System

Abstract

A system is provided.SOLUTION: A generative AI model means for analyzing the optimal matching between the crew and the shops by using the integrated database, a means for generating an optimal manpower allocation scheme based on the analysis result, a means for notifying the staff of the manpower allocation scheme based on the characteristics of the crew and the characteristics of the shops, and a means for collecting feedback information on the manpower allocation scheme; Means for updating the generative AI model to reflect the collected feedback in a next placement proposal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem that this invention aims to solve is that in a system that comprehensively analyzes the characteristics and aptitude of crew members and the store's situation to propose optimal staffing, conventional methods lack information and limit judgment, making it difficult to effectively allocate staff. This leads to sluggish performance, a deterioration in relationships with the store, and problems with optimal management. Furthermore, solving these problems requires a significant amount of man-hours, increasing the burden on the person in charge. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for acquiring crew characteristic data; means for acquiring store location information and evaluation data; means for storing the acquired crew characteristic data, store location information, and evaluation data in an integrated database; means for generating a generative AI model that analyzes optimal crew-store matching using data from the integrated database; means for generating an optimal staffing plan based on the analysis results; means for notifying a staffing manager of the staffing plan based on the crew characteristics and store characteristics; means for collecting feedback data on the staffing plan; and means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal. This eliminates the limitations on decision-making due to insufficient information and enables effective and efficient staffing. It also improves numerical values ​​and relationships with stores, reducing staffing manpower.

[0006] "Crew" refers to the employees and staff working at the store.

[0007] "Characteristic data" refers to data including information such as crew performance, evaluations, test results, and communication history.

[0008] A "store" is a physical location that offers services or products to customers.

[0009] "Location Information" refers to information regarding the geographic coordinates or location of a particular store.

[0010] "Evaluation data" refers to data that includes customer reviews and evaluation comments about a store.

[0011] An "integrated database" is a database for centrally managing information collected from multiple data sources.

[0012] A "generative AI model" is a model that uses artificial intelligence to analyze data and find the optimal match between crew and store.

[0013] "Matching" is the process of comparing and evaluating the characteristics of the crew and the store to find the most suitable combination.

[0014] A "staffing plan" is a proposal for how crew members should be assigned to a particular store.

[0015] "Personnel" means users of the system to manage staffing and crew.

[0016] "Feedback data" refers to evaluation data such as actual performance based on staffing plans and comments from staff members.

[0017] The "notification system" refers to a system for notifying personnel in charge of the generated staffing plan.

[0018] An "index" is a data structure that acts as a table of contents for efficiently searching and referencing data. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[0041] System Configuration

[0042] The system includes the following main components:

[0043] 1. Server

[0044] Data Collection Module

[0045] Integrated Database

[0046] Generative AI Models

[0047] Notification System

[0048] Feedback Collection Module

[0049] 2. Terminal

[0050] Agent User Interface

[0051] Feedback Input Interface

[0052] 3. Users

[0053] Person in Charge (the person who manages and staffs the crew)

[0054] Program processing

[0055] Data collection

[0056] The server uses the API of the company's internal system to obtain crew characteristic data, including comment history and reaction data from communication tools (e.g., Slack), test results from the e-learning system, and superior evaluations from the evaluation system.

[0057] The server uses the Google (registered trademark) Maps API to collect location information and evaluation comments for each store.

[0058] Data Integration

[0059] The server stores the collected data in an integrated database. Crew characteristics data is stored in the "crew_data" table, and store evaluation data is stored in the "store_data" table.

[0060] The server combines crew and store data and creates an index to enable quick access and searching.

[0061] analysis

[0062] The server uses data from the integrated database to train a generative AI model and analyze the optimal match between crew and store.

[0063] The generative AI model compares the crew's communication skills and performance with the store's customer demographics and characteristics to find optimal staffing plans.

[0064] suggestion

[0065] The server transmits the generated placement plan to the terminal of the person in charge via the notification system.

[0066] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0067] Feedback collection

[0068] The user (person in charge) will then carry out the actual personnel allocation based on the proposed allocation plan and provide feedback on the results to the system.

[0069] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0070] The server analyzes the collected feedback data and uses it to update the generative AI model, thereby improving the accuracy of future placement suggestions.

[0071] Specific examples

[0072] Data collection

[0073] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" via the Slack API.

[0074] The server uses the Google Maps API to collect the location information and most recent customer evaluation comments for "Store ID 456."

[0075] Data Integration

[0076] The server inserts the acquired data into the MySQL® integrated database. The "crew_data" table stores the comment history and reaction data of "user ID 123," and the "store_data" table stores the evaluation comments of "store ID 456."

[0077] Analysis and Recommendations

[0078] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Based on this analysis result, it proposes placing "User ID 123" in "Store ID 456."

[0079] The server transmits the generated placement plan to the person in charge through a notification system, and displays the notification on the person in charge's terminal.

[0080] Feedback and Updates

[0081] After the user performs the placement based on the proposal, the user inputs the placement results and feedback into the system.

[0082] The server collects the feedback data and updates the generative AI model for the next placement proposal.

[0083] The above is an embodiment of the present invention. This processing flow realizes optimal staffing between crews and stores, thereby improving business performance and reducing man-hours.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] The server uses the API of the internal system to obtain crew characteristic data. It calls the Slack API to collect comment history and reaction data from the past 30 days. It then queries the e-learning system API to obtain each crew member's test results and progress. It also obtains past evaluation data and feedback from superiors through the evaluation system API.

[0087] Step 2:

[0088] The server uses the Google Maps API to collect location information and customer reviews for each store. Specifically, it obtains geographic coordinates based on a specific store ID, and also collects the most recent customer reviews and comments.

[0089] Step 3:

[0090] The server stores the collected crew characteristic data, store location information, and evaluation data in an integrated database. Crew characteristic data is organized in the "crew_data" table and saved using the crew ID as a key. Store evaluation data is inserted into the "store_data" table and saved using the store ID as a key.

[0091] Step 4:

[0092] The server combines the crew and store data and creates an index for quick access and searching. Specifically, it uses an SQL query to join both data sets and generate new index fields.

[0093] Step 5:

[0094] The server trains a generative AI model using data from the integrated database. The model compares crew characteristics (communication skills, performance, ratings) with store characteristics (customer demographics, ratings, event status) to find the best match. Past deployment data and feedback are also used to train the model.

[0095] Step 6:

[0096] The server generates the staffing plan and notifies the person in charge. Specifically, the server converts the generated staffing plan into a document and sends it to the person in charge's terminal through the notification system. The notification includes details of the staffing plan, the reasons for the plan, and the expected results.

[0097] Step 7:

[0098] The user confirms the notified personnel deployment plan, checks the proposal through the user interface for the person in charge, and makes adjustments as necessary. The user then deploys the crew based on the confirmed deployment plan.

[0099] Step 8:

[0100] Users provide feedback to the system after deployment by entering the deployed crew's performance, satisfaction, and feedback comments through a feedback input interface, including specific achievements and problems after deployment.

[0101] Step 9:

[0102] The server collects the collected feedback data and stores it in an integrated database. It then analyzes the feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[0103] Step 10:

[0104] The server uses the updated generative AI model to further optimize the next staffing plan, thereby continuously achieving optimal staffing, improving performance and reducing labor costs.

[0105] Example 1

[0106] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0107] In the conventional system, matching employees with facilities was not possible while taking into full consideration the characteristics of the employees and the facilities, making it difficult to achieve appropriate placement. In addition, there was a lack of a mechanism for efficiently collecting feedback on placement results and reflecting it in the next placement, making continuous improvement difficult.

[0108] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0109] In this invention, the server includes means for acquiring employee characteristic data, means for acquiring facility location information and evaluation data, means for storing the acquired employee characteristic data, facility location information, and evaluation data in an integrated database, means for generating a generative AI model that analyzes an optimal match between employees and facilities using data from the integrated database, means for generating an optimal staffing plan based on the analysis results, means for notifying a person in charge of the staffing plan based on the employee characteristics and the facility characteristics, means for collecting feedback data on the staffing plan, means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal, means for acquiring facility evaluation data from customers, means for acquiring employee characteristic data from communication tools and an education system, and means for receiving feedback data from a terminal. This enables optimal staffing between employees and facilities, improving business efficiency and enabling continuous improvement in staffing.

[0110] "Employee" refers to a person employed by a company or organization to perform work.

[0111] "Characteristic data" refers to data that represents an employee's individual characteristics, such as their communication skills or performance.

[0112] "Facility" means a place of business where employees are located, including stores, factories, offices, etc.

[0113] "Location information" refers to data indicating a geographical location, and includes information such as latitude and longitude.

[0114] "Evaluation Data" refers to data representing evaluations and feedback on facilities and employees.

[0115] An "integrated database" refers to a database that centrally manages and stores information collected from multiple data sources.

[0116] A "generative AI model" is a model that uses machine learning and artificial intelligence to learn data patterns and make predictions and suggestions.

[0117] "Matching" refers to the process of analyzing the compatibility between employee characteristics and facility characteristics to find the optimal combination.

[0118] "Notification system" refers to a system that sends information or data to specific devices or personnel.

[0119] "Feedback data" refers to data that shows evaluations of staffing results and areas for improvement.

[0120] "Communication tools" refers to software and platforms used to communicate between employees and within an organization.

[0121] An "educational system" refers to a system that provides teaching materials and tests aimed at improving employees' skills and acquiring knowledge.

[0122] "Device" refers to a computer or mobile device used by a user or agent.

[0123] The present invention relates to a system for collecting, integrating, and analyzing employee characteristic data and facility evaluation data to achieve optimal staffing. Specific embodiments for carrying out the present invention will be described below.

[0124] System Configuration

[0125] The system includes the following main components:

[0126] 1. Server

[0127] Data Collection Module

[0128] Integrated Database

[0129] Generative AI Models

[0130] Notification System

[0131] Feedback Collection Module

[0132] 2. Terminal

[0133] Agent User Interface

[0134] Feedback Input Interface

[0135] 3. Users

[0136] Person in charge (the person who manages and staffs employees)

[0137] Data collection

[0138] The server uses the API of a communication tool (e.g., a chat system) to obtain employee characteristic data. Specifically, it collects 30 days of comment history and reaction data, test results from the education system, and supervisor evaluations from the evaluation system. The server also uses a geographic information API to collect facility location information and customer evaluation comments.

[0139] For example, the server performs the following operations:

[0140] Access the API endpoint https: / / api.chat-system.com / history?user=123 to retrieve the comment history and reaction data for "user ID 123."

[0141] Access the API endpoint https: / / api.geo-service.com / place / details?place_id=456 and collect location information and customer evaluation comments for "facility ID 456."

[0142] Data Integration

[0143] The collected data is stored in a MySQL integrated database by the server. Employee comment history and reaction data are stored in the "employee_data" table, and facility evaluation comments are stored in the "facility_data" table. The server also combines crew and facility data and generates indexes to enable quick access.

[0144] example:

[0145] sql

[0146] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[0147] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[0148] Data analysis

[0149] The server trains a generative AI model using data from the integrated database, which then analyzes the optimal match between employees and facilities. The generative AI model uses machine learning algorithms (e.g., TENSORFLOW (registered trademark) and PyTorch) to analyze employee communication skills and performance, as well as the customer demographics and characteristics of facilities, to find optimal staffing plans.

[0150] suggestion

[0151] The server sends the generated staffing plan to the staff member's device via a notification system. The device (the staff member's user interface) displays the proposed staffing plan, which the staff member can review and adjust. As a specific example of the operation here, the staff member could input the following prompts to the AI:

[0152] Please propose the optimal staffing plan based on the communication skill data of "User ID 123" over the past 30 days and the evaluation comments of "Facility ID 456."

[0153] Feedback collection

[0154] The user (person in charge) performs actual staffing based on the proposed staffing plan and inputs the results as feedback to the system. The terminal (feedback input interface) inputs the feedback data from the person in charge and sends it to the server. The server analyzes the collected feedback data and updates the generative AI model. This improves the accuracy of future staffing proposals.

[0155] The above is a specific embodiment for carrying out the present invention. This processing flow realizes optimal staffing between employees and facilities, and enables improved work efficiency and continuous improvement of staffing.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1: Data collection

[0158] The server sends requests to the APIs of communication tools and education systems to obtain employee characteristic data. Specifically, it collects data based on the following inputs:

[0159] (Input): API endpoint and query parameters (e.g. https: / / api.chat-system.com / history?user=123)

[0160] The server parses the JSON data returned from the API and extracts comment history and reaction data.

[0161] (Output): A JSON object containing the comment history and reaction data.

[0162] Specific behavior:

[0163] The server accesses the Slack API endpoint https: / / api.chat-system.com / history?user=123 and retrieves the message history and reaction data for the past 30 days for "user ID 123."

[0164] The server analyzes the JSON data obtained from the API and extracts the specific content of the comments and the type of each reaction.

[0165] Step 2: Data integration

[0166] The server generates SQL queries to store the collected data in a MySQL integrated database.

[0167] (Input): Speech history and reaction data, facility evaluation data

[0168] The server uses SQL queries to insert data into the database, which saves each piece of data in its corresponding table.

[0169] (Output): Employee characteristics data and facility evaluation data stored in a database

[0170] Specific behavior:

[0171] The server executes the following SQL query to insert the comment history and reaction data into the "employee_data" table:

[0172] sql

[0173] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[0174] Similarly, facility evaluation comments are stored in the "facility_data" table.

[0175] sql

[0176] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[0177] Step 3: Data Joining and Indexing

[0178] The server combines the employee characteristic data with the facility evaluation data and generates an index to enable rapid access and retrieval.

[0179] (Input): Employee characteristics data and facility evaluation data in the database

[0180] The server combines the data using SQL JOIN operations and generates the index.

[0181] (Output): The combined data and the generated index.

[0182] Specific behavior:

[0183] The server uses the following SQL query to join the data and generate the index:

[0184] sql

[0185] CREATE INDEX idx_user_store ON combined_data (user_id, store_id);

[0186] Step 4: Training the generative AI model

[0187] The server inputs data from the integrated database into the generative AI model and trains the model.

[0188] (Input): Combined employee and facility data in the database

[0189] The server uses machine learning algorithms to train the model and analyze the best matches.

[0190] (Output): Trained generative AI model and analysis results

[0191] Specific behavior:

[0192] The server runs Python programs and uses libraries such as TensorFlow or PyTorch to train generative AI models.

[0193] Training data includes employee communication skills and performance, as well as the customer demographics and characteristics of the facility.

[0194] Step 5: Generate and notify placement proposals

[0195] The server generates optimal staffing plans based on the analysis results obtained from the generative AI model.

[0196] (Input): Trained generative AI model and employee and facility data

[0197] The server sends the placement plan generated from the analysis results to the person in charge via a notification system.

[0198] (Output): Staffing plan sent to the person in charge's terminal

[0199] Specific behavior:

[0200] The server creates an optimal personnel allocation plan based on the analysis results.

[0201] The server transmits the placement plan to the terminal of the person in charge and displays it on the user interface for the person in charge.

[0202] Step 6: Gather feedback

[0203] The user performs actual staffing based on the proposed staffing plan and inputs the results into the system as feedback.

[0204] (Input): Results and feedback comments from the person in charge

[0205] The terminal collects feedback data through a feedback input interface and sends it to the server.

[0206] (Output): Feedback data sent to the server

[0207] Specific behavior:

[0208] The user assigns employees according to the assignment plan and inputs the results and feedback into the terminal.

[0209] The terminal transmits the collected feedback data to the server.

[0210] Step 7: Update the generative AI model

[0211] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future placement suggestions.

[0212] (Input): Feedback data and existing generative AI models

[0213] The server uses the feedback data to retrain and update the generative AI model.

[0214] (Output): Updated generative AI model

[0215] Specific behavior:

[0216] The server analyzes the collected feedback data and extracts the information needed to improve the accuracy of the model.

[0217] The server retrains the generative AI model and reflects it in the next placement proposal.

[0218] This is the specific flow of the program processing of this system. This procedure is expected to achieve optimal matching between employees and facilities and improve work efficiency.

[0219] (Application example 1)

[0220] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0221] Conventional factory robot allocation systems have the problem of being unable to achieve efficient work allocation because it is difficult to optimally match each robot based on its characteristics and task requirements. Furthermore, there is a lack of flexible system design that reflects feedback after task allocation. As a result, there are issues such as reduced productivity and insufficient robot operational efficiency.

[0222] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0223] In this invention, the server includes a means for acquiring personnel characteristic data, a means for acquiring work base location information and evaluation data, and a means for storing the acquired personnel characteristic data, work base location information, and evaluation data in an integrated database, thereby realizing a generative AI model that analyzes optimal matching between personnel and work bases.

[0224] "Personnel characteristic data" is data that indicates the specific attributes and capabilities of each personnel, such as the speed, accuracy, and power consumption of that personnel.

[0225] "Location information of work base" refers to the geographic coordinates of the location where work is performed and detailed information about that location.

[0226] "Evaluation data" refers to data that indicates evaluations and feedback on work sites and personnel.

[0227] An "integrated database" is a database that centrally manages and stores a wide variety of data and enables efficient access.

[0228] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data on personnel and work locations and generate optimal matching and placement plans.

[0229] A "notification system" is a mechanism for quickly and reliably notifying administrators and personnel of information generated by the system.

[0230] "Feedback data" refers to data that indicates actual results and evaluations based on the placement proposal, and is collected to be reflected in the next proposal.

[0231] An "index" is something like a table of contents created for data in a database to speed up data searches.

[0232] A "robotic arm" is a mechanical arm-like device used to perform tasks in a factory.

[0233] "Task requirement information" is information that indicates the conditions and requirements necessary for the performance of a specific work or task.

[0234] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[0235] System Configuration

[0236] The system includes the following main components:

[0237] 1. Server

[0238] Data Collection Module

[0239] Integrated Database

[0240] Generative AI Models

[0241] Notification System

[0242] Feedback Collection Module

[0243] 2. Terminal

[0244] Administrator User Interface

[0245] Feedback Input Interface

[0246] 3. Users

[0247] Manager (person who manages the placement of robots within the factory)

[0248] Program processing

[0249] The server collects, analyzes, proposes, and updates data in the following steps:

[0250] Technology used

[0251] 1. Hardware:

[0252] Robotic arms (e.g., typical factory robotic arms)

[0253] Sensors (e.g. Lidar, cameras)

[0254] Server (e.g. AWS (registered trademark) EC2)

[0255] 2. Software:

[0256] Data collection module (Python, Slack API, factory integrated management system API, etc.)

[0257] Integrated database (MySQL)

[0258] Generative AI models (e.g., TensorFlow, PyTorch)

[0259] Notification systems (e.g. Firebase)

[0260] Feedback collection module (e.g. Flask)

[0261] Data collection

[0262] The server obtains characteristic data for each robot (such as operating speed, accuracy, and power consumption) from the factory's integrated management system. It also collects task status information within the factory from sensors. For example, it obtains characteristic data such as operating speed, accuracy, and power consumption for "robot ID 123," and collects location information and required operating accuracy for "task ID 456."

[0263] Data Integration

[0264] The collected data is stored in the server's integrated MySQL database, where personnel characteristics data is stored in the "robot_data" table and task request data is stored in the "task_data" table.

[0265] analysis

[0266] The server uses data from the integrated database to train the generative AI model and analyzes the characteristics and task requirements of each robot. Based on the results of this analysis, it proposes optimal robot task assignments. For example, the generative AI model can input the characteristics data of "Robot ID 123" and the requirements of "Task ID 456," and determine that "Robot ID 123" is optimal for "Task ID 456."

[0267] suggestion

[0268] The server sends the generated task allocation plan to the administrator's terminal via the notification system. The administrator's user interface displays the proposed placement plan, which the administrator can review and adjust. For example, the generated placement plan is notified to the administrator's terminal, and the administrator performs the placement based on the proposal.

[0269] Feedback collection

[0270] The administrator performs placement based on the proposed placement plan and provides feedback to the system on the results. The server collects the feedback data and updates the generative AI model to reflect it in the next placement proposal.

[0271] Specific examples

[0272] Examples of prompt sentences include:

[0273] The characteristic data (operation speed, accuracy, power consumption) for "Robot ID 123" are as follows. Based on this, make the optimal allocation to meet the requirements (position information, operation accuracy) of "Task ID 456".

[0274] This is expected to improve the efficiency of robot placement within factories and increase productivity.

[0275] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0276] Step 1:

[0277] The server obtains the characteristic data of each robot through the factory integrated management system API. This includes the robot's operating speed, accuracy, power consumption, etc. Based on this input data, the characteristic data is collected and saved. Specifically, the server sends an API request and stores the obtained data in the "robot_data" table of the integrated database.

[0278] Step 2:

[0279] The server collects task status information from sensors in the factory. The acquired input data includes the task's location information and the required operating accuracy. Based on this data, detailed task information is saved in the "task_data" table. Specifically, it acquires real-time data from the sensors, organizes it, and inserts it into the database.

[0280] Step 3:

[0281] The server integrates the robot characteristic data and task request data stored in the integrated database and structures the data. Here, it creates indexes to speed up data searches. It uses data from the "robot_data" table and the "task_data" table as input and outputs indexed integrated data. Specific operations include data merging using SQL queries and creating indexes.

[0282] Step 4:

[0283] The server trains the generative AI model using data from the integrated database. The input is the integrated robot and task data, and it analyzes the optimal match based on this. The output is the optimal robot task assignment proposal as a result of the analysis. The specific operation is the training process of the generative AI model using TensorFlow and PyTorch.

[0284] Step 5:

[0285] The server sends the task allocation plan analyzed by the generative AI model to the administrator's device via the notification system. The input is the generated placement plan, and the output is displayed on the administrator's device as a notification. The specific operation is to send a push notification using Firebase.

[0286] Step 6:

[0287] The administrator executes the actual deployment based on the proposed deployment plan. The input is the deployment plan notified by the server, and the output is the actual deployment result. The specific operation is to confirm the deployment plan through the user interface and actually deploy the robot.

[0288] Step 7:

[0289] The administrator inputs feedback based on the deployment results into the feedback input interface. The input data is the deployment execution result and its evaluation. The output is sent to the server as feedback data. The specific operation is that the administrator submits the evaluation using the feedback form.

[0290] Step 8:

[0291] The server analyzes the collected feedback data and updates the generative AI model. The input data is the feedback data, which is used to improve the model's accuracy. The output is an updated AI model. Specifically, it adjusts the model's hyperparameters based on the previous feedback and retrains the model on a new dataset.

[0292] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0293] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[0294] System Configuration

[0295] The system includes the following main components:

[0296] 1. Server

[0297] Data Collection Module

[0298] Emotion Engine

[0299] Integrated Database

[0300] Generative AI Models

[0301] Notification System

[0302] Feedback Collection Module

[0303] 2. Terminal

[0304] Agent User Interface

[0305] Feedback Input Interface

[0306] 3. Users

[0307] Person in Charge (the person who manages and staffs the crew)

[0308] Program processing

[0309] Data collection

[0310] The server uses the API of the internal system to collect crew characteristic data. It calls the Slack API to obtain the past 30 days of comment history and reaction data. It then uses the e-Learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[0311] The server uses the Google Maps API to collect location information and review comments for each store, which includes geographic coordinates and review comments based on a specific store ID.

[0312] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[0313] Data Integration

[0314] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[0315] The server combines this data and creates an index to allow for quick access and searching.

[0316] analysis

[0317] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. Emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[0318] suggestion

[0319] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[0320] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0321] Feedback collection

[0322] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[0323] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0324] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[0325] Specific examples

[0326] Data collection

[0327] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" through the Slack API. It also retrieves the test results for "User ID 123" using the e-Learning system API and collects the supervisor's evaluation data through the evaluation system API.

[0328] The server uses the Google Maps API to collect location information and customer evaluation comments for "Store ID 456."

[0329] The server uses the emotion engine to analyze the recent emotional state of "user ID 123" and obtains emotional data.

[0330] Data Integration

[0331] The server stores the acquired data in a MySQL integrated database. The crew characteristics data is stored in the "crew_data" table, the store evaluation data is stored in the "store_data" table, and the emotion data is stored in a separate table.

[0332] Analysis and Recommendations

[0333] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account to adjust the crew's stress levels and motivation.

[0334] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[0335] Feedback and Updates

[0336] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[0337] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[0338] The above is an embodiment of the present invention. This system realizes optimal staffing between crews and stores, improving business performance and reducing man-hours. Furthermore, staffing plans that take crew emotional data into account also improve staff motivation and well-being.

[0339] The processing flow will be explained below.

[0340] Step 1:

[0341] The server uses the API of the internal system to obtain crew characteristic data. To do this, it calls the Slack API to collect comment history and reaction data for the past 30 days. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and obtains evaluation data from superiors through the evaluation system API.

[0342] Step 2:

[0343] The server uses the Google Maps API to collect location information and reviews for each store. It obtains geographic coordinates, reviews, and reviews from a specific store ID.

[0344] Step 3:

[0345] The server uses an emotion engine to acquire crew emotional data, specifically analyzing comments and responses from Slack and interaction data from the e-learning system, to estimate the crew's emotional state (e.g., stress level and motivation).

[0346] Step 4:

[0347] The server stores the collected crew characteristic data, store evaluation data, and emotion data in an integrated database. Crew characteristic data is stored in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[0348] Step 5:

[0349] The server then combines these data and creates indexes to enable fast access and searching, specifically by joining each data table using an SQL query to generate new index fields.

[0350] Step 6:

[0351] The server uses data from the integrated database to train a generative AI model, taking into account crew characteristics (e.g., communication skills, performance, and ratings) and store characteristics (e.g., customer demographics, ratings, and event status) as well as emotional data to analyze optimal matches.

[0352] Step 7:

[0353] The server generates optimal staffing plans based on the analysis results. The plans are based on crew characteristics, store characteristics, and crew emotion data. The plans include which stores each crew member should be assigned to, the reasons for doing so, and the expected results.

[0354] Step 8:

[0355] The server sends the generated staffing plan to the person in charge through a notification system, and a notification is sent to the person in charge's terminal, providing details of the specific staffing plan.

[0356] Step 9:

[0357] The user (person in charge) uses the terminal to check the notified personnel allocation plan. The user checks the details of the proposal and makes adjustments as necessary. The actual allocation is carried out based on the confirmed allocation plan.

[0358] Step 10:

[0359] The user provides feedback to the system after the deployment, including the performance, satisfaction, and feedback comments of the deployed crew. Emotional data is also evaluated and provided as feedback.

[0360] Step 11:

[0361] The server stores the collected feedback data in an integrated database, including changes in emotional data, and reflects this in the next proposal.

[0362] Step 12:

[0363] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future staffing recommendations.

[0364] Step 13:

[0365] The server uses the updated generative AI model to optimize the next staffing plan, thereby achieving continuous optimal staffing, improving performance and reducing labor costs.

[0366] Example 2

[0367] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] Conventional systems optimize staffing based on crew characteristics, store location information, and evaluation data, but do not generate staffing plans that take crew emotional data into account. This can result in crew stress levels and motivation levels being ignored, often resulting in less-than-optimal staffing. A new staffing system is needed that can improve crew well-being while maximizing performance.

[0369] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring crew characteristic data; means for acquiring store location information and evaluation data; means for collecting and analyzing emotion data; means for storing the acquired crew characteristic data, store location information, evaluation data, and emotion data in an integrated database; a generative AI model means for analyzing the optimal match between crew and store using data from the integrated database; means for creating an index to enable rapid data search; means for generating an optimal staffing plan based on the analysis results; means for notifying a person in charge of the staffing plan based on the crew characteristics and store characteristics; means for transmitting the staffing plan to the person in charge's terminal via a notification system; means for collecting feedback data on the staffing plan; and means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal. This enables optimal staffing that takes crew characteristics and emotions into consideration, thereby improving business performance and enhancing crew motivation and well-being.

[0370] "Crew characteristic data" refers to profile information such as each crew member's communication skills, achievements, and evaluations.

[0371] "Store Location Information" refers to the geographic coordinates (latitude and longitude) of each store.

[0372] "Rating Data" refers to customer feedback, reviews, and rating scores for a store.

[0373] "Emotional data" is data that indicates the emotional state of the crew and is analyzed from interactions with communication tools and educational systems.

[0374] The "integrated database" refers to a database that centrally stores and manages crew characteristics data, store location information, evaluation data, and emotional data.

[0375] "Generative AI model" refers to an artificial intelligence model that uses crew and store data to analyze optimal matches and generate staffing plans.

[0376] An "index" refers to a search key created to enable rapid retrieval of data.

[0377] "Notification system" refers to a system for notifying personnel in charge of the generated staffing plan.

[0378] "Feedback data" refers to data such as crew performance, satisfaction, and feedback comments regarding implemented staffing plans.

[0379] MODE FOR CARRYING OUT THE INVENTION

[0380] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data, store location information, and evaluation data to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[0381] System Configuration

[0382] The system includes the following main components:

[0383] 1. Server

[0384] Data Collection Module

[0385] Emotion Engine

[0386] Integrated Database

[0387] Generative AI Models

[0388] Notification System

[0389] Feedback Collection Module

[0390] 2. Terminal

[0391] Agent User Interface

[0392] Feedback Input Interface

[0393] 3. Users

[0394] Person in Charge (the person who manages and staffs the crew)

[0395] Data collection

[0396] The server uses the API of the internal system to collect crew characteristic data. For example, it calls the Slack API to obtain the past 30 days' worth of comment history and reaction data. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[0397] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[0398] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[0399] Data Integration

[0400] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[0401] The server creates an index of this data to allow for quick access and retrieval.

[0402] analysis

[0403] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. The emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[0404] suggestion

[0405] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[0406] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0407] Feedback collection

[0408] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[0409] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0410] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[0411] Specific examples

[0412] Data collection

[0413] The server retrieves the posting history and reaction data for the past 30 days for "Crew ID 123" through the Slack API, retrieves the test results for "Crew ID 123" using the e-learning system API, and collects the evaluation data of superiors through the evaluation system API.

[0414] The server uses the geographic information service API to collect location information and customer evaluation comments for "Store ID 456."

[0415] The server uses the emotion engine to analyze the recent emotional state of "Crew ID 123" and obtains emotional data.

[0416] Data Integration

[0417] The server stores the acquired data in an integrated database. Crew characteristics data is stored in the "crew_data" table, store evaluation data is stored in the "store_data" table, and emotion data is stored in a separate table.

[0418] Analysis and Recommendations

[0419] The server inputs this data into the generative AI model and analyzes that "Crew ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account, and the server adjusts the crew's stress level and motivation.

[0420] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[0421] Feedback and Updates

[0422] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[0423] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[0424] These steps will enable optimal staffing between crews and stores, improving performance and increasing crew motivation and well-being.

[0425] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0426] System program processing flow

[0427] Step 1: Data collection

[0428] Input: API of internal systems, data from communication tools

[0429] process:

[0430] The server uses the API of the company's internal system to collect crew characteristic data. Specifically, it calls the Slack API to obtain the comment history and reaction data for the past 30 days.

[0431] The server uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[0432] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[0433] The server uses an emotion engine to acquire crew emotional data, including data obtained by analyzing emotional states from interactions with communication tools and e-learning systems.

[0434] Output: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[0435] Step 2: Data integration

[0436] Input: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[0437] process:

[0438] The server stores the collected data in an integrated database: crew characteristics data in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[0439] The server indexes this data to allow for quick access and retrieval.

[0440] Output: Integrated database

[0441] Step 3: Analysis

[0442] Input: Integrated database

[0443] process:

[0444] The server uses data from the integrated database to train a generative AI model, which analyzes the optimal match by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data.

[0445] Output: A trained generative AI model

[0446] Step 4: Generate placement proposals

[0447] Input: A trained generative AI model

[0448] process:

[0449] The server generates optimal staffing plans based on the analysis results, which include the reasons for the staffing and the expected results.

[0450] Output: Staffing plan

[0451] Step 5: Notification of proposed placement

[0452] Input: Staffing plan

[0453] process:

[0454] The server sends the generated placement plan to the terminal of the person in charge via the notification system. Specifically, the placement plan is converted into a document and sent to the person in charge as notification content.

[0455] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0456] Output: The placement plan is notified to the person in charge's terminal.

[0457] Step 6: Gather feedback

[0458] Input: Implementation results based on the placement plan, feedback from the person in charge

[0459] process:

[0460] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[0461] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0462] Output: Feedback data

[0463] Step 7: Analyze feedback data and update the model

[0464] Input: Feedback data

[0465] process:

[0466] The server collects feedback data, stores it in an integrated database, and analyzes the collected feedback data to update the generative AI model.

[0467] Output: Updated generative AI model

[0468] In this way, optimal staffing of crews and stores can be achieved through each step, improving business performance and increasing crew motivation and well-being.

[0469] (Application example 2)

[0470] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0471] Conventional staffing systems only utilize characteristic data, location information, and evaluation data, and are unable to optimize staffing by taking into account the emotional state and motivation of crew members. This can lead to lower crew stress levels and motivation, which can hinder performance improvement and customer satisfaction. Furthermore, there is a lack of a mechanism to fully reflect feedback and improve the accuracy of next staffing proposals.

[0472] The identification process by the identification 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 means for acquiring crew characteristic data, means for acquiring store location information and evaluation data, and means for acquiring crew emotion data and storing this data in an integrated database. This makes it possible to generate more accurate and effective staffing plans based on the crew characteristic data and emotion data and the store characteristics, and notify the person in charge in real time.

[0473] The system further includes means for combining crew characteristic data, emotion data, store location information, and evaluation data and creating an index, which allows for rapid access and search of the data.

[0474] Furthermore, the system includes a means for transmitting the results of the staffing plan to the terminal of the person in charge in real time via the notification system, thereby enabling the person in charge to immediately check and adjust the staffing plan.

[0475] It includes a means to analyze the collected feedback data and update the generative AI model, which can then provide more accurate staffing recommendations in the next deployment proposal, improving crew motivation and well-being.

[0476] "Crew characteristic data" is information about individual characteristics of employees, such as communication skills, performance, and evaluations.

[0477] "Store location information and evaluation data" refers to information about the geographic location of a store and information about evaluation comments and evaluation scores from customers.

[0478] "Emotional data" is information about an employee's emotional state, such as stress level or motivation.

[0479] The "integrated database" is a database system that centrally stores characteristic data, emotion data, store location information, and evaluation data, enabling quick access and search of the data.

[0480] The "generative AI model" is an artificial intelligence model that analyzes and generates optimal staffing plans using crew characteristic data, emotional data, store location information, and evaluation data.

[0481] The "notification system" is a system that notifies personnel deployment plans generated by the generative AI model to the terminals of personnel in real time.

[0482] "Feedback data" refers to data regarding employee performance, satisfaction, emotional state, etc., based on the results of implementing staffing plans.

[0483] The "feedback collection means" is a function for collecting set feedback data and reflecting it in the integrated database and generative AI model.

[0484] This invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing proposals that also take emotion data into consideration. The system includes the following main components:

[0485] System Configuration

[0486] server

[0487] Data collection module: Collects crew characteristics data, emotion data, store location information and evaluation data.

[0488] Integrated database: Collected data is managed centrally, enabling quick search and access.

[0489] Generative AI model: Analyzes data and generates optimal staffing recommendations.

[0490] Notification system: Notifies the person in charge of the generated placement plan in real time.

[0491] Feedback collection module: Collects feedback data and updates the AI ​​model.

[0492] Terminal

[0493] User interface for personnel: An interface that displays the proposed staffing plan and allows personnel to review and adjust it.

[0494] Feedback input interface: An interface for inputting feedback on the implemented staffing plan.

[0495] User

[0496] Person in Charge: The person who manages and staffs the crew.

[0497] Program processing

[0498] Data collection

[0499] The server uses the Slack API to collect crew characteristic data. It also uses the e-Learning system API to obtain crew learning progress data and test results, and collects data from the evaluation system API. It uses the Google Maps API to collect store location information and evaluation comments. It uses an emotion engine (e.g., Affectiva) to collect employee emotion data.

[0500] Data Integration

[0501] The server stores the collected data in a MySQL integrated database: characteristic data in the "crew_data" table, store information in the "store_data" table, and emotion data in the "emotion_data" table.

[0502] Generate staffing plans

[0503] The server uses data from the integrated database to train a generative AI model, which references crew characteristics, emotional data, and store characteristics data to generate optimal staffing plans.

[0504] Suggestions and Notifications

[0505] The generated staffing plan is sent to the staff member's device in real time via the notification system, and the staff member's user interface displays the plan, allowing them to review and make any necessary adjustments.

[0506] Gathering feedback and updating the model

[0507] Feedback data is input by the staff through the feedback input interface, which is then sent to the server for analysis, which then updates the generative AI model and reflects it in the next staffing proposal.

[0508] Specific examples

[0509] Prompt Sentence Examples

[0510] Inputs to the generative AI model:

[0511] Crew characteristics: "Communication skills: 8 / 10, Performance: 9 / 10, Evaluation: Positive"

[0512] Emotional data: "Stress level: low, motivation: high"

[0513] Store data: "Store ID 456, Customer type: Family, Rating: 4.5 / 5"

[0514] User ID 123's characteristic data: {"Communication skills: 8 / 10","Performance: 9 / 10","Evaluation: Positive"}

[0515] Emotion data for user ID 123: {"Stress level: Low","Motivation: High"}

[0516] Store ID 456 store data: {"Customer demographic: Family","Rating: 4.5 / 5"}

[0517] Based on this data, generate optimal staffing plans.

[0518] Output of the generative AI model:

[0519] Placement plan: "Place user ID 123 at store ID 456"

[0520] Example notification:

[0521] "User ID 123 is a perfect fit for store ID 456. Reasons for placement: high communication skills, low stress level, family-friendly store characteristics."

[0522] This system will enable optimal staffing between crews and stores, improving performance and reducing man-hours. It will also improve staff motivation and well-being by providing staffing suggestions that take into account crew emotional data.

[0523] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0524] Step 1:

[0525] The server uses the Slack API to obtain 30 days' worth of crew characteristic data (comment history, reaction data). This data is combined with test results and learning progress data collected using the e-Learning system API, and evaluation data obtained from the evaluation system API. At this time, the crew characteristic data is input and characteristic data is collected.

[0526] Step 2:

[0527] The server uses the Google Maps API to obtain the store's location information and evaluation comments. At this time, the store's ID is used as input, and the obtained store's geographic coordinates and evaluation comments are output.

[0528] Step 3:

[0529] The server uses an emotion engine (e.g., Affectiva) to collect crew emotion data. The emotion data is obtained by analyzing interactions in communication tools and e-learning systems. The interaction data is used as input, and emotion data is obtained as output.

[0530] Step 4:

[0531] The server stores the collected crew characteristics data, store location information, evaluation data, and emotion data in an integrated database (MySQL). Each piece of data is stored in its own dedicated table (crew_data, store_data, emotion_data). Each piece of collected data is used as input, and is stored in the integrated database as output.

[0532] Step 5:

[0533] The server trains a generative AI model using data from the integrated database. To analyze the optimal match between crew and store, it generates prompt sentences and uses characteristic data, emotion data, and store data as inputs. This results in the output of optimal staffing recommendations.

[0534] Step 6:

[0535] The server sends the generated placement plan to the person in charge's device in real time via the notification system. The placement plan from the generative AI model is used as input, and the placement plan is notified to the person in charge's device as output.

[0536] Step 7:

[0537] The terminal uses a user interface for the staff member to display the proposed placement plan, which the staff member can review and adjust. The notified placement plan is used as input, and the reviewed and adjusted placement plan is obtained as output.

[0538] Step 8:

[0539] The user (person in charge) inputs feedback (performance, satisfaction, emotional state) for the implemented staffing plan through the feedback input interface. The feedback data is used as input and is sent to the server.

[0540] Step 9:

[0541] The server analyzes the collected feedback data and stores it in an integrated database. It also updates the generative AI model based on the feedback data. The feedback data is used as input, and the updated generative AI model is obtained as output.

[0542] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0543] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0544] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0545] [Second embodiment]

[0546] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0547] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0548] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0549] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0550] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0552] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0553] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0554] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0555] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0556] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0557] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0558] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[0559] System Configuration

[0560] The system includes the following main components:

[0561] 1. Server

[0562] Data Collection Module

[0563] Integrated Database

[0564] Generative AI Models

[0565] Notification System

[0566] Feedback Collection Module

[0567] 2. Terminal

[0568] Agent User Interface

[0569] Feedback Input Interface

[0570] 3. Users

[0571] Person in Charge (the person who manages and staffs the crew)

[0572] Program processing

[0573] Data collection

[0574] The server uses the API of the company's internal system to obtain crew characteristic data, including comment history and reaction data from communication tools (e.g., Slack), test results from the e-learning system, and superior evaluations from the evaluation system.

[0575] The server uses the Google Maps API to collect location information and evaluation comments for each store.

[0576] Data Integration

[0577] The server stores the collected data in an integrated database. Crew characteristics data is stored in the "crew_data" table, and store evaluation data is stored in the "store_data" table.

[0578] The server combines crew and store data and creates an index to enable quick access and searching.

[0579] analysis

[0580] The server uses data from the integrated database to train a generative AI model and analyze the optimal match between crew and store.

[0581] The generative AI model compares the crew's communication skills and performance with the store's customer demographics and characteristics to find optimal staffing plans.

[0582] suggestion

[0583] The server transmits the generated placement plan to the terminal of the person in charge via the notification system.

[0584] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0585] Feedback collection

[0586] The user (person in charge) will then carry out the actual personnel allocation based on the proposed allocation plan and provide feedback on the results to the system.

[0587] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0588] The server analyzes the collected feedback data and uses it to update the generative AI model, thereby improving the accuracy of future placement suggestions.

[0589] Specific examples

[0590] Data collection

[0591] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" via the Slack API.

[0592] The server uses the Google Maps API to collect the location information and most recent customer evaluation comments for "Store ID 456."

[0593] Data Integration

[0594] The server inserts the retrieved data into the MySQL integrated database. The "crew_data" table stores the comment history and reaction data of "user ID 123," and the "store_data" table stores the evaluation comments of "store ID 456."

[0595] Analysis and Recommendations

[0596] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Based on this analysis result, it proposes placing "User ID 123" in "Store ID 456."

[0597] The server transmits the generated placement plan to the person in charge through a notification system, and displays the notification on the person in charge's terminal.

[0598] Feedback and Updates

[0599] After the user performs the placement based on the proposal, the user inputs the placement results and feedback into the system.

[0600] The server collects the feedback data and updates the generative AI model for the next placement proposal.

[0601] The above is an embodiment of the present invention. This processing flow realizes optimal staffing between crews and stores, thereby improving business performance and reducing man-hours.

[0602] The processing flow will be explained below.

[0603] Step 1:

[0604] The server uses the API of the internal system to obtain crew characteristic data. It calls the Slack API to collect comment history and reaction data from the past 30 days. It then queries the e-learning system API to obtain each crew member's test results and progress. It also obtains past evaluation data and feedback from superiors through the evaluation system API.

[0605] Step 2:

[0606] The server uses the Google Maps API to collect location information and customer reviews for each store. Specifically, it obtains geographic coordinates based on a specific store ID, and also collects the most recent customer reviews and comments.

[0607] Step 3:

[0608] The server stores the collected crew characteristic data, store location information, and evaluation data in an integrated database. Crew characteristic data is organized in the "crew_data" table and saved using the crew ID as a key. Store evaluation data is inserted into the "store_data" table and saved using the store ID as a key.

[0609] Step 4:

[0610] The server combines the crew and store data and creates an index for quick access and searching. Specifically, it uses an SQL query to join both data sets and generate new index fields.

[0611] Step 5:

[0612] The server trains a generative AI model using data from the integrated database. The model compares crew characteristics (communication skills, performance, ratings) with store characteristics (customer demographics, ratings, event status) to find the best match. Past deployment data and feedback are also used to train the model.

[0613] Step 6:

[0614] The server generates the staffing plan and notifies the person in charge. Specifically, the server converts the generated staffing plan into a document and sends it to the person in charge's terminal through the notification system. The notification includes details of the staffing plan, the reasons for the plan, and the expected results.

[0615] Step 7:

[0616] The user confirms the notified personnel deployment plan, checks the proposal through the user interface for the person in charge, and makes adjustments as necessary. The user then deploys the crew based on the confirmed deployment plan.

[0617] Step 8:

[0618] Users provide feedback to the system after deployment by entering the deployed crew's performance, satisfaction, and feedback comments through a feedback input interface, including specific achievements and problems after deployment.

[0619] Step 9:

[0620] The server collects the collected feedback data and stores it in an integrated database. It then analyzes the feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[0621] Step 10:

[0622] The server uses the updated generative AI model to further optimize the next staffing plan, thereby continuously achieving optimal staffing, improving performance and reducing labor costs.

[0623] Example 1

[0624] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0625] In the conventional system, matching employees with facilities was not possible while taking into full consideration the characteristics of the employees and the facilities, making it difficult to achieve appropriate placement. In addition, there was a lack of a mechanism for efficiently collecting feedback on placement results and reflecting it in the next placement, making continuous improvement difficult.

[0626] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0627] In this invention, the server includes means for acquiring employee characteristic data, means for acquiring facility location information and evaluation data, means for storing the acquired employee characteristic data, facility location information, and evaluation data in an integrated database, means for generating a generative AI model that analyzes an optimal match between employees and facilities using data from the integrated database, means for generating an optimal staffing plan based on the analysis results, means for notifying a person in charge of the staffing plan based on the employee characteristics and the facility characteristics, means for collecting feedback data on the staffing plan, means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal, means for acquiring facility evaluation data from customers, means for acquiring employee characteristic data from communication tools and an education system, and means for receiving feedback data from a terminal. This enables optimal staffing between employees and facilities, improving business efficiency and enabling continuous improvement in staffing.

[0628] "Employee" refers to a person employed by a company or organization to perform work.

[0629] "Characteristic data" refers to data that represents an employee's individual characteristics, such as their communication skills or performance.

[0630] "Facility" means a place of business where employees are located, including stores, factories, offices, etc.

[0631] "Location information" refers to data indicating a geographical location, and includes information such as latitude and longitude.

[0632] "Evaluation Data" refers to data representing evaluations and feedback on facilities and employees.

[0633] An "integrated database" refers to a database that centrally manages and stores information collected from multiple data sources.

[0634] A "generative AI model" is a model that uses machine learning and artificial intelligence to learn data patterns and make predictions and suggestions.

[0635] "Matching" refers to the process of analyzing the compatibility between employee characteristics and facility characteristics to find the optimal combination.

[0636] "Notification system" refers to a system that sends information or data to specific devices or personnel.

[0637] "Feedback data" refers to data that shows evaluations of staffing results and areas for improvement.

[0638] "Communication tools" refers to software and platforms used to communicate between employees and within an organization.

[0639] An "educational system" refers to a system that provides teaching materials and tests aimed at improving employees' skills and acquiring knowledge.

[0640] "Device" refers to a computer or mobile device used by a user or agent.

[0641] The present invention relates to a system for collecting, integrating, and analyzing employee characteristic data and facility evaluation data to achieve optimal staffing. Specific embodiments for carrying out the present invention will be described below.

[0642] System Configuration

[0643] The system includes the following main components:

[0644] 1. Server

[0645] Data Collection Module

[0646] Integrated Database

[0647] Generative AI Models

[0648] Notification System

[0649] Feedback Collection Module

[0650] 2. Terminal

[0651] Agent User Interface

[0652] Feedback Input Interface

[0653] 3. Users

[0654] Person in charge (the person who manages and staffs employees)

[0655] Data collection

[0656] The server uses the API of a communication tool (e.g., a chat system) to obtain employee characteristic data. Specifically, it collects 30 days of comment history and reaction data, test results from the education system, and supervisor evaluations from the evaluation system. The server also uses a geographic information API to collect facility location information and customer evaluation comments.

[0657] For example, the server performs the following operations:

[0658] Access the API endpoint https: / / api.chat-system.com / history?user=123 to retrieve the comment history and reaction data for "user ID 123."

[0659] Access the API endpoint https: / / api.geo-service.com / place / details?place_id=456 and collect location information and customer evaluation comments for "facility ID 456."

[0660] Data Integration

[0661] The collected data is stored in a MySQL integrated database by the server. Employee comment history and reaction data are stored in the "employee_data" table, and facility evaluation comments are stored in the "facility_data" table. The server also combines crew and facility data and generates indexes to enable quick access.

[0662] example:

[0663] sql

[0664] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[0665] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[0666] Data analysis

[0667] The server trains a generative AI model using data from the integrated database, which then analyzes the optimal match between employees and facilities. The generative AI model uses machine learning algorithms (e.g., TensorFlow and PyTorch) to analyze employee communication skills and performance, as well as the customer demographics and characteristics of facilities, to find optimal staffing plans.

[0668] suggestion

[0669] The server sends the generated staffing plan to the staff member's device via a notification system. The device (the staff member's user interface) displays the proposed staffing plan, which the staff member can review and adjust. As a specific example of the operation here, the staff member could input the following prompts to the AI:

[0670] Please propose the optimal staffing plan based on the communication skill data of "User ID 123" over the past 30 days and the evaluation comments of "Facility ID 456."

[0671] Feedback collection

[0672] The user (person in charge) performs actual staffing based on the proposed staffing plan and inputs the results as feedback to the system. The terminal (feedback input interface) inputs the feedback data from the person in charge and sends it to the server. The server analyzes the collected feedback data and updates the generative AI model. This improves the accuracy of future staffing proposals.

[0673] The above is a specific embodiment for carrying out the present invention. This processing flow realizes optimal staffing between employees and facilities, and enables improved work efficiency and continuous improvement of staffing.

[0674] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0675] Step 1: Data collection

[0676] The server sends requests to the APIs of communication tools and education systems to obtain employee characteristic data. Specifically, it collects data based on the following inputs:

[0677] (Input): API endpoint and query parameters (e.g. https: / / api.chat-system.com / history?user=123)

[0678] The server parses the JSON data returned from the API and extracts comment history and reaction data.

[0679] (Output): A JSON object containing the comment history and reaction data.

[0680] Specific behavior:

[0681] The server accesses the Slack API endpoint https: / / api.chat-system.com / history?user=123 and retrieves the message history and reaction data for the past 30 days for "user ID 123."

[0682] The server analyzes the JSON data obtained from the API and extracts the specific content of the comments and the type of each reaction.

[0683] Step 2: Data integration

[0684] The server generates SQL queries to store the collected data in a MySQL integrated database.

[0685] (Input): Speech history and reaction data, facility evaluation data

[0686] The server uses SQL queries to insert data into the database, which saves each piece of data in its corresponding table.

[0687] (Output): Employee characteristics data and facility evaluation data stored in a database

[0688] Specific behavior:

[0689] The server executes the following SQL query to insert the comment history and reaction data into the "employee_data" table:

[0690] sql

[0691] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[0692] Similarly, facility evaluation comments are stored in the "facility_data" table.

[0693] sql

[0694] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[0695] Step 3: Data Joining and Indexing

[0696] The server combines the employee characteristic data with the facility evaluation data and generates an index to enable rapid access and retrieval.

[0697] (Input): Employee characteristics data and facility evaluation data in the database

[0698] The server combines the data using SQL JOIN operations and generates the index.

[0699] (Output): The combined data and the generated index.

[0700] Specific behavior:

[0701] The server uses the following SQL query to join the data and generate the index:

[0702] sql

[0703] CREATE INDEX idx_user_store ON combined_data (user_id, store_id);

[0704] Step 4: Training the generative AI model

[0705] The server inputs data from the integrated database into the generative AI model and trains the model.

[0706] (Input): Combined employee and facility data in the database

[0707] The server uses machine learning algorithms to train the model and analyze the best matches.

[0708] (Output): Trained generative AI model and analysis results

[0709] Specific behavior:

[0710] The server runs Python programs and uses libraries such as TensorFlow or PyTorch to train generative AI models.

[0711] Training data includes employee communication skills and performance, as well as the customer demographics and characteristics of the facility.

[0712] Step 5: Generate and notify placement proposals

[0713] The server generates optimal staffing plans based on the analysis results obtained from the generative AI model.

[0714] (Input): Trained generative AI model and employee and facility data

[0715] The server sends the placement plan generated from the analysis results to the person in charge via a notification system.

[0716] (Output): Staffing plan sent to the person in charge's terminal

[0717] Specific behavior:

[0718] The server creates an optimal personnel allocation plan based on the analysis results.

[0719] The server transmits the placement plan to the terminal of the person in charge and displays it on the user interface for the person in charge.

[0720] Step 6: Gather feedback

[0721] The user performs actual staffing based on the proposed staffing plan and inputs the results into the system as feedback.

[0722] (Input): Results and feedback comments from the person in charge

[0723] The terminal collects feedback data through a feedback input interface and sends it to the server.

[0724] (Output): Feedback data sent to the server

[0725] Specific behavior:

[0726] The user assigns employees according to the assignment plan and inputs the results and feedback into the terminal.

[0727] The terminal transmits the collected feedback data to the server.

[0728] Step 7: Update the generative AI model

[0729] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future placement suggestions.

[0730] (Input): Feedback data and existing generative AI models

[0731] The server uses the feedback data to retrain and update the generative AI model.

[0732] (Output): Updated generative AI model

[0733] Specific behavior:

[0734] The server analyzes the collected feedback data and extracts the information needed to improve the accuracy of the model.

[0735] The server retrains the generative AI model and reflects it in the next placement proposal.

[0736] This is the specific flow of the program processing of this system. This procedure is expected to achieve optimal matching between employees and facilities and improve work efficiency.

[0737] (Application example 1)

[0738] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0739] Conventional factory robot allocation systems have the problem of being unable to achieve efficient work allocation because it is difficult to optimally match each robot based on its characteristics and task requirements. Furthermore, there is a lack of flexible system design that reflects feedback after task allocation. As a result, there are issues such as reduced productivity and insufficient robot operational efficiency.

[0740] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0741] In this invention, the server includes a means for acquiring personnel characteristic data, a means for acquiring work base location information and evaluation data, and a means for storing the acquired personnel characteristic data, work base location information, and evaluation data in an integrated database, thereby realizing a generative AI model that analyzes optimal matching between personnel and work bases.

[0742] "Personnel characteristic data" is data that indicates the specific attributes and capabilities of each personnel, such as the speed, accuracy, and power consumption of that personnel.

[0743] "Location information of work base" refers to the geographic coordinates of the location where work is performed and detailed information about that location.

[0744] "Evaluation data" refers to data that indicates evaluations and feedback on work sites and personnel.

[0745] An "integrated database" is a database that centrally manages and stores a wide variety of data and enables efficient access.

[0746] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data on personnel and work locations and generate optimal matching and placement plans.

[0747] A "notification system" is a mechanism for quickly and reliably notifying administrators and personnel of information generated by the system.

[0748] "Feedback data" refers to data that indicates actual results and evaluations based on the placement proposal, and is collected to be reflected in the next proposal.

[0749] An "index" is something like a table of contents created for data in a database to speed up data searches.

[0750] A "robotic arm" is a mechanical arm-like device used to perform tasks in a factory.

[0751] "Task requirement information" is information that indicates the conditions and requirements necessary for the performance of a specific work or task.

[0752] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[0753] System Configuration

[0754] The system includes the following main components:

[0755] 1. Server

[0756] Data Collection Module

[0757] Integrated Database

[0758] Generative AI Models

[0759] Notification System

[0760] Feedback Collection Module

[0761] 2. Terminal

[0762] Administrator User Interface

[0763] Feedback Input Interface

[0764] 3. Users

[0765] Manager (person who manages the placement of robots within the factory)

[0766] Program processing

[0767] The server collects, analyzes, proposes, and updates data in the following steps:

[0768] Technology used

[0769] 1. Hardware:

[0770] Robotic arms (e.g., typical factory robotic arms)

[0771] Sensors (e.g. Lidar, cameras)

[0772] Server (e.g. AWS EC2)

[0773] 2. Software:

[0774] Data collection module (Python, Slack API, factory integrated management system API, etc.)

[0775] Integrated database (MySQL)

[0776] Generative AI models (e.g., TensorFlow, PyTorch)

[0777] Notification systems (e.g. Firebase)

[0778] Feedback collection module (e.g. Flask)

[0779] Data collection

[0780] The server obtains characteristic data for each robot (such as operating speed, accuracy, and power consumption) from the factory's integrated management system. It also collects task status information within the factory from sensors. For example, it obtains characteristic data such as operating speed, accuracy, and power consumption for "robot ID 123," and collects location information and required operating accuracy for "task ID 456."

[0781] Data Integration

[0782] The collected data is stored in the server's integrated MySQL database, where personnel characteristics data is stored in the "robot_data" table and task request data is stored in the "task_data" table.

[0783] analysis

[0784] The server uses data from the integrated database to train the generative AI model and analyzes the characteristics and task requirements of each robot. Based on the results of this analysis, it proposes optimal robot task assignments. For example, the generative AI model can input the characteristics data of "Robot ID 123" and the requirements of "Task ID 456," and determine that "Robot ID 123" is optimal for "Task ID 456."

[0785] suggestion

[0786] The server sends the generated task allocation plan to the administrator's terminal via the notification system. The administrator's user interface displays the proposed placement plan, which the administrator can review and adjust. For example, the generated placement plan is notified to the administrator's terminal, and the administrator performs the placement based on the proposal.

[0787] Feedback collection

[0788] The administrator performs placement based on the proposed placement plan and provides feedback to the system on the results. The server collects the feedback data and updates the generative AI model to reflect it in the next placement proposal.

[0789] Specific examples

[0790] Examples of prompt sentences include:

[0791] The characteristic data (operation speed, accuracy, power consumption) for "Robot ID 123" are as follows. Based on this, make the optimal allocation to meet the requirements (position information, operation accuracy) of "Task ID 456".

[0792] This is expected to improve the efficiency of robot placement within factories and increase productivity.

[0793] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0794] Step 1:

[0795] The server obtains the characteristic data of each robot through the factory integrated management system API. This includes the robot's operating speed, accuracy, power consumption, etc. Based on this input data, the characteristic data is collected and saved. Specifically, the server sends an API request and stores the obtained data in the "robot_data" table of the integrated database.

[0796] Step 2:

[0797] The server collects task status information from sensors in the factory. The acquired input data includes the task's location information and the required operating accuracy. Based on this data, detailed task information is saved in the "task_data" table. Specifically, it acquires real-time data from the sensors, organizes it, and inserts it into the database.

[0798] Step 3:

[0799] The server integrates the robot characteristic data and task request data stored in the integrated database and structures the data. Here, it creates indexes to speed up data searches. It uses data from the "robot_data" table and the "task_data" table as input and outputs indexed integrated data. Specific operations include data merging using SQL queries and creating indexes.

[0800] Step 4:

[0801] The server trains the generative AI model using data from the integrated database. The input is the integrated robot and task data, and it analyzes the optimal match based on this. The output is the optimal robot task assignment proposal as a result of the analysis. The specific operation is the training process of the generative AI model using TensorFlow and PyTorch.

[0802] Step 5:

[0803] The server sends the task allocation plan analyzed by the generative AI model to the administrator's device via the notification system. The input is the generated placement plan, and the output is displayed on the administrator's device as a notification. The specific operation is to send a push notification using Firebase.

[0804] Step 6:

[0805] The administrator executes the actual deployment based on the proposed deployment plan. The input is the deployment plan notified by the server, and the output is the actual deployment result. The specific operation is to confirm the deployment plan through the user interface and actually deploy the robot.

[0806] Step 7:

[0807] The administrator inputs feedback based on the deployment results into the feedback input interface. The input data is the deployment execution result and its evaluation. The output is sent to the server as feedback data. The specific operation is that the administrator submits the evaluation using the feedback form.

[0808] Step 8:

[0809] The server analyzes the collected feedback data and updates the generative AI model. The input data is the feedback data, which is used to improve the model's accuracy. The output is an updated AI model. Specifically, it adjusts the model's hyperparameters based on the previous feedback and retrains the model on a new dataset.

[0810] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0811] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[0812] System Configuration

[0813] The system includes the following main components:

[0814] 1. Server

[0815] Data Collection Module

[0816] Emotion Engine

[0817] Integrated Database

[0818] Generative AI Models

[0819] Notification System

[0820] Feedback Collection Module

[0821] 2. Terminal

[0822] Agent User Interface

[0823] Feedback Input Interface

[0824] 3. Users

[0825] Person in Charge (the person who manages and staffs the crew)

[0826] Program processing

[0827] Data collection

[0828] The server uses the API of the internal system to collect crew characteristic data. It calls the Slack API to obtain the past 30 days of comment history and reaction data. It then uses the e-Learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[0829] The server uses the Google Maps API to collect location information and review comments for each store, which includes geographic coordinates and review comments based on a specific store ID.

[0830] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[0831] Data Integration

[0832] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[0833] The server combines this data and creates an index to allow for quick access and searching.

[0834] analysis

[0835] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. Emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[0836] suggestion

[0837] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[0838] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0839] Feedback collection

[0840] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[0841] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0842] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[0843] Specific examples

[0844] Data collection

[0845] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" through the Slack API. It also retrieves the test results for "User ID 123" using the e-Learning system API and collects the supervisor's evaluation data through the evaluation system API.

[0846] The server uses the Google Maps API to collect location information and customer evaluation comments for "Store ID 456."

[0847] The server uses the emotion engine to analyze the recent emotional state of "user ID 123" and obtains emotional data.

[0848] Data Integration

[0849] The server stores the acquired data in a MySQL integrated database. The crew characteristics data is stored in the "crew_data" table, the store evaluation data is stored in the "store_data" table, and the emotion data is stored in a separate table.

[0850] Analysis and Recommendations

[0851] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account to adjust the crew's stress levels and motivation.

[0852] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[0853] Feedback and Updates

[0854] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[0855] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[0856] The above is an embodiment of the present invention. This system realizes optimal staffing between crews and stores, improving business performance and reducing man-hours. Furthermore, staffing plans that take crew emotional data into account also improve staff motivation and well-being.

[0857] The processing flow will be explained below.

[0858] Step 1:

[0859] The server uses the API of the internal system to obtain crew characteristic data. To do this, it calls the Slack API to collect comment history and reaction data for the past 30 days. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and obtains evaluation data from superiors through the evaluation system API.

[0860] Step 2:

[0861] The server uses the Google Maps API to collect location information and reviews for each store. It obtains geographic coordinates, reviews, and reviews from a specific store ID.

[0862] Step 3:

[0863] The server uses an emotion engine to acquire crew emotional data, specifically analyzing comments and responses from Slack and interaction data from the e-learning system, to estimate the crew's emotional state (e.g., stress level and motivation).

[0864] Step 4:

[0865] The server stores the collected crew characteristic data, store evaluation data, and emotion data in an integrated database. Crew characteristic data is stored in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[0866] Step 5:

[0867] The server then combines these data and creates indexes to enable fast access and searching, specifically by joining each data table using an SQL query to generate new index fields.

[0868] Step 6:

[0869] The server uses data from the integrated database to train a generative AI model, taking into account crew characteristics (e.g., communication skills, performance, and ratings) and store characteristics (e.g., customer demographics, ratings, and event status) as well as emotional data to analyze optimal matches.

[0870] Step 7:

[0871] The server generates optimal staffing plans based on the analysis results. The plans are based on crew characteristics, store characteristics, and crew emotion data. The plans include which stores each crew member should be assigned to, the reasons for doing so, and the expected results.

[0872] Step 8:

[0873] The server sends the generated staffing plan to the person in charge through a notification system, and a notification is sent to the person in charge's terminal, providing details of the specific staffing plan.

[0874] Step 9:

[0875] The user (person in charge) uses the terminal to check the notified personnel allocation plan. The user checks the details of the proposal and makes adjustments as necessary. The actual allocation is carried out based on the confirmed allocation plan.

[0876] Step 10:

[0877] The user provides feedback to the system after the deployment, including the performance, satisfaction, and feedback comments of the deployed crew. Emotional data is also evaluated and provided as feedback.

[0878] Step 11:

[0879] The server stores the collected feedback data in an integrated database, including changes in emotional data, and reflects this in the next proposal.

[0880] Step 12:

[0881] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future staffing recommendations.

[0882] Step 13:

[0883] The server uses the updated generative AI model to optimize the next staffing plan, thereby achieving continuous optimal staffing, improving performance and reducing labor costs.

[0884] Example 2

[0885] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0886] Conventional systems optimize staffing based on crew characteristics, store location information, and evaluation data, but do not generate staffing plans that take crew emotional data into account. This can result in crew stress levels and motivation levels being ignored, often resulting in less-than-optimal staffing. A new staffing system is needed that can improve crew well-being while maximizing performance.

[0887] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring crew characteristic data; means for acquiring store location information and evaluation data; means for collecting and analyzing emotion data; means for storing the acquired crew characteristic data, store location information, evaluation data, and emotion data in an integrated database; a generative AI model means for analyzing the optimal match between crew and store using data from the integrated database; means for creating an index to enable rapid data search; means for generating an optimal staffing plan based on the analysis results; means for notifying a person in charge of the staffing plan based on the crew characteristics and store characteristics; means for transmitting the staffing plan to the person in charge's terminal via a notification system; means for collecting feedback data on the staffing plan; and means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal. This enables optimal staffing that takes crew characteristics and emotions into consideration, thereby improving business performance and enhancing crew motivation and well-being.

[0888] "Crew characteristic data" refers to profile information such as each crew member's communication skills, achievements, and evaluations.

[0889] "Store Location Information" refers to the geographic coordinates (latitude and longitude) of each store.

[0890] "Rating Data" refers to customer feedback, reviews, and rating scores for a store.

[0891] "Emotional data" is data that indicates the emotional state of the crew and is analyzed from interactions with communication tools and educational systems.

[0892] The "integrated database" refers to a database that centrally stores and manages crew characteristics data, store location information, evaluation data, and emotional data.

[0893] "Generative AI model" refers to an artificial intelligence model that uses crew and store data to analyze optimal matches and generate staffing plans.

[0894] An "index" refers to a search key created to enable rapid retrieval of data.

[0895] "Notification system" refers to a system for notifying personnel in charge of the generated staffing plan.

[0896] "Feedback data" refers to data such as crew performance, satisfaction, and feedback comments regarding implemented staffing plans.

[0897] MODE FOR CARRYING OUT THE INVENTION

[0898] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data, store location information, and evaluation data to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[0899] System Configuration

[0900] The system includes the following main components:

[0901] 1. Server

[0902] Data Collection Module

[0903] Emotion Engine

[0904] Integrated Database

[0905] Generative AI Models

[0906] Notification System

[0907] Feedback Collection Module

[0908] 2. Terminal

[0909] Agent User Interface

[0910] Feedback Input Interface

[0911] 3. Users

[0912] Person in Charge (the person who manages and staffs the crew)

[0913] Data collection

[0914] The server uses the API of the internal system to collect crew characteristic data. For example, it calls the Slack API to obtain the past 30 days' worth of comment history and reaction data. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[0915] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[0916] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[0917] Data Integration

[0918] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[0919] The server creates an index of this data to allow for quick access and retrieval.

[0920] analysis

[0921] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. The emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[0922] suggestion

[0923] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[0924] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0925] Feedback collection

[0926] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[0927] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0928] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[0929] Specific examples

[0930] Data collection

[0931] The server retrieves the posting history and reaction data for the past 30 days for "Crew ID 123" through the Slack API, retrieves the test results for "Crew ID 123" using the e-learning system API, and collects the evaluation data of superiors through the evaluation system API.

[0932] The server uses the geographic information service API to collect location information and customer evaluation comments for "Store ID 456."

[0933] The server uses the emotion engine to analyze the recent emotional state of "Crew ID 123" and obtains emotional data.

[0934] Data Integration

[0935] The server stores the acquired data in an integrated database. Crew characteristics data is stored in the "crew_data" table, store evaluation data is stored in the "store_data" table, and emotion data is stored in a separate table.

[0936] Analysis and Recommendations

[0937] The server inputs this data into the generative AI model and analyzes that "Crew ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account, and the server adjusts the crew's stress level and motivation.

[0938] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[0939] Feedback and Updates

[0940] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[0941] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[0942] These steps will enable optimal staffing between crews and stores, improving performance and increasing crew motivation and well-being.

[0943] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0944] System program processing flow

[0945] Step 1: Data collection

[0946] Input: API of internal systems, data from communication tools

[0947] process:

[0948] The server uses the API of the company's internal system to collect crew characteristic data. Specifically, it calls the Slack API to obtain the comment history and reaction data for the past 30 days.

[0949] The server uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[0950] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[0951] The server uses an emotion engine to acquire crew emotional data, including data obtained by analyzing emotional states from interactions with communication tools and e-learning systems.

[0952] Output: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[0953] Step 2: Data integration

[0954] Input: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[0955] process:

[0956] The server stores the collected data in an integrated database: crew characteristics data in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[0957] The server indexes this data to allow for quick access and retrieval.

[0958] Output: Integrated database

[0959] Step 3: Analysis

[0960] Input: Integrated database

[0961] process:

[0962] The server uses data from the integrated database to train a generative AI model, which analyzes the optimal match by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data.

[0963] Output: A trained generative AI model

[0964] Step 4: Generate placement proposals

[0965] Input: A trained generative AI model

[0966] process:

[0967] The server generates optimal staffing plans based on the analysis results, which include the reasons for the staffing and the expected results.

[0968] Output: Staffing plan

[0969] Step 5: Notification of proposed placement

[0970] Input: Staffing plan

[0971] process:

[0972] The server sends the generated placement plan to the terminal of the person in charge via the notification system. Specifically, the placement plan is converted into a document and sent to the person in charge as notification content.

[0973] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[0974] Output: The placement plan is notified to the person in charge's terminal.

[0975] Step 6: Gather feedback

[0976] Input: Implementation results based on the placement plan, feedback from the person in charge

[0977] process:

[0978] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[0979] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[0980] Output: Feedback data

[0981] Step 7: Analyze feedback data and update the model

[0982] Input: Feedback data

[0983] process:

[0984] The server collects feedback data, stores it in an integrated database, and analyzes the collected feedback data to update the generative AI model.

[0985] Output: Updated generative AI model

[0986] In this way, optimal staffing of crews and stores can be achieved through each step, improving business performance and increasing crew motivation and well-being.

[0987] (Application example 2)

[0988] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0989] Conventional staffing systems only utilize characteristic data, location information, and evaluation data, and are unable to optimize staffing by taking into account the emotional state and motivation of crew members. This can lead to lower crew stress levels and motivation, which can hinder performance improvement and customer satisfaction. Furthermore, there is a lack of a mechanism to fully reflect feedback and improve the accuracy of next staffing proposals.

[0990] The identification process by the identification 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 means for acquiring crew characteristic data, means for acquiring store location information and evaluation data, and means for acquiring crew emotion data and storing this data in an integrated database. This makes it possible to generate more accurate and effective staffing plans based on the crew characteristic data and emotion data and the store characteristics, and notify the person in charge in real time.

[0991] The system further includes means for combining crew characteristic data, emotion data, store location information, and evaluation data and creating an index, which allows for rapid access and search of the data.

[0992] Furthermore, the system includes a means for transmitting the results of the staffing plan to the terminal of the person in charge in real time via the notification system, thereby enabling the person in charge to immediately check and adjust the staffing plan.

[0993] It includes a means to analyze the collected feedback data and update the generative AI model, which can then provide more accurate staffing recommendations in the next deployment proposal, improving crew motivation and well-being.

[0994] "Crew characteristic data" is information about individual characteristics of employees, such as communication skills, performance, and evaluations.

[0995] "Store location information and evaluation data" refers to information about the geographic location of a store and information about evaluation comments and evaluation scores from customers.

[0996] "Emotional data" is information about an employee's emotional state, such as stress level or motivation.

[0997] The "integrated database" is a database system that centrally stores characteristic data, emotion data, store location information, and evaluation data, enabling quick access and search of the data.

[0998] The "generative AI model" is an artificial intelligence model that analyzes and generates optimal staffing plans using crew characteristic data, emotional data, store location information, and evaluation data.

[0999] The "notification system" is a system that notifies personnel deployment plans generated by the generative AI model to the terminals of personnel in real time.

[1000] "Feedback data" refers to data regarding employee performance, satisfaction, emotional state, etc., based on the results of implementing staffing plans.

[1001] The "feedback collection means" is a function for collecting set feedback data and reflecting it in the integrated database and generative AI model.

[1002] This invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing proposals that also take emotion data into consideration. The system includes the following main components:

[1003] System Configuration

[1004] server

[1005] Data collection module: Collects crew characteristics data, emotion data, store location information and evaluation data.

[1006] Integrated database: Collected data is managed centrally, enabling quick search and access.

[1007] Generative AI model: Analyzes data and generates optimal staffing recommendations.

[1008] Notification system: Notifies the person in charge of the generated placement plan in real time.

[1009] Feedback collection module: Collects feedback data and updates the AI ​​model.

[1010] Terminal

[1011] User interface for personnel: An interface that displays the proposed staffing plan and allows personnel to review and adjust it.

[1012] Feedback input interface: An interface for inputting feedback on the implemented staffing plan.

[1013] User

[1014] Person in Charge: The person who manages and staffs the crew.

[1015] Program processing

[1016] Data collection

[1017] The server uses the Slack API to collect crew characteristic data. It also uses the e-Learning system API to obtain crew learning progress data and test results, and collects data from the evaluation system API. It uses the Google Maps API to collect store location information and evaluation comments. It uses an emotion engine (e.g., Affectiva) to collect employee emotion data.

[1018] Data Integration

[1019] The server stores the collected data in a MySQL integrated database: characteristic data in the "crew_data" table, store information in the "store_data" table, and emotion data in the "emotion_data" table.

[1020] Generate staffing plans

[1021] The server uses data from the integrated database to train a generative AI model, which references crew characteristics, emotional data, and store characteristics data to generate optimal staffing plans.

[1022] Suggestions and Notifications

[1023] The generated staffing plan is sent to the staff member's device in real time via the notification system, and the staff member's user interface displays the plan, allowing them to review and make any necessary adjustments.

[1024] Gathering feedback and updating the model

[1025] Feedback data is input by the staff through the feedback input interface, which is then sent to the server for analysis, which then updates the generative AI model and reflects it in the next staffing proposal.

[1026] Specific examples

[1027] Prompt Sentence Examples

[1028] Inputs to the generative AI model:

[1029] Crew characteristics: "Communication skills: 8 / 10, Performance: 9 / 10, Evaluation: Positive"

[1030] Emotional data: "Stress level: low, motivation: high"

[1031] Store data: "Store ID 456, Customer type: Family, Rating: 4.5 / 5"

[1032] User ID 123's characteristic data: {"Communication skills: 8 / 10","Performance: 9 / 10","Evaluation: Positive"}

[1033] Emotion data for user ID 123: {"Stress level: Low","Motivation: High"}

[1034] Store ID 456 store data: {"Customer demographic: Family","Rating: 4.5 / 5"}

[1035] Based on this data, generate optimal staffing plans.

[1036] Output of the generative AI model:

[1037] Placement plan: "Place user ID 123 at store ID 456"

[1038] Example notification:

[1039] "User ID 123 is a perfect fit for store ID 456. Reasons for placement: high communication skills, low stress level, family-friendly store characteristics."

[1040] This system will enable optimal staffing between crews and stores, improving performance and reducing man-hours. It will also improve staff motivation and well-being by providing staffing suggestions that take into account crew emotional data.

[1041] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1042] Step 1:

[1043] The server uses the Slack API to obtain 30 days' worth of crew characteristic data (comment history, reaction data). This data is combined with test results and learning progress data collected using the e-Learning system API, and evaluation data obtained from the evaluation system API. At this time, the crew characteristic data is input and characteristic data is collected.

[1044] Step 2:

[1045] The server uses the Google Maps API to obtain the store's location information and evaluation comments. At this time, the store's ID is used as input, and the obtained store's geographic coordinates and evaluation comments are output.

[1046] Step 3:

[1047] The server uses an emotion engine (e.g., Affectiva) to collect crew emotion data. The emotion data is obtained by analyzing interactions in communication tools and e-learning systems. The interaction data is used as input, and emotion data is obtained as output.

[1048] Step 4:

[1049] The server stores the collected crew characteristics data, store location information, evaluation data, and emotion data in an integrated database (MySQL). Each piece of data is stored in its own dedicated table (crew_data, store_data, emotion_data). Each piece of collected data is used as input, and is stored in the integrated database as output.

[1050] Step 5:

[1051] The server trains a generative AI model using data from the integrated database. To analyze the optimal match between crew and store, it generates prompt sentences and uses characteristic data, emotion data, and store data as inputs. This results in the output of optimal staffing recommendations.

[1052] Step 6:

[1053] The server sends the generated placement plan to the person in charge's device in real time via the notification system. The placement plan from the generative AI model is used as input, and the placement plan is notified to the person in charge's device as output.

[1054] Step 7:

[1055] The terminal uses a user interface for the staff member to display the proposed placement plan, which the staff member can review and adjust. The notified placement plan is used as input, and the reviewed and adjusted placement plan is obtained as output.

[1056] Step 8:

[1057] The user (person in charge) inputs feedback (performance, satisfaction, emotional state) for the implemented staffing plan through the feedback input interface. The feedback data is used as input and is sent to the server.

[1058] Step 9:

[1059] The server analyzes the collected feedback data and stores it in an integrated database. It also updates the generative AI model based on the feedback data. The feedback data is used as input, and the updated generative AI model is obtained as output.

[1060] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1061] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1062] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1063] [Third embodiment]

[1064] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1065] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1066] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1067] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1068] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1069] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1070] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1071] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1072] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1073] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1074] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1075] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1076] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[1077] System Configuration

[1078] The system includes the following main components:

[1079] 1. Server

[1080] Data Collection Module

[1081] Integrated Database

[1082] Generative AI Models

[1083] Notification System

[1084] Feedback Collection Module

[1085] 2. Terminal

[1086] Agent User Interface

[1087] Feedback Input Interface

[1088] 3. Users

[1089] Person in Charge (the person who manages and staffs the crew)

[1090] Program processing

[1091] Data collection

[1092] The server uses the API of the company's internal system to obtain crew characteristic data, including comment history and reaction data from communication tools (e.g., Slack), test results from the e-learning system, and superior evaluations from the evaluation system.

[1093] The server uses the Google Maps API to collect location information and evaluation comments for each store.

[1094] Data Integration

[1095] The server stores the collected data in an integrated database. Crew characteristics data is stored in the "crew_data" table, and store evaluation data is stored in the "store_data" table.

[1096] The server combines crew and store data and creates an index to enable quick access and searching.

[1097] analysis

[1098] The server uses data from the integrated database to train a generative AI model and analyze the optimal match between crew and store.

[1099] The generative AI model compares the crew's communication skills and performance with the store's customer demographics and characteristics to find optimal staffing plans.

[1100] suggestion

[1101] The server transmits the generated placement plan to the terminal of the person in charge via the notification system.

[1102] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1103] Feedback collection

[1104] The user (person in charge) will then carry out the actual personnel allocation based on the proposed allocation plan and provide feedback on the results to the system.

[1105] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1106] The server analyzes the collected feedback data and uses it to update the generative AI model, thereby improving the accuracy of future placement suggestions.

[1107] Specific examples

[1108] Data collection

[1109] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" via the Slack API.

[1110] The server uses the Google Maps API to collect the location information and most recent customer evaluation comments for "Store ID 456."

[1111] Data Integration

[1112] The server inserts the retrieved data into the MySQL integrated database. The "crew_data" table stores the comment history and reaction data of "user ID 123," and the "store_data" table stores the evaluation comments of "store ID 456."

[1113] Analysis and Recommendations

[1114] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Based on this analysis result, it proposes placing "User ID 123" in "Store ID 456."

[1115] The server transmits the generated placement plan to the person in charge through a notification system, and displays the notification on the person in charge's terminal.

[1116] Feedback and Updates

[1117] After the user performs the placement based on the proposal, the user inputs the placement results and feedback into the system.

[1118] The server collects the feedback data and updates the generative AI model for the next placement proposal.

[1119] The above is an embodiment of the present invention. This processing flow realizes optimal staffing between crews and stores, thereby improving business performance and reducing man-hours.

[1120] The processing flow will be explained below.

[1121] Step 1:

[1122] The server uses the API of the internal system to obtain crew characteristic data. It calls the Slack API to collect comment history and reaction data from the past 30 days. It then queries the e-learning system API to obtain each crew member's test results and progress. It also obtains past evaluation data and feedback from superiors through the evaluation system API.

[1123] Step 2:

[1124] The server uses the Google Maps API to collect location information and customer reviews for each store. Specifically, it obtains geographic coordinates based on a specific store ID, and also collects the most recent customer reviews and comments.

[1125] Step 3:

[1126] The server stores the collected crew characteristic data, store location information, and evaluation data in an integrated database. Crew characteristic data is organized in the "crew_data" table and saved using the crew ID as a key. Store evaluation data is inserted into the "store_data" table and saved using the store ID as a key.

[1127] Step 4:

[1128] The server combines the crew and store data and creates an index for quick access and searching. Specifically, it uses an SQL query to join both data sets and generate new index fields.

[1129] Step 5:

[1130] The server trains a generative AI model using data from the integrated database. The model compares crew characteristics (communication skills, performance, ratings) with store characteristics (customer demographics, ratings, event status) to find the best match. Past deployment data and feedback are also used to train the model.

[1131] Step 6:

[1132] The server generates the staffing plan and notifies the person in charge. Specifically, the server converts the generated staffing plan into a document and sends it to the person in charge's terminal through the notification system. The notification includes details of the staffing plan, the reasons for the plan, and the expected results.

[1133] Step 7:

[1134] The user confirms the notified personnel deployment plan, checks the proposal through the user interface for the person in charge, and makes adjustments as necessary. The user then deploys the crew based on the confirmed deployment plan.

[1135] Step 8:

[1136] Users provide feedback to the system after deployment by entering the deployed crew's performance, satisfaction, and feedback comments through a feedback input interface, including specific achievements and problems after deployment.

[1137] Step 9:

[1138] The server collects the collected feedback data and stores it in an integrated database. It then analyzes the feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[1139] Step 10:

[1140] The server uses the updated generative AI model to further optimize the next staffing plan, thereby continuously achieving optimal staffing, improving performance and reducing labor costs.

[1141] Example 1

[1142] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1143] In the conventional system, matching employees with facilities was not possible while taking into full consideration the characteristics of the employees and the facilities, making it difficult to achieve appropriate placement. In addition, there was a lack of a mechanism for efficiently collecting feedback on placement results and reflecting it in the next placement, making continuous improvement difficult.

[1144] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1145] In this invention, the server includes means for acquiring employee characteristic data, means for acquiring facility location information and evaluation data, means for storing the acquired employee characteristic data, facility location information, and evaluation data in an integrated database, means for generating a generative AI model that analyzes an optimal match between employees and facilities using data from the integrated database, means for generating an optimal staffing plan based on the analysis results, means for notifying a person in charge of the staffing plan based on the employee characteristics and the facility characteristics, means for collecting feedback data on the staffing plan, means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal, means for acquiring facility evaluation data from customers, means for acquiring employee characteristic data from communication tools and an education system, and means for receiving feedback data from a terminal. This enables optimal staffing between employees and facilities, improving business efficiency and enabling continuous improvement in staffing.

[1146] "Employee" refers to a person employed by a company or organization to perform work.

[1147] "Characteristic data" refers to data that represents an employee's individual characteristics, such as their communication skills or performance.

[1148] "Facility" means a place of business where employees are located, including stores, factories, offices, etc.

[1149] "Location information" refers to data indicating a geographical location, and includes information such as latitude and longitude.

[1150] "Evaluation Data" refers to data representing evaluations and feedback on facilities and employees.

[1151] An "integrated database" refers to a database that centrally manages and stores information collected from multiple data sources.

[1152] A "generative AI model" is a model that uses machine learning and artificial intelligence to learn data patterns and make predictions and suggestions.

[1153] "Matching" refers to the process of analyzing the compatibility between employee characteristics and facility characteristics to find the optimal combination.

[1154] "Notification system" refers to a system that sends information or data to specific devices or personnel.

[1155] "Feedback data" refers to data that shows evaluations of staffing results and areas for improvement.

[1156] "Communication tools" refers to software and platforms used to communicate between employees and within an organization.

[1157] An "educational system" refers to a system that provides teaching materials and tests aimed at improving employees' skills and acquiring knowledge.

[1158] "Device" refers to a computer or mobile device used by a user or agent.

[1159] The present invention relates to a system for collecting, integrating, and analyzing employee characteristic data and facility evaluation data to achieve optimal staffing. Specific embodiments for carrying out the present invention will be described below.

[1160] System Configuration

[1161] The system includes the following main components:

[1162] 1. Server

[1163] Data Collection Module

[1164] Integrated Database

[1165] Generative AI Models

[1166] Notification System

[1167] Feedback Collection Module

[1168] 2. Terminal

[1169] Agent User Interface

[1170] Feedback Input Interface

[1171] 3. Users

[1172] Person in charge (the person who manages and staffs employees)

[1173] Data collection

[1174] The server uses the API of a communication tool (e.g., a chat system) to obtain employee characteristic data. Specifically, it collects 30 days of comment history and reaction data, test results from the education system, and supervisor evaluations from the evaluation system. The server also uses a geographic information API to collect facility location information and customer evaluation comments.

[1175] For example, the server performs the following operations:

[1176] Access the API endpoint https: / / api.chat-system.com / history?user=123 to retrieve the comment history and reaction data for "user ID 123."

[1177] Access the API endpoint https: / / api.geo-service.com / place / details?place_id=456 and collect location information and customer evaluation comments for "facility ID 456."

[1178] Data Integration

[1179] The collected data is stored in a MySQL integrated database by the server. Employee comment history and reaction data are stored in the "employee_data" table, and facility evaluation comments are stored in the "facility_data" table. The server also combines crew and facility data and generates indexes to enable quick access.

[1180] example:

[1181] sql

[1182] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[1183] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[1184] Data analysis

[1185] The server trains a generative AI model using data from the integrated database, which then analyzes the optimal match between employees and facilities. The generative AI model uses machine learning algorithms (e.g., TensorFlow and PyTorch) to analyze employee communication skills and performance, as well as the customer demographics and characteristics of facilities, to find optimal staffing plans.

[1186] suggestion

[1187] The server sends the generated staffing plan to the staff member's device via a notification system. The device (the staff member's user interface) displays the proposed staffing plan, which the staff member can review and adjust. As a specific example of the operation here, the staff member could input the following prompts to the AI:

[1188] Please propose the optimal staffing plan based on the communication skill data of "User ID 123" over the past 30 days and the evaluation comments of "Facility ID 456."

[1189] Feedback collection

[1190] The user (person in charge) performs actual staffing based on the proposed staffing plan and inputs the results as feedback to the system. The terminal (feedback input interface) inputs the feedback data from the person in charge and sends it to the server. The server analyzes the collected feedback data and updates the generative AI model. This improves the accuracy of future staffing proposals.

[1191] The above is a specific embodiment for carrying out the present invention. This processing flow realizes optimal staffing between employees and facilities, and enables improved work efficiency and continuous improvement of staffing.

[1192] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1193] Step 1: Data collection

[1194] The server sends requests to the APIs of communication tools and education systems to obtain employee characteristic data. Specifically, it collects data based on the following inputs:

[1195] (Input): API endpoint and query parameters (e.g. https: / / api.chat-system.com / history?user=123)

[1196] The server parses the JSON data returned from the API and extracts comment history and reaction data.

[1197] (Output): A JSON object containing the comment history and reaction data.

[1198] Specific behavior:

[1199] The server accesses the Slack API endpoint https: / / api.chat-system.com / history?user=123 and retrieves the message history and reaction data for the past 30 days for "user ID 123."

[1200] The server analyzes the JSON data obtained from the API and extracts the specific content of the comments and the type of each reaction.

[1201] Step 2: Data integration

[1202] The server generates SQL queries to store the collected data in a MySQL integrated database.

[1203] (Input): Speech history and reaction data, facility evaluation data

[1204] The server uses SQL queries to insert data into the database, which saves each piece of data in its corresponding table.

[1205] (Output): Employee characteristics data and facility evaluation data stored in a database

[1206] Specific behavior:

[1207] The server executes the following SQL query to insert the comment history and reaction data into the "employee_data" table:

[1208] sql

[1209] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[1210] Similarly, facility evaluation comments are stored in the "facility_data" table.

[1211] sql

[1212] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[1213] Step 3: Data Joining and Indexing

[1214] The server combines the employee characteristic data with the facility evaluation data and generates an index to enable rapid access and retrieval.

[1215] (Input): Employee characteristics data and facility evaluation data in the database

[1216] The server combines the data using SQL JOIN operations and generates the index.

[1217] (Output): The combined data and the generated index.

[1218] Specific behavior:

[1219] The server uses the following SQL query to join the data and generate the index:

[1220] sql

[1221] CREATE INDEX idx_user_store ON combined_data (user_id, store_id);

[1222] Step 4: Training the generative AI model

[1223] The server inputs data from the integrated database into the generative AI model and trains the model.

[1224] (Input): Combined employee and facility data in the database

[1225] The server uses machine learning algorithms to train the model and analyze the best matches.

[1226] (Output): Trained generative AI model and analysis results

[1227] Specific behavior:

[1228] The server runs Python programs and uses libraries such as TensorFlow or PyTorch to train generative AI models.

[1229] Training data includes employee communication skills and performance, as well as the customer demographics and characteristics of the facility.

[1230] Step 5: Generate and notify placement proposals

[1231] The server generates optimal staffing plans based on the analysis results obtained from the generative AI model.

[1232] (Input): Trained generative AI model and employee and facility data

[1233] The server sends the placement plan generated from the analysis results to the person in charge via a notification system.

[1234] (Output): Staffing plan sent to the person in charge's terminal

[1235] Specific behavior:

[1236] The server creates an optimal personnel allocation plan based on the analysis results.

[1237] The server transmits the placement plan to the terminal of the person in charge and displays it on the user interface for the person in charge.

[1238] Step 6: Gather feedback

[1239] The user performs actual staffing based on the proposed staffing plan and inputs the results into the system as feedback.

[1240] (Input): Results and feedback comments from the person in charge

[1241] The terminal collects feedback data through a feedback input interface and sends it to the server.

[1242] (Output): Feedback data sent to the server

[1243] Specific behavior:

[1244] The user assigns employees according to the assignment plan and inputs the results and feedback into the terminal.

[1245] The terminal transmits the collected feedback data to the server.

[1246] Step 7: Update the generative AI model

[1247] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future placement suggestions.

[1248] (Input): Feedback data and existing generative AI models

[1249] The server uses the feedback data to retrain and update the generative AI model.

[1250] (Output): Updated generative AI model

[1251] Specific behavior:

[1252] The server analyzes the collected feedback data and extracts the information needed to improve the accuracy of the model.

[1253] The server retrains the generative AI model and reflects it in the next placement proposal.

[1254] This is the specific flow of the program processing of this system. This procedure is expected to achieve optimal matching between employees and facilities and improve work efficiency.

[1255] (Application example 1)

[1256] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1257] Conventional factory robot allocation systems have the problem of being unable to achieve efficient work allocation because it is difficult to optimally match each robot based on its characteristics and task requirements. Furthermore, there is a lack of flexible system design that reflects feedback after task allocation. As a result, there are issues such as reduced productivity and insufficient robot operational efficiency.

[1258] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1259] In this invention, the server includes a means for acquiring personnel characteristic data, a means for acquiring work base location information and evaluation data, and a means for storing the acquired personnel characteristic data, work base location information, and evaluation data in an integrated database, thereby realizing a generative AI model that analyzes optimal matching between personnel and work bases.

[1260] "Personnel characteristic data" is data that indicates the specific attributes and capabilities of each personnel, such as the speed, accuracy, and power consumption of that personnel.

[1261] "Location information of work base" refers to the geographic coordinates of the location where work is performed and detailed information about that location.

[1262] "Evaluation data" refers to data that indicates evaluations and feedback on work sites and personnel.

[1263] An "integrated database" is a database that centrally manages and stores a wide variety of data and enables efficient access.

[1264] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data on personnel and work locations and generate optimal matching and placement plans.

[1265] A "notification system" is a mechanism for quickly and reliably notifying administrators and personnel of information generated by the system.

[1266] "Feedback data" refers to data that indicates actual results and evaluations based on the placement proposal, and is collected to be reflected in the next proposal.

[1267] An "index" is something like a table of contents created for data in a database to speed up data searches.

[1268] A "robotic arm" is a mechanical arm-like device used to perform tasks in a factory.

[1269] "Task requirement information" is information that indicates the conditions and requirements necessary for the performance of a specific work or task.

[1270] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[1271] System Configuration

[1272] The system includes the following main components:

[1273] 1. Server

[1274] Data Collection Module

[1275] Integrated Database

[1276] Generative AI Models

[1277] Notification System

[1278] Feedback Collection Module

[1279] 2. Terminal

[1280] Administrator User Interface

[1281] Feedback Input Interface

[1282] 3. Users

[1283] Manager (person who manages the placement of robots within the factory)

[1284] Program processing

[1285] The server collects, analyzes, proposes, and updates data in the following steps:

[1286] Technology used

[1287] 1. Hardware:

[1288] Robotic arms (e.g., typical factory robotic arms)

[1289] Sensors (e.g. Lidar, cameras)

[1290] Server (e.g. AWS EC2)

[1291] 2. Software:

[1292] Data collection module (Python, Slack API, factory integrated management system API, etc.)

[1293] Integrated database (MySQL)

[1294] Generative AI models (e.g., TensorFlow, PyTorch)

[1295] Notification systems (e.g. Firebase)

[1296] Feedback collection module (e.g. Flask)

[1297] Data collection

[1298] The server obtains characteristic data for each robot (such as operating speed, accuracy, and power consumption) from the factory's integrated management system. It also collects task status information within the factory from sensors. For example, it obtains characteristic data such as operating speed, accuracy, and power consumption for "robot ID 123," and collects location information and required operating accuracy for "task ID 456."

[1299] Data Integration

[1300] The collected data is stored in the server's integrated MySQL database, where personnel characteristics data is stored in the "robot_data" table and task request data is stored in the "task_data" table.

[1301] analysis

[1302] The server uses data from the integrated database to train the generative AI model and analyzes the characteristics and task requirements of each robot. Based on the results of this analysis, it proposes optimal robot task assignments. For example, the generative AI model can input the characteristics data of "Robot ID 123" and the requirements of "Task ID 456," and determine that "Robot ID 123" is optimal for "Task ID 456."

[1303] suggestion

[1304] The server sends the generated task allocation plan to the administrator's terminal via the notification system. The administrator's user interface displays the proposed placement plan, which the administrator can review and adjust. For example, the generated placement plan is notified to the administrator's terminal, and the administrator performs the placement based on the proposal.

[1305] Feedback collection

[1306] The administrator performs placement based on the proposed placement plan and provides feedback to the system on the results. The server collects the feedback data and updates the generative AI model to reflect it in the next placement proposal.

[1307] Specific examples

[1308] Examples of prompt sentences include:

[1309] The characteristic data (operation speed, accuracy, power consumption) for "Robot ID 123" are as follows. Based on this, make the optimal allocation to meet the requirements (position information, operation accuracy) of "Task ID 456".

[1310] This is expected to improve the efficiency of robot placement within factories and increase productivity.

[1311] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1312] Step 1:

[1313] The server obtains the characteristic data of each robot through the factory integrated management system API. This includes the robot's operating speed, accuracy, power consumption, etc. Based on this input data, the characteristic data is collected and saved. Specifically, the server sends an API request and stores the obtained data in the "robot_data" table of the integrated database.

[1314] Step 2:

[1315] The server collects task status information from sensors in the factory. The acquired input data includes the task's location information and the required operating accuracy. Based on this data, detailed task information is saved in the "task_data" table. Specifically, it acquires real-time data from the sensors, organizes it, and inserts it into the database.

[1316] Step 3:

[1317] The server integrates the robot characteristic data and task request data stored in the integrated database and structures the data. Here, it creates indexes to speed up data searches. It uses data from the "robot_data" table and the "task_data" table as input and outputs indexed integrated data. Specific operations include data merging using SQL queries and creating indexes.

[1318] Step 4:

[1319] The server trains the generative AI model using data from the integrated database. The input is the integrated robot and task data, and it analyzes the optimal match based on this. The output is the optimal robot task assignment proposal as a result of the analysis. The specific operation is the training process of the generative AI model using TensorFlow and PyTorch.

[1320] Step 5:

[1321] The server sends the task allocation plan analyzed by the generative AI model to the administrator's device via the notification system. The input is the generated placement plan, and the output is displayed on the administrator's device as a notification. The specific operation is to send a push notification using Firebase.

[1322] Step 6:

[1323] The administrator executes the actual deployment based on the proposed deployment plan. The input is the deployment plan notified by the server, and the output is the actual deployment result. The specific operation is to confirm the deployment plan through the user interface and actually deploy the robot.

[1324] Step 7:

[1325] The administrator inputs feedback based on the deployment results into the feedback input interface. The input data is the deployment execution result and its evaluation. The output is sent to the server as feedback data. The specific operation is that the administrator submits the evaluation using the feedback form.

[1326] Step 8:

[1327] The server analyzes the collected feedback data and updates the generative AI model. The input data is the feedback data, which is used to improve the model's accuracy. The output is an updated AI model. Specifically, it adjusts the model's hyperparameters based on the previous feedback and retrains the model on a new dataset.

[1328] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1329] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[1330] System Configuration

[1331] The system includes the following main components:

[1332] 1. Server

[1333] Data Collection Module

[1334] Emotion Engine

[1335] Integrated Database

[1336] Generative AI Models

[1337] Notification System

[1338] Feedback Collection Module

[1339] 2. Terminal

[1340] Agent User Interface

[1341] Feedback Input Interface

[1342] 3. Users

[1343] Person in Charge (the person who manages and staffs the crew)

[1344] Program processing

[1345] Data collection

[1346] The server uses the API of the internal system to collect crew characteristic data. It calls the Slack API to obtain the past 30 days of comment history and reaction data. It then uses the e-Learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[1347] The server uses the Google Maps API to collect location information and review comments for each store, which includes geographic coordinates and review comments based on a specific store ID.

[1348] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[1349] Data Integration

[1350] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[1351] The server combines this data and creates an index to allow for quick access and searching.

[1352] analysis

[1353] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. Emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[1354] suggestion

[1355] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[1356] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1357] Feedback collection

[1358] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[1359] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1360] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[1361] Specific examples

[1362] Data collection

[1363] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" through the Slack API. It also retrieves the test results for "User ID 123" using the e-Learning system API and collects the supervisor's evaluation data through the evaluation system API.

[1364] The server uses the Google Maps API to collect location information and customer evaluation comments for "Store ID 456."

[1365] The server uses the emotion engine to analyze the recent emotional state of "user ID 123" and obtains emotional data.

[1366] Data Integration

[1367] The server stores the acquired data in a MySQL integrated database. The crew characteristics data is stored in the "crew_data" table, the store evaluation data is stored in the "store_data" table, and the emotion data is stored in a separate table.

[1368] Analysis and Recommendations

[1369] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account to adjust the crew's stress levels and motivation.

[1370] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[1371] Feedback and Updates

[1372] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[1373] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[1374] The above is an embodiment of the present invention. This system realizes optimal staffing between crews and stores, improving business performance and reducing man-hours. Furthermore, staffing plans that take crew emotional data into account also improve staff motivation and well-being.

[1375] The processing flow will be explained below.

[1376] Step 1:

[1377] The server uses the API of the internal system to obtain crew characteristic data. To do this, it calls the Slack API to collect comment history and reaction data for the past 30 days. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and obtains evaluation data from superiors through the evaluation system API.

[1378] Step 2:

[1379] The server uses the Google Maps API to collect location information and reviews for each store. It obtains geographic coordinates, reviews, and reviews from a specific store ID.

[1380] Step 3:

[1381] The server uses an emotion engine to acquire crew emotional data, specifically analyzing comments and responses from Slack and interaction data from the e-learning system, to estimate the crew's emotional state (e.g., stress level and motivation).

[1382] Step 4:

[1383] The server stores the collected crew characteristic data, store evaluation data, and emotion data in an integrated database. Crew characteristic data is stored in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[1384] Step 5:

[1385] The server then combines these data and creates indexes to enable fast access and searching, specifically by joining each data table using an SQL query to generate new index fields.

[1386] Step 6:

[1387] The server uses data from the integrated database to train a generative AI model, taking into account crew characteristics (e.g., communication skills, performance, and ratings) and store characteristics (e.g., customer demographics, ratings, and event status) as well as emotional data to analyze optimal matches.

[1388] Step 7:

[1389] The server generates optimal staffing plans based on the analysis results. The plans are based on crew characteristics, store characteristics, and crew emotion data. The plans include which stores each crew member should be assigned to, the reasons for doing so, and the expected results.

[1390] Step 8:

[1391] The server sends the generated staffing plan to the person in charge through a notification system, and a notification is sent to the person in charge's terminal, providing details of the specific staffing plan.

[1392] Step 9:

[1393] The user (person in charge) uses the terminal to check the notified personnel allocation plan. The user checks the details of the proposal and makes adjustments as necessary. The actual allocation is carried out based on the confirmed allocation plan.

[1394] Step 10:

[1395] The user provides feedback to the system after the deployment, including the performance, satisfaction, and feedback comments of the deployed crew. Emotional data is also evaluated and provided as feedback.

[1396] Step 11:

[1397] The server stores the collected feedback data in an integrated database, including changes in emotional data, and reflects this in the next proposal.

[1398] Step 12:

[1399] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future staffing recommendations.

[1400] Step 13:

[1401] The server uses the updated generative AI model to optimize the next staffing plan, thereby achieving continuous optimal staffing, improving performance and reducing labor costs.

[1402] Example 2

[1403] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1404] Conventional systems optimize staffing based on crew characteristics, store location information, and evaluation data, but do not generate staffing plans that take crew emotional data into account. This can result in crew stress levels and motivation levels being ignored, often resulting in less-than-optimal staffing. A new staffing system is needed that can improve crew well-being while maximizing performance.

[1405] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring crew characteristic data; means for acquiring store location information and evaluation data; means for collecting and analyzing emotion data; means for storing the acquired crew characteristic data, store location information, evaluation data, and emotion data in an integrated database; a generative AI model means for analyzing the optimal match between crew and store using data from the integrated database; means for creating an index to enable rapid data search; means for generating an optimal staffing plan based on the analysis results; means for notifying a person in charge of the staffing plan based on the crew characteristics and store characteristics; means for transmitting the staffing plan to the person in charge's terminal via a notification system; means for collecting feedback data on the staffing plan; and means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal. This enables optimal staffing that takes crew characteristics and emotions into consideration, thereby improving business performance and enhancing crew motivation and well-being.

[1406] "Crew characteristic data" refers to profile information such as each crew member's communication skills, achievements, and evaluations.

[1407] "Store Location Information" refers to the geographic coordinates (latitude and longitude) of each store.

[1408] "Rating Data" refers to customer feedback, reviews, and rating scores for a store.

[1409] "Emotional data" is data that indicates the emotional state of the crew and is analyzed from interactions with communication tools and educational systems.

[1410] The "integrated database" refers to a database that centrally stores and manages crew characteristics data, store location information, evaluation data, and emotional data.

[1411] "Generative AI model" refers to an artificial intelligence model that uses crew and store data to analyze optimal matches and generate staffing plans.

[1412] An "index" refers to a search key created to enable rapid retrieval of data.

[1413] "Notification system" refers to a system for notifying personnel in charge of the generated staffing plan.

[1414] "Feedback data" refers to data such as crew performance, satisfaction, and feedback comments regarding implemented staffing plans.

[1415] MODE FOR CARRYING OUT THE INVENTION

[1416] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data, store location information, and evaluation data to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[1417] System Configuration

[1418] The system includes the following main components:

[1419] 1. Server

[1420] Data Collection Module

[1421] Emotion Engine

[1422] Integrated Database

[1423] Generative AI Models

[1424] Notification System

[1425] Feedback Collection Module

[1426] 2. Terminal

[1427] Agent User Interface

[1428] Feedback Input Interface

[1429] 3. Users

[1430] Person in Charge (the person who manages and staffs the crew)

[1431] Data collection

[1432] The server uses the API of the internal system to collect crew characteristic data. For example, it calls the Slack API to obtain the past 30 days' worth of comment history and reaction data. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[1433] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[1434] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[1435] Data Integration

[1436] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[1437] The server creates an index of this data to allow for quick access and retrieval.

[1438] analysis

[1439] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. The emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[1440] suggestion

[1441] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[1442] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1443] Feedback collection

[1444] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[1445] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1446] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[1447] Specific examples

[1448] Data collection

[1449] The server retrieves the posting history and reaction data for the past 30 days for "Crew ID 123" through the Slack API, retrieves the test results for "Crew ID 123" using the e-learning system API, and collects the evaluation data of superiors through the evaluation system API.

[1450] The server uses the geographic information service API to collect location information and customer evaluation comments for "Store ID 456."

[1451] The server uses the emotion engine to analyze the recent emotional state of "Crew ID 123" and obtains emotional data.

[1452] Data Integration

[1453] The server stores the acquired data in an integrated database. Crew characteristics data is stored in the "crew_data" table, store evaluation data is stored in the "store_data" table, and emotion data is stored in a separate table.

[1454] Analysis and Recommendations

[1455] The server inputs this data into the generative AI model and analyzes that "Crew ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account, and the server adjusts the crew's stress level and motivation.

[1456] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[1457] Feedback and Updates

[1458] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[1459] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[1460] These steps will enable optimal staffing between crews and stores, improving performance and increasing crew motivation and well-being.

[1461] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1462] System program processing flow

[1463] Step 1: Data collection

[1464] Input: API of internal systems, data from communication tools

[1465] process:

[1466] The server uses the API of the company's internal system to collect crew characteristic data. Specifically, it calls the Slack API to obtain the comment history and reaction data for the past 30 days.

[1467] The server uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[1468] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[1469] The server uses an emotion engine to acquire crew emotional data, including data obtained by analyzing emotional states from interactions with communication tools and e-learning systems.

[1470] Output: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[1471] Step 2: Data integration

[1472] Input: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[1473] process:

[1474] The server stores the collected data in an integrated database: crew characteristics data in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[1475] The server indexes this data to allow for quick access and retrieval.

[1476] Output: Integrated database

[1477] Step 3: Analysis

[1478] Input: Integrated database

[1479] process:

[1480] The server uses data from the integrated database to train a generative AI model, which analyzes the optimal match by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data.

[1481] Output: A trained generative AI model

[1482] Step 4: Generate placement proposals

[1483] Input: A trained generative AI model

[1484] process:

[1485] The server generates optimal staffing plans based on the analysis results, which include the reasons for the staffing and the expected results.

[1486] Output: Staffing plan

[1487] Step 5: Notification of proposed placement

[1488] Input: Staffing plan

[1489] process:

[1490] The server sends the generated placement plan to the terminal of the person in charge via the notification system. Specifically, the placement plan is converted into a document and sent to the person in charge as notification content.

[1491] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1492] Output: The placement plan is notified to the person in charge's terminal.

[1493] Step 6: Gather feedback

[1494] Input: Implementation results based on the placement plan, feedback from the person in charge

[1495] process:

[1496] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[1497] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1498] Output: Feedback data

[1499] Step 7: Analyze feedback data and update the model

[1500] Input: Feedback data

[1501] process:

[1502] The server collects feedback data, stores it in an integrated database, and analyzes the collected feedback data to update the generative AI model.

[1503] Output: Updated generative AI model

[1504] In this way, optimal staffing of crews and stores can be achieved through each step, improving business performance and increasing crew motivation and well-being.

[1505] (Application example 2)

[1506] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1507] Conventional staffing systems only utilize characteristic data, location information, and evaluation data, and are unable to optimize staffing by taking into account the emotional state and motivation of crew members. This can lead to lower crew stress levels and motivation, which can hinder performance improvement and customer satisfaction. Furthermore, there is a lack of a mechanism to fully reflect feedback and improve the accuracy of next staffing proposals.

[1508] The identification process by the identification 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 means for acquiring crew characteristic data, means for acquiring store location information and evaluation data, and means for acquiring crew emotion data and storing this data in an integrated database. This makes it possible to generate more accurate and effective staffing plans based on the crew characteristic data and emotion data and the store characteristics, and notify the person in charge in real time.

[1509] The system further includes means for combining crew characteristic data, emotion data, store location information, and evaluation data and creating an index, which allows for rapid access and search of the data.

[1510] Furthermore, the system includes a means for transmitting the results of the staffing plan to the terminal of the person in charge in real time via the notification system, thereby enabling the person in charge to immediately check and adjust the staffing plan.

[1511] It includes a means to analyze the collected feedback data and update the generative AI model, which can then provide more accurate staffing recommendations in the next deployment proposal, improving crew motivation and well-being.

[1512] "Crew characteristic data" is information about individual characteristics of employees, such as communication skills, performance, and evaluations.

[1513] "Store location information and evaluation data" refers to information about the geographic location of a store and information about evaluation comments and evaluation scores from customers.

[1514] "Emotional data" is information about an employee's emotional state, such as stress level or motivation.

[1515] The "integrated database" is a database system that centrally stores characteristic data, emotion data, store location information, and evaluation data, enabling quick access and search of the data.

[1516] The "generative AI model" is an artificial intelligence model that analyzes and generates optimal staffing plans using crew characteristic data, emotional data, store location information, and evaluation data.

[1517] The "notification system" is a system that notifies personnel deployment plans generated by the generative AI model to the terminals of personnel in real time.

[1518] "Feedback data" refers to data regarding employee performance, satisfaction, emotional state, etc., based on the results of implementing staffing plans.

[1519] The "feedback collection means" is a function for collecting set feedback data and reflecting it in the integrated database and generative AI model.

[1520] This invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing proposals that also take emotion data into consideration. The system includes the following main components:

[1521] System Configuration

[1522] server

[1523] Data collection module: Collects crew characteristics data, emotion data, store location information and evaluation data.

[1524] Integrated database: Collected data is managed centrally, enabling quick search and access.

[1525] Generative AI model: Analyzes data and generates optimal staffing recommendations.

[1526] Notification system: Notifies the person in charge of the generated placement plan in real time.

[1527] Feedback collection module: Collects feedback data and updates the AI ​​model.

[1528] Terminal

[1529] User interface for personnel: An interface that displays the proposed staffing plan and allows personnel to review and adjust it.

[1530] Feedback input interface: An interface for inputting feedback on the implemented staffing plan.

[1531] User

[1532] Person in Charge: The person who manages and staffs the crew.

[1533] Program processing

[1534] Data collection

[1535] The server uses the Slack API to collect crew characteristic data. It also uses the e-Learning system API to obtain crew learning progress data and test results, and collects data from the evaluation system API. It uses the Google Maps API to collect store location information and evaluation comments. It uses an emotion engine (e.g., Affectiva) to collect employee emotion data.

[1536] Data Integration

[1537] The server stores the collected data in a MySQL integrated database: characteristic data in the "crew_data" table, store information in the "store_data" table, and emotion data in the "emotion_data" table.

[1538] Generate staffing plans

[1539] The server uses data from the integrated database to train a generative AI model, which references crew characteristics, emotional data, and store characteristics data to generate optimal staffing plans.

[1540] Suggestions and Notifications

[1541] The generated staffing plan is sent to the staff member's device in real time via the notification system, and the staff member's user interface displays the plan, allowing them to review and make any necessary adjustments.

[1542] Gathering feedback and updating the model

[1543] Feedback data is input by the staff through the feedback input interface, which is then sent to the server for analysis, which then updates the generative AI model and reflects it in the next staffing proposal.

[1544] Specific examples

[1545] Prompt Sentence Examples

[1546] Inputs to the generative AI model:

[1547] Crew characteristics: "Communication skills: 8 / 10, Performance: 9 / 10, Evaluation: Positive"

[1548] Emotional data: "Stress level: low, motivation: high"

[1549] Store data: "Store ID 456, Customer type: Family, Rating: 4.5 / 5"

[1550] User ID 123's characteristic data: {"Communication skills: 8 / 10","Performance: 9 / 10","Evaluation: Positive"}

[1551] Emotion data for user ID 123: {"Stress level: Low","Motivation: High"}

[1552] Store ID 456 store data: {"Customer demographic: Family","Rating: 4.5 / 5"}

[1553] Based on this data, generate optimal staffing plans.

[1554] Output of the generative AI model:

[1555] Placement plan: "Place user ID 123 at store ID 456"

[1556] Example notification:

[1557] "User ID 123 is a perfect fit for store ID 456. Reasons for placement: high communication skills, low stress level, family-friendly store characteristics."

[1558] This system will enable optimal staffing between crews and stores, improving performance and reducing man-hours. It will also improve staff motivation and well-being by providing staffing suggestions that take into account crew emotional data.

[1559] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1560] Step 1:

[1561] The server uses the Slack API to obtain 30 days' worth of crew characteristic data (comment history, reaction data). This data is combined with test results and learning progress data collected using the e-Learning system API, and evaluation data obtained from the evaluation system API. At this time, the crew characteristic data is input and characteristic data is collected.

[1562] Step 2:

[1563] The server uses the Google Maps API to obtain the store's location information and evaluation comments. At this time, the store's ID is used as input, and the obtained store's geographic coordinates and evaluation comments are output.

[1564] Step 3:

[1565] The server uses an emotion engine (e.g., Affectiva) to collect crew emotion data. The emotion data is obtained by analyzing interactions in communication tools and e-learning systems. The interaction data is used as input, and emotion data is obtained as output.

[1566] Step 4:

[1567] The server stores the collected crew characteristics data, store location information, evaluation data, and emotion data in an integrated database (MySQL). Each piece of data is stored in its own dedicated table (crew_data, store_data, emotion_data). Each piece of collected data is used as input, and is stored in the integrated database as output.

[1568] Step 5:

[1569] The server trains a generative AI model using data from the integrated database. To analyze the optimal match between crew and store, it generates prompt sentences and uses characteristic data, emotion data, and store data as inputs. This results in the output of optimal staffing recommendations.

[1570] Step 6:

[1571] The server sends the generated placement plan to the person in charge's device in real time via the notification system. The placement plan from the generative AI model is used as input, and the placement plan is notified to the person in charge's device as output.

[1572] Step 7:

[1573] The terminal uses a user interface for the staff member to display the proposed placement plan, which the staff member can review and adjust. The notified placement plan is used as input, and the reviewed and adjusted placement plan is obtained as output.

[1574] Step 8:

[1575] The user (person in charge) inputs feedback (performance, satisfaction, emotional state) for the implemented staffing plan through the feedback input interface. The feedback data is used as input and is sent to the server.

[1576] Step 9:

[1577] The server analyzes the collected feedback data and stores it in an integrated database. It also updates the generative AI model based on the feedback data. The feedback data is used as input, and the updated generative AI model is obtained as output.

[1578] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1579] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1580] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1581] [Fourth embodiment]

[1582] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1583] 7, a 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.

[1584] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1585] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1586] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1587] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1588] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1589] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1590] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1591] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1592] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1593] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1594] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1595] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[1596] System Configuration

[1597] The system includes the following main components:

[1598] 1. Server

[1599] Data Collection Module

[1600] Integrated Database

[1601] Generative AI Models

[1602] Notification System

[1603] Feedback Collection Module

[1604] 2. Terminal

[1605] Agent User Interface

[1606] Feedback Input Interface

[1607] 3. Users

[1608] Person in Charge (the person who manages and staffs the crew)

[1609] Program processing

[1610] Data collection

[1611] The server uses the API of the company's internal system to obtain crew characteristic data, including comment history and reaction data from communication tools (e.g., Slack), test results from the e-learning system, and superior evaluations from the evaluation system.

[1612] The server uses the Google Maps API to collect location information and evaluation comments for each store.

[1613] Data Integration

[1614] The server stores the collected data in an integrated database. Crew characteristics data is stored in the "crew_data" table, and store evaluation data is stored in the "store_data" table.

[1615] The server combines crew and store data and creates an index to enable quick access and searching.

[1616] analysis

[1617] The server uses data from the integrated database to train a generative AI model and analyze the optimal match between crew and store.

[1618] The generative AI model compares the crew's communication skills and performance with the store's customer demographics and characteristics to find optimal staffing plans.

[1619] suggestion

[1620] The server transmits the generated placement plan to the terminal of the person in charge via the notification system.

[1621] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1622] Feedback collection

[1623] The user (person in charge) will then carry out the actual personnel allocation based on the proposed allocation plan and provide feedback on the results to the system.

[1624] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1625] The server analyzes the collected feedback data and uses it to update the generative AI model, thereby improving the accuracy of future placement suggestions.

[1626] Specific examples

[1627] Data collection

[1628] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" via the Slack API.

[1629] The server uses the Google Maps API to collect the location information and most recent customer evaluation comments for "Store ID 456."

[1630] Data Integration

[1631] The server inserts the retrieved data into the MySQL integrated database. The "crew_data" table stores the comment history and reaction data of "user ID 123," and the "store_data" table stores the evaluation comments of "store ID 456."

[1632] Analysis and Recommendations

[1633] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Based on this analysis result, it proposes placing "User ID 123" in "Store ID 456."

[1634] The server transmits the generated placement plan to the person in charge through a notification system, and displays the notification on the person in charge's terminal.

[1635] Feedback and Updates

[1636] After the user performs the placement based on the proposal, the user inputs the placement results and feedback into the system.

[1637] The server collects the feedback data and updates the generative AI model for the next placement proposal.

[1638] The above is an embodiment of the present invention. This processing flow realizes optimal staffing between crews and stores, thereby improving business performance and reducing man-hours.

[1639] The processing flow will be explained below.

[1640] Step 1:

[1641] The server uses the API of the internal system to obtain crew characteristic data. It calls the Slack API to collect comment history and reaction data from the past 30 days. It then queries the e-learning system API to obtain each crew member's test results and progress. It also obtains past evaluation data and feedback from superiors through the evaluation system API.

[1642] Step 2:

[1643] The server uses the Google Maps API to collect location information and customer reviews for each store. Specifically, it obtains geographic coordinates based on a specific store ID, and also collects the most recent customer reviews and comments.

[1644] Step 3:

[1645] The server stores the collected crew characteristic data, store location information, and evaluation data in an integrated database. Crew characteristic data is organized in the "crew_data" table and saved using the crew ID as a key. Store evaluation data is inserted into the "store_data" table and saved using the store ID as a key.

[1646] Step 4:

[1647] The server combines the crew and store data and creates an index for quick access and searching. Specifically, it uses an SQL query to join both data sets and generate new index fields.

[1648] Step 5:

[1649] The server trains a generative AI model using data from the integrated database. The model compares crew characteristics (communication skills, performance, ratings) with store characteristics (customer demographics, ratings, event status) to find the best match. Past deployment data and feedback are also used to train the model.

[1650] Step 6:

[1651] The server generates the staffing plan and notifies the person in charge. Specifically, the server converts the generated staffing plan into a document and sends it to the person in charge's terminal through the notification system. The notification includes details of the staffing plan, the reasons for the plan, and the expected results.

[1652] Step 7:

[1653] The user confirms the notified personnel deployment plan, checks the proposal through the user interface for the person in charge, and makes adjustments as necessary. The user then deploys the crew based on the confirmed deployment plan.

[1654] Step 8:

[1655] Users provide feedback to the system after deployment by entering the deployed crew's performance, satisfaction, and feedback comments through a feedback input interface, including specific achievements and problems after deployment.

[1656] Step 9:

[1657] The server collects the collected feedback data and stores it in an integrated database. It then analyzes the feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[1658] Step 10:

[1659] The server uses the updated generative AI model to further optimize the next staffing plan, thereby continuously achieving optimal staffing, improving performance and reducing labor costs.

[1660] Example 1

[1661] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1662] In the conventional system, matching employees with facilities was not possible while taking into full consideration the characteristics of the employees and the facilities, making it difficult to achieve appropriate placement. In addition, there was a lack of a mechanism for efficiently collecting feedback on placement results and reflecting it in the next placement, making continuous improvement difficult.

[1663] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1664] In this invention, the server includes means for acquiring employee characteristic data, means for acquiring facility location information and evaluation data, means for storing the acquired employee characteristic data, facility location information, and evaluation data in an integrated database, means for generating a generative AI model that analyzes an optimal match between employees and facilities using data from the integrated database, means for generating an optimal staffing plan based on the analysis results, means for notifying a person in charge of the staffing plan based on the employee characteristics and the facility characteristics, means for collecting feedback data on the staffing plan, means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal, means for acquiring facility evaluation data from customers, means for acquiring employee characteristic data from communication tools and an education system, and means for receiving feedback data from a terminal. This enables optimal staffing between employees and facilities, improving business efficiency and enabling continuous improvement in staffing.

[1665] "Employee" refers to a person employed by a company or organization to perform work.

[1666] "Characteristic data" refers to data that represents an employee's individual characteristics, such as their communication skills or performance.

[1667] "Facility" means a place of business where employees are located, including stores, factories, offices, etc.

[1668] "Location information" refers to data indicating a geographical location, and includes information such as latitude and longitude.

[1669] "Evaluation Data" refers to data representing evaluations and feedback on facilities and employees.

[1670] An "integrated database" refers to a database that centrally manages and stores information collected from multiple data sources.

[1671] A "generative AI model" is a model that uses machine learning and artificial intelligence to learn data patterns and make predictions and suggestions.

[1672] "Matching" refers to the process of analyzing the compatibility between employee characteristics and facility characteristics to find the optimal combination.

[1673] "Notification system" refers to a system that sends information or data to specific devices or personnel.

[1674] "Feedback data" refers to data that shows evaluations of staffing results and areas for improvement.

[1675] "Communication tools" refers to software and platforms used to communicate between employees and within an organization.

[1676] An "educational system" refers to a system that provides teaching materials and tests aimed at improving employees' skills and acquiring knowledge.

[1677] "Device" refers to a computer or mobile device used by a user or agent.

[1678] The present invention relates to a system for collecting, integrating, and analyzing employee characteristic data and facility evaluation data to achieve optimal staffing. Specific embodiments for carrying out the present invention will be described below.

[1679] System Configuration

[1680] The system includes the following main components:

[1681] 1. Server

[1682] Data Collection Module

[1683] Integrated Database

[1684] Generative AI Models

[1685] Notification System

[1686] Feedback Collection Module

[1687] 2. Terminal

[1688] Agent User Interface

[1689] Feedback Input Interface

[1690] 3. Users

[1691] Person in charge (the person who manages and staffs employees)

[1692] Data collection

[1693] The server uses the API of a communication tool (e.g., a chat system) to obtain employee characteristic data. Specifically, it collects 30 days of comment history and reaction data, test results from the education system, and supervisor evaluations from the evaluation system. The server also uses a geographic information API to collect facility location information and customer evaluation comments.

[1694] For example, the server performs the following operations:

[1695] Access the API endpoint https: / / api.chat-system.com / history?user=123 to retrieve the comment history and reaction data for "user ID 123."

[1696] Access the API endpoint https: / / api.geo-service.com / place / details?place_id=456 and collect location information and customer evaluation comments for "facility ID 456."

[1697] Data Integration

[1698] The collected data is stored in a MySQL integrated database by the server. Employee comment history and reaction data are stored in the "employee_data" table, and facility evaluation comments are stored in the "facility_data" table. The server also combines crew and facility data and generates indexes to enable quick access.

[1699] example:

[1700] sql

[1701] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[1702] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[1703] Data analysis

[1704] The server trains a generative AI model using data from the integrated database, which then analyzes the optimal match between employees and facilities. The generative AI model uses machine learning algorithms (e.g., TensorFlow and PyTorch) to analyze employee communication skills and performance, as well as the customer demographics and characteristics of facilities, to find optimal staffing plans.

[1705] suggestion

[1706] The server sends the generated staffing plan to the staff member's device via a notification system. The device (the staff member's user interface) displays the proposed staffing plan, which the staff member can review and adjust. As a specific example of the operation here, the staff member could input the following prompts to the AI:

[1707] Please propose the optimal staffing plan based on the communication skill data of "User ID 123" over the past 30 days and the evaluation comments of "Facility ID 456."

[1708] Feedback collection

[1709] The user (person in charge) performs actual staffing based on the proposed staffing plan and inputs the results as feedback to the system. The terminal (feedback input interface) inputs the feedback data from the person in charge and sends it to the server. The server analyzes the collected feedback data and updates the generative AI model. This improves the accuracy of future staffing proposals.

[1710] The above is a specific embodiment for carrying out the present invention. This processing flow realizes optimal staffing between employees and facilities, and enables improved work efficiency and continuous improvement of staffing.

[1711] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1712] Step 1: Data collection

[1713] The server sends requests to the APIs of communication tools and education systems to obtain employee characteristic data. Specifically, it collects data based on the following inputs:

[1714] (Input): API endpoint and query parameters (e.g. https: / / api.chat-system.com / history?user=123)

[1715] The server parses the JSON data returned from the API and extracts comment history and reaction data.

[1716] (Output): A JSON object containing the comment history and reaction data.

[1717] Specific behavior:

[1718] The server accesses the Slack API endpoint https: / / api.chat-system.com / history?user=123 and retrieves the message history and reaction data for the past 30 days for "user ID 123."

[1719] The server analyzes the JSON data obtained from the API and extracts the specific content of the comments and the type of each reaction.

[1720] Step 2: Data integration

[1721] The server generates SQL queries to store the collected data in a MySQL integrated database.

[1722] (Input): Speech history and reaction data, facility evaluation data

[1723] The server uses SQL queries to insert data into the database, which saves each piece of data in its corresponding table.

[1724] (Output): Employee characteristics data and facility evaluation data stored in a database

[1725] Specific behavior:

[1726] The server executes the following SQL query to insert the comment history and reaction data into the "employee_data" table:

[1727] sql

[1728] INSERT INTO employee_data (user_id, history) VALUES ('123', 'Speech history data');

[1729] Similarly, facility evaluation comments are stored in the "facility_data" table.

[1730] sql

[1731] INSERT INTO facility_data (facility_id, reviews) VALUES ('456', 'rating_comments');

[1732] Step 3: Data Joining and Indexing

[1733] The server combines the employee characteristic data with the facility evaluation data and generates an index to enable rapid access and retrieval.

[1734] (Input): Employee characteristics data and facility evaluation data in the database

[1735] The server combines the data using SQL JOIN operations and generates the index.

[1736] (Output): The combined data and the generated index.

[1737] Specific behavior:

[1738] The server uses the following SQL query to join the data and generate the index:

[1739] sql

[1740] CREATE INDEX idx_user_store ON combined_data (user_id, store_id);

[1741] Step 4: Training the generative AI model

[1742] The server inputs data from the integrated database into the generative AI model and trains the model.

[1743] (Input): Combined employee and facility data in the database

[1744] The server uses machine learning algorithms to train the model and analyze the best matches.

[1745] (Output): Trained generative AI model and analysis results

[1746] Specific behavior:

[1747] The server runs Python programs and uses libraries such as TensorFlow or PyTorch to train generative AI models.

[1748] Training data includes employee communication skills and performance, as well as the customer demographics and characteristics of the facility.

[1749] Step 5: Generate and notify placement proposals

[1750] The server generates optimal staffing plans based on the analysis results obtained from the generative AI model.

[1751] (Input): Trained generative AI model and employee and facility data

[1752] The server sends the placement plan generated from the analysis results to the person in charge via a notification system.

[1753] (Output): Staffing plan sent to the person in charge's terminal

[1754] Specific behavior:

[1755] The server creates an optimal personnel allocation plan based on the analysis results.

[1756] The server transmits the placement plan to the terminal of the person in charge and displays it on the user interface for the person in charge.

[1757] Step 6: Gather feedback

[1758] The user performs actual staffing based on the proposed staffing plan and inputs the results into the system as feedback.

[1759] (Input): Results and feedback comments from the person in charge

[1760] The terminal collects feedback data through a feedback input interface and sends it to the server.

[1761] (Output): Feedback data sent to the server

[1762] Specific behavior:

[1763] The user assigns employees according to the assignment plan and inputs the results and feedback into the terminal.

[1764] The terminal transmits the collected feedback data to the server.

[1765] Step 7: Update the generative AI model

[1766] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future placement suggestions.

[1767] (Input): Feedback data and existing generative AI models

[1768] The server uses the feedback data to retrain and update the generative AI model.

[1769] (Output): Updated generative AI model

[1770] Specific behavior:

[1771] The server analyzes the collected feedback data and extracts the information needed to improve the accuracy of the model.

[1772] The server retrains the generative AI model and reflects it in the next placement proposal.

[1773] This is the specific flow of the program processing of this system. This procedure is expected to achieve optimal matching between employees and facilities and improve work efficiency.

[1774] (Application example 1)

[1775] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1776] Conventional factory robot allocation systems have the problem of being unable to achieve efficient work allocation because it is difficult to optimally match each robot based on its characteristics and task requirements. Furthermore, there is a lack of flexible system design that reflects feedback after task allocation. As a result, there are issues such as reduced productivity and insufficient robot operational efficiency.

[1777] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1778] In this invention, the server includes a means for acquiring personnel characteristic data, a means for acquiring work base location information and evaluation data, and a means for storing the acquired personnel characteristic data, work base location information, and evaluation data in an integrated database, thereby realizing a generative AI model that analyzes optimal matching between personnel and work bases.

[1779] "Personnel characteristic data" is data that indicates the specific attributes and capabilities of each personnel, such as the speed, accuracy, and power consumption of that personnel.

[1780] "Location information of work base" refers to the geographic coordinates of the location where work is performed and detailed information about that location.

[1781] "Evaluation data" refers to data that indicates evaluations and feedback on work sites and personnel.

[1782] An "integrated database" is a database that centrally manages and stores a wide variety of data and enables efficient access.

[1783] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data on personnel and work locations and generate optimal matching and placement plans.

[1784] A "notification system" is a mechanism for quickly and reliably notifying administrators and personnel of information generated by the system.

[1785] "Feedback data" refers to data that indicates actual results and evaluations based on the placement proposal, and is collected to be reflected in the next proposal.

[1786] An "index" is something like a table of contents created for data in a database to speed up data searches.

[1787] A "robotic arm" is a mechanical arm-like device used to perform tasks in a factory.

[1788] "Task requirement information" is information that indicates the conditions and requirements necessary for the performance of a specific work or task.

[1789] To implement the present invention, the following system configuration and processing flow are adopted. In each step, the roles of the server, terminal, and user are clarified and explained based on a specific example.

[1790] System Configuration

[1791] The system includes the following main components:

[1792] 1. Server

[1793] Data Collection Module

[1794] Integrated Database

[1795] Generative AI Models

[1796] Notification System

[1797] Feedback Collection Module

[1798] 2. Terminal

[1799] Administrator User Interface

[1800] Feedback Input Interface

[1801] 3. Users

[1802] Manager (person who manages the placement of robots within the factory)

[1803] Program processing

[1804] The server collects, analyzes, proposes, and updates data in the following steps:

[1805] Technology used

[1806] 1. Hardware:

[1807] Robotic arms (e.g., typical factory robotic arms)

[1808] Sensors (e.g. Lidar, cameras)

[1809] Server (e.g. AWS EC2)

[1810] 2. Software:

[1811] Data collection module (Python, Slack API, factory integrated management system API, etc.)

[1812] Integrated database (MySQL)

[1813] Generative AI models (e.g., TensorFlow, PyTorch)

[1814] Notification systems (e.g. Firebase)

[1815] Feedback collection module (e.g. Flask)

[1816] Data collection

[1817] The server obtains characteristic data for each robot (such as operating speed, accuracy, and power consumption) from the factory's integrated management system. It also collects task status information within the factory from sensors. For example, it obtains characteristic data such as operating speed, accuracy, and power consumption for "robot ID 123," and collects location information and required operating accuracy for "task ID 456."

[1818] Data Integration

[1819] The collected data is stored in the server's integrated MySQL database, where personnel characteristics data is stored in the "robot_data" table and task request data is stored in the "task_data" table.

[1820] analysis

[1821] The server uses data from the integrated database to train the generative AI model and analyzes the characteristics and task requirements of each robot. Based on the results of this analysis, it proposes optimal robot task assignments. For example, the generative AI model can input the characteristics data of "Robot ID 123" and the requirements of "Task ID 456," and determine that "Robot ID 123" is optimal for "Task ID 456."

[1822] suggestion

[1823] The server sends the generated task allocation plan to the administrator's terminal via the notification system. The administrator's user interface displays the proposed placement plan, which the administrator can review and adjust. For example, the generated placement plan is notified to the administrator's terminal, and the administrator performs the placement based on the proposal.

[1824] Feedback collection

[1825] The administrator performs placement based on the proposed placement plan and provides feedback to the system on the results. The server collects the feedback data and updates the generative AI model to reflect it in the next placement proposal.

[1826] Specific examples

[1827] Examples of prompt sentences include:

[1828] The characteristic data (operation speed, accuracy, power consumption) for "Robot ID 123" are as follows. Based on this, make the optimal allocation to meet the requirements (position information, operation accuracy) of "Task ID 456".

[1829] This is expected to improve the efficiency of robot placement within factories and increase productivity.

[1830] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1831] Step 1:

[1832] The server obtains the characteristic data of each robot through the factory integrated management system API. This includes the robot's operating speed, accuracy, power consumption, etc. Based on this input data, the characteristic data is collected and saved. Specifically, the server sends an API request and stores the obtained data in the "robot_data" table of the integrated database.

[1833] Step 2:

[1834] The server collects task status information from sensors in the factory. The acquired input data includes the task's location information and the required operating accuracy. Based on this data, detailed task information is saved in the "task_data" table. Specifically, it acquires real-time data from the sensors, organizes it, and inserts it into the database.

[1835] Step 3:

[1836] The server integrates the robot characteristic data and task request data stored in the integrated database and structures the data. Here, it creates indexes to speed up data searches. It uses data from the "robot_data" table and the "task_data" table as input and outputs indexed integrated data. Specific operations include data merging using SQL queries and creating indexes.

[1837] Step 4:

[1838] The server trains the generative AI model using data from the integrated database. The input is the integrated robot and task data, and it analyzes the optimal match based on this. The output is the optimal robot task assignment proposal as a result of the analysis. The specific operation is the training process of the generative AI model using TensorFlow and PyTorch.

[1839] Step 5:

[1840] The server sends the task allocation plan analyzed by the generative AI model to the administrator's device via the notification system. The input is the generated placement plan, and the output is displayed on the administrator's device as a notification. The specific operation is to send a push notification using Firebase.

[1841] Step 6:

[1842] The administrator executes the actual deployment based on the proposed deployment plan. The input is the deployment plan notified by the server, and the output is the actual deployment result. The specific operation is to confirm the deployment plan through the user interface and actually deploy the robot.

[1843] Step 7:

[1844] The administrator inputs feedback based on the deployment results into the feedback input interface. The input data is the deployment execution result and its evaluation. The output is sent to the server as feedback data. The specific operation is that the administrator submits the evaluation using the feedback form.

[1845] Step 8:

[1846] The server analyzes the collected feedback data and updates the generative AI model. The input data is the feedback data, which is used to improve the model's accuracy. The output is an updated AI model. Specifically, it adjusts the model's hyperparameters based on the previous feedback and retrains the model on a new dataset.

[1847] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1848] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[1849] System Configuration

[1850] The system includes the following main components:

[1851] 1. Server

[1852] Data Collection Module

[1853] Emotion Engine

[1854] Integrated Database

[1855] Generative AI Models

[1856] Notification System

[1857] Feedback Collection Module

[1858] 2. Terminal

[1859] Agent User Interface

[1860] Feedback Input Interface

[1861] 3. Users

[1862] Person in Charge (the person who manages and staffs the crew)

[1863] Program processing

[1864] Data collection

[1865] The server uses the API of the internal system to collect crew characteristic data. It calls the Slack API to obtain the past 30 days of comment history and reaction data. It then uses the e-Learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[1866] The server uses the Google Maps API to collect location information and review comments for each store, which includes geographic coordinates and review comments based on a specific store ID.

[1867] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[1868] Data Integration

[1869] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[1870] The server combines this data and creates an index to allow for quick access and searching.

[1871] analysis

[1872] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. Emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[1873] suggestion

[1874] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[1875] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1876] Feedback collection

[1877] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[1878] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1879] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[1880] Specific examples

[1881] Data collection

[1882] The server retrieves the posting history and reaction data for the past 30 days for "User ID 123" through the Slack API. It also retrieves the test results for "User ID 123" using the e-Learning system API and collects the supervisor's evaluation data through the evaluation system API.

[1883] The server uses the Google Maps API to collect location information and customer evaluation comments for "Store ID 456."

[1884] The server uses the emotion engine to analyze the recent emotional state of "user ID 123" and obtains emotional data.

[1885] Data Integration

[1886] The server stores the acquired data in a MySQL integrated database. The crew characteristics data is stored in the "crew_data" table, the store evaluation data is stored in the "store_data" table, and the emotion data is stored in a separate table.

[1887] Analysis and Recommendations

[1888] The server inputs this data into the generative AI model and analyzes that "User ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account to adjust the crew's stress levels and motivation.

[1889] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[1890] Feedback and Updates

[1891] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[1892] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[1893] The above is an embodiment of the present invention. This system realizes optimal staffing between crews and stores, improving business performance and reducing man-hours. Furthermore, staffing plans that take crew emotional data into account also improve staff motivation and well-being.

[1894] The processing flow will be explained below.

[1895] Step 1:

[1896] The server uses the API of the internal system to obtain crew characteristic data. To do this, it calls the Slack API to collect comment history and reaction data for the past 30 days. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and obtains evaluation data from superiors through the evaluation system API.

[1897] Step 2:

[1898] The server uses the Google Maps API to collect location information and reviews for each store. It obtains geographic coordinates, reviews, and reviews from a specific store ID.

[1899] Step 3:

[1900] The server uses an emotion engine to acquire crew emotional data, specifically analyzing comments and responses from Slack and interaction data from the e-learning system, to estimate the crew's emotional state (e.g., stress level and motivation).

[1901] Step 4:

[1902] The server stores the collected crew characteristic data, store evaluation data, and emotion data in an integrated database. Crew characteristic data is stored in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[1903] Step 5:

[1904] The server then combines these data and creates indexes to enable fast access and searching, specifically by joining each data table using an SQL query to generate new index fields.

[1905] Step 6:

[1906] The server uses data from the integrated database to train a generative AI model, taking into account crew characteristics (e.g., communication skills, performance, and ratings) and store characteristics (e.g., customer demographics, ratings, and event status) as well as emotional data to analyze optimal matches.

[1907] Step 7:

[1908] The server generates optimal staffing plans based on the analysis results. The plans are based on crew characteristics, store characteristics, and crew emotion data. The plans include which stores each crew member should be assigned to, the reasons for doing so, and the expected results.

[1909] Step 8:

[1910] The server sends the generated staffing plan to the person in charge through a notification system, and a notification is sent to the person in charge's terminal, providing details of the specific staffing plan.

[1911] Step 9:

[1912] The user (person in charge) uses the terminal to check the notified personnel allocation plan. The user checks the details of the proposal and makes adjustments as necessary. The actual allocation is carried out based on the confirmed allocation plan.

[1913] Step 10:

[1914] The user provides feedback to the system after the deployment, including the performance, satisfaction, and feedback comments of the deployed crew. Emotional data is also evaluated and provided as feedback.

[1915] Step 11:

[1916] The server stores the collected feedback data in an integrated database, including changes in emotional data, and reflects this in the next proposal.

[1917] Step 12:

[1918] The server analyzes the collected feedback data and updates the generative AI model, which improves the accuracy of future staffing recommendations.

[1919] Step 13:

[1920] The server uses the updated generative AI model to optimize the next staffing plan, thereby achieving continuous optimal staffing, improving performance and reducing labor costs.

[1921] Example 2

[1922] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1923] Conventional systems optimize staffing based on crew characteristics, store location information, and evaluation data, but do not generate staffing plans that take crew emotional data into account. This can result in crew stress levels and motivation levels being ignored, often resulting in less-than-optimal staffing. A new staffing system is needed that can improve crew well-being while maximizing performance.

[1924] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring crew characteristic data; means for acquiring store location information and evaluation data; means for collecting and analyzing emotion data; means for storing the acquired crew characteristic data, store location information, evaluation data, and emotion data in an integrated database; a generative AI model means for analyzing the optimal match between crew and store using data from the integrated database; means for creating an index to enable rapid data search; means for generating an optimal staffing plan based on the analysis results; means for notifying a person in charge of the staffing plan based on the crew characteristics and store characteristics; means for transmitting the staffing plan to the person in charge's terminal via a notification system; means for collecting feedback data on the staffing plan; and means for updating the generative AI model to reflect the collected feedback data in the next staffing proposal. This enables optimal staffing that takes crew characteristics and emotions into consideration, thereby improving business performance and enhancing crew motivation and well-being.

[1925] "Crew characteristic data" refers to profile information such as each crew member's communication skills, achievements, and evaluations.

[1926] "Store Location Information" refers to the geographic coordinates (latitude and longitude) of each store.

[1927] "Rating Data" refers to customer feedback, reviews, and rating scores for a store.

[1928] "Emotional data" is data that indicates the emotional state of the crew and is analyzed from interactions with communication tools and educational systems.

[1929] The "integrated database" refers to a database that centrally stores and manages crew characteristics data, store location information, evaluation data, and emotional data.

[1930] "Generative AI model" refers to an artificial intelligence model that uses crew and store data to analyze optimal matches and generate staffing plans.

[1931] An "index" refers to a search key created to enable rapid retrieval of data.

[1932] "Notification system" refers to a system for notifying personnel in charge of the generated staffing plan.

[1933] "Feedback data" refers to data such as crew performance, satisfaction, and feedback comments regarding implemented staffing plans.

[1934] MODE FOR CARRYING OUT THE INVENTION

[1935] The present invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data, store location information, and evaluation data to generate staffing plans that also take emotion data into consideration. The system configuration and processing are described in detail below.

[1936] System Configuration

[1937] The system includes the following main components:

[1938] 1. Server

[1939] Data Collection Module

[1940] Emotion Engine

[1941] Integrated Database

[1942] Generative AI Models

[1943] Notification System

[1944] Feedback Collection Module

[1945] 2. Terminal

[1946] Agent User Interface

[1947] Feedback Input Interface

[1948] 3. Users

[1949] Person in Charge (the person who manages and staffs the crew)

[1950] Data collection

[1951] The server uses the API of the internal system to collect crew characteristic data. For example, it calls the Slack API to obtain the past 30 days' worth of comment history and reaction data. Next, it uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[1952] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[1953] The server uses an emotion engine to acquire crew members' emotional data. Specifically, it analyzes and acquires their emotional states from interactions with communication tools and e-learning systems.

[1954] Data Integration

[1955] The server stores the collected crew characteristic data, store location information, evaluation data, and emotion data in an integrated database. The characteristic data is stored in the "crew_data" table, the store evaluation data in the "store_data" table, and the emotion data in a separate table.

[1956] The server creates an index of this data to allow for quick access and retrieval.

[1957] analysis

[1958] The server trains a generative AI model using data from the integrated database. The model analyzes optimal matches by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data. The emotional data reflects the crew's stress level and motivation, contributing to more accurate allocation plan generation.

[1959] suggestion

[1960] The server sends the generated deployment plan to the person in charge's terminal via the notification system. Specifically, the server converts the generated deployment plan into a document and notifies the person in charge via the notification system. The notification includes details of the deployment plan, reasons, and expected results.

[1961] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[1962] Feedback collection

[1963] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[1964] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[1965] The server collects feedback data and stores it in an integrated database. It then analyzes the collected feedback data and updates the generative AI model, thereby improving the accuracy of future placement suggestions.

[1966] Specific examples

[1967] Data collection

[1968] The server retrieves the posting history and reaction data for the past 30 days for "Crew ID 123" through the Slack API, retrieves the test results for "Crew ID 123" using the e-learning system API, and collects the evaluation data of superiors through the evaluation system API.

[1969] The server uses the geographic information service API to collect location information and customer evaluation comments for "Store ID 456."

[1970] The server uses the emotion engine to analyze the recent emotional state of "Crew ID 123" and obtains emotional data.

[1971] Data Integration

[1972] The server stores the acquired data in an integrated database. Crew characteristics data is stored in the "crew_data" table, store evaluation data is stored in the "store_data" table, and emotion data is stored in a separate table.

[1973] Analysis and Recommendations

[1974] The server inputs this data into the generative AI model and analyzes that "Crew ID 123" is the best fit for "Store ID 456." Emotional data is also taken into account, and the server adjusts the crew's stress level and motivation.

[1975] The server transmits the generated placement plan to the person in charge through a notification system, and notifies the person in charge at his / her terminal.

[1976] Feedback and Updates

[1977] The user executes the deployment based on the proposal and feeds back the results to the system. After deployment, the user inputs the crew's performance, satisfaction, and emotional data based on feedback comments.

[1978] The server analyzes the collected feedback data, updates the generative AI model, and reflects it in the next placement proposal.

[1979] These steps will enable optimal staffing between crews and stores, improving performance and increasing crew motivation and well-being.

[1980] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1981] System program processing flow

[1982] Step 1: Data collection

[1983] Input: API of internal systems, data from communication tools

[1984] process:

[1985] The server uses the API of the company's internal system to collect crew characteristic data. Specifically, it calls the Slack API to obtain the comment history and reaction data for the past 30 days.

[1986] The server uses the e-learning system API to obtain each crew member's test results and progress, and collects past evaluation data from the evaluation system API.

[1987] The server uses a geographic information service API to collect location information and rating comments for each store, including geographic coordinates and rating comments based on a specific store ID.

[1988] The server uses an emotion engine to acquire crew emotional data, including data obtained by analyzing emotional states from interactions with communication tools and e-learning systems.

[1989] Output: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[1990] Step 2: Data integration

[1991] Input: Crew characteristics data, test results, evaluation data, store location information, evaluation comments, emotion data

[1992] process:

[1993] The server stores the collected data in an integrated database: crew characteristics data in the "crew_data" table, store evaluation data in the "store_data" table, and emotion data in a separate table.

[1994] The server indexes this data to allow for quick access and retrieval.

[1995] Output: Integrated database

[1996] Step 3: Analysis

[1997] Input: Integrated database

[1998] process:

[1999] The server uses data from the integrated database to train a generative AI model, which analyzes the optimal match by taking into account crew characteristics (communication skills, performance, ratings) and store characteristics (customer demographics, ratings, event status), as well as emotional data.

[2000] Output: A trained generative AI model

[2001] Step 4: Generate placement proposals

[2002] Input: A trained generative AI model

[2003] process:

[2004] The server generates optimal staffing plans based on the analysis results, which include the reasons for the staffing and the expected results.

[2005] Output: Staffing plan

[2006] Step 5: Notification of proposed placement

[2007] Input: Staffing plan

[2008] process:

[2009] The server sends the generated placement plan to the terminal of the person in charge via the notification system. Specifically, the placement plan is converted into a document and sent to the person in charge as notification content.

[2010] The terminal (user interface for the person in charge) displays the proposed staffing plan, which the person in charge can review and adjust.

[2011] Output: The placement plan is notified to the person in charge's terminal.

[2012] Step 6: Gather feedback

[2013] Input: Implementation results based on the placement plan, feedback from the person in charge

[2014] process:

[2015] The user (person in charge) provides feedback on the implemented staffing plan, including crew performance, satisfaction, and feedback comments.

[2016] The terminal (feedback input interface) inputs feedback data from the person in charge and transmits it to the server.

[2017] Output: Feedback data

[2018] Step 7: Analyze feedback data and update the model

[2019] Input: Feedback data

[2020] process:

[2021] The server collects feedback data, stores it in an integrated database, and analyzes the collected feedback data to update the generative AI model.

[2022] Output: Updated generative AI model

[2023] In this way, optimal staffing of crews and stores can be achieved through each step, improving business performance and increasing crew motivation and well-being.

[2024] (Application example 2)

[2025] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2026] Conventional staffing systems only utilize characteristic data, location information, and evaluation data, and are unable to optimize staffing by taking into account the emotional state and motivation of crew members. This can lead to lower crew stress levels and motivation, which can hinder performance improvement and customer satisfaction. Furthermore, there is a lack of a mechanism to fully reflect feedback and improve the accuracy of next staffing proposals.

[2027] The identification process by the identification 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 means for acquiring crew characteristic data, means for acquiring store location information and evaluation data, and means for acquiring crew emotion data and storing this data in an integrated database. This makes it possible to generate more accurate and effective staffing plans based on the crew characteristic data and emotion data and the store characteristics, and notify the person in charge in real time.

[2028] The system further includes means for combining crew characteristic data, emotion data, store location information, and evaluation data and creating an index, which allows for rapid access and search of the data.

[2029] Furthermore, the system includes a means for transmitting the results of the staffing plan to the terminal of the person in charge in real time via the notification system, thereby enabling the person in charge to immediately check and adjust the staffing plan.

[2030] It includes a means to analyze the collected feedback data and update the generative AI model, which can then provide more accurate staffing recommendations in the next deployment proposal, improving crew motivation and well-being.

[2031] "Crew characteristic data" is information about individual characteristics of employees, such as communication skills, performance, and evaluations.

[2032] "Store location information and evaluation data" refers to information about the geographic location of a store and information about evaluation comments and evaluation scores from customers.

[2033] "Emotional data" is information about an employee's emotional state, such as stress level or motivation.

[2034] The "integrated database" is a database system that centrally stores characteristic data, emotion data, store location information, and evaluation data, enabling quick access and search of the data.

[2035] The "generative AI model" is an artificial intelligence model that analyzes and generates optimal staffing plans using crew characteristic data, emotional data, store location information, and evaluation data.

[2036] The "notification system" is a system that notifies personnel deployment plans generated by the generative AI model to the terminals of personnel in real time.

[2037] "Feedback data" refers to data regarding employee performance, satisfaction, emotional state, etc., based on the results of implementing staffing plans.

[2038] The "feedback collection means" is a function for collecting set feedback data and reflecting it in the integrated database and generative AI model.

[2039] This invention combines an emotion engine with a system that proposes optimal staffing based on crew characteristic data and store information to generate staffing proposals that also take emotion data into consideration. The system includes the following main components:

[2040] System Configuration

[2041] server

[2042] Data collection module: Collects crew characteristics data, emotion data, store location information and evaluation data.

[2043] Integrated database: Collected data is managed centrally, enabling quick search and access.

[2044] Generative AI model: Analyzes data and generates optimal staffing recommendations.

[2045] Notification system: Notifies the person in charge of the generated placement plan in real time.

[2046] Feedback collection module: Collects feedback data and updates the AI ​​model.

[2047] Terminal

[2048] User interface for personnel: An interface that displays the proposed staffing plan and allows personnel to review and adjust it.

[2049] Feedback input interface: An interface for inputting feedback on the implemented staffing plan.

[2050] User

[2051] Person in Charge: The person who manages and staffs the crew.

[2052] Program processing

[2053] Data collection

[2054] The server uses the Slack API to collect crew characteristic data. It also uses the e-Learning system API to obtain crew learning progress data and test results, and collects data from the evaluation system API. It uses the Google Maps API to collect store location information and evaluation comments. It uses an emotion engine (e.g., Affectiva) to collect employee emotion data.

[2055] Data Integration

[2056] The server stores the collected data in a MySQL integrated database: characteristic data in the "crew_data" table, store information in the "store_data" table, and emotion data in the "emotion_data" table.

[2057] Generate staffing plans

[2058] The server uses data from the integrated database to train a generative AI model, which references crew characteristics, emotional data, and store characteristics data to generate optimal staffing plans.

[2059] Suggestions and Notifications

[2060] The generated staffing plan is sent to the staff member's device in real time via the notification system, and the staff member's user interface displays the plan, allowing them to review and make any necessary adjustments.

[2061] Gathering feedback and updating the model

[2062] Feedback data is input by the staff through the feedback input interface, which is then sent to the server for analysis, which then updates the generative AI model and reflects it in the next staffing proposal.

[2063] Specific examples

[2064] Prompt Sentence Examples

[2065] Inputs to the generative AI model:

[2066] Crew characteristics: "Communication skills: 8 / 10, Performance: 9 / 10, Evaluation: Positive"

[2067] Emotional data: "Stress level: low, motivation: high"

[2068] Store data: "Store ID 456, Customer type: Family, Rating: 4.5 / 5"

[2069] User ID 123's characteristic data: {"Communication skills: 8 / 10","Performance: 9 / 10","Evaluation: Positive"}

[2070] Emotion data for user ID 123: {"Stress level: Low","Motivation: High"}

[2071] Store ID 456 store data: {"Customer demographic: Family","Rating: 4.5 / 5"}

[2072] Based on this data, generate optimal staffing plans.

[2073] Output of the generative AI model:

[2074] Placement plan: "Place user ID 123 at store ID 456"

[2075] Example notification:

[2076] "User ID 123 is a perfect fit for store ID 456. Reasons for placement: high communication skills, low stress level, family-friendly store characteristics."

[2077] This system will enable optimal staffing between crews and stores, improving performance and reducing man-hours. It will also improve staff motivation and well-being by providing staffing suggestions that take into account crew emotional data.

[2078] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2079] Step 1:

[2080] The server uses the Slack API to obtain 30 days' worth of crew characteristic data (comment history, reaction data). This data is combined with test results and learning progress data collected using the e-Learning system API, and evaluation data obtained from the evaluation system API. At this time, the crew characteristic data is input and characteristic data is collected.

[2081] Step 2:

[2082] The server uses the Google Maps API to obtain the store's location information and evaluation comments. At this time, the store's ID is used as input, and the obtained store's geographic coordinates and evaluation comments are output.

[2083] Step 3:

[2084] The server uses an emotion engine (e.g., Affectiva) to collect crew emotion data. The emotion data is obtained by analyzing interactions in communication tools and e-learning systems. The interaction data is used as input, and emotion data is obtained as output.

[2085] Step 4:

[2086] The server stores the collected crew characteristics data, store location information, evaluation data, and emotion data in an integrated database (MySQL). Each piece of data is stored in its own dedicated table (crew_data, store_data, emotion_data). Each piece of collected data is used as input, and is stored in the integrated database as output.

[2087] Step 5:

[2088] The server trains a generative AI model using data from the integrated database. To analyze the optimal match between crew and store, it generates prompt sentences and uses characteristic data, emotion data, and store data as inputs. This results in the output of optimal staffing recommendations.

[2089] Step 6:

[2090] The server sends the generated placement plan to the person in charge's device in real time via the notification system. The placement plan from the generative AI model is used as input, and the placement plan is notified to the person in charge's device as output.

[2091] Step 7:

[2092] The terminal uses a user interface for the staff member to display the proposed placement plan, which the staff member can review and adjust. The notified placement plan is used as input, and the reviewed and adjusted placement plan is obtained as output.

[2093] Step 8:

[2094] The user (person in charge) inputs feedback (performance, satisfaction, emotional state) for the implemented staffing plan through the feedback input interface. The feedback data is used as input and is sent to the server.

[2095] Step 9:

[2096] The server analyzes the collected feedback data and stores it in an integrated database. It also updates the generative AI model based on the feedback data. The feedback data is used as input, and the updated generative AI model is obtained as output.

[2097] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2098] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2099] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2100] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2101] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2102] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2103] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2104] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2105] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2106] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2107] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2108] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2109] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2110] 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.

[2111] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2112] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2113] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[2114] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2115] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2116] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an exampl...

Claims

1. a means for acquiring crew characteristic data; A means for acquiring store location information and evaluation data; A means for storing the acquired crew characteristic data and store location information and evaluation data in an integrated database; A generative AI model means for analyzing optimal matching between crews and stores using data from the integrated database; A means for generating an optimal personnel allocation plan based on the analysis results; a means for informing personnel of staffing proposals based on crew characteristics and store characteristics; a means of collecting feedback data on staffing proposals; A means for updating the generative AI model to incorporate the collected feedback data into the next placement proposal; and A system including:

2. 2. The system of claim 1, further comprising means for combining crew characteristic data with store location information and evaluation data using data stored in the integrated database to create an index.

3. 10. The system of claim 1, further comprising means for transmitting the staffing plan to a terminal of a staff member via a notification system.

Images