on the personality traits and emotion information of workers and robots.

[1210] "Data analysis means" refers to methods for preprocessing and analyzing collected data.

[1211] "Personality trait evaluation method using generative AI models" refers to a method of evaluating a user's personality traits and skill set using generative AI models.

[1212] A "personnel allocation recommendation method" is a means of recommending the optimal personnel allocation and team composition based on collected data and evaluation results.

[1213] A "feedback analysis method" is a means of collecting and analyzing feedback regarding the progress of a project or task.

[1214] A "database update method" is a means of updating a database using analysis results and feedback data.

[1215] "Emotional analysis methods" refer to methods for analyzing user emotional information from data collected using natural language processing technology.

[1216] A "real-time data collection method" is a means of collecting motion data and text data of workers and robots in real time.

[1217] A "task automation system" is a method for automatically assigning tasks to workers or robots based on project requirements and user profiles.

[1218] This document describes a system for carrying out this invention. This system enables optimal placement and task allocation of workers and robots in a factory. The specific details are shown below.

[1219] Hardware and software

[1220] Hardware:

[1221] Factory robots

[1222] Sensors (camera, microphone, temperature sensor, etc.)

[1223] Server (for data analysis and AI model execution)

[1224] software:

[1225] Natural language processing tools (e.g., spaCy, NLTK)

[1226] Sentiment analysis engines (e.g., IBM Watson, Microsoft Cognitive Services)

[1227] Generative AI models (e.g., GPT-4)

[1228] Databases (e.g., MySQL, PostgreSQL)

[1229] Program processing details

[1230] The server first collects data in real time from factory workers and robots. The collected data includes work motion data and text data (conversation logs). Data from sensors and log files is sent to the server.

[1231] Next, the server uses natural language processing techniques to analyze the data and extract sentiment information from the collected data. The sentiment analysis engine recognizes the user's emotional state from the text data and obtains sentiment information such as positive, negative, or neutral. This sentiment information is stored in a database.

[1232] Subsequently, the server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of the workers and robots in detail. This generates a personality profile for each worker and robot, which is then stored in a database.

[1233] Once project requirements are entered, the server automatically assigns tasks to the most suitable workers or robots based on profiles stored in the database. This takes into account the skill sets and personality traits required for each task in the project. The assignment results are also stored in the database.

[1234] Finally, the server collects and analyzes feedback on the project's progress and the harmony of the work. The results of the feedback are used to update the profiles of the workers and robots. The updated profiles are then used for future task assignments.

[1235] Specific example

[1236] For example, Project A requires workers and robots with strong task management skills and stable emotions. Based on these requirements, the system automatically assigns the most suitable members and updates their profiles based on feedback during the project.

[1237] Prompt example

[1238] "In Project A, Task A1 requires high precision and a stable emotional state. Task A2 emphasizes task management skills and the allocation of appropriate workers and robots."

[1239] Thus, the present invention is a system that takes into account the emotional information and personality traits of workers and robots, and significantly improves work efficiency and harmony within the factory.

[1240] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1241] Step 1:

[1242] The server collects data in real time from factory workers and robots. Inputs include motion data and conversation logs from sensors and log files. The server receives this data and preprocesses it using a data collection module. Specific operations include standardizing data formats and filtering out unnecessary data. The output is the preprocessed data.

[1243] Step 2:

[1244] The server analyzes the preprocessed data using natural language processing techniques. The input includes the preprocessed data obtained in step 1. Here, a natural language processing tool (e.g., spaCy) is used to analyze the text data. Specific operations include keyword extraction and contextual analysis from the text data. The output is the analyzed text data.

[1245] Step 3:

[1246] The server analyzes the parsed text data using a sentiment analysis engine and extracts sentiment information. The input includes the parsed text data obtained in step 2. Using a sentiment analysis engine (e.g., IBM Watson), it obtains sentiment information such as positive, negative, and neutral from the text data. Specifically, this involves sentiment tagging of the text data. The output is text data containing sentiment information.

[1247] Step 4:

[1248] The server uses a generative AI model to analyze data containing emotional information and evaluate the personality traits and skill sets of workers and robots. The input includes emotionally charged text data obtained in step 3. A generative AI model (e.g., GPT-4) is used to evaluate personality profiles and skill sets. The specific operations involve inputting data into the model and extracting evaluation results. The output consists of personality profiles and skill sets.

[1249] Step 5:

[1250] The terminal inputs project requirements into the server. This input includes required skill sets, personality traits, roles, and emotional stability. This input then submits the specific project requirements to the server. The process involves the user inputting requirements into the terminal and sending data to the server. The output is the project requirements.

[1251] Step 6:

[1252] The server automatically assigns tasks to the most suitable workers or robots based on project requirements. Inputs include project requirements obtained in step 5 and personality profiles and skill sets obtained in step 4. An automated task assignment algorithm is used to calculate the optimal combination. Specific operations include data combination processing and generation of assignment results. The output is the optimal task assignment result.

[1253] Step 7:

[1254] The server collects and analyzes feedback on work progress and team cohesion throughout the project. Input includes feedback data. The server uses a feedback analysis engine to re-analyze sentiment information and work data. Specific operations include collecting and analyzing feedback data. Output includes evaluation results and updated profiles.

[1255] Step 8:

[1256] The server updates the database with worker and robot profiles based on the feedback analysis results. The input includes the evaluation results obtained in step 7. The server uses a database update module to update the profile information. Specifically, it updates and maintains the database. The output is the updated database.

[1257] The above describes the specific processing steps and their operation for implementing this invention.

[1258] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1259] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1260] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1261] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1262] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1263] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1264] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1265] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1266] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1267] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1268] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1269] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1270] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1271] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1272] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1273] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1274] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1275] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1276] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1277] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1278] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1279] The following is further disclosed regarding the embodiments described above.

[1280] (Claim 1)

[1281] Data analysis means,

[1282] A method for evaluating personality traits using a generative AI model,

[1283] Personnel assignment recommendation methods,

[1284] Feedback analysis methods,

[1285] Database update method,

[1286] A system that includes this.

[1287] (Claim 2)

[1288] The data analysis means includes collecting and preprocessing surveys, emails, chats, and meeting records, according to claim 1.

[1289] (Claim 3)

[1290] The system according to claim 1, wherein the means for evaluating personality traits using a generative AI model evaluates personality traits using natural language processing technology.

[1291] "Example 1"

[1292] (Claim 1)

[1293] Data analysis means,

[1294] A method for evaluating personality traits using a generative AI model,

[1295] Personnel assignment recommendation methods,

[1296] Feedback analysis methods,

[1297] Database update method,

[1298] A system that includes this.

[1299] (Claim 2)

[1300] The system according to claim 1, wherein the data analysis means collects and preprocesses questionnaires answered by users when they access the system, past emails, chat messages, and meeting records, the preprocessing including noise removal and extraction of meaningful information.

[1301] (Claim 3)

[1302] The system according to claim 1, wherein the means for evaluating personality traits using a generative AI model uses natural language processing technology as an analysis technique to evaluate personality traits and skills, and stores the evaluation results as a profile in a database.

[1303] (Claim 4)

[1304] The personnel placement recommendation means matches evaluated personality traits and skill profiles based on project requirements entered into a terminal and recommends appropriate members, as described in claim 1.

[1305] (Claim 5)

[1306] The system according to claim 1, wherein the feedback analysis means collects user feedback regarding the progress of the project and the degree of team harmony, and updates the profile based on the results of the analysis.

[1307] "Application Example 1"

[1308] (Claim 1)

[1309] Data analysis means,

[1310] A method for evaluating personality traits using a generative AI model,

[1311] Personnel assignment recommendation methods,

[1312] Feedback analysis methods,

[1313] Database update method,

[1314] Functions for data collection and preprocessing,

[1315] Functions that analyze personality and abilities,

[1316] A feature that recommends team formations,

[1317] A feature to update the profile based on feedback,

[1318] A system that includes this.

[1319] (Claim 2)

[1320] The data analysis means includes collecting and pre-processing questionnaires, communication records, and business records, according to claim 1.

[1321] (Claim 3)

[1322] The system according to claim 1, wherein the means for evaluating personality traits using a generative AI model evaluates personality traits and abilities using natural language processing technology.

[1323] "Example 2 of combining an emotion engine"

[1324] (Claim 1)

[1325] Data analysis means,

[1326] A method for evaluating personality traits using a generative AI model,

[1327] Personnel assignment recommendation methods,

[1328] Feedback analysis methods,

[1329] Database update method,

[1330] A means of emotion analysis using an emotion engine that recognizes the user's emotions,

[1331] A system that includes this.

[1332] (Claim 2)

[1333] The system according to claim 1, wherein the data analysis means is a means for collecting and preprocessing questionnaires, emails, chats, and meeting records, and for extracting keywords from the collected information.

[1334] (Claim 3)

[1335] The system according to claim 1, wherein the means for evaluating personality traits using a generative AI model is a means for extracting emotional information from text using natural language processing technology and incorporating the emotional information to evaluate personality traits.

[1336] "Application example 2 when combining with an emotional engine"

[1337] (Claim 1)

[1338] Data analysis means,

[1339] A method for evaluating personality traits using a generative AI model,

[1340] Personnel assignment recommendation methods,

[1341] Feedback analysis methods,

[1342] Database update method,

[1343] Emotion analysis methods,

[1344] Real-time data collection methods,

[1345] Task automatic assignment method,

[1346] A system that includes this.

[1347] (Claim 2)

[1348] The data analysis means includes collecting and preprocessing questionnaires, electronic communications, and log data, according to claim 1.

[1349] (Claim 3)

[1350] The system according to claim 1, wherein the means for evaluating personality traits using a generative AI model evaluates personality traits and analyzes emotional information using natural language processing technology. [Explanation of Symbols]

[1351] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A data analysis method for collecting and preprocessing surveys, emails, chats, and meeting records, A personality trait evaluation means that uses a generative AI model to perform a process that objectively evaluates the user's personality traits and skills, A personnel placement recommendation tool that calculates the optimal team structure and staffing based on evaluation results and creates a specific placement plan, A feedback analysis tool that analyzes user-provided feedback to evaluate actual performance and team harmony, A database update mechanism that updates personality profiles and skill maps based on feedback and newly collected data, A system that includes this.

Images