system

Abstract

Provide a system. [Solution] A means for analyzing usage data of a company's internal communication applications using generative AI; A means for calculating a company vitality score based on the analysis results of the usage data; means for providing said vitality score to a financial institution; A system including:

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] Small and medium-sized enterprises often struggle with cash flow, and often need additional financing, especially when they have already borrowed up to their credit limit or when costs are rising. However, traditional loan evaluation models are based solely on financial data, making it difficult to assess a company's actual vitality and vibrancy. This makes it difficult to evaluate a company's true vitality, making it difficult to make appropriate lending decisions. [Means for solving the problem]

[0005] The present invention provides a system that calculates a company's vitality score by analyzing usage data of the company's internal communication application using a generative AI. Specifically, the system includes a means for analyzing the content of messages in the communication application to calculate the frequency of positive and negative words, and generating a company's vitality score by taking into account the total number of messages and response speed. This vitality score is provided to financial institutions, which can use it to evaluate the company and make lending decisions. This makes it possible to incorporate a company's actual vitality and activity into the evaluation, leading to more appropriate lending decisions.

[0006] "Generative AI" is a type of artificial intelligence technology designed to automatically analyze and evaluate data.

[0007] An "enterprise" is a legal entity or sole proprietorship that provides goods or services and operates for profit.

[0008] An "internal communications application" is an electronic messaging tool for sharing information and communicating within a company.

[0009] "Usage Data" refers to records of message content, frequency, response speed, etc. in internal communication applications.

[0010] "Analysis" is the process of analyzing usage data and extracting specific patterns or information.

[0011] The "vitality score" is an evaluation index that quantifies the vitality and activity of a company.

[0012] A "financial institution" is an organization or institution that supplies funds, such as a bank or credit union.

[0013] "Provision" refers to the act of passing analysis results and evaluation indicators to other systems or organizations.

[0014] "Message Content" refers to the text or information sent or received in an internal communication application.

[0015] "Positive words" are words or phrases that have a positive meaning.

[0016] "Negative words" are words or phrases that have a negative meaning.

[0017] "Frequency" is the number of times an event or behavior occurs within a particular time frame.

[0018] "Total Messages" refers to the total number of messages sent or received within a given period of time.

[0019] "Reply speed" is an index that indicates how quickly a reply is made to a message.

[0020] A "score" is a numerical result of an evaluation or measurement.

[0021] "Evaluation" is the process of judging an object and measuring its value based on specific criteria.

[0022] "Lending decision" is the process by which a financial institution decides whether to provide a loan to a company.

[0023] A "loan" is an act in which a financial institution lends a certain amount of money to a company. [Brief explanation of the drawings]

[0024] [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

[0025] 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.

[0026] First, the terms used in the following description will be explained.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] [First embodiment]

[0033] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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."

[0045] The system of this invention uses generative AI to analyze usage data from internal communication applications of small and medium-sized enterprises, and builds a unique scoring model based on the results. This provides financial institutions with a company vitality score, supporting their evaluation and lending decisions. The system is composed of the following processing flow and components.

[0046] Overall system configuration

[0047] The overall configuration of this system mainly consists of the following components:

[0048] Terminals (devices running internal corporate communication applications)

[0049] Server (performs data analysis and scoring)

[0050] Financial institution systems (using scores to evaluate and make lending decisions)

[0051] Terminal functions

[0052] The device runs an internal communication application that company personnel use on a daily basis. Users use this application to communicate for business purposes. During this time, a dedicated monitoring tool runs in the background and collects the following data:

[0053] Message content

[0054] The date and time the message was sent and received

[0055] Total number of messages

[0056] Positive and negative words

[0057] The collected data is automatically sent to a server.

[0058] Server-side features

[0059] The server receives the usage data of the internal communication application sent from the device and stores it in a database.The server then uses the generation AI to perform the following analysis.

[0060] 1. Use natural language processing (NLP) techniques to extract positive and negative words from message content.

[0061] 2. Calculate statistics such as total number of messages and response speed.

[0062] 3. Based on these analysis results, a company's vitality score is calculated.

[0063] The generated vitality score is calculated based on a scoring algorithm to quantify the vitality and activity of the company. This score is stored in a database and made available to financial institutions via API.

[0064] Financial institution system functions

[0065] The financial institution's system obtains the vitality score for each company through the API. Financial institution personnel use this score to make lending decisions. Specific methods of use are as follows:

[0066] Obtain a vitality score for companies that apply for loans.

[0067] Check whether the score meets certain criteria.

[0068] If necessary, we will evaluate it comprehensively in conjunction with other financial data.

[0069] Specific examples

[0070] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[0071] Number of positive words: 250

[0072] Number of negative words: 50

[0073] Total number of messages: 1000

[0074] Average response time: 2 hours

[0075] Based on this data, the generative AI calculates a vitality score of 85 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff member uses this score to review whether to grant additional financing to Company A.

[0076] As described above, this invention utilizes generative AI to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the vitality of a company, and is expected to lead to more appropriate lending decisions.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] When users communicate for business purposes using an internal communication application within a company (e.g., a business messaging app), data such as the content of the conversation, the time the message was sent, the time it was received, and the speed of the reply are automatically recorded.

[0080] Step 2:

[0081] A dedicated monitoring tool installed on the device periodically collects data from internal communication applications, organizes it, encrypts it, and sends it to a server, including the content of messages, timestamps of messages sent and received, and the total number of messages.

[0082] Step 3:

[0083] The server stores the received data in a database for analysis. The data is stored in a database management system (DBMS) in a format that can be efficiently accessed by each company.

[0084] Step 4:

[0085] The server's generation AI performs natural language processing (NLP) based on the collected data. Specifically, it analyzes the content of messages to detect positive words (e.g., "great," "thank you") and negative words (e.g., "problem," "trouble") and calculates their frequency.

[0086] Step 5:

[0087] The server also calculates statistics such as the total number of messages and reply speed, which refers to the average time it takes for a message to be replied to after it is sent.

[0088] Step 6:

[0089] The server's scoring algorithm calculates a company's vitality score based on the NLP analysis results and statistical information. The vitality score is a numerical representation of a company's vitality and energy, ranging from 0 to 100.

[0090] Step 7:

[0091] The server stores this vitality score in a database and makes it accessible to financial institutions. It also provides an API for retrieving the score, which financial institutions can use to obtain the necessary information.

[0092] Step 8:

[0093] Financial institutions' systems obtain a company's vitality score through the API, and financial institution personnel use the score in combination with other financial data to evaluate the company and make lending decisions.

[0094] Step 9:

[0095] Financial institutions provide the server with feedback data on actual loan results and company performance, which the server uses to make adjustments to improve the accuracy of the scoring algorithm.

[0096] Step 10:

[0097] The server's generation AI continuously improves its algorithm based on feedback data, improving the accuracy of the vitality score assessment, thereby improving the performance and reliability of the entire system.

[0098] The above steps will realize a system that analyzes usage data of a company's internal communication applications and evaluates the company's vitality. This system will be a valuable tool for financial institutions in making lending decisions.

[0099] Example 1

[0100] 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."

[0101] When evaluating small and medium-sized enterprises and making lending decisions, current evaluation methods have the problem of not accurately reflecting the actual vitality and activity of the company. In particular, there is a lack of means to properly evaluate the state of a company's internal communication, making it difficult for financial institutions to make appropriate decisions when providing loans. This can result in an inaccurate evaluation that reflects the vitality of the company, and can delay appropriate lending decisions.

[0102] 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.

[0103] In this invention, the server includes: a means for the terminal to collect data using a communication application; a means for the server to receive data sent from the terminal and extract positive and negative words using natural language processing (NLP) technology; a means for the server to calculate the total number of messages and the reply speed; a means for the server to calculate a company's vitality score using a generating AI; and a means for the server to store the calculated vitality score in a database and provide it to financial institutions via an API. This enables detailed analysis of a company's internal communication data and accurately evaluates the company's vitality and activity. As a result, financial institutions can make more appropriate lending decisions and efficiently support the growth of small and medium-sized enterprises.

[0104] A "terminal" is a device that runs communication applications and is used by a user in their daily work.

[0105] "Data" refers to information collected from communication applications, including message content, sent date and time, received date and time, total number of messages, frequency of occurrence of positive and negative words, and the like.

[0106] A "server" is a central computing device that receives data sent from the terminals and performs analysis and scoring.

[0107] "Natural language processing (NLP) technology" is a technology that analyzes the meaning and context of text data and extracts specific elements such as positive and negative words.

[0108] "Positive and negative words" are important keywords in assessing the vitality and vibrancy of a company in the content of a message, and are words that indicate the positive or negative state of a company's communication.

[0109] "Total Messages" means the total number of all Messages sent within a specified period of time.

[0110] "Reply speed" is the average time it takes for a reply to be sent after a message is sent.

[0111] "Generative AI" is a system that uses artificial intelligence technology to analyze data and calculate a company's vitality score based on a certain algorithm.

[0112] The "vitality score" is a numerical representation of a company's communication activity and vitality, and serves as a reference index for financial institutions when making lending decisions.

[0113] A "database" is a digital storage device where the server stores analysis results and vitality scores.

[0114] "API" stands for Application Program Interface, a specification and protocol for exchanging data between servers and financial institution systems.

[0115] A "financial institution" is a financial service provider such as a bank or money lender that provides loans to companies.

[0116] The system of the present invention uses AI to analyze usage data of internal communication applications of small and medium-sized enterprises, and calculates a vitality score for the company based on the results.Furthermore, this score is provided to financial institutions to support their evaluation and lending decisions.

[0117] Hardware and software used

[0118] Hardware

[0119] Terminal: A device used by a company's personnel that runs internal communication applications.

[0120] Server: The central computing device that performs data analysis and scoring.

[0121] Database: Connected to the server, it stores data and analysis results.

[0122] software

[0123] Internal communication applications: Applications for communicating within a company.

[0124] Generative AI model: An artificial intelligence model for analyzing data and calculating vitality scores.

[0125] Natural Language Processing (NLP) technology: Technology that analyzes message content and extracts positive and negative words.

[0126] API: An interface for financial institutions to obtain health scores.

[0127] Specific data processing and calculation

[0128] 1. Data Collection

[0129] The terminal collects the following data from the communications made by the user through the internal communication application:

[0130] Message content

[0131] The date and time the message was sent and received

[0132] Total number of messages

[0133] Frequency of positive and negative words

[0134] 2. Data Transmission

[0135] The terminal periodically transmits the collected data to the server.

[0136] 3. Data Receipt and Storage

[0137] The server receives the data sent from the terminal and stores it in a database.

[0138] 4. Natural Language Processing (NLP)

[0139] The server analyzes the received message content using NLP technology and extracts positive and negative words.

[0140] 5. Calculating statistical data

[0141] The server calculates the total number of messages and reply speed from the analyzed data.

[0142] 6. Calculating vitality score

[0143] The server calculates a company's vitality score using a generative AI model based on NLP analysis results and statistical data.

[0144] 7. Saving to the database

[0145] The server stores the calculated vitality score in a database.

[0146] 8. API Provision

[0147] The server provides financial institutions with the ability to obtain vitality scores via an API.

[0148] Specific examples

[0149] For example, if Company A uses an internal communication application to communicate on a daily basis, the chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[0150] Number of positive words: 250

[0151] Number of negative words: 50

[0152] Total number of messages: 1000

[0153] Average response time: 2 hours

[0154] Based on this data, the generative AI model calculates a vitality score for Company A of 85. This score is stored in a database and made available to financial institutions via API. Financial institutions then use the obtained vitality score to make loan decisions for Company A.

[0155] Example prompts

[0156] Please collect one month's worth of internal communication data from Company A and send it to the server, including message content, sent date and time, received date and time, positive words, negative words, and total number of messages.

[0157] Analyze the communication data of Company A, extract positive and negative words, and calculate a vitality score based on the total number of messages and the speed of replies.

[0158] "Get Company A's Vitality Score from the API and verify that this score meets the lending criteria. Evaluate other financial data as well, if necessary."

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1:

[0161] A user communicates business-related information using an internal communication application within a company. For example, the user sends a message saying, "The meeting was good." The terminal collects the content of the message sent by the user, the date and time, the date and time it was received, the total number of messages, and the occurrence of positive and negative words. In this case, the terminal collects the message content "The meeting was good" and the date and time it was sent, and counts the positive word "good."

[0162] Input: The message sent by the user

[0163] Output: Collected message content, date and time, and frequency of positive and negative words

[0164] Step 2:

[0165] The device periodically transmits the collected data to the server. Specifically, the device periodically transfers the message content, the date and time of sending, the date and time of receiving, the total number of messages, and the frequency of occurrence of positive and negative words to the server.

[0166] Input: Data collected on the device

[0167] Output: Data sent to the server

[0168] Step 3:

[0169] The server receives the data sent from the terminal and stores it in a database. The server saves the collected message content, the sending date and time, the receiving date and time, the total number of messages, and the frequency of occurrence of positive and negative words in the database.

[0170] Input: Data sent from the terminal

[0171] Output: Data stored in the database

[0172] Step 4:

[0173] The server uses NLP technology to analyze the message content stored in the database. Specifically, the server analyzes the received message content and extracts positive and negative words. For example, the server recognizes and counts the positive word "good" from the message "The meeting was good."

[0174] Input: Message content stored in the database

[0175] Output: Extracted positive and negative words

[0176] Step 5:

[0177] The server calculates the total number of messages and the reply rate. For example, the server calculates that the total number of messages sent in a month is 1000, and the average reply rate is 2 hours.

[0178] Input: The sent and received dates and times of messages stored in the database

[0179] Output: Calculated total number of messages and reply rate

[0180] Step 6:

[0181] The server uses a generative AI model based on the NLP analysis results and statistical data to calculate a company's vitality score. For example, if the number of positive words appearing is 250 and the number of negative words appearing is 50, the generative AI will use this data to calculate a vitality score of 85.

[0182] Input: extracted positive and negative words, calculated statistics

[0183] Output: Company Vitality Score

[0184] Step 7:

[0185] The server stores the calculated vitality score in a database.

[0186] Input: Calculated vitality score

[0187] Output: Vitality scores stored in a database

[0188] Step 8:

[0189] The server provides the calculated vitality score to financial institutions via API. Financial institutions obtain the company's vitality score from the API and make lending decisions based on this score.

[0190] Input: Saved Vitality Score

[0191] Output: Vitality score provided through the API

[0192] (Application example 1)

[0193] 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."

[0194] Communication within industrial facilities is important for improving productivity and the working environment, but there is a lack of means to objectively evaluate and manage the quality of communication between workers. This can lead to a decline in productivity and a deterioration in the working environment. The purpose of this invention is to solve this problem by proposing a system that analyzes communication data within industrial facilities and calculates and provides a vitality score for the industrial facility based on the results.

[0195] 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.

[0196] In this invention, the server includes a means for analyzing usage data of internal communication applications in an industrial facility using a generating AI, a means for calculating a vitality score of the industrial facility based on the results of the analysis of the usage data, and a means for providing the vitality score to a manager, thereby enabling an objective evaluation of the quality of communication within the industrial facility and improving productivity and the working environment.

[0197] "Generative AI" is an artificial intelligence technology that analyzes usage data from internal communication applications and extracts insights from the data.

[0198] An "industrial facility" is a place where manufacturing or production activities are carried out and where many workers and machinery are in operation.

[0199] An "internal communications application" is a software tool that enables communication between workers within an industrial facility, helping them send and receive messages and share information.

[0200] "Usage data" refers to data such as message content, sending date and time, receiving date and time, and total number of messages generated in the process of using an internal communication application.

[0201] The "Vibrancy Score" is a numerical representation of the quality of communication and worker activity within an industrial facility, calculated based on the frequency of positive and negative words, the total number of messages, and the speed of replies.

[0202] A "manager" is a person or position that supervises the operation of industrial facilities and the working conditions of workers, and works to improve productivity and the working environment.

[0203] "Positive words" are words with positive or forward-looking meanings that are included in the message content of an internal communication application.

[0204] "Negative words" are words with negative or backward meanings that are included in the message content of an internal communication application.

[0205] "Analysis" is the process of processing usage data from internal communication applications and extracting useful information and patterns from it.

[0206] "Providing" is the act of calculating the vitality score and then transmitting the result to the administrator or related parties.

[0207] This invention relates to a system that collects and analyzes communication data between workers within an industrial facility and uses generative AI to calculate and provide a vitality score for the industrial facility.

[0208] Program processing explanation

[0209] First, the terminal collects usage data, such as message content, sent and received dates and times, and total number of messages, via internal communication applications used within the industrial facility. This terminal is a device used daily by workers and transmits this data to a server in real time.

[0210] The server stores the received usage data in a database and analyzes the message content using TextBlob and other natural language processing (NLP) libraries. Specifically, it extracts positive and negative words from the message content and calculates their frequency. It also calculates statistical data such as the total number of messages and reply speed.

[0211] The server then calculates the industrial facility's vitality score based on the analysis results. This score is calculated based on the frequency of positive and negative words, the total number of messages, and the response speed. The calculated vitality score is provided to the administrator via an API.

[0212] Specific hardware used includes computer terminals, network equipment, and servers in industrial facilities, and software used includes Python, TextBlob (a natural language processing library), and a database management system (e.g., MySQL®).

[0213] Specific examples

[0214] For example, when a worker in an industrial facility sends a message such as "Great job!" or "I'm happy with my performance on the assembly line," the device collects these messages and sends them to the server. The server then analyzes the message content using TextBlob and extracts positive words. Specifically, words such as "great" and "satisfied" are recognized as positive words.

[0215] Based on these analysis results, the server calculates a high vitality score for the industrial facility. At the same time, the total number of messages and average response time are also taken into account as evaluation factors. The calculated vitality score is provided to the administrator via API, and the administrator can use this to consider measures to improve the working environment and productivity throughout the facility.

[0216] Prompt Sentence Examples

[0217] Analyze internal communication data within an industrial facility and calculate a vitality score. For example, the following data is available:

[0218] Message: "Great job!"

[0219] Sent date and time: "2023-01-01 10:00:00"

[0220] Total number of messages: 100

[0221] Calculate a vitality score based on the analysis results and suggest areas for improvement.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] The terminal collects messages sent by workers within an industrial facility using an internal communication application. Specifically, it collects data such as message content, the date and time of sending, the date and time of receiving, and the total number of messages. This data is temporarily stored in the terminal. The input of this step is the message sent by the worker, and the output is the collected message data.

[0225] Step 2:

[0226] The terminal periodically sends the collected message data to the server. This data is transferred to the server via the network and stored in a database on the server. The input of this step is the message data collected by the terminal, and the output is the message data sent to the server.

[0227] Step 3:

[0228] The server stores the received message data in a database. Using a database management system (e.g., MySQL), the server saves detailed information such as the sending date and time, the receiving date and time, and the message content in the database. The input to this step is the message data sent from the terminal, and the output is the message data stored in the database.

[0229] Step 4:

[0230] The server analyzes the stored message content using a natural language processing (NLP) library such as TextBlob. It extracts positive and negative words from the message content and calculates their frequency. The input to this step is the message content stored in the database, and the output is frequency data for positive and negative words.

[0231] Step 5:

[0232] The server calculates statistical data such as the total number of messages and reply speed. Specifically, it calculates the average message sending speed, reply speed, total number of messages, etc., and stores them as the respective statistical data. The input to this step is the message sending and receiving information stored in the database, and the output is the calculated statistical data.

[0233] Step 6:

[0234] The server calculates the industrial facility's vitality score based on the extracted positive and negative word frequency data and the calculated statistical data. A scoring algorithm is used to quantify the positive and negative elements and calculate an overall score. The input for this step is the positive and negative word frequency data and statistical data, and the output is the vitality score.

[0235] Step 7:

[0236] The server provides the calculated vitality score to the administrator via API. The administrator considers measures to improve the working environment and productivity in the industrial facility based on the provided vitality score. The input of this step is the calculated vitality score, and the output is the vitality score provided to the administrator.

[0237] 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.

[0238] The system of the present invention uses a generative AI to analyze usage data from an SME's internal communication application, and then combines this with an emotion engine that recognizes user emotions to calculate a company's vitality score. This vitality score is provided to financial institutions to assist in evaluating the company and making lending decisions. Below, we will explain in detail how this system is implemented.

[0239] Overall system configuration

[0240] This system consists of the following components:

[0241] Terminals (devices running internal corporate communication applications)

[0242] Server (performs data analysis, emotion recognition and scoring)

[0243] Emotion engine (analyzes the user's emotional state)

[0244] Financial institution systems (using scores to evaluate and make lending decisions)

[0245] Terminal functions

[0246] The device runs an internal communication application that is used daily by company employees. Users communicate through this application for business purposes. A monitoring tool installed on the device runs in the background and collects the following data:

[0247] Message content

[0248] Message sending and receiving timestamps

[0249] Total number of messages

[0250] Frequency of positive and negative words

[0251] The collected data is encrypted and sent to a server.

[0252] Server-side features

[0253] The server receives the data sent from the device, stores it in a database, and then analyzes the data using generative AI and an emotion engine.

[0254] 1. Analysis using natural language processing (NLP)

[0255] The server's generation AI automatically extracts positive and negative words from the message content and calculates their frequency.

[0256] 2. Emotion Recognition by Emotion Engine

[0257] An emotion engine on the server analyzes the message content and determines the user's emotional state.

[0258] The emotion engine classifies the user's emotions into multiple categories (e.g., joy, sadness, anger, surprise, etc.).

[0259] 3. Calculating statistical data

[0260] Calculate statistics such as total number of messages, reply rate, etc.

[0261] 4. Calculating the vitality score

[0262] The server's scoring algorithm calculates a company's vitality score based on the results of NLP analysis, the results of the emotion engine, and statistical data.

[0263] The generated vitality score is stored in a database and made available to financial institutions via an API.

[0264] Functions of financial institution systems

[0265] Financial institutions' systems obtain a company's vitality score through the API. Financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions. Specific usage methods are as follows:

[0266] The vitality score of companies that have applied for loans is retrieved and displayed via API.

[0267] Based on the score obtained, we check whether the company's vitality meets certain standards.

[0268] Evaluate alongside traditional financial data, as appropriate.

[0269] Specific examples

[0270] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[0271] Number of positive words: 300

[0272] Number of negative words: 60

[0273] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[0274] Total number of messages: 1200

[0275] Average response time: 1.5 hours

[0276] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff uses this score to review whether to grant additional financing to Company A.

[0277] As described above, this invention utilizes generative AI and an emotion engine to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the actual vitality of a company, and is expected to lead to more appropriate lending decisions.

[0278] The processing flow will be explained below.

[0279] Step 1:

[0280] When users communicate with each other through internal company communications applications, data such as the content of messages exchanged, timestamps of messages sent and received, and response speeds are recorded in real time.

[0281] Step 2:

[0282] The monitoring tool installed on the device collects data from internal communication applications at regular intervals, organizes it, encrypts it, and sends it to a server, including the content of messages and the frequency of exchanges.

[0283] Step 3:

[0284] The server stores the received data in a database for analysis, organized by company and stored in an efficiently accessible format.

[0285] Step 4:

[0286] The server's generated AI uses the stored data to perform natural language processing (NLP) analysis, extracting positive and negative words from the message content and recording their frequency.

[0287] Step 5:

[0288] The server's emotion engine determines the user's emotional state from the message content in parallel with NLP analysis. The emotion engine classifies the message content into multiple emotion categories (e.g., joy, sadness, anger, surprise, etc.) and calculates the proportion of each category.

[0289] Step 6:

[0290] The server also calculates statistics such as message totals and reply speeds, for example, reply speed is calculated as the average time it takes for each message to be replied to after it has been sent.

[0291] Step 7:

[0292] Based on the analysis results of the generative AI and emotion engine, as well as statistical data, the server's scoring algorithm calculates a company's vitality score, which is a numerical representation of a company's vitality and activity, expressed on a scale of 0 to 100, for example.

[0293] Step 8:

[0294] The generated vitality scores are stored in a database on the server, and an API is provided to make them accessible to financial institutions, who can then inquire about the company's score via this API.

[0295] Step 9:

[0296] The financial institution's system obtains a company's vitality score via the API, which is then used by financial institution personnel to evaluate the company and make lending decisions.

[0297] Step 10:

[0298] Financial institutions send feedback data on actual loan results and corporate performance back to the server, which then uses this feedback to adjust the AI ​​and scoring algorithm to improve the accuracy of future scores.

[0299] As a result, users, terminals, servers, and financial institutions can work together to build an evaluation system that reflects the dynamism of small and medium-sized enterprises, and support optimal lending decisions.

[0300] Example 2

[0301] 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."

[0302] It has been difficult with conventional technology to quantify a company's vitality and employee emotions and use that information to support financial institutions in making lending decisions. Small and medium-sized enterprises, in particular, lack effective means of analyzing information obtained from daily business communications, making it difficult to accurately assess the actual emotional state of employees and the company's vitality.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0304] In this invention, the server includes: means for collecting the content, timestamp, total number, and frequency of positive and negative words in messages sent by users through the company's internal communication application; means for encrypting the collected data and transmitting it to the server; means for the server to receive the encrypted data and store it in a database; means for automatically analyzing the frequency of positive and negative words from the message content using a generative AI model; means for analyzing the user's emotional state and classifying it into multiple emotional categories using an emotion engine; means for calculating statistical information such as the total number of messages and reply speed; means for calculating a company vitality score based on the analysis results and statistical data obtained from the generative AI model and the emotion engine; and means for storing the calculated vitality score in a database and providing it to financial institutions via an API. This allows for accurate evaluation of a company's vitality and employee emotions, enabling financial institutions to make more appropriate lending decisions based on the results.

[0305] A "terminal" is a device on which a company's internal communication application runs, and is a device with which users conduct daily business communications.

[0306] "Server" is a central computing unit for storing collected data and analyzing the data using generative AI models and emotion engines.

[0307] "User" refers to an employee who uses a company's internal communication application to communicate for business purposes.

[0308] A "generative AI model" is an artificial intelligence model based on machine learning that analyzes text data and calculates the frequency of positive and negative words.

[0309] An "emotion engine" is software or algorithm that analyzes the content of a message to determine the user's emotional state and classify it into multiple emotional categories.

[0310] The "vitality score" is a quantified score that measures a company's vitality and the mental state of its employees based on the analysis results of the generative AI model and emotion engine, as well as other statistical data.

[0311] "Data collection means" refers to a system configuration for collecting message content, timestamps, total number of messages, and frequency of positive and negative words from a company's internal communication applications.

[0312] "Data transmission means" refers to the protocols and procedures for encrypting collected data and transmitting it securely to the server.

[0313] "Data storage means" refers to a system configuration that stores data received by the server in a database in an appropriate format so that it can be analyzed later.

[0314] An "API" is an interface that other systems can access programmatically, and is a means for providing health scores to financial institutions' systems.

[0315] "Statistical information" is data used to quantitatively evaluate the usage of a company's internal communication applications, such as the total number of messages and response speed.

[0316] The present invention is a system that evaluates the vitality of a company based on data obtained using the company's internal communication application and provides the results to financial institutions. How this system is implemented will be described in detail below.

[0317] Terminal functions

[0318] The device is a device that runs an internal communication application used by company employees on a daily basis. When a user communicates through this application, a monitoring tool installed on the device runs in the background and collects the following data:

[0319] Message content

[0320] Message sending and receiving timestamps

[0321] Total number of messages

[0322] Frequency of positive and negative words

[0323] The collected data is encrypted and sent to a server over the company's internal network.

[0324] Server-side features

[0325] The server receives the data sent from the device and stores it in a database. The server analyzes the data using the following software and algorithms:

[0326] Natural Language Processing (NLP): Generative AI models such as BERT (Bidirectional Encoder Representations from Transformers) are used to automatically extract positive and negative words from message content and calculate their frequency.

[0327] Emotion Engine: Analyzes message content to determine the user's emotional state. The emotion engine uses a text-based emotion analysis algorithm to classify emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[0328] Calculating statistics: Software for calculating statistics such as total number of messages and reply speed.

[0329] Based on these analysis results, the server uses a scoring algorithm to calculate a company's vitality score, which is then stored in a database and made available to financial institutions via API.

[0330] Financial institution system functions

[0331] Financial institutions' systems receive a company's vitality score through the API, and financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions.

[0332] Specific examples

[0333] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[0334] Number of positive words: 300

[0335] Number of negative words: 60

[0336] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[0337] Total number of messages: 1200

[0338] Average response time: 1.5 hours

[0339] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to the financial institution's system, and the financial institution's staff uses this score to review whether to grant additional loans to Company A.

[0340] Example prompts for generative AI models

[0341] For example, by inputting a prompt such as "I would like the company's overall vitality score calculated based on last month's employee communication data" into the generative AI model, the process of automatically calculating the company's vitality score will be carried out.

[0342] The above is a specific embodiment of the present invention. The present invention utilizes generative AI and an emotion engine to evaluate a company's vitality and dynamism, supporting financial institutions in making lending decisions. This enables more accurate evaluations that reflect a company's actual vitality, and is expected to lead to more appropriate lending decisions.

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] Step 1:

[0345] Data collection

[0346] Input: Message content sent by a user through a company's internal communication application.

[0347] How it works: A monitoring tool installed on the device collects message content, timestamps, total number of messages, and frequency of positive and negative words.

[0348] Data processing: Organizing and structuring the collected data.

[0349] Output: Structured and organized data (message content, timestamps, positive word frequencies, negative word frequencies, etc.).

[0350] Step 2:

[0351] Data transmission

[0352] Input: The data collected and structured in Step 1.

[0353] How it works: The device encrypts the data and sends it to the server over the company's internal network (e.g., TLS protocol).

[0354] Data processing: Data encryption and transmission.

[0355] Output: The encrypted data sent to the server.

[0356] Step 3:

[0357] Data storage

[0358] Input: The encrypted data received by the server.

[0359] What it does: The server decrypts the data it receives and stores it in a database.

[0360] Data calculation: Decrypt the data and store it in the database.

[0361] Output: Decrypted data stored in a database.

[0362] Step 4:

[0363] Natural Language Processing (NLP) Analysis

[0364] Input: Message content stored in the database.

[0365] How it works: A generative AI model on the server analyzes message content and calculates the frequency of positive and negative words.

[0366] Data calculation: Word frequency calculation through text analysis (example model: BERT).

[0367] Output: Positive and negative word frequency data.

[0368] Step 5:

[0369] Emotion recognition by emotion engine

[0370] Input: Message content data obtained in step 4.

[0371] How it works: The server's emotion engine analyzes the user's emotional state and classifies emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[0372] Data Computing: Sentiment Classification through Sentiment Analysis Algorithms.

[0373] Output: Distribution data for each emotion category.

[0374] Step 6:

[0375] Statistical Data Calculations

[0376] Input: Analysis results from the previous stage, total number of messages, reply speed, etc.

[0377] How it works: The server calculates statistics such as message totals, reply speed, etc.

[0378] Data calculation: Statistical calculations (total number of messages, average reply speed, etc.).

[0379] Output: Statistics data.

[0380] Step 7:

[0381] Calculating vitality score

[0382] Input: Analysis results of natural language processing and emotion engine, statistical data.

[0383] How it works: The server's scoring algorithm calculates a vitality score based on these inputs.

[0384] Data calculation: Comprehensive evaluation using a scoring algorithm.

[0385] Output: Company Vitality Score.

[0386] Step 8:

[0387] Providing scores

[0388] Input: Vitality score calculated in step 7.

[0389] How it works: The server stores the vitality score in a database and makes it available to financial institutions via an API.

[0390] Data Computing: Managing API endpoints and providing data.

[0391] Output: Vitality score provided to financial institutions.

[0392] The above are the specific processing steps and detailed operations for implementing the invention. By explaining the data input and output at each step and the specific operations, the flow of the entire system becomes clear, enabling the invention to be implemented effectively.

[0393] (Application example 2)

[0394] 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."

[0395] Conventional factory performance evaluations rely primarily on mechanical data and human intuition, making it difficult to accurately evaluate the overall health and work efficiency of the factory. This invention solves this problem by comprehensively analyzing the operation data of robots in the factory and the message data of workers, and quantitatively evaluating the overall factory performance based on the results.

[0396] 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 analyzing operation data and message data within the factory using a generation AI, means for calculating a performance score based on the analysis results of the operation data and message data, and means for providing the performance score to the management system. This makes it possible to accurately evaluate the health status and work efficiency of the entire factory and derive appropriate maintenance and work environment improvement measures.

[0397] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data.

[0398] "Operational data" refers to operational information such as the operating status of robots and machines in a factory and the frequency of errors.

[0399] "Message data" refers to text messages and communications exchanged between workers and staff within a factory.

[0400] The "performance score" is an overall evaluation index calculated based on the operation data and message data of robots and workers in the factory.

[0401] A "management system" is an information system for operating and managing a factory, and its role is to integrate, display, and manage data such as performance scores.

[0402] The system of the present invention uses generative AI to analyze motion data and message data to evaluate the performance of robots and workers in a factory, and calculates a performance score from the results. This system consists of the following components:

[0403] Overall system configuration

[0404] 1. Server:

[0405] The server plays a central role in analyzing the data using generative AI and emotion engines.

[0406] For actual data analysis, we use the NLPProcessor, which performs natural language processing (NLP), and the EmotionEngine, which performs emotion recognition.

[0407] 2. Terminal:

[0408] The terminal is responsible for collecting operational data and message data from various sensors and communication devices within the factory.

[0409] The data collected by the device is encrypted and sent to the server.

[0410] 3. Management system:

[0411] The management system provides an interface to visualize evaluation results such as performance scores and support appropriate measures.

[0412] Program Description

[0413] 1. Data Collection:

[0414] Operational data such as operating time and frequency of errors is collected from robots in factories.

[0415] Message data is collected from workers through an internal communication application.

[0416] The collected data is sent to a server via the terminal.

[0417] 2. Data Analysis:

[0418] The server uses the NLPProcessor to analyze the message data and calculate the frequency of occurrence of positive and negative words.

[0419] At the same time, the Emotion Engine is used to analyze the emotional state of the worker from the message data and calculate an emotion score.

[0420] 3. Calculation of Performance Score:

[0421] The server integrates the collected motion data and emotion data to calculate a performance score.

[0422] The performance score is a quantitative assessment of the overall health and work efficiency of the factory.

[0423] 4. Providing results:

[0424] The calculated performance scores are provided to the management system so that factory managers can easily view them.

[0425] Based on this information, appropriate measures can be taken to maintain the robot and improve the working environment.

[0426] Specific examples

[0427] For example, suppose the following data is collected at a factory:

[0428] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[0429] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[0430] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[0431] Based on this data, a performance score was calculated, resulting in a score of 70. This information was notified to managers and used as a reference for taking measures to maintain the robot and improve the working environment.

[0432] Example of input prompt for generative AI model

[0433] "Based on the factory robot's operational data and the messages from the workers, please calculate and report an overall score. Use the following data."

[0434] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[0435] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[0436] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[0437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0438] Step 1:

[0439] This system collects operation data and message data from robots and workers in the factory. The terminal acquires data from the internal communication applications of each robot and worker, encrypts this data, and sends it to the server. For example, the system collects information such as the robot's operating time, error rate, and messages exchanged by workers via the internal communication application. The input is the robot and worker data, and the output is encrypted data sent to the server.

[0440] Step 2:

[0441] The server stores the received operation data and message data in a database. The server receives encrypted data sent from the terminal, decrypts it to its original format, and stores it in the database. The input is the encrypted data, and the output is the format stored in the database.

[0442] Step 3:

[0443] The server analyzes message data using an NLPProcessor. The NLPProcessor extracts positive and negative words from the message and calculates their frequency of occurrence. The input is the message data, and the output is the frequency of occurrence of positive and negative words. Specifically, the words in the message are tokenized, classified into positive and negative categories using a synonym dictionary, and the frequency of occurrence is counted.

[0444] Step 4:

[0445] The server uses the Emotion Engine to analyze the emotional state from the message data. The Emotion Engine analyzes the message data and calculates an emotional score such as joy, sadness, or anger. The input is the message data, and the output is the emotional score. Specifically, it receives the message text as input, assigns an emotional label using a pre-trained model, and calculates a probability score for each emotion.

[0446] Step 5:

[0447] The server calculates a performance score based on the operational data and emotional score. The operational data (e.g., uptime, error rate) and emotional score (e.g., 40% joy) are integrated and weighted to calculate a performance score as an overall evaluation. The input is the operational data and emotional score, and the output is the performance score. Specifically, the server normalizes various data and calculates an overall score based on a pre-set evaluation algorithm.

[0448] Step 6:

[0449] The server provides the calculated performance scores to the management system. The management system visualizes the provided performance scores and displays them via an interface so that factory managers can view them. The input is the performance scores, and the output is the visualized evaluation results. Specifically, the performance scores are displayed on the management system's dashboard, and appropriate actions are suggested based on the results.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] [Second embodiment]

[0454] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0455] 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.

[0456] 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).

[0457] 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.

[0458] 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.

[0459] 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).

[0460] 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. 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] In the smart glasses 214, the 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.

[0465] 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."

[0466] The system of this invention uses generative AI to analyze usage data from internal communication applications of small and medium-sized enterprises, and builds a unique scoring model based on the results. This provides financial institutions with a company vitality score, supporting their evaluation and lending decisions. The system is composed of the following processing flow and components.

[0467] Overall system configuration

[0468] The overall configuration of this system mainly consists of the following components:

[0469] Terminals (devices running internal corporate communication applications)

[0470] Server (performs data analysis and scoring)

[0471] Financial institution systems (using scores to evaluate and make lending decisions)

[0472] Terminal functions

[0473] The device runs an internal communication application that company personnel use on a daily basis. Users use this application to communicate for business purposes. During this time, a dedicated monitoring tool runs in the background and collects the following data:

[0474] Message content

[0475] The date and time the message was sent and received

[0476] Total number of messages

[0477] Positive and negative words

[0478] The collected data is automatically sent to a server.

[0479] Server-side features

[0480] The server receives the usage data of the internal communication application sent from the device and stores it in a database.The server then uses the generation AI to perform the following analysis.

[0481] 1. Use natural language processing (NLP) techniques to extract positive and negative words from message content.

[0482] 2. Calculate statistics such as total number of messages and response speed.

[0483] 3. Based on these analysis results, a company's vitality score is calculated.

[0484] The generated vitality score is calculated based on a scoring algorithm to quantify the vitality and activity of the company. This score is stored in a database and made available to financial institutions via API.

[0485] Financial institution system functions

[0486] The financial institution's system obtains the vitality score for each company through the API. Financial institution personnel use this score to make lending decisions. Specific methods of use are as follows:

[0487] Obtain a vitality score for companies that apply for loans.

[0488] Check whether the score meets certain criteria.

[0489] If necessary, we will evaluate it comprehensively in conjunction with other financial data.

[0490] Specific examples

[0491] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[0492] Number of positive words: 250

[0493] Number of negative words: 50

[0494] Total number of messages: 1000

[0495] Average response time: 2 hours

[0496] Based on this data, the generative AI calculates a vitality score of 85 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff member uses this score to review whether to grant additional financing to Company A.

[0497] As described above, this invention utilizes generative AI to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the vitality of a company, and is expected to lead to more appropriate lending decisions.

[0498] The processing flow will be explained below.

[0499] Step 1:

[0500] When users communicate for business purposes using an internal communication application within a company (e.g., a business messaging app), data such as the content of the conversation, the time the message was sent, the time it was received, and the speed of the reply are automatically recorded.

[0501] Step 2:

[0502] A dedicated monitoring tool installed on the device periodically collects data from internal communication applications, organizes it, encrypts it, and sends it to a server, including the content of messages, timestamps of messages sent and received, and the total number of messages.

[0503] Step 3:

[0504] The server stores the received data in a database for analysis. The data is stored in a database management system (DBMS) in a format that can be efficiently accessed by each company.

[0505] Step 4:

[0506] The server's generation AI performs natural language processing (NLP) based on the collected data. Specifically, it analyzes the content of messages to detect positive words (e.g., "great," "thank you") and negative words (e.g., "problem," "trouble") and calculates their frequency.

[0507] Step 5:

[0508] The server also calculates statistics such as the total number of messages and reply speed, which refers to the average time it takes for a message to be replied to after it is sent.

[0509] Step 6:

[0510] The server's scoring algorithm calculates a company's vitality score based on the NLP analysis results and statistical information. The vitality score is a numerical representation of a company's vitality and energy, ranging from 0 to 100.

[0511] Step 7:

[0512] The server stores this vitality score in a database and makes it accessible to financial institutions. It also provides an API for retrieving the score, which financial institutions can use to obtain the necessary information.

[0513] Step 8:

[0514] Financial institutions' systems obtain a company's vitality score through the API, and financial institution personnel use the score in combination with other financial data to evaluate the company and make lending decisions.

[0515] Step 9:

[0516] Financial institutions provide the server with feedback data on actual loan results and company performance, which the server uses to make adjustments to improve the accuracy of the scoring algorithm.

[0517] Step 10:

[0518] The server's generation AI continuously improves its algorithm based on feedback data, improving the accuracy of the vitality score assessment, thereby improving the performance and reliability of the entire system.

[0519] The above steps will realize a system that analyzes usage data of a company's internal communication applications and evaluates the company's vitality. This system will be a valuable tool for financial institutions in making lending decisions.

[0520] Example 1

[0521] 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."

[0522] When evaluating small and medium-sized enterprises and making lending decisions, current evaluation methods have the problem of not accurately reflecting the actual vitality and activity of the company. In particular, there is a lack of means to properly evaluate the state of a company's internal communication, making it difficult for financial institutions to make appropriate decisions when providing loans. This can result in an inaccurate evaluation that reflects the vitality of the company, and can delay appropriate lending decisions.

[0523] 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.

[0524] In this invention, the server includes: a means for the terminal to collect data using a communication application; a means for the server to receive data sent from the terminal and extract positive and negative words using natural language processing (NLP) technology; a means for the server to calculate the total number of messages and the reply speed; a means for the server to calculate a company's vitality score using a generating AI; and a means for the server to store the calculated vitality score in a database and provide it to financial institutions via an API. This enables detailed analysis of a company's internal communication data and accurately evaluates the company's vitality and activity. As a result, financial institutions can make more appropriate lending decisions and efficiently support the growth of small and medium-sized enterprises.

[0525] A "terminal" is a device that runs communication applications and is used by a user in their daily work.

[0526] "Data" refers to information collected from communication applications, including message content, sent date and time, received date and time, total number of messages, frequency of occurrence of positive and negative words, and the like.

[0527] A "server" is a central computing device that receives data sent from the terminals and performs analysis and scoring.

[0528] "Natural language processing (NLP) technology" is a technology that analyzes the meaning and context of text data and extracts specific elements such as positive and negative words.

[0529] "Positive and negative words" are important keywords in assessing the vitality and vibrancy of a company in the content of a message, and are words that indicate the positive or negative state of a company's communication.

[0530] "Total Messages" means the total number of all Messages sent within a specified period of time.

[0531] "Reply speed" is the average time it takes for a reply to be sent after a message is sent.

[0532] "Generative AI" is a system that uses artificial intelligence technology to analyze data and calculate a company's vitality score based on a certain algorithm.

[0533] The "vitality score" is a numerical representation of a company's communication activity and vitality, and serves as a reference index for financial institutions when making lending decisions.

[0534] A "database" is a digital storage device where the server stores analysis results and vitality scores.

[0535] "API" stands for Application Program Interface, a specification and protocol for exchanging data between servers and financial institution systems.

[0536] A "financial institution" is a financial service provider such as a bank or money lender that provides loans to companies.

[0537] The system of the present invention uses AI to analyze usage data of internal communication applications of small and medium-sized enterprises, and calculates a vitality score for the company based on the results.Furthermore, this score is provided to financial institutions to support their evaluation and lending decisions.

[0538] Hardware and software used

[0539] Hardware

[0540] Terminal: A device used by a company's personnel that runs internal communication applications.

[0541] Server: The central computing device that performs data analysis and scoring.

[0542] Database: Connected to the server, it stores data and analysis results.

[0543] software

[0544] Internal communication applications: Applications for communicating within a company.

[0545] Generative AI model: An artificial intelligence model for analyzing data and calculating vitality scores.

[0546] Natural Language Processing (NLP) technology: Technology that analyzes message content and extracts positive and negative words.

[0547] API: An interface for financial institutions to obtain health scores.

[0548] Specific data processing and calculation

[0549] 1. Data Collection

[0550] The terminal collects the following data from the communications made by the user through the internal communication application:

[0551] Message content

[0552] The date and time the message was sent and received

[0553] Total number of messages

[0554] Frequency of positive and negative words

[0555] 2. Data Transmission

[0556] The terminal periodically transmits the collected data to the server.

[0557] 3. Data Receipt and Storage

[0558] The server receives the data sent from the terminal and stores it in a database.

[0559] 4. Natural Language Processing (NLP)

[0560] The server analyzes the received message content using NLP technology and extracts positive and negative words.

[0561] 5. Calculating statistical data

[0562] The server calculates the total number of messages and reply speed from the analyzed data.

[0563] 6. Calculating vitality score

[0564] The server calculates a company's vitality score using a generative AI model based on NLP analysis results and statistical data.

[0565] 7. Saving to the database

[0566] The server stores the calculated vitality score in a database.

[0567] 8. API Provision

[0568] The server provides financial institutions with the ability to obtain vitality scores via an API.

[0569] Specific examples

[0570] For example, if Company A uses an internal communication application to communicate on a daily basis, the chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[0571] Number of positive words: 250

[0572] Number of negative words: 50

[0573] Total number of messages: 1000

[0574] Average response time: 2 hours

[0575] Based on this data, the generative AI model calculates a vitality score for Company A of 85. This score is stored in a database and made available to financial institutions via API. Financial institutions then use the obtained vitality score to make loan decisions for Company A.

[0576] Example prompts

[0577] Please collect one month's worth of internal communication data from Company A and send it to the server, including message content, sent date and time, received date and time, positive words, negative words, and total number of messages.

[0578] Analyze the communication data of Company A, extract positive and negative words, and calculate a vitality score based on the total number of messages and the speed of replies.

[0579] "Get Company A's Vitality Score from the API and verify that this score meets the lending criteria. Evaluate other financial data as well, if necessary."

[0580] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0581] Step 1:

[0582] A user communicates business-related information using an internal communication application within a company. For example, the user sends a message saying, "The meeting was good." The terminal collects the content of the message sent by the user, the date and time, the date and time it was received, the total number of messages, and the occurrence of positive and negative words. In this case, the terminal collects the message content "The meeting was good" and the date and time it was sent, and counts the positive word "good."

[0583] Input: The message sent by the user

[0584] Output: Collected message content, date and time, and frequency of positive and negative words

[0585] Step 2:

[0586] The device periodically transmits the collected data to the server. Specifically, the device periodically transfers the message content, the date and time of sending, the date and time of receiving, the total number of messages, and the frequency of occurrence of positive and negative words to the server.

[0587] Input: Data collected on the device

[0588] Output: Data sent to the server

[0589] Step 3:

[0590] The server receives the data sent from the terminal and stores it in a database. The server saves the collected message content, the sending date and time, the receiving date and time, the total number of messages, and the frequency of occurrence of positive and negative words in the database.

[0591] Input: Data sent from the terminal

[0592] Output: Data stored in the database

[0593] Step 4:

[0594] The server uses NLP technology to analyze the message content stored in the database. Specifically, the server analyzes the received message content and extracts positive and negative words. For example, the server recognizes and counts the positive word "good" from the message "The meeting was good."

[0595] Input: Message content stored in the database

[0596] Output: Extracted positive and negative words

[0597] Step 5:

[0598] The server calculates the total number of messages and the reply rate. For example, the server calculates that the total number of messages sent in a month is 1000, and the average reply rate is 2 hours.

[0599] Input: The sent and received dates and times of messages stored in the database

[0600] Output: Calculated total number of messages and reply rate

[0601] Step 6:

[0602] The server uses a generative AI model based on the NLP analysis results and statistical data to calculate a company's vitality score. For example, if the number of positive words appearing is 250 and the number of negative words appearing is 50, the generative AI will use this data to calculate a vitality score of 85.

[0603] Input: extracted positive and negative words, calculated statistics

[0604] Output: Company Vitality Score

[0605] Step 7:

[0606] The server stores the calculated vitality score in a database.

[0607] Input: Calculated vitality score

[0608] Output: Vitality scores stored in a database

[0609] Step 8:

[0610] The server provides the calculated vitality score to financial institutions via API. Financial institutions obtain the company's vitality score from the API and make lending decisions based on this score.

[0611] Input: Saved Vitality Score

[0612] Output: Vitality score provided through the API

[0613] (Application example 1)

[0614] 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."

[0615] Communication within industrial facilities is important for improving productivity and the working environment, but there is a lack of means to objectively evaluate and manage the quality of communication between workers. This can lead to a decline in productivity and a deterioration in the working environment. The purpose of this invention is to solve this problem by proposing a system that analyzes communication data within industrial facilities and calculates and provides a vitality score for the industrial facility based on the results.

[0616] 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.

[0617] In this invention, the server includes a means for analyzing usage data of internal communication applications in an industrial facility using a generating AI, a means for calculating a vitality score of the industrial facility based on the results of the analysis of the usage data, and a means for providing the vitality score to a manager, thereby enabling an objective evaluation of the quality of communication within the industrial facility and improving productivity and the working environment.

[0618] "Generative AI" is an artificial intelligence technology that analyzes usage data from internal communication applications and extracts insights from the data.

[0619] An "industrial facility" is a place where manufacturing or production activities are carried out and where many workers and machinery are in operation.

[0620] An "internal communications application" is a software tool that enables communication between workers within an industrial facility, helping them send and receive messages and share information.

[0621] "Usage data" refers to data such as message content, sending date and time, receiving date and time, and total number of messages generated in the process of using an internal communication application.

[0622] The "vitality score" is a numerical representation of the quality of communication and worker activity within an industrial facility, calculated based on the frequency of positive and negative words, the total number of messages, and the speed of replies.

[0623] A "manager" is a person or position that supervises the operation of industrial facilities and the working conditions of workers, and works to improve productivity and the working environment.

[0624] "Positive words" are words with positive or forward-looking meanings that are included in the message content of an internal communication application.

[0625] "Negative words" are words with negative or backward meanings that are included in the message content of an internal communication application.

[0626] "Analysis" is the process of processing usage data from internal communication applications and extracting useful information and patterns from it.

[0627] "Providing" is the act of calculating the vitality score and then transmitting the result to the administrator or related parties.

[0628] This invention relates to a system that collects and analyzes communication data between workers within an industrial facility and uses generative AI to calculate and provide a vitality score for the industrial facility.

[0629] Program processing explanation

[0630] First, the terminal collects usage data, such as message content, sent and received dates and times, and total number of messages, via internal communication applications used within the industrial facility. This terminal is a device used daily by workers and transmits this data to a server in real time.

[0631] The server stores the received usage data in a database and analyzes the message content using TextBlob and other natural language processing (NLP) libraries. Specifically, it extracts positive and negative words from the message content and calculates their frequency. It also calculates statistical data such as the total number of messages and reply speed.

[0632] The server then calculates the industrial facility's vitality score based on the analysis results. This score is calculated based on the frequency of positive and negative words, the total number of messages, and the response speed. The calculated vitality score is provided to the administrator via an API.

[0633] The specific hardware used includes computer terminals, network equipment, and servers in industrial facilities, and the software used includes Python, TextBlob (a natural language processing library), and a database management system (e.g., MySQL).

[0634] Specific examples

[0635] For example, when a worker in an industrial facility sends a message such as "Great job!" or "I'm happy with my performance on the assembly line," the device collects these messages and sends them to the server. The server then analyzes the message content using TextBlob and extracts positive words. Specifically, words such as "great" and "satisfied" are recognized as positive words.

[0636] Based on these analysis results, the server calculates a high vitality score for the industrial facility. At the same time, the total number of messages and average response time are also taken into account as evaluation factors. The calculated vitality score is provided to the administrator via API, and the administrator can use this to consider measures to improve the working environment and productivity throughout the facility.

[0637] Prompt Sentence Examples

[0638] Analyze internal communication data within an industrial facility and calculate a vitality score. For example, the following data is available:

[0639] Message: "Great job!"

[0640] Sent date and time: "2023-01-01 10:00:00"

[0641] Total number of messages: 100

[0642] Calculate a vitality score based on the analysis results and suggest areas for improvement.

[0643] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0644] Step 1:

[0645] The terminal collects messages sent by workers within an industrial facility using an internal communication application. Specifically, it collects data such as message content, the date and time of sending, the date and time of receiving, and the total number of messages. This data is temporarily stored in the terminal. The input of this step is the message sent by the worker, and the output is the collected message data.

[0646] Step 2:

[0647] The terminal periodically sends the collected message data to the server. This data is transferred to the server via the network and stored in a database on the server. The input of this step is the message data collected by the terminal, and the output is the message data sent to the server.

[0648] Step 3:

[0649] The server stores the received message data in a database. Using a database management system (e.g., MySQL), the server saves detailed information such as the sending date and time, the receiving date and time, and the message content in the database. The input to this step is the message data sent from the terminal, and the output is the message data stored in the database.

[0650] Step 4:

[0651] The server analyzes the stored message content using a natural language processing (NLP) library such as TextBlob. It extracts positive and negative words from the message content and calculates their frequency. The input to this step is the message content stored in the database, and the output is frequency data for positive and negative words.

[0652] Step 5:

[0653] The server calculates statistical data such as the total number of messages and reply speed. Specifically, it calculates the average message sending speed, reply speed, total number of messages, etc., and stores them as the respective statistical data. The input to this step is the message sending and receiving information stored in the database, and the output is the calculated statistical data.

[0654] Step 6:

[0655] The server calculates the industrial facility's vitality score based on the extracted positive and negative word frequency data and the calculated statistical data. A scoring algorithm is used to quantify the positive and negative elements and calculate an overall score. The input for this step is the positive and negative word frequency data and statistical data, and the output is the vitality score.

[0656] Step 7:

[0657] The server provides the calculated vitality score to the administrator via API. The administrator considers measures to improve the working environment and productivity in the industrial facility based on the provided vitality score. The input of this step is the calculated vitality score, and the output is the vitality score provided to the administrator.

[0658] 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.

[0659] The system of the present invention uses a generative AI to analyze usage data from an SME's internal communication application, and then combines this with an emotion engine that recognizes user emotions to calculate a company's vitality score. This vitality score is provided to financial institutions to assist in evaluating the company and making lending decisions. Below, we will explain in detail how this system is implemented.

[0660] Overall system configuration

[0661] This system consists of the following components:

[0662] Terminals (devices running internal corporate communication applications)

[0663] Server (performs data analysis, emotion recognition and scoring)

[0664] Emotion engine (analyzes the user's emotional state)

[0665] Financial institution systems (using scores to evaluate and make lending decisions)

[0666] Terminal functions

[0667] The device runs an internal communication application that is used daily by company employees. Users communicate through this application for business purposes. A monitoring tool installed on the device runs in the background and collects the following data:

[0668] Message content

[0669] Message sending and receiving timestamps

[0670] Total number of messages

[0671] Frequency of positive and negative words

[0672] The collected data is encrypted and sent to a server.

[0673] Server-side features

[0674] The server receives the data sent from the device, stores it in a database, and then analyzes the data using generative AI and an emotion engine.

[0675] 1. Analysis using natural language processing (NLP)

[0676] The server's generation AI automatically extracts positive and negative words from the message content and calculates their frequency.

[0677] 2. Emotion Recognition by Emotion Engine

[0678] An emotion engine on the server analyzes the message content and determines the user's emotional state.

[0679] The emotion engine classifies the user's emotions into multiple categories (e.g., joy, sadness, anger, surprise, etc.).

[0680] 3. Calculating statistical data

[0681] Calculate statistics such as total number of messages, reply rate, etc.

[0682] 4. Calculating the vitality score

[0683] The server's scoring algorithm calculates a company's vitality score based on the results of NLP analysis, the results of the emotion engine, and statistical data.

[0684] The generated vitality score is stored in a database and made available to financial institutions via an API.

[0685] Financial institution system functions

[0686] Financial institutions' systems obtain a company's vitality score through the API. Financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions. Specific usage methods are as follows:

[0687] The vitality score of companies that have applied for loans is retrieved and displayed via API.

[0688] Based on the score obtained, we check whether the company's vitality meets certain standards.

[0689] Evaluate alongside traditional financial data, as appropriate.

[0690] Specific examples

[0691] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[0692] Number of positive words: 300

[0693] Number of negative words: 60

[0694] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[0695] Total number of messages: 1200

[0696] Average response time: 1.5 hours

[0697] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff uses this score to review whether to grant additional financing to Company A.

[0698] As described above, this invention utilizes generative AI and an emotion engine to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the actual vitality of a company, and is expected to lead to more appropriate lending decisions.

[0699] The processing flow will be explained below.

[0700] Step 1:

[0701] When users communicate with each other through internal company communications applications, data such as the content of messages exchanged, timestamps of messages sent and received, and response times are recorded in real time.

[0702] Step 2:

[0703] The monitoring tool installed on the device collects data from internal communication applications at regular intervals, organizes it, encrypts it, and sends it to a server, including the content of messages and the frequency of exchanges.

[0704] Step 3:

[0705] The server stores the received data in a database for analysis, organized by company and stored in an efficiently accessible format.

[0706] Step 4:

[0707] The server's generated AI uses the stored data to perform natural language processing (NLP) analysis, extracting positive and negative words from the message content and recording their frequency.

[0708] Step 5:

[0709] The server's emotion engine determines the user's emotional state from the message content in parallel with NLP analysis. The emotion engine classifies the message content into multiple emotion categories (e.g., joy, sadness, anger, surprise, etc.) and calculates the proportion of each category.

[0710] Step 6:

[0711] The server also calculates statistics such as message totals and reply speeds, for example, reply speed is calculated as the average time it takes for each message to be replied to after it has been sent.

[0712] Step 7:

[0713] Based on the analysis results of the generative AI and emotion engine, as well as statistical data, the server's scoring algorithm calculates a company's vitality score, which is a numerical representation of a company's vitality and activity, expressed on a scale of 0 to 100, for example.

[0714] Step 8:

[0715] The generated vitality scores are stored in a database on the server, and an API is provided to make them accessible to financial institutions, who can then inquire about the company's score via this API.

[0716] Step 9:

[0717] The financial institution's system obtains a company's vitality score via the API, which is then used by financial institution personnel to evaluate the company and make lending decisions.

[0718] Step 10:

[0719] Financial institutions send feedback data on actual loan results and corporate performance back to the server, which then uses this feedback to adjust the AI ​​and scoring algorithm to improve the accuracy of future scores.

[0720] As a result, users, terminals, servers, and financial institutions can work together to build an evaluation system that reflects the dynamism of small and medium-sized enterprises, and support optimal lending decisions.

[0721] Example 2

[0722] 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."

[0723] It has been difficult with conventional technology to quantify a company's vitality and employee emotions and use that information to support financial institutions in making lending decisions. Small and medium-sized enterprises, in particular, lack effective means of analyzing information obtained from daily business communications, making it difficult to accurately assess the actual emotional state of employees and the company's vitality.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0725] In this invention, the server includes: means for collecting the content, timestamp, total number, and frequency of positive and negative words in messages sent by users through the company's internal communication application; means for encrypting the collected data and transmitting it to the server; means for the server to receive the encrypted data and store it in a database; means for automatically analyzing the frequency of positive and negative words from the message content using a generative AI model; means for analyzing the user's emotional state and classifying it into multiple emotional categories using an emotion engine; means for calculating statistical information such as the total number of messages and reply speed; means for calculating a company vitality score based on the analysis results and statistical data obtained from the generative AI model and the emotion engine; and means for storing the calculated vitality score in a database and providing it to financial institutions via an API. This allows for accurate evaluation of a company's vitality and employee emotions, enabling financial institutions to make more appropriate lending decisions based on the results.

[0726] A "terminal" is a device on which a company's internal communication application runs, and is a device with which users conduct daily business communications.

[0727] "Server" is a central computing unit for storing collected data and analyzing the data using generative AI models and emotion engines.

[0728] "User" refers to an employee who uses a company's internal communication application to communicate for business purposes.

[0729] A "generative AI model" is an artificial intelligence model based on machine learning that analyzes text data and calculates the frequency of positive and negative words.

[0730] An "emotion engine" is software or algorithm that analyzes the content of a message to determine the user's emotional state and classify it into multiple emotional categories.

[0731] The "vitality score" is a quantified score that measures a company's vitality and the mental state of its employees based on the analysis results of the generative AI model and emotion engine, as well as other statistical data.

[0732] "Data collection means" refers to a system configuration for collecting message content, timestamps, total number of messages, and frequency of positive and negative words from a company's internal communication applications.

[0733] "Data transmission means" refers to the protocols and procedures for encrypting collected data and transmitting it securely to the server.

[0734] "Data storage means" refers to a system configuration that stores data received by the server in a database in an appropriate format so that it can be analyzed later.

[0735] An "API" is an interface that other systems can access programmatically, and is a means for providing health scores to financial institutions' systems.

[0736] "Statistical information" is data used to quantitatively evaluate the usage of a company's internal communication applications, such as the total number of messages and response speed.

[0737] The present invention is a system that evaluates the vitality of a company based on data obtained using the company's internal communication application and provides the results to financial institutions. How this system is implemented will be described in detail below.

[0738] Terminal functions

[0739] The device is a device that runs an internal communication application used by company employees on a daily basis. When a user communicates through this application, a monitoring tool installed on the device runs in the background and collects the following data:

[0740] Message content

[0741] Message sending and receiving timestamps

[0742] Total number of messages

[0743] Frequency of positive and negative words

[0744] The collected data is encrypted and sent to a server over the company's internal network.

[0745] Server-side features

[0746] The server receives the data sent from the device and stores it in a database. The server analyzes the data using the following software and algorithms:

[0747] Natural Language Processing (NLP): Generative AI models such as BERT (Bidirectional Encoder Representations from Transformers) are used to automatically extract positive and negative words from message content and calculate their frequency.

[0748] Emotion Engine: Analyzes message content to determine the user's emotional state. The emotion engine uses a text-based emotion analysis algorithm to classify emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[0749] Calculating statistics: Software for calculating statistics such as total number of messages and reply speed.

[0750] Based on these analysis results, the server uses a scoring algorithm to calculate a company's vitality score, which is then stored in a database and made available to financial institutions via API.

[0751] Financial institution system functions

[0752] Financial institutions' systems receive a company's vitality score through the API, and financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions.

[0753] Specific examples

[0754] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[0755] Number of positive words: 300

[0756] Number of negative words: 60

[0757] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[0758] Total number of messages: 1200

[0759] Average response time: 1.5 hours

[0760] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to the financial institution's system, and the financial institution's staff uses this score to review whether to grant additional loans to Company A.

[0761] Example prompts for generative AI models

[0762] For example, by inputting a prompt such as "I would like the company's overall vitality score calculated based on last month's employee communication data" into the generative AI model, the process of automatically calculating the company's vitality score will be carried out.

[0763] The above is a specific embodiment of the present invention. The present invention utilizes generative AI and an emotion engine to evaluate the vitality and dynamism of a company and support financial institutions in making lending decisions. This enables more accurate evaluations that reflect the actual vitality of a company, and is expected to lead to more appropriate lending decisions.

[0764] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0765] Step 1:

[0766] Data collection

[0767] Input: Message content sent by a user through a company's internal communication application.

[0768] How it works: A monitoring tool installed on the device collects message content, timestamps, total number of messages, and frequency of positive and negative words.

[0769] Data processing: Organizing and structuring the collected data.

[0770] Output: Structured and organized data (message content, timestamps, positive word frequencies, negative word frequencies, etc.).

[0771] Step 2:

[0772] Data transmission

[0773] Input: The data collected and structured in Step 1.

[0774] How it works: The device encrypts the data and sends it to the server over the company's internal network (e.g., TLS protocol).

[0775] Data processing: Data encryption and transmission.

[0776] Output: The encrypted data sent to the server.

[0777] Step 3:

[0778] Data storage

[0779] Input: The encrypted data received by the server.

[0780] What it does: The server decrypts the data it receives and stores it in a database.

[0781] Data calculation: Decrypt the data and store it in the database.

[0782] Output: Decrypted data stored in a database.

[0783] Step 4:

[0784] Natural Language Processing (NLP) Analysis

[0785] Input: Message content stored in the database.

[0786] How it works: A generative AI model on the server analyzes message content and calculates the frequency of positive and negative words.

[0787] Data calculation: Word frequency calculation through text analysis (example model: BERT).

[0788] Output: Positive and negative word frequency data.

[0789] Step 5:

[0790] Emotion recognition by emotion engine

[0791] Input: Message content data obtained in step 4.

[0792] How it works: The server's emotion engine analyzes the user's emotional state and classifies emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[0793] Data Computing: Sentiment Classification through Sentiment Analysis Algorithms.

[0794] Output: Distribution data for each emotion category.

[0795] Step 6:

[0796] Statistical Data Calculations

[0797] Input: Analysis results from the previous stage, total number of messages, reply speed, etc.

[0798] How it works: The server calculates statistics such as message totals, reply speed, etc.

[0799] Data calculation: Statistical calculations (total number of messages, average reply speed, etc.).

[0800] Output: Statistics data.

[0801] Step 7:

[0802] Calculating vitality score

[0803] Input: Analysis results of natural language processing and emotion engine, statistical data.

[0804] How it works: The server's scoring algorithm calculates a vitality score based on these inputs.

[0805] Data calculation: Comprehensive evaluation using a scoring algorithm.

[0806] Output: Company Vitality Score.

[0807] Step 8:

[0808] Providing scores

[0809] Input: Vitality score calculated in step 7.

[0810] How it works: The server stores the vitality score in a database and makes it available to financial institutions via an API.

[0811] Data Computing: Managing API endpoints and providing data.

[0812] Output: Vitality score provided to financial institutions.

[0813] The above are the specific processing steps and detailed operations for implementing the invention. By explaining the data input and output at each step and the specific operations, the flow of the entire system becomes clear, enabling the invention to be implemented effectively.

[0814] (Application example 2)

[0815] 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."

[0816] Conventional factory performance evaluations rely primarily on mechanical data and human intuition, making it difficult to accurately evaluate the overall health and work efficiency of the factory. This invention solves this problem by comprehensively analyzing the operation data of robots in the factory and the message data of workers, and quantitatively evaluating the overall factory performance based on the results.

[0817] 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 analyzing operation data and message data within the factory using a generation AI, means for calculating a performance score based on the analysis results of the operation data and message data, and means for providing the performance score to the management system. This makes it possible to accurately evaluate the health status and work efficiency of the entire factory and derive appropriate maintenance and work environment improvement measures.

[0818] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data.

[0819] "Operational data" refers to operational information such as the operating status of robots and machines in a factory and the frequency of errors.

[0820] "Message data" refers to text messages and communications exchanged between workers and staff within a factory.

[0821] The "performance score" is an overall evaluation index calculated based on the operation data and message data of robots and workers in the factory.

[0822] A "management system" is an information system for operating and managing a factory, and its role is to integrate, display, and manage data such as performance scores.

[0823] The system of the present invention uses generative AI to analyze operation data and message data to evaluate the performance of robots and workers in a factory, and calculates a performance score from the results. This system consists of the following components:

[0824] Overall system configuration

[0825] 1. Server:

[0826] The server plays a central role in analyzing the data using generative AI and emotion engines.

[0827] For actual data analysis, we use the NLPProcessor, which performs natural language processing (NLP), and the EmotionEngine, which performs emotion recognition.

[0828] 2. Terminal:

[0829] The terminal is responsible for collecting operational data and message data from various sensors and communication devices within the factory.

[0830] The data collected by the device is encrypted and sent to the server.

[0831] 3. Management system:

[0832] The management system provides an interface to visualize evaluation results such as performance scores and support appropriate measures.

[0833] Program Description

[0834] 1. Data Collection:

[0835] Operational data such as operating time and frequency of errors is collected from robots in factories.

[0836] Message data is collected from workers through an internal communication application.

[0837] The collected data is sent to a server via the terminal.

[0838] 2. Data Analysis:

[0839] The server uses the NLPProcessor to analyze the message data and calculate the frequency of occurrence of positive and negative words.

[0840] At the same time, the Emotion Engine is used to analyze the emotional state of the worker from the message data and calculate an emotion score.

[0841] 3. Calculation of Performance Score:

[0842] The server integrates the collected motion data and emotion data to calculate a performance score.

[0843] The performance score is a quantitative assessment of the overall health and work efficiency of the factory.

[0844] 4. Providing results:

[0845] The calculated performance scores are provided to the management system so that factory managers can easily view them.

[0846] Based on this information, appropriate measures can be taken to maintain the robot and improve the working environment.

[0847] Specific examples

[0848] For example, suppose the following data is collected at a factory:

[0849] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[0850] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[0851] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[0852] Based on this data, a performance score was calculated, resulting in a score of 70. This information was notified to managers and used as a reference for taking measures to maintain the robot and improve the working environment.

[0853] Example of input prompt for generative AI model

[0854] "Based on the factory robot's operational data and the messages from the workers, please calculate and report an overall score. Use the following data."

[0855] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[0856] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[0857] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[0858] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0859] Step 1:

[0860] This system collects operation data and message data from robots and workers in the factory. The terminal acquires data from the internal communication applications of each robot and worker, encrypts this data, and sends it to the server. For example, the system collects information such as the robot's operating time, error rate, and messages exchanged by workers via the internal communication application. The input is the robot and worker data, and the output is encrypted data sent to the server.

[0861] Step 2:

[0862] The server stores the received operation data and message data in a database. The server receives encrypted data sent from the terminal, decrypts it to its original format, and stores it in the database. The input is the encrypted data, and the output is the format stored in the database.

[0863] Step 3:

[0864] The server analyzes message data using an NLPProcessor. The NLPProcessor extracts positive and negative words from the message and calculates their frequency of occurrence. The input is the message data, and the output is the frequency of occurrence of positive and negative words. Specifically, the words in the message are tokenized, classified into positive and negative categories using a synonym dictionary, and the frequency of occurrence is counted.

[0865] Step 4:

[0866] The server uses the Emotion Engine to analyze the emotional state from the message data. The Emotion Engine analyzes the message data and calculates an emotional score such as joy, sadness, or anger. The input is the message data, and the output is the emotional score. Specifically, it receives the message text as input, assigns an emotional label using a pre-trained model, and calculates a probability score for each emotion.

[0867] Step 5:

[0868] The server calculates a performance score based on the operational data and emotional score. The operational data (e.g., uptime, error rate) and emotional score (e.g., 40% joy) are integrated and weighted to calculate a performance score as an overall evaluation. The input is the operational data and emotional score, and the output is the performance score. Specifically, the server normalizes various data and calculates an overall score based on a pre-set evaluation algorithm.

[0869] Step 6:

[0870] The server provides the calculated performance scores to the management system. The management system visualizes the provided performance scores and displays them via an interface so that factory managers can view them. The input is the performance scores, and the output is the visualized evaluation results. Specifically, the performance scores are displayed on the management system's dashboard, and appropriate actions are suggested based on the results.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] [Third embodiment]

[0875] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0876] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0877] 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).

[0878] 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.

[0879] 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.

[0880] 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).

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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."

[0887] The system of this invention uses generative AI to analyze usage data from internal communication applications of small and medium-sized enterprises, and builds a unique scoring model based on the results. This provides financial institutions with a company vitality score, supporting their evaluation and lending decisions. The system is composed of the following processing flow and components.

[0888] Overall system configuration

[0889] The overall configuration of this system mainly consists of the following components:

[0890] Terminals (devices running internal corporate communication applications)

[0891] Server (performs data analysis and scoring)

[0892] Financial institution systems (using scores to evaluate and make lending decisions)

[0893] Terminal functions

[0894] The device runs an internal communication application that company personnel use on a daily basis. Users use this application to communicate for business purposes. During this time, a dedicated monitoring tool runs in the background and collects the following data:

[0895] Message content

[0896] The date and time the message was sent and received

[0897] Total number of messages

[0898] Positive and negative words

[0899] The collected data is automatically sent to a server.

[0900] Server-side features

[0901] The server receives the usage data of the internal communication application sent from the device and stores it in a database.The server then uses the generation AI to perform the following analysis.

[0902] 1. Use natural language processing (NLP) techniques to extract positive and negative words from message content.

[0903] 2. Calculate statistics such as total number of messages and response speed.

[0904] 3. Based on these analysis results, a company's vitality score is calculated.

[0905] The generated vitality score is calculated based on a scoring algorithm to quantify the vitality and activity of the company. This score is stored in a database and made available to financial institutions via API.

[0906] Financial institution system functions

[0907] The financial institution's system obtains the vitality score for each company through the API. Financial institution personnel use this score to make lending decisions. Specific methods of use are as follows:

[0908] Obtain a vitality score for companies that apply for loans.

[0909] Check whether the score meets certain criteria.

[0910] If necessary, we will evaluate it comprehensively in conjunction with other financial data.

[0911] Specific examples

[0912] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[0913] Number of positive words: 250

[0914] Number of negative words: 50

[0915] Total number of messages: 1000

[0916] Average response time: 2 hours

[0917] Based on this data, the generative AI calculates a vitality score of 85 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff member uses this score to review whether to grant additional financing to Company A.

[0918] As described above, this invention utilizes generative AI to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the vitality of a company, and is expected to lead to more appropriate lending decisions.

[0919] The processing flow will be explained below.

[0920] Step 1:

[0921] When users communicate for business purposes using an internal communication application within a company (e.g., a business messaging app), data such as the content of the conversation, the time the message was sent, the time it was received, and the speed of the reply are automatically recorded.

[0922] Step 2:

[0923] A dedicated monitoring tool installed on the device periodically collects data from internal communication applications, organizes it, encrypts it, and sends it to a server, including the content of messages, timestamps of messages sent and received, and the total number of messages.

[0924] Step 3:

[0925] The server stores the received data in a database for analysis. The data is stored in a database management system (DBMS) in a format that can be efficiently accessed by each company.

[0926] Step 4:

[0927] The server's generation AI performs natural language processing (NLP) based on the collected data. Specifically, it analyzes the content of messages to detect positive words (e.g., "great," "thank you") and negative words (e.g., "problem," "trouble") and calculates their frequency.

[0928] Step 5:

[0929] The server also calculates statistics such as the total number of messages and reply speed, which refers to the average time it takes for a message to be replied to after it is sent.

[0930] Step 6:

[0931] The server's scoring algorithm calculates a company's vitality score based on the NLP analysis results and statistical information. The vitality score is a numerical representation of a company's vitality and energy, ranging from 0 to 100.

[0932] Step 7:

[0933] The server stores this vitality score in a database and makes it accessible to financial institutions. It also provides an API for retrieving the score, which financial institutions can use to obtain the necessary information.

[0934] Step 8:

[0935] Financial institutions' systems obtain a company's vitality score through the API, and financial institution personnel use the score in combination with other financial data to evaluate the company and make lending decisions.

[0936] Step 9:

[0937] Financial institutions provide the server with feedback data on actual loan results and company performance, which the server uses to make adjustments to improve the accuracy of the scoring algorithm.

[0938] Step 10:

[0939] The server's generation AI continuously improves its algorithm based on feedback data, improving the accuracy of the vitality score assessment, thereby improving the performance and reliability of the entire system.

[0940] The above steps will realize a system that analyzes usage data of a company's internal communication applications and evaluates the company's vitality. This system will be a valuable tool for financial institutions in making lending decisions.

[0941] Example 1

[0942] 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."

[0943] When evaluating small and medium-sized enterprises and making lending decisions, current evaluation methods have the problem of not accurately reflecting the actual vitality and activity of the company. In particular, there is a lack of means to properly evaluate the state of a company's internal communication, making it difficult for financial institutions to make appropriate decisions when providing loans. This can result in an inaccurate evaluation that reflects the vitality of the company, and can delay appropriate lending decisions.

[0944] 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.

[0945] In this invention, the server includes: a means for the terminal to collect data using a communication application; a means for the server to receive data sent from the terminal and extract positive and negative words using natural language processing (NLP) technology; a means for the server to calculate the total number of messages and the reply speed; a means for the server to calculate a company's vitality score using a generating AI; and a means for the server to store the calculated vitality score in a database and provide it to financial institutions via an API. This enables detailed analysis of a company's internal communication data and accurately evaluates the company's vitality and activity. As a result, financial institutions can make more appropriate lending decisions and efficiently support the growth of small and medium-sized enterprises.

[0946] A "terminal" is a device that runs communication applications and is used by a user in their daily work.

[0947] "Data" refers to information collected from communication applications, including message content, sent date and time, received date and time, total number of messages, frequency of occurrence of positive and negative words, and the like.

[0948] A "server" is a central computing device that receives data sent from the terminals and performs analysis and scoring.

[0949] "Natural language processing (NLP) technology" is a technology that analyzes the meaning and context of text data and extracts specific elements such as positive and negative words.

[0950] "Positive and negative words" are important keywords in assessing the vitality and vibrancy of a company in the content of a message, and are words that indicate the positive or negative state of a company's communication.

[0951] "Total Messages" means the total number of all Messages sent within a specified period of time.

[0952] "Reply speed" is the average time it takes for a reply to be sent after a message is sent.

[0953] "Generative AI" is a system that uses artificial intelligence technology to analyze data and calculate a company's vitality score based on a certain algorithm.

[0954] The "vitality score" is a numerical representation of a company's communication activity and vitality, and serves as a reference index for financial institutions when making lending decisions.

[0955] A "database" is a digital storage device where the server stores analysis results and vitality scores.

[0956] "API" stands for Application Program Interface, a specification and protocol for exchanging data between servers and financial institution systems.

[0957] A "financial institution" is a financial service provider such as a bank or money lender that provides loans to companies.

[0958] The system of the present invention uses AI to analyze usage data of internal communication applications of small and medium-sized enterprises, and calculates a vitality score for the company based on the results.Furthermore, this score is provided to financial institutions to support their evaluation and lending decisions.

[0959] Hardware and software used

[0960] Hardware

[0961] Terminal: A device used by a company's personnel that runs internal communication applications.

[0962] Server: The central computing device that performs data analysis and scoring.

[0963] Database: Connected to the server, it stores data and analysis results.

[0964] software

[0965] Internal communication applications: Applications for communicating within a company.

[0966] Generative AI model: An artificial intelligence model for analyzing data and calculating vitality scores.

[0967] Natural Language Processing (NLP) technology: Technology that analyzes message content and extracts positive and negative words.

[0968] API: An interface for financial institutions to obtain health scores.

[0969] Specific data processing and calculation

[0970] 1. Data Collection

[0971] The terminal collects the following data from the communications made by the user through the internal communication application:

[0972] Message content

[0973] The date and time the message was sent and received

[0974] Total number of messages

[0975] Frequency of positive and negative words

[0976] 2. Data Transmission

[0977] The terminal periodically transmits the collected data to the server.

[0978] 3. Data Receipt and Storage

[0979] The server receives the data sent from the terminal and stores it in a database.

[0980] 4. Natural Language Processing (NLP)

[0981] The server analyzes the received message content using NLP technology and extracts positive and negative words.

[0982] 5. Calculating statistical data

[0983] The server calculates the total number of messages and reply speed from the analyzed data.

[0984] 6. Calculating vitality score

[0985] The server calculates a company's vitality score using a generative AI model based on NLP analysis results and statistical data.

[0986] 7. Saving to the database

[0987] The server stores the calculated vitality score in a database.

[0988] 8. API Provision

[0989] The server provides financial institutions with the ability to obtain vitality scores via an API.

[0990] Specific examples

[0991] For example, if Company A uses an internal communication application to communicate on a daily basis, the chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[0992] Number of positive words: 250

[0993] Number of negative words: 50

[0994] Total number of messages: 1000

[0995] Average response time: 2 hours

[0996] Based on this data, the generative AI model calculates a vitality score for Company A of 85. This score is stored in a database and made available to financial institutions via API. Financial institutions then use the obtained vitality score to make loan decisions for Company A.

[0997] Example prompts

[0998] Please collect one month's worth of internal communication data from Company A and send it to the server, including message content, sent date and time, received date and time, positive words, negative words, and total number of messages.

[0999] Analyze the communication data of Company A, extract positive and negative words, and calculate a vitality score based on the total number of messages and the speed of replies.

[1000] "Get Company A's Vitality Score from the API and verify that this score meets the lending criteria. Evaluate other financial data as well, if necessary."

[1001] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1002] Step 1:

[1003] A user communicates business-related information using an internal communication application within a company. For example, the user sends a message saying, "The meeting was good." The terminal collects the content of the message sent by the user, the date and time, the date and time it was received, the total number of messages, and the occurrence of positive and negative words. In this case, the terminal collects the message content "The meeting was good" and the date and time it was sent, and counts the positive word "good."

[1004] Input: The message sent by the user

[1005] Output: Collected message content, date and time, and frequency of positive and negative words

[1006] Step 2:

[1007] The device periodically transmits the collected data to the server. Specifically, the device periodically transfers the message content, the date and time of sending, the date and time of receiving, the total number of messages, and the frequency of occurrence of positive and negative words to the server.

[1008] Input: Data collected on the device

[1009] Output: Data sent to the server

[1010] Step 3:

[1011] The server receives the data sent from the terminal and stores it in a database. The server saves the collected message content, the sending date and time, the receiving date and time, the total number of messages, and the frequency of occurrence of positive and negative words in the database.

[1012] Input: Data sent from the terminal

[1013] Output: Data stored in the database

[1014] Step 4:

[1015] The server uses NLP technology to analyze the message content stored in the database. Specifically, the server analyzes the received message content and extracts positive and negative words. For example, the server recognizes and counts the positive word "good" from the message "The meeting was good."

[1016] Input: Message content stored in the database

[1017] Output: Extracted positive and negative words

[1018] Step 5:

[1019] The server calculates the total number of messages and the reply rate. For example, the server calculates that the total number of messages sent in a month is 1000, and the average reply rate is 2 hours.

[1020] Input: The sent and received dates and times of messages stored in the database

[1021] Output: Calculated total number of messages and reply rate

[1022] Step 6:

[1023] The server uses a generative AI model based on the NLP analysis results and statistical data to calculate a company's vitality score. For example, if the number of positive words appearing is 250 and the number of negative words appearing is 50, the generative AI will use this data to calculate a vitality score of 85.

[1024] Input: extracted positive and negative words, calculated statistics

[1025] Output: Company Vitality Score

[1026] Step 7:

[1027] The server stores the calculated vitality score in a database.

[1028] Input: Calculated vitality score

[1029] Output: Vitality scores stored in a database

[1030] Step 8:

[1031] The server provides the calculated vitality score to financial institutions via API. Financial institutions obtain the company's vitality score from the API and make lending decisions based on this score.

[1032] Input: Saved Vitality Score

[1033] Output: Vitality score provided through the API

[1034] (Application example 1)

[1035] 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."

[1036] Communication within industrial facilities is important for improving productivity and the working environment, but there is a lack of means to objectively evaluate and manage the quality of communication between workers. This can lead to a decline in productivity and a deterioration in the working environment. The purpose of this invention is to solve this problem by proposing a system that analyzes communication data within industrial facilities and calculates and provides a vitality score for the industrial facility based on the results.

[1037] 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.

[1038] In this invention, the server includes a means for analyzing usage data of internal communication applications in an industrial facility using a generating AI, a means for calculating a vitality score of the industrial facility based on the results of the analysis of the usage data, and a means for providing the vitality score to a manager, thereby enabling an objective evaluation of the quality of communication within the industrial facility and improving productivity and the working environment.

[1039] "Generative AI" is an artificial intelligence technology that analyzes usage data from internal communication applications and extracts insights from the data.

[1040] An "industrial facility" is a place where manufacturing or production activities are carried out and where many workers and machinery are in operation.

[1041] An "internal communications application" is a software tool that enables communication between workers within an industrial facility, helping them send and receive messages and share information.

[1042] "Usage data" refers to data such as message content, sending date and time, receiving date and time, and total number of messages generated in the process of using an internal communication application.

[1043] The "vitality score" is a numerical representation of the quality of communication and worker activity within an industrial facility, calculated based on the frequency of positive and negative words, the total number of messages, and the speed of replies.

[1044] A "manager" is a person or position that supervises the operation of industrial facilities and the working conditions of workers, and works to improve productivity and the working environment.

[1045] "Positive words" are words with positive or forward-looking meanings that are included in the message content of an internal communication application.

[1046] "Negative words" are words with negative or backward meanings that are included in the message content of an internal communication application.

[1047] "Analysis" is the process of processing usage data from internal communication applications and extracting useful information and patterns from it.

[1048] "Providing" is the act of calculating the vitality score and then transmitting the result to the administrator or related parties.

[1049] This invention relates to a system that collects and analyzes communication data between workers within an industrial facility and uses generative AI to calculate and provide a vitality score for the industrial facility.

[1050] Program processing explanation

[1051] First, the terminal collects usage data, such as message content, sent and received dates and times, and total number of messages, via internal communication applications used within the industrial facility. This terminal is a device used daily by workers and transmits this data to a server in real time.

[1052] The server stores the received usage data in a database and analyzes the message content using TextBlob and other natural language processing (NLP) libraries. Specifically, it extracts positive and negative words from the message content and calculates their frequency. It also calculates statistical data such as the total number of messages and reply speed.

[1053] The server then calculates the industrial facility's vitality score based on the analysis results. This score is calculated based on the frequency of positive and negative words, the total number of messages, and the response speed. The calculated vitality score is provided to the administrator via an API.

[1054] The specific hardware used includes computer terminals, network equipment, and servers in industrial facilities, and the software used includes Python, TextBlob (a natural language processing library), and a database management system (e.g., MySQL).

[1055] Specific examples

[1056] For example, when a worker in an industrial facility sends a message such as "Great job!" or "I'm happy with my performance on the assembly line," the device collects these messages and sends them to the server. The server then analyzes the message content using TextBlob and extracts positive words. Specifically, words such as "great" and "satisfied" are recognized as positive words.

[1057] Based on these analysis results, the server calculates a high vitality score for the industrial facility. At the same time, the total number of messages and average response time are also taken into account as evaluation factors. The calculated vitality score is provided to the administrator via API, and the administrator can use this to consider measures to improve the working environment and productivity throughout the facility.

[1058] Prompt Sentence Examples

[1059] Analyze internal communication data within an industrial facility and calculate a vitality score. For example, the following data is available:

[1060] Message: "Great job!"

[1061] Sent date and time: "2023-01-01 10:00:00"

[1062] Total number of messages: 100

[1063] Calculate a vitality score based on the analysis results and suggest areas for improvement.

[1064] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1065] Step 1:

[1066] The terminal collects messages sent by workers within an industrial facility using an internal communication application. Specifically, it collects data such as message content, the date and time of sending, the date and time of receiving, and the total number of messages. This data is temporarily stored in the terminal. The input of this step is the message sent by the worker, and the output is the collected message data.

[1067] Step 2:

[1068] The terminal periodically sends the collected message data to the server. This data is transferred to the server via the network and stored in a database on the server. The input of this step is the message data collected by the terminal, and the output is the message data sent to the server.

[1069] Step 3:

[1070] The server stores the received message data in a database. Using a database management system (e.g., MySQL), the server saves detailed information such as the sending date and time, the receiving date and time, and the message content in the database. The input to this step is the message data sent from the terminal, and the output is the message data stored in the database.

[1071] Step 4:

[1072] The server analyzes the stored message content using a natural language processing (NLP) library such as TextBlob. It extracts positive and negative words from the message content and calculates their frequency. The input to this step is the message content stored in the database, and the output is frequency data for positive and negative words.

[1073] Step 5:

[1074] The server calculates statistical data such as the total number of messages and reply speed. Specifically, it calculates the average message sending speed, reply speed, total number of messages, etc., and stores them as the respective statistical data. The input to this step is the message sending and receiving information stored in the database, and the output is the calculated statistical data.

[1075] Step 6:

[1076] The server calculates the industrial facility's vitality score based on the extracted positive and negative word frequency data and the calculated statistical data. A scoring algorithm is used to quantify the positive and negative elements and calculate an overall score. The input for this step is the positive and negative word frequency data and statistical data, and the output is the vitality score.

[1077] Step 7:

[1078] The server provides the calculated vitality score to the administrator via API. The administrator considers measures to improve the working environment and productivity in the industrial facility based on the provided vitality score. The input of this step is the calculated vitality score, and the output is the vitality score provided to the administrator.

[1079] 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.

[1080] The system of the present invention uses a generative AI to analyze usage data from an SME's internal communication application, and then combines this with an emotion engine that recognizes user emotions to calculate a company's vitality score. This vitality score is provided to financial institutions to assist in evaluating the company and making lending decisions. Below, we will explain in detail how this system is implemented.

[1081] Overall system configuration

[1082] This system consists of the following components:

[1083] Terminals (devices running internal corporate communication applications)

[1084] Server (performs data analysis, emotion recognition and scoring)

[1085] Emotion engine (analyzes the user's emotional state)

[1086] Financial institution systems (using scores to evaluate and make lending decisions)

[1087] Terminal functions

[1088] The device runs an internal communication application that is used daily by company employees. Users communicate through this application for business purposes. A monitoring tool installed on the device runs in the background and collects the following data:

[1089] Message content

[1090] Message sending and receiving timestamps

[1091] Total number of messages

[1092] Frequency of positive and negative words

[1093] The collected data is encrypted and sent to a server.

[1094] Server-side features

[1095] The server receives the data sent from the device, stores it in a database, and then analyzes the data using generative AI and an emotion engine.

[1096] 1. Analysis using natural language processing (NLP)

[1097] The server's generation AI automatically extracts positive and negative words from the message content and calculates their frequency.

[1098] 2. Emotion Recognition by Emotion Engine

[1099] An emotion engine on the server analyzes the message content and determines the user's emotional state.

[1100] The emotion engine classifies the user's emotions into multiple categories (e.g., joy, sadness, anger, surprise, etc.).

[1101] 3. Calculating statistical data

[1102] Calculate statistics such as total number of messages, reply rate, etc.

[1103] 4. Calculating the vitality score

[1104] The server's scoring algorithm calculates a company's vitality score based on the results of NLP analysis, the results of the emotion engine, and statistical data.

[1105] The generated vitality score is stored in a database and made available to financial institutions via an API.

[1106] Financial institution system functions

[1107] Financial institutions' systems obtain a company's vitality score through the API. Financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions. Specific usage methods are as follows:

[1108] The vitality score of companies that have applied for loans is retrieved and displayed via API.

[1109] Based on the score obtained, we check whether the company's vitality meets certain standards.

[1110] Evaluate alongside traditional financial data, as appropriate.

[1111] Specific examples

[1112] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[1113] Number of positive words: 300

[1114] Number of negative words: 60

[1115] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[1116] Total number of messages: 1200

[1117] Average response time: 1.5 hours

[1118] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff uses this score to review whether to grant additional financing to Company A.

[1119] As described above, this invention utilizes generative AI and an emotion engine to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the actual vitality of a company, and is expected to lead to more appropriate lending decisions.

[1120] The processing flow will be explained below.

[1121] Step 1:

[1122] When users communicate with each other through internal company communications applications, data such as the content of messages exchanged, timestamps of messages sent and received, and response times are recorded in real time.

[1123] Step 2:

[1124] The monitoring tool installed on the device collects data from internal communication applications at regular intervals, organizes it, encrypts it, and sends it to a server, including the content of messages and the frequency of exchanges.

[1125] Step 3:

[1126] The server stores the received data in a database for analysis, organized by company and stored in an efficiently accessible format.

[1127] Step 4:

[1128] The server's generated AI uses the stored data to perform natural language processing (NLP) analysis, extracting positive and negative words from the message content and recording their frequency.

[1129] Step 5:

[1130] The server's emotion engine determines the user's emotional state from the message content in parallel with NLP analysis. The emotion engine classifies the message content into multiple emotion categories (e.g., joy, sadness, anger, surprise, etc.) and calculates the proportion of each category.

[1131] Step 6:

[1132] The server also calculates statistics such as message totals and reply speeds, for example, reply speed is calculated as the average time it takes for each message to be replied to after it has been sent.

[1133] Step 7:

[1134] Based on the analysis results of the generative AI and emotion engine, as well as statistical data, the server's scoring algorithm calculates a company's vitality score, which is a numerical representation of a company's vitality and activity, expressed on a scale of 0 to 100, for example.

[1135] Step 8:

[1136] The generated vitality scores are stored in a database on the server, and an API is provided to make them accessible to financial institutions, who can then inquire about the company's score via this API.

[1137] Step 9:

[1138] The financial institution's system obtains a company's vitality score via the API, which is then used by financial institution personnel to evaluate the company and make lending decisions.

[1139] Step 10:

[1140] Financial institutions send feedback data on actual loan results and corporate performance back to the server, which then uses this feedback to adjust the AI ​​and scoring algorithm to improve the accuracy of future scores.

[1141] As a result, users, terminals, servers, and financial institutions can work together to build an evaluation system that reflects the dynamism of small and medium-sized enterprises, and support optimal lending decisions.

[1142] Example 2

[1143] 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."

[1144] It has been difficult with conventional technology to quantify a company's vitality and employee emotions and use that information to support financial institutions in making lending decisions. Small and medium-sized enterprises, in particular, lack effective means of analyzing information obtained from daily business communications, making it difficult to accurately assess the actual emotional state of employees and the company's vitality.

[1145] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1146] In this invention, the server includes: means for collecting the content, timestamp, total number, and frequency of positive and negative words in messages sent by users through the company's internal communication application; means for encrypting the collected data and transmitting it to the server; means for the server to receive the encrypted data and store it in a database; means for automatically analyzing the frequency of positive and negative words from the message content using a generative AI model; means for analyzing the user's emotional state and classifying it into multiple emotional categories using an emotion engine; means for calculating statistical information such as the total number of messages and reply speed; means for calculating a company vitality score based on the analysis results and statistical data obtained from the generative AI model and the emotion engine; and means for storing the calculated vitality score in a database and providing it to financial institutions via an API. This allows for accurate evaluation of a company's vitality and employee emotions, enabling financial institutions to make more appropriate lending decisions based on the results.

[1147] A "terminal" is a device on which a company's internal communication application runs, and is a device with which users conduct daily business communications.

[1148] "Server" is a central computing unit for storing collected data and analyzing the data using generative AI models and emotion engines.

[1149] "User" refers to an employee who uses a company's internal communication application to communicate for business purposes.

[1150] A "generative AI model" is an artificial intelligence model based on machine learning that analyzes text data and calculates the frequency of positive and negative words.

[1151] An "emotion engine" is software or algorithm that analyzes the content of a message to determine the user's emotional state and classify it into multiple emotional categories.

[1152] The "vitality score" is a quantified score that measures a company's vitality and the mental state of its employees based on the analysis results of the generative AI model and emotion engine, as well as other statistical data.

[1153] "Data collection means" refers to a system configuration for collecting message content, timestamps, total number of messages, and frequency of positive and negative words from a company's internal communication applications.

[1154] "Data transmission means" refers to the protocols and procedures for encrypting collected data and transmitting it securely to the server.

[1155] "Data storage means" refers to a system configuration that stores data received by the server in a database in an appropriate format so that it can be analyzed later.

[1156] An "API" is an interface that other systems can access programmatically, and is a means for providing health scores to financial institutions' systems.

[1157] "Statistical information" is data used to quantitatively evaluate the usage of a company's internal communication applications, such as the total number of messages and response speed.

[1158] The present invention is a system that evaluates the vitality of a company based on data obtained using the company's internal communication application and provides the results to financial institutions. How this system is implemented will be described in detail below.

[1159] Terminal functions

[1160] The device is a device that runs an internal communication application used by company employees on a daily basis. When a user communicates through this application, a monitoring tool installed on the device runs in the background and collects the following data:

[1161] Message content

[1162] Message sending and receiving timestamps

[1163] Total number of messages

[1164] Frequency of positive and negative words

[1165] The collected data is encrypted and sent to a server over the company's internal network.

[1166] Server-side features

[1167] The server receives the data sent from the device and stores it in a database. The server analyzes the data using the following software and algorithms:

[1168] Natural Language Processing (NLP): Generative AI models such as BERT (Bidirectional Encoder Representations from Transformers) are used to automatically extract positive and negative words from message content and calculate their frequency.

[1169] Emotion Engine: Analyzes message content to determine the user's emotional state. The emotion engine uses a text-based emotion analysis algorithm to classify emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[1170] Calculating statistics: Software for calculating statistics such as total number of messages and reply speed.

[1171] Based on these analysis results, the server uses a scoring algorithm to calculate a company's vitality score, which is then stored in a database and made available to financial institutions via API.

[1172] Financial institution system functions

[1173] Financial institutions' systems receive a company's vitality score through the API, and financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions.

[1174] Specific examples

[1175] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[1176] Number of positive words: 300

[1177] Number of negative words: 60

[1178] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[1179] Total number of messages: 1200

[1180] Average response time: 1.5 hours

[1181] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to the financial institution's system, and the financial institution's staff uses this score to review whether to grant additional loans to Company A.

[1182] Example prompts for generative AI models

[1183] For example, by inputting a prompt such as "I would like the company's overall vitality score calculated based on last month's employee communication data" into the generative AI model, the process of automatically calculating the company's vitality score will be carried out.

[1184] The above is a specific embodiment of the present invention. The present invention utilizes generative AI and an emotion engine to evaluate a company's vitality and dynamism, supporting financial institutions in making lending decisions. This enables more accurate evaluations that reflect a company's actual vitality, and is expected to lead to more appropriate lending decisions.

[1185] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1186] Step 1:

[1187] Data collection

[1188] Input: Message content sent by a user through a company's internal communication application.

[1189] How it works: A monitoring tool installed on the device collects message content, timestamps, total number of messages, and frequency of positive and negative words.

[1190] Data processing: Organizing and structuring the collected data.

[1191] Output: Structured and organized data (message content, timestamps, positive word frequencies, negative word frequencies, etc.).

[1192] Step 2:

[1193] Data transmission

[1194] Input: The data collected and structured in Step 1.

[1195] How it works: The device encrypts the data and sends it to the server over the company's internal network (e.g., TLS protocol).

[1196] Data processing: Data encryption and transmission.

[1197] Output: The encrypted data sent to the server.

[1198] Step 3:

[1199] Data storage

[1200] Input: The encrypted data received by the server.

[1201] What it does: The server decrypts the data it receives and stores it in a database.

[1202] Data calculation: Decrypt the data and store it in the database.

[1203] Output: Decrypted data stored in a database.

[1204] Step 4:

[1205] Natural Language Processing (NLP) Analysis

[1206] Input: Message content stored in the database.

[1207] How it works: A generative AI model on the server analyzes message content and calculates the frequency of positive and negative words.

[1208] Data calculation: Word frequency calculation through text analysis (example model: BERT).

[1209] Output: Positive and negative word frequency data.

[1210] Step 5:

[1211] Emotion recognition by emotion engine

[1212] Input: Message content data obtained in step 4.

[1213] How it works: The server's emotion engine analyzes the user's emotional state and classifies emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[1214] Data Computing: Sentiment Classification through Sentiment Analysis Algorithms.

[1215] Output: Distribution data for each emotion category.

[1216] Step 6:

[1217] Statistical Data Calculations

[1218] Input: Analysis results from the previous stage, total number of messages, reply speed, etc.

[1219] How it works: The server calculates statistics such as message totals, reply speed, etc.

[1220] Data calculation: Statistical calculations (total number of messages, average reply speed, etc.).

[1221] Output: Statistics data.

[1222] Step 7:

[1223] Calculating vitality score

[1224] Input: Analysis results of natural language processing and emotion engine, statistical data.

[1225] How it works: The server's scoring algorithm calculates a vitality score based on these inputs.

[1226] Data calculation: Comprehensive evaluation using a scoring algorithm.

[1227] Output: Company Vitality Score.

[1228] Step 8:

[1229] Providing scores

[1230] Input: Vitality score calculated in step 7.

[1231] How it works: The server stores the vitality score in a database and makes it available to financial institutions via an API.

[1232] Data Computing: Managing API endpoints and providing data.

[1233] Output: Vitality score provided to financial institutions.

[1234] The above are the specific processing steps and detailed operations for implementing the invention. By explaining the data input and output at each step and the specific operations, the flow of the entire system becomes clear, enabling the invention to be implemented effectively.

[1235] (Application example 2)

[1236] 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."

[1237] Conventional factory performance evaluations rely primarily on mechanical data and human intuition, making it difficult to accurately evaluate the overall health and work efficiency of the factory. This invention solves this problem by comprehensively analyzing the operation data of robots in the factory and the message data of workers, and quantitatively evaluating the overall factory performance based on the results.

[1238] 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 analyzing operation data and message data within the factory using a generation AI, means for calculating a performance score based on the analysis results of the operation data and message data, and means for providing the performance score to the management system. This makes it possible to accurately evaluate the health status and work efficiency of the entire factory and derive appropriate maintenance and work environment improvement measures.

[1239] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data.

[1240] "Operational data" refers to operational information such as the operating status of robots and machines in a factory and the frequency of errors.

[1241] "Message data" refers to text messages and communications exchanged between workers and staff within a factory.

[1242] The "performance score" is an overall evaluation index calculated based on the operation data and message data of robots and workers in the factory.

[1243] A "management system" is an information system for operating and managing a factory, and its role is to integrate, display, and manage data such as performance scores.

[1244] The system of the present invention uses generative AI to analyze motion data and message data to evaluate the performance of robots and workers in a factory, and calculates a performance score from the results. This system consists of the following components:

[1245] Overall system configuration

[1246] 1. Server:

[1247] The server plays a central role in analyzing the data using generative AI and emotion engines.

[1248] For actual data analysis, we use the NLPProcessor, which performs natural language processing (NLP), and the EmotionEngine, which performs emotion recognition.

[1249] 2. Terminal:

[1250] The terminal is responsible for collecting operational data and message data from various sensors and communication devices within the factory.

[1251] The data collected by the device is encrypted and sent to the server.

[1252] 3. Management system:

[1253] The management system provides an interface to visualize evaluation results such as performance scores and support appropriate measures.

[1254] Program Description

[1255] 1. Data Collection:

[1256] Operational data such as operating time and frequency of errors is collected from robots in factories.

[1257] Message data is collected from workers through an internal communication application.

[1258] The collected data is sent to a server via the terminal.

[1259] 2. Data Analysis:

[1260] The server uses the NLPProcessor to analyze the message data and calculate the frequency of occurrence of positive and negative words.

[1261] At the same time, the Emotion Engine is used to analyze the emotional state of the worker from the message data and calculate an emotion score.

[1262] 3. Calculation of Performance Score:

[1263] The server integrates the collected motion data and emotion data to calculate a performance score.

[1264] The performance score is a quantitative assessment of the overall health and work efficiency of the factory.

[1265] 4. Providing results:

[1266] The calculated performance scores are provided to the management system so that factory managers can easily view them.

[1267] Based on this information, appropriate measures can be taken to maintain the robot and improve the working environment.

[1268] Specific examples

[1269] For example, suppose the following data is collected at a factory:

[1270] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[1271] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[1272] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[1273] Based on this data, a performance score was calculated, resulting in a score of 70. This information was notified to managers and used as a reference for taking measures to maintain the robot and improve the working environment.

[1274] Example of input prompt for generative AI model

[1275] "Based on the factory robot's operational data and the messages from the workers, please calculate and report an overall score. Use the following data."

[1276] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[1277] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[1278] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[1279] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1280] Step 1:

[1281] This system collects operation data and message data from robots and workers in the factory. The terminal acquires data from the internal communication applications of each robot and worker, encrypts this data, and sends it to the server. For example, the system collects information such as the robot's operating time, error rate, and messages exchanged by workers via the internal communication application. The input is the robot and worker data, and the output is encrypted data sent to the server.

[1282] Step 2:

[1283] The server stores the received operation data and message data in a database. The server receives encrypted data sent from the terminal, decrypts it to its original format, and stores it in a database. The input is the encrypted data, and the output is the format stored in the database.

[1284] Step 3:

[1285] The server analyzes message data using an NLPProcessor. The NLPProcessor extracts positive and negative words from the message and calculates their frequency of occurrence. The input is the message data, and the output is the frequency of occurrence of positive and negative words. Specifically, the words in the message are tokenized, classified into positive and negative categories using a synonym dictionary, and the frequency of occurrence is counted.

[1286] Step 4:

[1287] The server uses the Emotion Engine to analyze the emotional state from the message data. The Emotion Engine analyzes the message data and calculates an emotional score such as joy, sadness, or anger. The input is the message data, and the output is the emotional score. Specifically, it receives the message text as input, assigns an emotional label using a pre-trained model, and calculates a probability score for each emotion.

[1288] Step 5:

[1289] The server calculates a performance score based on the operational data and emotional score. The operational data (e.g., uptime, error rate) and emotional score (e.g., 40% joy) are integrated and weighted to calculate a performance score as an overall evaluation. The input is the operational data and emotional score, and the output is the performance score. Specifically, the server normalizes various data and calculates an overall score based on a pre-set evaluation algorithm.

[1290] Step 6:

[1291] The server provides the calculated performance scores to the management system. The management system visualizes the provided performance scores and displays them via an interface so that factory managers can view them. The input is the performance scores, and the output is the visualized evaluation results. Specifically, the performance scores are displayed on the management system's dashboard, and appropriate actions are suggested based on the results.

[1292] 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.

[1293] 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.

[1294] 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.

[1295] [Fourth embodiment]

[1296] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1297] 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.

[1298] 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).

[1299] 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.

[1300] 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.

[1301] 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).

[1302] 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.

[1303] 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.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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."

[1309] The system of this invention uses generative AI to analyze usage data from internal communication applications of small and medium-sized enterprises, and builds a unique scoring model based on the results. This provides financial institutions with a company vitality score, supporting their evaluation and lending decisions. The system is composed of the following processing flow and components.

[1310] Overall system configuration

[1311] The overall configuration of this system mainly consists of the following components:

[1312] Terminals (devices running internal corporate communication applications)

[1313] Server (performs data analysis and scoring)

[1314] Financial institution systems (using scores to evaluate and make lending decisions)

[1315] Terminal functions

[1316] The device runs an internal communication application that company personnel use on a daily basis. Users use this application to communicate for business purposes. During this time, a dedicated monitoring tool runs in the background and collects the following data:

[1317] Message content

[1318] The date and time the message was sent and received

[1319] Total number of messages

[1320] Positive and negative words

[1321] The collected data is automatically sent to a server.

[1322] Server-side features

[1323] The server receives the usage data of the internal communication application sent from the device and stores it in a database.The server then uses the generation AI to perform the following analysis.

[1324] 1. Use natural language processing (NLP) techniques to extract positive and negative words from message content.

[1325] 2. Calculate statistics such as total number of messages and response speed.

[1326] 3. Based on these analysis results, a company's vitality score is calculated.

[1327] The generated vitality score is calculated based on a scoring algorithm to quantify the vitality and activity of the company. This score is stored in a database and made available to financial institutions via API.

[1328] Financial institution system functions

[1329] The financial institution's system obtains the vitality score for each company through the API. Financial institution personnel use this score to make lending decisions. Specific methods of use are as follows:

[1330] Obtain a vitality score for companies that apply for loans.

[1331] Check whether the score meets certain criteria.

[1332] If necessary, we will evaluate it comprehensively in conjunction with other financial data.

[1333] Specific examples

[1334] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[1335] Number of positive words: 250

[1336] Number of negative words: 50

[1337] Total number of messages: 1000

[1338] Average response time: 2 hours

[1339] Based on this data, the generative AI calculates a vitality score of 85 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff member uses this score to review whether to grant additional financing to Company A.

[1340] As described above, this invention utilizes generative AI to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the vitality of a company, and is expected to lead to more appropriate lending decisions.

[1341] The processing flow will be explained below.

[1342] Step 1:

[1343] When users communicate for business purposes using an internal communication application within a company (e.g., a business messaging app), data such as the content of the conversation, the time the message was sent, the time it was received, and the speed of the reply are automatically recorded.

[1344] Step 2:

[1345] A dedicated monitoring tool installed on the device periodically collects data from internal communication applications, organizes it, encrypts it, and sends it to a server, including the content of messages, timestamps of messages sent and received, and the total number of messages.

[1346] Step 3:

[1347] The server stores the received data in a database for analysis. The data is stored in a database management system (DBMS) in a format that can be efficiently accessed by each company.

[1348] Step 4:

[1349] The server's generation AI performs natural language processing (NLP) based on the collected data. Specifically, it analyzes the content of messages to detect positive words (e.g., "great," "thank you") and negative words (e.g., "problem," "trouble") and calculates their frequency.

[1350] Step 5:

[1351] The server also calculates statistics such as the total number of messages and reply speed, which refers to the average time it takes for a message to be replied to after it is sent.

[1352] Step 6:

[1353] The server's scoring algorithm calculates a company's vitality score based on the NLP analysis results and statistical information. The vitality score is a numerical representation of a company's vitality and energy, ranging from 0 to 100.

[1354] Step 7:

[1355] The server stores this vitality score in a database and makes it accessible to financial institutions. It also provides an API for retrieving the score, which financial institutions can use to obtain the necessary information.

[1356] Step 8:

[1357] Financial institutions' systems obtain a company's vitality score through the API, and financial institution personnel use the score in combination with other financial data to evaluate the company and make lending decisions.

[1358] Step 9:

[1359] Financial institutions provide the server with feedback data on actual loan results and company performance, which the server uses to make adjustments to improve the accuracy of the scoring algorithm.

[1360] Step 10:

[1361] The server's generation AI continuously improves its algorithm based on feedback data, improving the accuracy of the vitality score assessment, thereby improving the performance and reliability of the entire system.

[1362] The above steps will realize a system that analyzes usage data of a company's internal communication applications and evaluates the company's vitality. This system will be a valuable tool for financial institutions in making lending decisions.

[1363] Example 1

[1364] 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."

[1365] When evaluating small and medium-sized enterprises and making lending decisions, current evaluation methods have the problem of not accurately reflecting the actual vitality and activity of the company. In particular, there is a lack of means to properly evaluate the state of a company's internal communication, making it difficult for financial institutions to make appropriate decisions when providing loans. This can result in an inaccurate evaluation that reflects the vitality of the company, and can delay appropriate lending decisions.

[1366] 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.

[1367] In this invention, the server includes: a means for the terminal to collect data using a communication application; a means for the server to receive data sent from the terminal and extract positive and negative words using natural language processing (NLP) technology; a means for the server to calculate the total number of messages and the reply speed; a means for the server to calculate a company's vitality score using a generating AI; and a means for the server to store the calculated vitality score in a database and provide it to financial institutions via an API. This enables detailed analysis of a company's internal communication data and accurately evaluates the company's vitality and activity. As a result, financial institutions can make more appropriate lending decisions and efficiently support the growth of small and medium-sized enterprises.

[1368] A "terminal" is a device that runs communication applications and is used by a user in their daily work.

[1369] "Data" refers to information collected from communication applications, including message content, sent date and time, received date and time, total number of messages, frequency of occurrence of positive and negative words, and the like.

[1370] A "server" is a central computing device that receives data sent from the terminals and performs analysis and scoring.

[1371] "Natural language processing (NLP) technology" is a technology that analyzes the meaning and context of text data and extracts specific elements such as positive and negative words.

[1372] "Positive and negative words" are important keywords in assessing the vitality and vibrancy of a company in the content of a message, and are words that indicate the positive or negative state of a company's communication.

[1373] "Total Messages" means the total number of all Messages sent within a specified period of time.

[1374] "Reply speed" is the average time it takes for a reply to be sent after a message is sent.

[1375] "Generative AI" is a system that uses artificial intelligence technology to analyze data and calculate a company's vitality score based on a certain algorithm.

[1376] The "vitality score" is a numerical representation of a company's communication activity and vitality, and serves as a reference index for financial institutions when making lending decisions.

[1377] A "database" is a digital storage device where the server stores analysis results and vitality scores.

[1378] "API" stands for Application Program Interface, a specification and protocol for exchanging data between servers and financial institution systems.

[1379] A "financial institution" is a financial service provider such as a bank or money lender that provides loans to companies.

[1380] The system of the present invention uses AI to analyze usage data of internal communication applications of small and medium-sized enterprises, and calculates a vitality score for the company based on the results.Furthermore, this score is provided to financial institutions to support their evaluation and lending decisions.

[1381] Hardware and software used

[1382] Hardware

[1383] Terminal: A device used by a company's personnel that runs internal communication applications.

[1384] Server: The central computing device that performs data analysis and scoring.

[1385] Database: Connected to the server, it stores data and analysis results.

[1386] software

[1387] Internal communication applications: Applications for communicating within a company.

[1388] Generative AI model: An artificial intelligence model for analyzing data and calculating vitality scores.

[1389] Natural Language Processing (NLP) technology: Technology that analyzes message content and extracts positive and negative words.

[1390] API: An interface for financial institutions to obtain health scores.

[1391] Specific data processing and calculation

[1392] 1. Data Collection

[1393] The terminal collects the following data from the communications made by the user through the internal communication application:

[1394] Message content

[1395] The date and time the message was sent and received

[1396] Total number of messages

[1397] Frequency of positive and negative words

[1398] 2. Data Transmission

[1399] The terminal periodically transmits the collected data to the server.

[1400] 3. Data Receipt and Storage

[1401] The server receives the data sent from the terminal and stores it in a database.

[1402] 4. Natural Language Processing (NLP)

[1403] The server analyzes the received message content using NLP technology and extracts positive and negative words.

[1404] 5. Calculating statistical data

[1405] The server calculates the total number of messages and reply speed from the analyzed data.

[1406] 6. Calculating vitality score

[1407] The server calculates a company's vitality score using a generative AI model based on NLP analysis results and statistical data.

[1408] 7. Saving to the database

[1409] The server stores the calculated vitality score in a database.

[1410] 8. API Provision

[1411] The server provides financial institutions with the ability to obtain vitality scores via an API.

[1412] Specific examples

[1413] For example, if Company A uses an internal communication application to communicate on a daily basis, the chat history for the past month is periodically sent from the device to the server. The server analyzes this data and obtains the following results:

[1414] Number of positive words: 250

[1415] Number of negative words: 50

[1416] Total number of messages: 1000

[1417] Average response time: 2 hours

[1418] Based on this data, the generative AI model calculates a vitality score for Company A of 85. This score is stored in a database and made available to financial institutions via API. Financial institutions then use the obtained vitality score to make loan decisions for Company A.

[1419] Example prompts

[1420] Please collect one month's worth of internal communication data from Company A and send it to the server, including message content, sent date and time, received date and time, positive words, negative words, and total number of messages.

[1421] Analyze the communication data of Company A, extract positive and negative words, and calculate a vitality score based on the total number of messages and the speed of replies.

[1422] "Get Company A's Vitality Score from the API and verify that this score meets the lending criteria. Evaluate other financial data as well, if necessary."

[1423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1424] Step 1:

[1425] A user communicates business-related information using an internal communication application within a company. For example, the user sends a message saying, "The meeting was good." The terminal collects the content of the message sent by the user, the date and time, the date and time it was received, the total number of messages, and the occurrence of positive and negative words. In this case, the terminal collects the message content "The meeting was good" and the date and time it was sent, and counts the positive word "good."

[1426] Input: The message sent by the user

[1427] Output: Collected message content, date and time, and frequency of positive and negative words

[1428] Step 2:

[1429] The device periodically transmits the collected data to the server. Specifically, the device periodically transfers the message content, the date and time of sending, the date and time of receiving, the total number of messages, and the frequency of occurrence of positive and negative words to the server.

[1430] Input: Data collected on the device

[1431] Output: Data sent to the server

[1432] Step 3:

[1433] The server receives the data sent from the terminal and stores it in a database. The server saves the collected message content, the sending date and time, the receiving date and time, the total number of messages, and the frequency of occurrence of positive and negative words in the database.

[1434] Input: Data sent from the terminal

[1435] Output: Data stored in the database

[1436] Step 4:

[1437] The server uses NLP technology to analyze the message content stored in the database. Specifically, the server analyzes the received message content and extracts positive and negative words. For example, the server recognizes and counts the positive word "good" from the message "The meeting was good."

[1438] Input: Message content stored in the database

[1439] Output: Extracted positive and negative words

[1440] Step 5:

[1441] The server calculates the total number of messages and the reply rate. For example, the server calculates that the total number of messages sent in a month is 1000, and the average reply rate is 2 hours.

[1442] Input: The sent and received dates and times of messages stored in the database

[1443] Output: Calculated total number of messages and reply rate

[1444] Step 6:

[1445] The server uses a generative AI model based on the NLP analysis results and statistical data to calculate a company's vitality score. For example, if the number of positive words appearing is 250 and the number of negative words appearing is 50, the generative AI will use this data to calculate a vitality score of 85.

[1446] Input: extracted positive and negative words, calculated statistics

[1447] Output: Company Vitality Score

[1448] Step 7:

[1449] The server stores the calculated vitality score in a database.

[1450] Input: Calculated vitality score

[1451] Output: Vitality scores stored in a database

[1452] Step 8:

[1453] The server provides the calculated vitality score to financial institutions via API. Financial institutions obtain the company's vitality score from the API and make lending decisions based on this score.

[1454] Input: Saved Vitality Score

[1455] Output: Vitality score provided through the API

[1456] (Application example 1)

[1457] 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."

[1458] Communication within industrial facilities is important for improving productivity and the working environment, but there is a lack of means to objectively evaluate and manage the quality of communication between workers. This can lead to a decline in productivity and a deterioration in the working environment. The purpose of this invention is to solve this problem by proposing a system that analyzes communication data within industrial facilities and calculates and provides a vitality score for the industrial facility based on the results.

[1459] 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.

[1460] In this invention, the server includes a means for analyzing usage data of internal communication applications in an industrial facility using a generating AI, a means for calculating a vitality score of the industrial facility based on the results of the analysis of the usage data, and a means for providing the vitality score to a manager, thereby enabling an objective evaluation of the quality of communication within the industrial facility and improving productivity and the working environment.

[1461] "Generative AI" is an artificial intelligence technology that analyzes usage data from internal communication applications and extracts insights from the data.

[1462] An "industrial facility" is a place where manufacturing or production activities are carried out and where many workers and machinery are in operation.

[1463] An "internal communications application" is a software tool that enables communication between workers within an industrial facility, helping them send and receive messages and share information.

[1464] "Usage data" refers to data such as message content, sending date and time, receiving date and time, and total number of messages generated in the process of using an internal communication application.

[1465] The "vitality score" is a numerical representation of the quality of communication and worker activity within an industrial facility, calculated based on the frequency of positive and negative words, the total number of messages, and the speed of replies.

[1466] A "manager" is a person or position that supervises the operation of industrial facilities and the working conditions of workers, and works to improve productivity and the working environment.

[1467] "Positive words" are words with positive or forward-looking meanings that are included in the message content of an internal communication application.

[1468] "Negative words" are words with negative or backward meanings that are included in the message content of an internal communication application.

[1469] "Analysis" is the process of processing usage data from internal communication applications and extracting useful information and patterns from it.

[1470] "Providing" is the act of calculating the vitality score and then transmitting the result to the administrator or related parties.

[1471] This invention relates to a system that collects and analyzes communication data between workers within an industrial facility and uses generative AI to calculate and provide a vitality score for the industrial facility.

[1472] Program processing explanation

[1473] First, the terminal collects usage data, such as message content, sent and received dates and times, and total number of messages, via internal communication applications used within the industrial facility. This terminal is a device used daily by workers and transmits this data to a server in real time.

[1474] The server stores the received usage data in a database and analyzes the message content using TextBlob and other natural language processing (NLP) libraries. Specifically, it extracts positive and negative words from the message content and calculates their frequency. It also calculates statistical data such as the total number of messages and reply speed.

[1475] The server then calculates the industrial facility's vitality score based on the analysis results. This score is calculated based on the frequency of positive and negative words, the total number of messages, and the response speed. The calculated vitality score is provided to the administrator via an API.

[1476] The specific hardware used includes computer terminals, network equipment, and servers in industrial facilities, and the software used includes Python, TextBlob (a natural language processing library), and a database management system (e.g., MySQL).

[1477] Specific examples

[1478] For example, when a worker in an industrial facility sends a message such as "Great job!" or "I'm happy with my performance on the assembly line," the device collects these messages and sends them to the server. The server then analyzes the message content using TextBlob and extracts positive words. Specifically, words such as "great" and "satisfied" are recognized as positive words.

[1479] Based on these analysis results, the server calculates a high vitality score for the industrial facility. At the same time, the total number of messages and average response time are also taken into account as evaluation factors. The calculated vitality score is provided to the administrator via API, and the administrator can use this to consider measures to improve the working environment and productivity throughout the facility.

[1480] Prompt Sentence Examples

[1481] Analyze internal communication data within an industrial facility and calculate a vitality score. For example, the following data is available:

[1482] Message: "Great job!"

[1483] Sent date and time: "2023-01-01 10:00:00"

[1484] Total number of messages: 100

[1485] Calculate a vitality score based on the analysis results and suggest areas for improvement.

[1486] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1487] Step 1:

[1488] The terminal collects messages sent by workers within an industrial facility using an internal communication application. Specifically, it collects data such as message content, the date and time of sending, the date and time of receiving, and the total number of messages. This data is temporarily stored in the terminal. The input of this step is the message sent by the worker, and the output is the collected message data.

[1489] Step 2:

[1490] The terminal periodically sends the collected message data to the server. This data is transferred to the server via the network and stored in a database on the server. The input of this step is the message data collected by the terminal, and the output is the message data sent to the server.

[1491] Step 3:

[1492] The server stores the received message data in a database. Using a database management system (e.g., MySQL), the server saves detailed information such as the sending date and time, the receiving date and time, and the message content in the database. The input to this step is the message data sent from the terminal, and the output is the message data stored in the database.

[1493] Step 4:

[1494] The server analyzes the stored message content using a natural language processing (NLP) library such as TextBlob. It extracts positive and negative words from the message content and calculates their frequency. The input to this step is the message content stored in the database, and the output is frequency data for positive and negative words.

[1495] Step 5:

[1496] The server calculates statistical data such as the total number of messages and reply speed. Specifically, it calculates the average message sending speed, reply speed, total number of messages, etc., and stores them as the respective statistical data. The input to this step is the message sending and receiving information stored in the database, and the output is the calculated statistical data.

[1497] Step 6:

[1498] The server calculates the industrial facility's vitality score based on the extracted positive and negative word frequency data and the calculated statistical data. A scoring algorithm is used to quantify the positive and negative elements and calculate an overall score. The input for this step is the positive and negative word frequency data and statistical data, and the output is the vitality score.

[1499] Step 7:

[1500] The server provides the calculated vitality score to the administrator via API. The administrator considers measures to improve the working environment and productivity in the industrial facility based on the provided vitality score. The input of this step is the calculated vitality score, and the output is the vitality score provided to the administrator.

[1501] 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.

[1502] The system of the present invention uses a generative AI to analyze usage data from an SME's internal communication application, and then combines this with an emotion engine that recognizes user emotions to calculate a company's vitality score. This vitality score is provided to financial institutions to assist in evaluating the company and making lending decisions. Below, we will explain in detail how this system is implemented.

[1503] Overall system configuration

[1504] This system consists of the following components:

[1505] Terminals (devices running internal corporate communication applications)

[1506] Server (performs data analysis, emotion recognition and scoring)

[1507] Emotion engine (analyzes the user's emotional state)

[1508] Financial institution systems (using scores to evaluate and make lending decisions)

[1509] Terminal functions

[1510] The device runs an internal communication application that is used daily by company employees. Users communicate through this application for business purposes. A monitoring tool installed on the device runs in the background and collects the following data:

[1511] Message content

[1512] Message sending and receiving timestamps

[1513] Total number of messages

[1514] Frequency of positive and negative words

[1515] The collected data is encrypted and sent to a server.

[1516] Server-side features

[1517] The server receives the data sent from the device, stores it in a database, and then analyzes the data using generative AI and an emotion engine.

[1518] 1. Analysis using natural language processing (NLP)

[1519] The server's generation AI automatically extracts positive and negative words from the message content and calculates their frequency.

[1520] 2. Emotion Recognition by Emotion Engine

[1521] An emotion engine on the server analyzes the message content and determines the user's emotional state.

[1522] The emotion engine classifies the user's emotions into multiple categories (e.g., joy, sadness, anger, surprise, etc.).

[1523] 3. Calculating statistical data

[1524] Calculate statistics such as total number of messages, reply rate, etc.

[1525] 4. Calculating the vitality score

[1526] The server's scoring algorithm calculates a company's vitality score based on the results of NLP analysis, the results of the emotion engine, and statistical data.

[1527] The generated vitality score is stored in a database and made available to financial institutions via an API.

[1528] Financial institution system functions

[1529] Financial institutions' systems obtain a company's vitality score through the API. Financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions. Specific usage methods are as follows:

[1530] The vitality score of companies that have applied for loans is retrieved and displayed via API.

[1531] Based on the score obtained, we check whether the company's vitality meets certain standards.

[1532] Evaluate alongside traditional financial data, as appropriate.

[1533] Specific examples

[1534] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[1535] Number of positive words: 300

[1536] Number of negative words: 60

[1537] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[1538] Total number of messages: 1200

[1539] Average response time: 1.5 hours

[1540] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to Financial Institution B's system, and the financial institution's staff uses this score to review whether to grant additional financing to Company A.

[1541] As described above, this invention utilizes generative AI and an emotion engine to evaluate the vitality and vigor of a company and support financial institutions in making lending decisions. This will enable more accurate evaluations that reflect the actual vitality of a company, and is expected to lead to more appropriate lending decisions.

[1542] The processing flow will be explained below.

[1543] Step 1:

[1544] When users communicate with each other through internal company communications applications, data such as the content of messages exchanged, timestamps of messages sent and received, and response times are recorded in real time.

[1545] Step 2:

[1546] The monitoring tool installed on the device collects data from internal communication applications at regular intervals, organizes it, encrypts it, and sends it to a server, including the content of messages and the frequency of exchanges.

[1547] Step 3:

[1548] The server stores the received data in a database for analysis, organized by company and stored in an efficiently accessible format.

[1549] Step 4:

[1550] The server's generated AI uses the stored data to perform natural language processing (NLP) analysis, extracting positive and negative words from the message content and recording their frequency.

[1551] Step 5:

[1552] The server's emotion engine determines the user's emotional state from the message content in parallel with NLP analysis. The emotion engine classifies the message content into multiple emotion categories (e.g., joy, sadness, anger, surprise, etc.) and calculates the proportion of each category.

[1553] Step 6:

[1554] The server also calculates statistics such as message totals and reply speeds, for example, reply speed is calculated as the average time it takes for each message to be replied to after it has been sent.

[1555] Step 7:

[1556] Based on the analysis results of the generative AI and emotion engine, as well as statistical data, the server's scoring algorithm calculates a company's vitality score, which is a numerical representation of a company's vitality and activity, expressed on a scale of 0 to 100, for example.

[1557] Step 8:

[1558] The generated vitality scores are stored in a database on the server, and an API is provided to make them accessible to financial institutions, who can then inquire about the company's score via this API.

[1559] Step 9:

[1560] The financial institution's system obtains a company's vitality score via the API, which is then used by financial institution personnel to evaluate the company and make lending decisions.

[1561] Step 10:

[1562] Financial institutions send feedback data on actual loan results and corporate performance back to the server, which then uses this feedback to adjust the AI ​​and scoring algorithm to improve the accuracy of future scores.

[1563] As a result, users, terminals, servers, and financial institutions can work together to build an evaluation system that reflects the dynamism of small and medium-sized enterprises, and support optimal lending decisions.

[1564] Example 2

[1565] 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."

[1566] It has been difficult with conventional technology to quantify a company's vitality and employee emotions and use that information to support financial institutions in making lending decisions. Small and medium-sized enterprises, in particular, lack effective means of analyzing information obtained from daily business communications, making it difficult to accurately assess the actual emotional state of employees and the company's vitality.

[1567] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1568] In this invention, the server includes: means for collecting the content, timestamp, total number, and frequency of positive and negative words in messages sent by users through the company's internal communication application; means for encrypting the collected data and transmitting it to the server; means for the server to receive the encrypted data and store it in a database; means for automatically analyzing the frequency of positive and negative words from the message content using a generative AI model; means for analyzing the user's emotional state and classifying it into multiple emotional categories using an emotion engine; means for calculating statistical information such as the total number of messages and reply speed; means for calculating a company vitality score based on the analysis results and statistical data obtained from the generative AI model and the emotion engine; and means for storing the calculated vitality score in a database and providing it to financial institutions via an API. This allows for accurate evaluation of a company's vitality and employee emotions, enabling financial institutions to make more appropriate lending decisions based on the results.

[1569] A "terminal" is a device on which a company's internal communication application runs, and is a device with which users conduct daily business communications.

[1570] "Server" is a central computing unit for storing collected data and analyzing the data using generative AI models and emotion engines.

[1571] "User" refers to an employee who uses a company's internal communication application to communicate for business purposes.

[1572] A "generative AI model" is an artificial intelligence model based on machine learning that analyzes text data and calculates the frequency of positive and negative words.

[1573] An "emotion engine" is software or algorithm that analyzes the content of a message to determine the user's emotional state and classify it into multiple emotional categories.

[1574] The "vitality score" is a quantified score that measures a company's vitality and the mental state of its employees based on the analysis results of the generative AI model and emotion engine, as well as other statistical data.

[1575] "Data collection means" refers to a system configuration for collecting message content, timestamps, total number of messages, and frequency of positive and negative words from a company's internal communication applications.

[1576] "Data transmission means" refers to the protocols and procedures for encrypting collected data and transmitting it securely to the server.

[1577] "Data storage means" refers to a system configuration that stores data received by the server in a database in an appropriate format so that it can be analyzed later.

[1578] An "API" is an interface that other systems can access programmatically, and is a means for providing health scores to financial institutions' systems.

[1579] "Statistical information" is data used to quantitatively evaluate the usage of a company's internal communication applications, such as the total number of messages and response speed.

[1580] The present invention is a system that evaluates the vitality of a company based on data obtained using the company's internal communication application and provides the results to financial institutions. How this system is implemented will be described in detail below.

[1581] Terminal functions

[1582] The device is a device that runs an internal communication application used by company employees on a daily basis. When a user communicates through this application, a monitoring tool installed on the device runs in the background and collects the following data:

[1583] Message content

[1584] Message sending and receiving timestamps

[1585] Total number of messages

[1586] Frequency of positive and negative words

[1587] The collected data is encrypted and sent to a server over the company's internal network.

[1588] Server-side features

[1589] The server receives the data sent from the device and stores it in a database. The server analyzes the data using the following software and algorithms:

[1590] Natural Language Processing (NLP): Generative AI models such as BERT (Bidirectional Encoder Representations from Transformers) are used to automatically extract positive and negative words from message content and calculate their frequency.

[1591] Emotion Engine: Analyzes message content to determine the user's emotional state. The emotion engine uses a text-based emotion analysis algorithm to classify emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[1592] Calculating statistics: Software for calculating statistics such as total number of messages and reply speed.

[1593] Based on these analysis results, the server uses a scoring algorithm to calculate a company's vitality score, which is then stored in a database and made available to financial institutions via API.

[1594] Financial institution system functions

[1595] Financial institutions' systems receive a company's vitality score through the API, and financial institution personnel use this score in conjunction with other financial data to evaluate the company and make lending decisions.

[1596] Specific examples

[1597] For example, suppose Company A uses an internal communication application to communicate on a daily basis. The device periodically sends chat history from the past month to the server. The server analyzes this data and obtains the following results:

[1598] Number of positive words: 300

[1599] Number of negative words: 60

[1600] Emotion engine analysis results: Happiness 50%, Sadness 20%, Anger 10%, Surprise 20%

[1601] Total number of messages: 1200

[1602] Average response time: 1.5 hours

[1603] Based on this data, generative AI and an emotion engine are used to calculate a vitality score of 87 for Company A. This score is provided to the financial institution's system, and the financial institution's staff uses this score to review whether to grant additional loans to Company A.

[1604] Example prompts for generative AI models

[1605] For example, by inputting a prompt such as "I would like the company's overall vitality score calculated based on last month's employee communication data" into the generative AI model, the process of automatically calculating the company's vitality score will be carried out.

[1606] The above is a specific embodiment of the present invention. The present invention utilizes generative AI and an emotion engine to evaluate a company's vitality and dynamism, supporting financial institutions in making lending decisions. This enables more accurate evaluations that reflect a company's actual vitality, and is expected to lead to more appropriate lending decisions.

[1607] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1608] Step 1:

[1609] Data collection

[1610] Input: Message content sent by a user through a company's internal communication application.

[1611] How it works: A monitoring tool installed on the device collects message content, timestamps, total number of messages, and frequency of positive and negative words.

[1612] Data processing: Organizing and structuring the collected data.

[1613] Output: Structured and organized data (message content, timestamps, positive word frequencies, negative word frequencies, etc.).

[1614] Step 2:

[1615] Data transmission

[1616] Input: The data collected and structured in Step 1.

[1617] How it works: The device encrypts the data and sends it to the server over the company's internal network (e.g., TLS protocol).

[1618] Data processing: Data encryption and transmission.

[1619] Output: The encrypted data sent to the server.

[1620] Step 3:

[1621] Data storage

[1622] Input: The encrypted data received by the server.

[1623] What it does: The server decrypts the data it receives and stores it in a database.

[1624] Data calculation: Decrypt the data and store it in the database.

[1625] Output: Decrypted data stored in a database.

[1626] Step 4:

[1627] Natural Language Processing (NLP) Analysis

[1628] Input: Message content stored in the database.

[1629] How it works: A generative AI model on the server analyzes message content and calculates the frequency of positive and negative words.

[1630] Data calculation: Word frequency calculation through text analysis (example model: BERT).

[1631] Output: Positive and negative word frequency data.

[1632] Step 5:

[1633] Emotion recognition by emotion engine

[1634] Input: Message content data obtained in step 4.

[1635] How it works: The server's emotion engine analyzes the user's emotional state and classifies emotions into multiple categories (e.g., joy, sadness, anger, surprise).

[1636] Data Computing: Sentiment Classification through Sentiment Analysis Algorithms.

[1637] Output: Distribution data for each emotion category.

[1638] Step 6:

[1639] Statistical Data Calculations

[1640] Input: Analysis results from the previous stage, total number of messages, reply speed, etc.

[1641] How it works: The server calculates statistics such as message totals, reply speed, etc.

[1642] Data calculation: Statistical calculations (total number of messages, average reply speed, etc.).

[1643] Output: Statistics data.

[1644] Step 7:

[1645] Calculating vitality score

[1646] Input: Analysis results of natural language processing and emotion engine, statistical data.

[1647] How it works: The server's scoring algorithm calculates a vitality score based on these inputs.

[1648] Data calculation: Comprehensive evaluation using a scoring algorithm.

[1649] Output: Company Vitality Score.

[1650] Step 8:

[1651] Providing scores

[1652] Input: Vitality score calculated in step 7.

[1653] How it works: The server stores the vitality score in a database and makes it available to financial institutions via an API.

[1654] Data Computing: Managing API endpoints and providing data.

[1655] Output: Vitality score provided to financial institutions.

[1656] The above are the specific processing steps and detailed operations for implementing the invention. By explaining the data input and output at each step and the specific operations, the flow of the entire system becomes clear, enabling the invention to be implemented effectively.

[1657] (Application example 2)

[1658] 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."

[1659] Conventional factory performance evaluations rely primarily on mechanical data and human intuition, making it difficult to accurately evaluate the overall health and work efficiency of the factory. This invention solves this problem by comprehensively analyzing the operation data of robots in the factory and the message data of workers, and quantitatively evaluating the overall factory performance based on the results.

[1660] 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 analyzing operation data and message data within the factory using a generation AI, means for calculating a performance score based on the analysis results of the operation data and message data, and means for providing the performance score to the management system. This makes it possible to accurately evaluate the health status and work efficiency of the entire factory and derive appropriate maintenance and work environment improvement measures.

[1661] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data.

[1662] "Operational data" refers to operational information such as the operating status of robots and machines in a factory and the frequency of errors.

[1663] "Message data" refers to text messages and communications exchanged between workers and staff within a factory.

[1664] The "performance score" is an overall evaluation index calculated based on the operation data and message data of robots and workers in the factory.

[1665] A "management system" is an information system for operating and managing a factory, and its role is to integrate, display, and manage data such as performance scores.

[1666] The system of the present invention uses generative AI to analyze motion data and message data to evaluate the performance of robots and workers in a factory, and calculates a performance score from the results. This system consists of the following components:

[1667] Overall system configuration

[1668] 1. Server:

[1669] The server plays a central role in analyzing the data using generative AI and emotion engines.

[1670] For actual data analysis, we use the NLPProcessor, which performs natural language processing (NLP), and the EmotionEngine, which performs emotion recognition.

[1671] 2. Terminal:

[1672] The terminal is responsible for collecting operational data and message data from various sensors and communication devices within the factory.

[1673] The data collected by the device is encrypted and sent to the server.

[1674] 3. Management system:

[1675] The management system provides an interface to visualize evaluation results such as performance scores and support appropriate measures.

[1676] Program Description

[1677] 1. Data Collection:

[1678] Operational data such as operating time and frequency of errors is collected from robots in factories.

[1679] Message data is collected from workers through an internal communication application.

[1680] The collected data is sent to a server via the terminal.

[1681] 2. Data Analysis:

[1682] The server uses the NLPProcessor to analyze the message data and calculate the frequency of occurrence of positive and negative words.

[1683] At the same time, the Emotion Engine is used to analyze the emotional state of the worker from the message data and calculate an emotion score.

[1684] 3. Calculation of Performance Score:

[1685] The server integrates the collected motion data and emotion data to calculate a performance score.

[1686] The performance score is a quantitative assessment of the overall health and work efficiency of the factory.

[1687] 4. Providing results:

[1688] The calculated performance scores are provided to the management system so that factory managers can easily view them.

[1689] Based on this information, appropriate measures can be taken to maintain the robot and improve the working environment.

[1690] Specific examples

[1691] For example, suppose the following data is collected at a factory:

[1692] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[1693] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[1694] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[1695] Based on this data, a performance score was calculated, resulting in a score of 70. This information was notified to managers and used as a reference for taking measures to maintain the robot and improve the working environment.

[1696] Example of input prompt for generative AI model

[1697] "Based on the factory robot's operational data and the messages from the workers, please calculate and report an overall score. Use the following data."

[1698] Robot 1 operating data: Operating time 20 hours / day, error rate 0.2%

[1699] Worker messages: 5,000 (positive words: 300 times, negative words: 50 times)

[1700] Emotion engine results: Joy 40%, Anger 20%, Sadness 10%

[1701] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1702] Step 1:

[1703] This system collects operation data and message data from robots and workers in the factory. The terminal acquires data from the internal communication applications of each robot and worker, encrypts this data, and sends it to the server. For example, the system collects information such as the robot's operating time, error rate, and messages exchanged by workers via the internal communication application. The input is the robot and worker data, and the output is encrypted data sent to the server.

[1704] Step 2:

[1705] The server stores the received operation data and message data in a database. The server receives encrypted data sent from the terminal, decrypts it to its original format, and stores it in the database. The input is the encrypted data, and the output is the format stored in the database.

[1706] Step 3:

[1707] The server analyzes message data using an NLPProcessor. The NLPProcessor extracts positive and negative words from the message and calculates their frequency of occurrence. The input is the message data, and the output is the frequency of occurrence of positive and negative words. Specifically, the words in the message are tokenized, classified into positive and negative categories using a synonym dictionary, and the frequency of occurrence is counted.

[1708] Step 4:

[1709] The server uses the Emotion Engine to analyze the emotional state from the message data. The Emotion Engine analyzes the message data and calculates an emotional score such as joy, sadness, or anger. The input is the message data, and the output is the emotional score. Specifically, it receives the message text as input, assigns an emotional label using a pre-trained model, and calculates a probability score for each emotion.

[1710] Step 5:

[1711] The server calculates a performance score based on the operational data and emotional score. The operational data (e.g., uptime, error rate) and emotional score (e.g., 40% joy) are integrated and weighted to calculate a performance score as an overall evaluation. The input is the operational data and emotional score, and the output is the performance score. Specifically, the server normalizes various data and calculates an overall score based on a pre-set evaluation algorithm.

[1712] Step 6:

[1713] The server provides the calculated performance scores to the management system. The management system visualizes the provided performance scores and displays them via an interface so that factory managers can view them. The input is the performance scores, and the output is the visualized evaluation results. Specifically, the performance scores are displayed on the management system's dashboard, and appropriate actions are suggested based on the results.

[1714] 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.

[1715] 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.

[1716] 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 robot 414.

[1717] 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.

[1718] FIG. 9 illustrates 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 behaviors 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.

[1719] 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.

[1720] 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).

[1721] 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.

[1722] 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."

[1723] 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.

[1724] 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).

[1725] 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.

[1726] 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.

[1727] 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.

[1728] 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.

[1729] 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.

[1730] 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.

[1731] 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.

[1732] 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.

[1733] 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 example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1734] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1735] The following is further disclosed regarding the above embodiment.

[1736] (Claim 1)

[1737] A means of analyzing usage data of a company's internal communication applications using generative AI;

[1738] A means for calculating a company vitality score based on the analysis results of the usage data;

[1739] means for providing said vitality score to a financial institution;

[1740] A system including:

[1741] (Claim 2)

[1742] 2. The system according to claim 1, wherein the generation AI comprises means for analyzing message content of a communication application and calculating the frequency of positive and negative words.

[1743] (Claim 3)

[1744] 2. The system of claim 1, wherein the vitality score is calculated based on a total number of messages and a reply rate in an internal communication application of a company.

[1745] "Example 1"

[1746] (Claim 1)

[1747] means for the terminal to collect data using a communication application;

[1748] A means for the server to receive the data transmitted from the terminal and extract positive words and negative words using natural language processing (NLP) technology;

[1749] a means for the server to calculate the total number of messages and reply rate;

[1750] A means for the server to calculate a company's vitality score using generated AI;

[1751] The server calculates the vitality score, stores it in a database, and provides it to financial institutions via API.

[1752] A system including:

[1753] (Claim 2)

[1754] 2. The system according to claim 1, wherein the server comprises means for analyzing message content of a communication application and calculating the frequency of positive and negative words.

[1755] (Claim 3)

[1756] 2. The system of claim 1, wherein the vitality score is calculated based on a total number of messages and a reply rate in an internal communication application of a company.

[1757] "Application Example 1"

[1758] (Claim 1)

[1759] A means for analyzing usage data of internal communication applications in an industrial facility using generative AI;

[1760] means for calculating a vitality score of the industrial facility based on the analysis results of the usage data;

[1761] means for providing the vitality score to a manager;

[1762] A system including:

[1763] (Claim 2)

[1764] 2. The system according to claim 1, wherein the generation AI comprises means for analyzing message content of an internal communication application to calculate the frequency of positive and negative words.

[1765] (Claim 3)

[1766] 10. The system of claim 1, wherein the health score is calculated based on a total number of messages and a reply rate in an internal communication application of an industrial facility.

[1767] "Example 2: Combining Emotion Engines"

[1768] (Claim 1)

[1769] A means for collecting the content, timestamp, total number, and frequency of positive and negative words in messages sent by users through the company's internal communication application;

[1770] means for encrypting the collected data and transmitting it to a server;

[1771] means for the server to receive the encrypted data and store it in a database;

[1772] A means for automatically analyzing the frequency of positive and negative words from message content using a generative AI model;

[1773] means for analyzing a user's emotional state and classifying it into a plurality of emotional categories using an emotion engine;

[1774] a means for calculating statistics such as message totals and reply rates;

[1775] A means for calculating a company's vitality score based on the analysis results and statistical data obtained from the generative AI model and the emotion engine;

[1776] The calculated vitality score is stored in a database and provided to financial institutions via API.

[1777] A system including:

[1778] (Claim 2)

[1779] 2. The system of claim 1, wherein the generative AI model comprises means for analyzing message content of a communication application to calculate the frequency of positive and negative words.

[1780] (Claim 3)

[1781] 2. The system of claim 1, wherein the vitality score is calculated based on a total number of messages and a reply rate in an internal communication application of a company.

[1782] "Application example 2 when combining emotion engines"

[1783] (Claim 1)

[1784] A means for analyzing operation data and message data in a factory using a generative AI;

[1785] means for calculating a performance score based on the analysis results of the action data and message data;

[1786] means for providing said performance scores to a management system;

[1787] A system including:

[1788] (Claim 2)

[1789] 2. The system according to claim 1, wherein the generation AI comprises means for analyzing the content of a worker's message and calculating the frequency of positive and negative words.

[1790] (Claim 3)

[1791] 2. The system of claim 1, wherein the performance score is calculated based on operational data within a factory. [Explanation of symbols]

[1792] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing usage data of an enterprise's internal communication application using generative AI; A means for calculating a company vitality score based on the analysis results of the usage data; means for providing the vitality score to a financial institution; A system including:

2. 2. The system of claim 1, wherein the generating AI comprises means for analyzing message content of a communication application to calculate frequencies of positive and negative words.

3. 2. The system of claim 1, wherein the vitality score is calculated based on a total number of messages and a reply rate in an internal communication application of a company.

Images