System

Abstract

To provide a system.SOLUTION: A system comprises: means for analyzing an organizational culture from the content of electronic communication; means for diagnosing the organizational culture on the basis of an analysis result of the organizational culture; means for comparing a diagnostic result of the organizational culture with a diagnostic result of an organizational culture of other organization; means for proposing an improvement action on the basis of a comparison result obtained by comparing the diagnostic result; and means for supporting an improvement cycle on the basis of the proposed improvement action.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Organizational culture has a significant impact on organizational performance, but evaluation and improvement of organizational culture can be subjective, and specific improvement measures can be difficult to find. [Means for solving the problem]

[0005] This invention analyzes organizational culture from the content of emails and chats, and diagnoses the culture of each organization (department / section). Furthermore, it compares the diagnostic results with those of other organizations and proposes improvement actions. Then, by supporting the improvement cycle based on the proposed improvement actions, it is possible to objectively and specifically evaluate and improve organizational culture. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, the contents of emails and chats within an organization are collected. The collected data is analyzed using natural language processing technology to extract elements that serve as indicators of organizational culture (e.g., the level of active communication, whether specific values ​​are being adopted, etc.).

[0029] "Example 2"

[0030] Next, the culture of each organization (department / section) is diagnosed based on the extracted elements. The results are stored in a database that allows comparison with other organizations.

[0031] "Example 3"

[0032] Furthermore, improvement actions are proposed based on the results of the diagnosis. The proposed improvement actions are notified to relevant parties within the organization to help start the improvement cycle. Specifically, for departments where communication is sluggish, actions such as holding regular meetings or proposing team-building activities could be considered.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Collect email and chat content from within the organization. Specifically, obtain data from the organization's email server and chat tools.

[0036] Step 2: Analyze the collected data using natural language processing technology. Specifically, using techniques such as text mining and sentiment analysis, extract elements such as the level of communication activity and whether specific values ​​are being calculated.

[0037] "Example 2"

[0038] Step 1: Diagnose the culture of each organization (department / section) based on the extracted elements. Specifically, evaluate the extracted elements as indicators of organizational culture and diagnose the culture of each organization.

[0039] Step 2: The diagnostic results are stored in a database. Specifically, the diagnostic results are classified by organization and stored in a database that allows comparison with other organizations.

[0040] "Example 3"

[0041] Step 1: Propose improvement actions based on the diagnosis results. Specifically, for departments where communication is sluggish, consider actions such as holding regular meetings or proposing team-building activities.

[0042] Step 2: Notify the relevant parties within the organization of the proposed improvement actions. Specifically, communicate the improvement actions to the relevant parties via email or chat tools and help start the improvement cycle.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form 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."

[0045] Conventional organizational culture analysis systems have had difficulty effectively collecting and analyzing email and chat content to extract indicators of organizational culture. Furthermore, they lacked a means to display the extracted indicators in an easy-to-understand manner for users, making it difficult to propose specific guidelines for action aimed at improving organizational culture. This made it impossible to accurately evaluate the level of communication within an organization or the degree to which values ​​are shared, and to take appropriate action to improve it.

[0046] 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.

[0047] In this invention, the server includes means for collecting email and chat content, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology, means for extracting indicators of organizational culture from the analysis results, and means for displaying the extracted indicators to the user. This makes it possible to accurately evaluate the level of communication within the organization and the degree of shared values, and to provide the user with specific guidelines for action.

[0048] "Email" means a digital message sent or received over the Internet or other computer network.

[0049] "Chat" is a means of communication for exchanging text messages in real time.

[0050] "Means of collection" refers to the technology and process used to capture email and chat content and store it in a database.

[0051] "Preprocessing means" refers to techniques and processes such as data cleaning and tokenization that prepare collected data in a form that is easier to analyze.

[0052] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language.

[0053] "Analysis means" are techniques or processes that use pre-processed data to extract specific information or patterns.

[0054] "Organizational culture indicators" are specific indicators for evaluating an organization's culture, such as the level of communication within the organization and the degree of shared values.

[0055] "Means of extraction" refers to the techniques and processes used to extract useful information and indicators from the analysis results.

[0056] The "display means" refers to the techniques and processes for visually presenting the extracted indicators to the user.

[0057] A "generative AI model" is a model that uses artificial intelligence to generate new information and indicators from data.

[0058] This invention is a system that collects the contents of emails and chats within an organization, analyzes them using natural language processing technology, extracts indicators of organizational culture, and provides users with specific guidelines for action.

[0059] Data collection

[0060] The server collects email and chat content. Specifically, it uses common communication platforms such as Microsoft® Exchange Server and Slack® API to obtain email and chat history within the organization. This allows the communication data within the organization to be stored in a database.

[0061] Data Preprocessing

[0062] The server preprocesses the collected data, which includes text cleaning (removing unnecessary characters and spaces), tokenization (splitting words and sentences), and stop-word removal (removing common words). This is done using natural language processing libraries such as Python's NLTK and spaCy.

[0063] Natural Language Processing (NLP)

[0064] The server then analyzes the preprocessed data using natural language processing techniques. Specifically, it performs sentiment analysis and topic modeling to extract useful information from the text data. Sentiment analysis is performed using the Python spaCy library, and topic modeling is performed using LDA (Latent Dirichlet Allocation).

[0065] Extracting indicators

[0066] The server extracts indicators of organizational culture from the analysis results. For example, it evaluates the level of active communication or the extent to which specific values ​​are shared. A generative AI model (e.g., GPT-4 (registered trademark) from OpenAI (registered trademark)) is used for this evaluation. Using the generative AI model, specific indicators of organizational culture are generated based on the analysis results.

[0067] Displaying the results

[0068] The terminal displays the extracted indicators to the user. The user can log in to the system and check the indicators of organizational culture. For example, when the user types "Tell me how active communication was last month" into the terminal, the server retrieves the corresponding indicators from the database and sends them to the terminal. The terminal displays the retrieved indicators to the user.

[0069] Specific examples

[0070] Suppose a user logs into the system and wants to check how active communication is within their organization. The user types in "Tell me how active communication was last month" on their terminal. The server analyzes the collected email and chat data and generates a result using a generative AI model. The result is displayed as "Communication was very active last month, with particularly a lot of discussion about Project X."

[0071] Prompt Sentence Examples

[0072] "Analyze email and chat content within your organization to assess communication intensity and shared values."

[0073] In this way, the server is a system that consistently performs data collection, analysis, and indicator extraction, providing users with specific indicators of organizational culture.

[0074] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0075] Step 1: Data collection

[0076] The server collects email and chat content. Specifically, it retrieves data from email servers and chat platforms through APIs. The input is raw data retrieved from the email and chat APIs, and the output is unprocessed text data stored in a database. Specifically, the server periodically calls the API to retrieve new messages and store them in the database.

[0077] Step 2: Data Preprocessing

[0078] The server preprocesses the collected data. The input is raw text data stored in a database, and the output is preprocessed, clean text data. Specifically, the server uses Python's NLTK and spaCy libraries to tokenize the text data, remove unnecessary characters and spaces, and remove stop words.

[0079] Step 3: Natural Language Processing (NLP)

[0080] The server analyzes the preprocessed data using natural language processing technology. The input is preprocessed clean text data, and the output is a sentiment score and topic model as the analysis results. Specifically, the server performs sentiment analysis using the Python spaCy library and performs topic modeling using LDA (Latent Dirichlet Allocation).

[0081] Step 4: Extracting metrics

[0082] The server extracts organizational culture indicators from the analysis results. The input is the analysis results such as sentiment scores and topic models, and the output is the organizational culture indicators. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate specific organizational culture indicators based on the analysis results.

[0083] Step 5: View the results

[0084] The terminal displays the extracted indicators to the user. The input is the indicators of organizational culture, and the output is specific indicator information displayed to the user. In concrete terms, when the user types "Tell me how active communication was last month" into the terminal, the server retrieves the corresponding indicators from the database and sends them to the terminal. The terminal then displays the retrieved indicators to the user.

[0085] (Application example 1)

[0086] Next, a description will be given of Application Example 1 of Embodiment 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."

[0087] Conventional organizational culture analysis systems primarily target email and chat content in office environments, and do not provide information on improving communication, work efficiency, or safety within factories. Furthermore, they lack real-time feedback functionality, making it difficult to take immediate action to improve. This has resulted in insufficient efforts to improve work efficiency and safety within factories.

[0088] 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.

[0089] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for analyzing communication within the factory and providing information useful for improving work efficiency and safety, and means for providing feedback to managers and workers in real time, thereby enabling improvements in work efficiency and safety within the factory.

[0090] "Email" means a digital message sent or received over the Internet or other network.

[0091] "Chat" is a means of communication for exchanging text messages in real time.

[0092] "Organizational culture" is the set of values, beliefs, and behaviors shared within an organization.

[0093] An "analytical means" is a method or device for collecting data and analyzing that data using specific algorithms or techniques.

[0094] A "diagnostic means" is a method or device for assessing a particular condition or problem based on the results of an analysis.

[0095] A "comparison tool" is a method or device for contrasting different data sets or results to find differences and commonalities.

[0096] "Proposal means" refers to a method or device for suggesting specific actions or improvement measures based on the results of analysis or diagnosis.

[0097] "Supporting measures" are methods or devices that provide the necessary support and resources in implementing the proposed actions or improvements.

[0098] "Communication within the factory" refers to the exchange of information and communication between workers and managers within the factory.

[0099] "Work efficiency" is an index that indicates how much work can be completed within a certain time.

[0100] "Safety" is an indicator of how safe the work environment and work processes are to avoid accidents and dangers.

[0101] A "means for providing feedback" is a method or device for returning information in real time based on the results of analysis or diagnosis.

[0102] A system for carrying out the present invention includes a program that collects the contents of emails and chats and analyzes them using natural language processing technology. A specific embodiment of this system is described below.

[0103] The server first collects email and chat content, which involves connecting to a mail server such as an IMAP server and retrieving all emails from the user's mailbox. The retrieved email content is collected in text format.

[0104] Next, the server uses natural language processing technology to analyze the collected email and chat content. Specifically, it uses NLTK's VADER Sentiment Analyzer to perform sentiment analysis on each email. It also performs TF-IDF vectorization to convert the email content into a numerical vector. Finally, it clusters the email content using KMeans clustering.

[0105] Based on the analysis results, the server diagnoses the culture of each organization (department / section) and compares the results with other organizations, making it possible to evaluate the level of communication within the organization and whether specific values ​​are being adopted.

[0106] Furthermore, the server proposes improvement actions based on the diagnosis results, including specific guidelines for improving organizational culture. Based on the proposed improvement actions, the server supports the improvement cycle.

[0107] The server analyzes communications within the factory and provides real-time feedback to managers and workers to provide information that will help improve work efficiency and safety. This feedback is based on the results of analysis and diagnosis.

[0108] As a concrete example, the following prompt sentence could be input to a generative AI model:

[0109] "I want to develop an application that analyzes communications within a factory and provides information that will help improve work efficiency and safety. I want to apply technology that collects email and chat content and analyzes it using natural language processing technology to extract elements that serve as indicators of organizational culture."

[0110] By inputting this prompt into a generative AI model, more specific analysis results and ideas for how to provide feedback can be obtained.

[0111] The hardware used is a mail server (e.g., IMAP server) and a computer that performs analysis. The software used is Python, NLTK, and Scikit-learn. This will enable improved work efficiency and safety within the factory.

[0112] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0113] Step 1:

[0114] The server collects emails and chat messages. Specifically, it connects to the IMAP server and retrieves all messages from the user's mailbox. The input is the user's email account information, and the output is the email message in text format.

[0115] Step 2:

[0116] The server saves the collected email and chat content in text format. The input is the email content acquired in step 1, and the output is the email content saved in a text file or database.

[0117] Step 3:

[0118] The server uses natural language processing technology to analyze the content of collected emails and chats. Specifically, it uses NLTK's VADER Sentiment Analyzer to perform sentiment analysis of each email. The input is the text content of the email, and the output is a sentiment score for each email.

[0119] Step 4:

[0120] The server performs TF-IDF vectorization to convert the email content into a numerical vector. The input is the email content in text format, and the output is a numerical vector.

[0121] Step 5:

[0122] The server clusters the email content using KMeans clustering. The input is a numeric vector, and the output is a cluster label for each email.

[0123] Step 6:

[0124] The server diagnoses the culture of each organization (department / section) based on the analysis results. The input is the emotion score and cluster label, and the output is the organizational culture diagnosis result.

[0125] Step 7:

[0126] The server compares the diagnosis results with other organizations. The input is the diagnosis results of the organizational culture, and the output is the comparison results with other organizations.

[0127] Step 8:

[0128] The server proposes improvement actions based on the diagnosis results. The input is the organizational culture diagnosis results and the results of comparison with other organizations, and the output is a proposal of specific improvement actions.

[0129] Step 9:

[0130] The server supports an improvement cycle based on the proposed improvement actions, with the input being the proposed improvement actions and the output being support information for the improvement cycle.

[0131] Step 10:

[0132] The server analyzes communications within the factory and provides information useful for improving work efficiency and safety. The input is the analysis results of emails and chats, and the output is information related to work efficiency and safety.

[0133] Step 11:

[0134] The server provides real-time feedback to managers and workers. The input is information about work efficiency and safety, and the output is feedback to managers and workers.

[0135] Example 2

[0136] Next, a description will be given of Example 2 of Form 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."

[0137] Conventional organizational culture diagnostic systems analyze organizational culture solely from email and chat content, which can result in biased and incomplete data. Furthermore, the criteria for comparing diagnostic results with other organizations are often vague, and suggested improvement actions often lack specificity. This makes it difficult to accurately diagnose organizational culture and make effective improvements.

[0138] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for extracting cultural elements from the preprocessed data, a means for diagnosing the culture of each organization based on the extracted cultural elements, a means for comparing the diagnosis results with other organizations, and a means for storing the diagnosis results in a database. This enables accurate diagnosis of organizational culture and comparison with other organizations, and makes it possible to propose specific improvement actions.

[0139] "Means for collecting data" refers to a device or method for collecting data such as feedback from users and survey results.

[0140] "Means for pre-processing collected data" refers to a device or method for pre-processing collected data, such as cleaning and tokenizing it.

[0141] A "means for extracting cultural elements" is a device or method for extracting organizational cultural elements from data preprocessed using a generative AI model.

[0142] The "means for diagnosing the culture of each organization" is a device or method for diagnosing the culture of each organization based on the extracted cultural elements.

[0143] "Means for comparing diagnostic results with other tissues" refers to a device or method for comparing diagnostic results with diagnostic results of other tissues.

[0144] The "means for storing diagnostic results in a database" refers to a device or method for storing the generated diagnostic results in a database.

[0145] A "generative AI model" is a model that uses artificial intelligence to generate specific information from data.

[0146] A "prompt" is an instruction sentence input to a generative AI model, which contains a question or command to extract specific information.

[0147] The present invention relates to a system for diagnosing the culture of an organization and comparing it with other organizations. A specific embodiment of this system will be described below.

[0148] First, the user collects data about the organization's culture, such as employee feedback and survey results. The user then sends this data to the server via their device. The data is often sent in CSV or JSON format.

[0149] Next, the server preprocesses the received data. Specifically, it cleans the data (removes unnecessary characters and noise) and tokenizes it (divides the text into words). The server preprocesses the text data using the Python libraries NLTK and spaCy.

[0150] The server then uses a generative AI model (e.g., a model using artificial intelligence) to extract cultural elements from the preprocessed data. The server inputs prompt sentences into the generative AI model to extract cultural elements. Specific examples of prompt sentences include the following:

[0151] "Please extract organizational culture elements from the following feedback data:

[0152] 1. There is active communication between team members.

[0153] 2. New ideas are frequently proposed.

[0154] 3. Cooperation among employees is emphasized.

[0155] By inputting this prompt into a generative AI model, the model extracts cultural elements such as "communication," "innovation," and "cooperation."

[0156] Next, the server generates a cultural diagnosis of the organization based on the extracted cultural elements. The diagnosis results are formatted in a format that allows comparison with other organizations. For example, the server may generate a diagnosis result such as, "This organization has active communication and frequent innovation."

[0157] Finally, the server stores the generated diagnostic results in a database, which facilitates comparison with other organizations. The server stores data using an RDBMS such as MySQL (registered trademark) or PostgreSQL.

[0158] This system enables accurate diagnosis of organizational culture and comparison with other organizations, enabling proposals for specific improvement actions.

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

[0160] Step 1: Data collection

[0161] Users collect data about their organization's culture, including employee feedback and survey results.

[0162] Input: Feedback and survey result data.

[0163] Output: Collected data.

[0164] Specific operation: The terminal receives the data entered by the user into the questionnaire form and sends it to the server.

[0165] Step 2: Data Preprocessing

[0166] The server preprocesses the received data, specifically cleaning the data (removing unnecessary characters and noise) and tokenizing (dividing the text into words).

[0167] Input: Collected data.

[0168] Output: Preprocessed data.

[0169] Specific operation: Remove unnecessary spaces and special characters from the feedback data received by the server and split it into words. Uses Python libraries NLTK and spaCy.

[0170] Step 3: Extracting cultural elements

[0171] The server uses a generative AI model to extract cultural elements from the pre-processed data.

[0172] Input: Preprocessed data.

[0173] Output: Extracted cultural elements.

[0174] Specific operation: The server inputs the prompt statement, "Please extract organizational cultural elements from the following feedback data: 1. Communication between team members is active. 2. New ideas are frequently proposed. 3. Cooperation between employees is emphasized," into the generative AI model, and extracts cultural elements such as "communication," "innovation," and "cooperation."

[0175] Step 4: Generate diagnostic results

[0176] The server generates a cultural diagnosis result for the organization based on the extracted cultural elements.

[0177] Input: Extracted cultural elements.

[0178] Output: Organizational culture diagnostic results.

[0179] Specific operation: Based on the extracted cultural elements, the server generates diagnostic results such as "This organization has active communication and frequent innovation."

[0180] Step 5: Store in the database

[0181] The server stores the generated diagnostic results in a database.

[0182] Input: Organizational culture diagnostic results.

[0183] Output: Diagnostic results stored in a database.

[0184] Specific operation: The diagnostic results generated by the server are saved in a database in the form of "organization ID," "cultural elements," "diagnosis results," etc. RDBMS such as MySQL or PostgreSQL is used.

[0185] (Application example 2)

[0186] Next, a description will be given of Application Example 2 of Form 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."

[0187] Conventional organizational culture diagnostic systems were limited to analyzing organizational culture based on the content of emails and chats, making it difficult to diagnose the work patterns and communication styles of each department within a factory in real time.In addition, they lacked the functionality to propose an efficient work environment based on the diagnostic results, making it difficult to contribute to improving productivity throughout the organization.

[0188] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0189] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for collecting data from sensors and cameras, means for inputting the collected data into a generative AI model to diagnose the culture of each department, means for storing the diagnosis results in a database and comparing them with other departments, and means for generating a report proposing an efficient work environment. This makes it possible to diagnose the work patterns and communication styles of each department in a factory in real time and propose an efficient work environment.

[0190] "Email" means a digital message sent or received over the Internet.

[0191] "Chat" is a means of communication for exchanging text messages in real time.

[0192] "Organizational culture" is the set of values, beliefs, and behaviors shared within an organization.

[0193] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[0194] "Diagnosis" is the act of identifying a specific condition or problem based on data.

[0195] "Comparison" is the act of contrasting two or more objects and revealing their differences and similarities.

[0196] An "improvement action" is a specific action or measure taken to solve a specific problem.

[0197] An "improvement cycle" is a series of processes for continuous improvement.

[0198] A "sensor" is a device that detects physical phenomena and converts them into data.

[0199] A "camera" is a device that captures images or videos.

[0200] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information or predictions from data.

[0201] A "database" is a system for efficiently storing, managing, and retrieving data.

[0202] A "report" is a document that organizes and reports information on a specific topic.

[0203] "Work environment" is the collective term for the physical and psychological environment in which work takes place.

[0204] A system for carrying out the present invention has the following configuration: The server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for collecting data from sensors and cameras, means for inputting the collected data into a generative AI model to diagnose the culture of each department, means for storing the diagnosis results in a database and comparing them with other departments, and means for generating a report that proposes an efficient work environment.

[0205] First, the server uses sensors and cameras installed in the factory to collect real-time data on the work patterns and communication styles of each department. The collected data is preprocessed using OpenCV, an image processing library, to extract features. Next, the extracted features are input into a generative AI model to diagnose the culture of each department. This generative AI model is built using scikit-learn, a machine learning library.

[0206] The results of the diagnosis are stored in a database and compared with those of other departments. The database stores past data and best practices for proposing efficient work environments. The server generates reports that suggest efficient work environments based on this data. These reports are provided in dashboard format for users to view.

[0207] As a concrete example, consider the case of diagnosing the culture of the assembly department and the inspection department and proposing an efficient work environment. The server diagnoses the work patterns and communication style of the assembly department and inputs prompt sentences to the generative AI model to propose an efficient work environment. An example of a prompt sentence is as follows:

[0208] "Please diagnose the work patterns and communication styles of the assembly department and propose an efficient work environment."

[0209] This prompt can be used to input data into the generative AI model to obtain diagnostic results. Based on the diagnostic results, the server generates a report suggesting an efficient work environment and provides it to the user.

[0210] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0211] Step 1:

[0212] The server uses sensors and cameras installed in the factory to collect real-time data on the work patterns and communication styles of each department. The input is data from the sensors and cameras, and the output is the collected raw data. Specifically, the cameras periodically capture images, and the sensors collect environmental data (temperature, humidity, volume, etc.).

[0213] Step 2:

[0214] The server preprocesses the collected data using OpenCV, an image processing library. The input is the raw data collected in step 1, and the output is the preprocessed data. Specifically, the image data is converted to grayscale, and noise removal and edge detection are performed.

[0215] Step 3:

[0216] The server extracts features from the preprocessed data. The input is the preprocessed data, and the output is the extracted features. Specifically, it uses the SIFT (Scale-Invariant Feature Transform) algorithm to detect feature points in the image and generate a feature vector.

[0217] Step 4:

[0218] The server inputs the extracted features into a generative AI model to diagnose the culture of each department. The input is the features, and the output is the diagnosis result. Specifically, the generative AI model is built using the scikit-learn library, and performs clustering and classification based on the features.

[0219] Step 5:

[0220] The server stores the diagnostic results in a database. The input is the diagnostic results, and the output is the diagnostic results stored in the database. Specifically, the server inserts the diagnostic results into the appropriate tables using a database management system (DBMS).

[0221] Step 6:

[0222] The server compares the results with those of other departments based on the diagnostic results stored in the database. The input is the diagnostic results stored in the database, and the output is the comparison results. Specifically, it uses SQL queries to compare with the diagnostic results of other departments and perform statistical analysis.

[0223] Step 7:

[0224] The server generates a report proposing an efficient work environment. The input is the comparison result, and the output is a proposal report. Specifically, the server uses a report generation tool to create a document proposing an efficient work environment based on the comparison result.

[0225] Step 8:

[0226] The user views the report generated by the server in the form of a dashboard. The input is the proposal report, and the output is the dashboard that the user views. Specifically, the user accesses the dashboard using a web browser and checks the proposal report.

[0227] Example 3

[0228] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0229] Conventional organizational culture analysis systems simply analyze the content of emails and chats, but are inadequate in proposing specific improvement actions or supporting their implementation. Furthermore, there is a lack of a way to effectively communicate the analysis results to relevant parties, which often delays the start of the improvement cycle. This creates the problem of not improving the quality and efficiency of communication throughout the organization.

[0230] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0231] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for performing sentiment analysis and topic modeling of text data using a generative AI model, and means for notifying relevant parties of the proposed improvement actions using a notification system. This makes it possible to perform a detailed analysis of the communication situation within an organization and quickly propose and notify specific improvement actions.

[0232] "Email" is a means of communication for sending and receiving text and files over the Internet.

[0233] "Chat" is a means of communication for exchanging text messages in real time.

[0234] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[0235] "Analysis" is the process of examining data in detail to understand its meaning and structure.

[0236] "Diagnosis" is a means of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[0237] "Comparison" is a means of contrasting different data or results and revealing their differences and similarities.

[0238] "Improvement actions" are specific guidelines and measures proposed based on the diagnostic results.

[0239] An "improvement cycle" is a series of processes in which improvement actions are carried out, the results are evaluated, and the results are used to lead to the next improvement.

[0240] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze and generate text data.

[0241] "Sentiment analysis" is a method of extracting emotions and feelings from text data and evaluating their trends.

[0242] "Topic modeling" is a method for extracting major themes and topics from text data and understanding their structure.

[0243] A "notification system" is a communication method or platform for quickly conveying specific information to relevant parties.

[0244] The present invention is a system for analyzing the communication situation within an organization and proposing improvement actions. A specific embodiment of this system is described below.

[0245] Hardware and software used

[0246] Hardware: Servers, terminals (PCs, smartphones)

[0247] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), notification systems (e.g., Slack, email)

[0248] System Overview

[0249] In this system, the server collects email and chat content within the organization and analyzes it using a generative AI model. Based on the analysis results, the system diagnoses the communication situation in each department and proposes improvement actions. The proposed improvement actions are notified to relevant parties using a notification system, helping to start the improvement cycle.

[0250] Specific actions

[0251] 1. Data Collection

[0252] The server collects communication data from the email server or chat system (e.g., Slack, MICROSOFT TEAMS (registered trademark)) for the past month. Specifically, it uses an API to obtain email sending and receiving history and chat logs, and stores them in a database.

[0253] 2. Data analysis

[0254] The server analyzes the collected data. Generative AI models (e.g., GPT-4) are used to perform sentiment analysis and topic modeling on the text data. For example, email content can be analyzed to determine whether it contains more positive or negative interactions.

[0255] 3. Generating diagnostic results

[0256] The server then uses the analysis results to diagnose the communication situation in each department, generating a diagnosis such as, "Department A has a lot of positive interactions, while Department B has a lot of negative interactions."

[0257] 4. Proposal of improvement actions

[0258] Based on the results of the diagnosis, the server uses a generative AI model to propose improvement actions. For example, it generates specific actions such as "Propose regular meetings to Department B."

[0259] 5. Notification

[0260] The server notifies the relevant parties of the proposed improvement action. The server notifies the relevant parties of the improvement action using a notification system (e.g., Slack, email). For example, using the Slack API, a message is sent to the manager of Department B suggesting "holding regular meetings."

[0261] 6. Start the improvement cycle

[0262] Users (stakeholders) receive notifications and take suggested improvement actions, for example, the manager of department B schedules and runs a regular meeting.

[0263] Examples of concrete examples and prompts

[0264] Specific examples

[0265] Data collection: The server collects email sending and receiving history for the past month from the email server.

[0266] Data analysis: The server uses the generated AI model to analyze the sentiment of the email content and evaluate whether it contains a lot of positive or negative interactions.

[0267] Generating diagnostic results: Department A is diagnosed as having many positive interactions, while Department B is diagnosed as having many negative interactions.

[0268] Proposal for improvement action: Propose to Department B that they hold regular meetings.

[0269] Notification: The server uses Slack to notify the manager of department B of the improvement action.

[0270] Initiating the improvement cycle: Department B's manager schedules and conducts regular meetings.

[0271] Prompt Sentence Examples

[0272] "Communication within Department B is lacking. Please suggest some action to improve it."

[0273] In this way, the system diagnoses the communication situation within the organization and proposes appropriate improvement actions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0274] Step 1:

[0275] Data collection

[0276] The server collects communication data from the mail server and chat system for the past month. Specifically, it uses an API to obtain email sending and receiving history and chat logs and stores them in a database.

[0277] Input: Communication data from mail servers and chat systems

[0278] Output: Communication data stored in a database

[0279] Step 2:

[0280] Data Preprocessing

[0281] The server preprocesses the collected data, specifically cleaning the text data (removing unnecessary characters and spaces), tokenizing it (dividing it into words), and removing stop words (removing frequently occurring but meaningless words).

[0282] Input: Communication data stored in a database

[0283] Output: Preprocessed text data

[0284] Step 3:

[0285] Data analysis

[0286] The server analyzes the preprocessed data. It uses a generative AI model (e.g., GPT-4) to perform sentiment analysis and topic modeling on the text data. For example, it analyzes the content of emails and evaluates whether they contain a lot of positive or negative interactions.

[0287] Input: Preprocessed text data

[0288] Output: Sentiment analysis and topic modeling results

[0289] Step 4:

[0290] Generating diagnostic results

[0291] The server then uses the analysis results to diagnose the communication situation in each department, generating a diagnosis such as, "Department A has a lot of positive interactions, while Department B has a lot of negative interactions."

[0292] Input: Sentiment analysis results and topic modeling results

[0293] Output: Diagnostic results regarding the communication status of each department

[0294] Step 5:

[0295] Proposal of improvement actions

[0296] Based on the results of the diagnosis, the server uses a generative AI model to propose improvement actions. For example, it generates specific actions such as "Propose regular meetings to Department B."

[0297] Input: Diagnostic results regarding the communication status of each department

[0298] Output: Suggested improvement actions

[0299] Step 6:

[0300] notification

[0301] The server notifies the relevant parties of the proposed improvement action. The server notifies the relevant parties of the improvement action using a notification system (e.g., Slack, email). For example, using the Slack API, a message is sent to the manager of Department B suggesting "holding regular meetings."

[0302] Input: Proposed improvement action

[0303] Output: Notification message sent to interested parties

[0304] Step 7:

[0305] Start of the improvement cycle

[0306] Users (stakeholders) receive notifications and take suggested improvement actions, for example, the manager of department B schedules and runs a regular meeting.

[0307] Input: Notification message sent to interested parties

[0308] Output: Improvement actions taken

[0309] (Application example 3)

[0310] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0311] Conventional organizational culture analysis systems can propose improvement actions based on the analysis results, but these proposals are not properly communicated to the relevant parties, which means that the improvement cycle is not carried out effectively. In addition, the proposed improvement actions are not presented as concrete guidelines, so it is unclear how the relevant parties should act, and they often do not lead to actual improvements. This has led to the issue of insufficient improvement in communication and efficiency throughout the organization.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0313] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for notifying relevant parties of the improvement actions based on the diagnosis results, means for generating specific action guidelines for executing the proposed improvement actions, and means for notifying relevant parties of the generated action guidelines.As a result, specific improvement actions based on the diagnosis results are appropriately notified to relevant parties and executed, thereby enabling improvement of communication and efficiency throughout the organization.

[0314] "Email" means a digital message sent or received over the Internet or other computer network.

[0315] "Chat" is a means of communication for exchanging text messages in real time.

[0316] "Organizational culture" refers to the values, beliefs, and codes of behavior shared within an organization.

[0317] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[0318] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[0319] "Comparison" is the process of contrasting different elements to reveal their differences and similarities.

[0320] "Improvement actions" are specific improvement measures proposed based on the results of the diagnosis.

[0321] "Notification" is the process of communicating information to interested parties.

[0322] A "code of conduct" is an instruction or guideline that indicates specific behavior.

[0323] "Stakeholders" are people or groups within or outside an organization who are involved in a particular project or task.

[0324] A "server" is a computer system that provides data and services over a network.

[0325] The system for implementing this invention consists of three main elements: a server, terminals, and users. The server plays a central role in analyzing the content of emails and chats and diagnosing organizational culture. The terminals are devices through which users interface with the server, and users are the entities that operate the system and take action to improve it.

[0326] Server Roles and Operations

[0327] The server analyzes and calculates data using the following hardware and software.

[0328] Hardware: A server machine with a powerful processor, sufficient memory, and ample storage.

[0329] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning frameworks (e.g., TENSORFLOW®, PyTorch), database management systems (e.g., MySQL, PostgreSQL).

[0330] The server first collects email and chat content and analyzes this data using natural language processing technology. Based on the analysis results, it diagnoses the culture of each organization (department / section) and compares it with other organizations. Based on the diagnosis results, a generative AI model is used to propose specific improvement actions. The proposed improvement actions are notified to the relevant parties and are then generated as specific guidelines for action.

[0331] Terminal roles and processing

[0332] A terminal is a device through which a user interfaces with a server, and uses the following hardware and software:

[0333] Hardware: Devices such as computers, tablets, and smartphones.

[0334] Software: web browsers, email clients, chat applications.

[0335] The device receives notifications and action guidelines sent from the server and displays them to the user, who can then take specific action to improve the situation.

[0336] User Roles and Actions

[0337] Users are the ones who operate the system and take action to improve it. They receive notifications and guidelines from the server via their devices and take specific actions based on them. For example, they hold regular meetings or carry out team-building activities.

[0338] Specific examples

[0339] For example, if communication in a particular department within a factory is diagnosed as being sluggish, the server will suggest the following improvement actions:

[0340] Suggest holding regular meetings.

[0341] Suggest team-building activities.

[0342] These suggestions are communicated to relevant parties via the terminal, and users then take action to improve the situation in accordance with specific guidelines.

[0343] Prompt Sentence Examples

[0344] An example of a prompt sentence to input to the generative AI model is as follows:

[0345] Develop a system that diagnoses the communication situation within a factory and proposes improvement actions. Based on the results of the diagnosis, it should propose regular meetings and team building activities, and include a function to notify relevant parties by email.

[0346] In this way, providing specific modes for carrying out the invention can improve communication and efficiency throughout an organization.

[0347] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0348] Step 1:

[0349] The server collects email and chat content. This involves retrieving data from mail and chat servers. The input is raw email and chat data, and the output is text data for analysis. Specifically, it retrieves emails using IMAP and SMTP protocols and collects chat data using APIs.

[0350] Step 2:

[0351] The server analyzes the collected text data using natural language processing technology. The input is the text data collected in step 1, and the output is the analysis results. Specifically, it uses natural language processing libraries such as NLTK and spaCy to perform text tokenization, part-of-speech tagging, sentiment analysis, etc.

[0352] Step 3:

[0353] The server diagnoses the culture of each organization (department / section) based on the analysis results. The input is the analysis results obtained in step 2, and the output is the diagnosis results. Specifically, a machine learning model is used to reverse-calculate the level of communication activity and specific values.

[0354] Step 4:

[0355] The server compares the diagnosis results with those of other organizations. The input is the diagnosis results obtained in step 3, and the output is the comparison results. Specifically, the results are compared with the diagnosis results of other organizations stored in the database and a relative evaluation is performed.

[0356] Step 5:

[0357] The server proposes improvement actions based on the diagnosis results. The input is the comparison result obtained in step 4, and the output is the proposed improvement actions. Specifically, a generative AI model is used to generate specific improvement actions. Prompt statements are used to give appropriate instructions to the model.

[0358] Step 6:

[0359] The server notifies the stakeholders of the proposed remediation actions. The input is the remediation action generated in step 5, and the output is the sending of a notification. Specifically, it sends an email using the SMTP protocol and a chat message using an API.

[0360] Step 7:

[0361] The server generates a specific action plan for implementing the proposed improvement actions. The input is the improvement action generated in step 5, and the output is a specific action plan. Specifically, a generative AI model is used to create a detailed action plan.

[0362] Step 8:

[0363] The server notifies the relevant parties of the generated action plan. The input is the action plan generated in step 7, and the output is sending a notification. Specifically, it sends an email using the SMTP protocol and a chat message using an API.

[0364] Step 9:

[0365] The user receives notifications and action guidelines from the server through their terminal and takes specific improvement actions based on them. The input is the notifications and action guidelines sent in step 8, and the output is the implemented improvement actions. Specifically, this involves holding regular meetings and carrying out team-building activities.

[0366] 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.

[0367] "Example 1"

[0368] In one embodiment of the present invention, an emotion engine is used to analyze a user's emotions from the content of emails and chats. Specifically, the emotion engine uses natural language processing and machine learning techniques to recognize a user's emotions and track changes in those emotions. For example, the emotion engine infers a user's emotional state from the words, expressions, emoticons, and other elements used by the user in emails and chats.

[0369] "Example 2"

[0370] The analysis results of the emotion engine are also reflected in the diagnosis of organizational culture. Specifically, changes in user emotions are evaluated as an indicator of organizational culture, and the culture of each organization is diagnosed. For example, if the user's emotions are changing positively, the organization's culture is diagnosed as being good. Conversely, if the user's emotions are changing negatively, the organization's culture is diagnosed as having problems.

[0371] "Example 3"

[0372] Furthermore, the system suggests improvement actions based on changes in the user's emotions. Specifically, if the user's emotions are changing negatively, the system identifies the cause and suggests improvement actions to resolve the cause. For example, if the system determines that the cause of the user's negative emotions is a lack of communication, it suggests holding regular meetings or team-building activities.

[0373] The processing flow of each embodiment will be described below.

[0374] "Example 1"

[0375] Step 1: The emotion engine collects email and chat content from users.

[0376] Step 2: Recognize the user's emotions from the collected information using natural language processing and machine learning technologies.

[0377] Step 3: Track the user's emotional changes and save the results.

[0378] "Example 2"

[0379] Step 1: Obtain the analysis results of the emotion engine.

[0380] Step 2: Evaluate the analysis results as indicators of organizational culture.

[0381] Step 3: Based on the assessment results, diagnose the organization's culture and save the results.

[0382] "Example 3"

[0383] Step 1: Obtain diagnostic results of changes in user sentiment and organizational culture.

[0384] Step 2: If the emotional change is negative, identify its cause.

[0385] Step 3: Propose improvement actions to eliminate the causes and save the results.

[0386] Example 1

[0387] Next, a description will be given of Example 1 of Form 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."

[0388] In modern organizations, communication via email and chat is extremely important, but there is a lack of effective ways to analyze the content of email and chat and use it to diagnose and improve organizational culture. It is also difficult to analyze user sentiment and understand the health of the organization. This poses a challenge, delaying improvements to the quality of organizational communication and culture.

[0389] 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.

[0390] In this invention, the server includes means for collecting the contents of emails and chats, means for preprocessing the collected data, and means for analyzing the preprocessed data using natural language processing technology, which makes it possible to analyze the level of communication activity within an organization, whether specific values ​​are being calculated, and to analyze user emotions.

[0391] "Email" means a digital message sent or received over the Internet.

[0392] "Chat" is a means of communication for exchanging text messages in real time.

[0393] "Means of collection" refers to the methods and technologies used to obtain email and chat content.

[0394] "Preprocessing means" refers to methods and techniques for converting collected data into a format that is easy to analyze.

[0395] "Natural language processing technology" is a technology that allows computers to analyze, understand, and generate human language.

[0396] "Analytical means" are methods and techniques for analyzing data and extracting meaning and patterns.

[0397] "Organizational culture" is the collection of values, beliefs, and codes of conduct shared within an organization.

[0398] A "diagnostic means" is a method or technique for assessing the state of tissue based on the results of an analysis.

[0399] "Comparative means" are methods or techniques for comparing diagnostic results with results from other tissues.

[0400] "Improvement actions" are specific actions taken to solve organizational problems and improve performance.

[0401] "Proposal means" are methods and techniques for proposing improvement actions.

[0402] "Supporting measures" are methods and techniques to support the implementation of the proposed improvement actions.

[0403] An "emotion engine" is software or algorithms for analyzing user emotions from text data.

[0404] A "user" is an individual or member of an organization who uses email or chat.

[0405] The present invention is a system for collecting the contents of emails and chats within an organization and analyzing them using natural language processing technology. A specific embodiment of this system will be described below.

[0406] Data collection

[0407] The server collects email and chat content within the organization. Specifically, it uses the APIs of mail servers and chat platforms to obtain users' email and chat messages. For example, it can use the APIs of Microsoft Exchange and Slack. The server periodically accesses these platforms to collect new messages.

[0408] Data Preprocessing

[0409] The server preprocesses the collected data by using the Python libraries NLTK and spaCy to tokenize the text data, remove unnecessary symbols and spaces, and clean up email and chat metadata (sender, recipient, timestamp, etc.).

[0410] Analysis using natural language processing

[0411] The server then uses natural language processing technology to analyze the preprocessed data. Specifically, it performs grammatical analysis of the text and extracts keywords. For example, it uses spaCy to identify parts of speech such as nouns and verbs and extract important keywords. This allows it to extract elements that serve as indicators of organizational culture (for example, how active communication is, or whether specific values ​​are being worked out).

[0412] Emotion analysis

[0413] The server uses an emotion engine to analyze the user's emotions from the content of emails and chats. The emotion engine uses Google® Cloud Natural Language API and IBM Watson® Natural Language Understanding. Using these tools, the server infers the user's emotional state from the words, expressions, and emojis used in emails and chats, and tracks changes in that state.

[0414] Saving and displaying results

[0415] The server stores the analysis results in a database. Specifically, a relational database such as MySQL or PostgreSQL is used. The stored data is displayed on a dashboard that can be accessed by administrators and users. The dashboard is built using a web framework such as Django or Flask.

[0416] Specific examples

[0417] For example, if a user reports "the project is progressing smoothly" by email, the server collects and preprocesses this email. Next, it uses natural language processing technology to extract keywords such as "project," "smooth," and "progressing." It then uses an emotion engine to recognize positive emotions and stores the results in a database. Finally, administrators can view the results through a dashboard.

[0418] Prompt Sentence Examples

[0419] Examples of prompts to be input to a generative AI model include:

[0420] "Please analyze the user's sentiment from the following text:

[0421] 1. 'The project is progressing smoothly'

[0422] 2. 'This task is very difficult'

[0423] Using this prompt, the generative AI model can analyze the user's emotions from the text and return the results.

[0424] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0425] Step 1:

[0426] The server collects email and chat content. Specifically, it uses the API of a mail server or chat platform to obtain user email and chat messages. For example, it uses the API of Microsoft Exchange or Slack. The input is the raw message data obtained from the API, and the output is the collected message data.

[0427] Step 2:

[0428] The server preprocesses the collected data. Specifically, it uses the Python libraries NLTK and spaCy to tokenize the text data and remove unnecessary symbols and spaces. It also organizes email and chat metadata (sender, recipient, timestamp, etc.). The input is the collected message data, and the output is the preprocessed, clean text data.

[0429] Step 3:

[0430] The server analyzes the preprocessed data using natural language processing technology. Specifically, it performs grammatical analysis of the text and extracts keywords. For example, it uses spaCy to identify parts of speech such as nouns and verbs and extract important keywords. The input is the preprocessed, clean text data, and the output is the analyzed keywords and grammatical information.

[0431] Step 4:

[0432] The server uses an emotion engine to analyze the user's emotions from the content of emails and chats. The emotion engine uses Google Cloud Natural Language API and IBM Watson Natural Language Understanding. These tools are used to estimate the user's emotional state from the words, expressions, and emojis used by the user in emails and chats, and track changes in that state. The input is the analyzed keywords and grammatical information, and the output is the estimated result of the user's emotional state.

[0433] Step 5:

[0434] The server stores the analysis results in a database. Specifically, a relational database such as MySQL or PostgreSQL is used. The stored data is displayed on a dashboard that can be accessed by administrators and users. The dashboard is built using a web framework such as Django or Flask. The input is the estimation result of the user's emotional state, and the output is the analysis results stored in the database.

[0435] Step 6:

[0436] Users check the analysis results through a dashboard. Specifically, they access the dashboard using a web browser and view information such as the level of communication activity in the organization, whether specific values ​​are being calculated, and the user's emotional state. The input is the analysis results stored in the database, and the output is the display of the analysis results that the user views.

[0437] (Application example 1)

[0438] Next, a description will be given of Application Example 1 of Embodiment 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."

[0439] Conventional organizational culture analysis systems analyze email and chat content to diagnose organizational culture and suggest improvement actions, but they were unable to monitor specific factory environments or employee emotional states in real time. This made it difficult to grasp the level of communication within a factory and the emotional state of employees, and to suggest appropriate improvement actions.

[0440] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting an improvement cycle based on the proposed improvement actions, means for collecting the content of emails and chats within the factory, means for analyzing the collected data using natural language processing technology and recognizing emotions, means for extracting indicators of organizational culture, and means for visualizing the emotions and indicators of organizational culture. This makes it possible to monitor the activity of communication within the factory and the emotional states of employees in real time and propose appropriate improvement actions.

[0441] "Email" means a digital message sent or received over the Internet or other network.

[0442] "Chat" is a means of communication for exchanging text messages in real time.

[0443] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[0444] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[0445] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[0446] "Comparison" is the process of contrasting different data or results to reveal similarities and differences.

[0447] "Improvement actions" are specific actions or measures proposed based on the diagnostic results.

[0448] An "improvement cycle" is a series of processes in which improvement actions are carried out, the results are evaluated, and the next improvement action is planned and executed.

[0449] "Natural language processing technology" is a technology that uses computers to understand, analyze, and generate human language.

[0450] An "emotion engine" is software that analyzes and recognizes user emotions from text data.

[0451] An "indicator" is a standard or measure for quantitatively evaluating a specific phenomenon or condition.

[0452] "Visualization" is the process of visually representing data or information to make it easier to understand.

[0453] The system for implementing this invention collects the contents of emails and chats within a factory and analyzes them using natural language processing technology and an emotion engine to monitor indicators of organizational culture and the emotional state of employees in real time. Specific embodiments are described below.

[0454] Hardware and software used

[0455] Hardware: Robots in factories (e.g. general-purpose robots)

[0456] Software: Python, NLTK, Scikit-learn, Matplotlib

[0457] Data collection

[0458] The server collects email and chat content from within the factory as text files, allowing for centralized management of communication data within the factory.

[0459] Natural Language Processing and Sentiment Analysis

[0460] The server analyzes the collected data using natural language processing technology and recognizes the user's emotions using an emotion engine. Specifically, it uses NLTK's SentimentIntensityAnalyzer to analyze the emotions in each email and chat.

[0461] Extracting indicators of organizational culture

[0462] The server extracts indicators of organizational culture by vectorizing the text data using TfidfVectorizer and reducing the dimensions using PCA, which allows us to evaluate the level of communication within the factory and whether specific values ​​are being adopted.

[0463] Data Visualization

[0464] The server uses Matplotlib to visualize the sentiment and organizational culture indicators in a two-dimensional plot, allowing users to visually grasp the state of communication within the factory and the emotional state of employees.

[0465] Specific examples

[0466] For example, if an email sent within a factory contains the content "Today's production line is going smoothly. Thank you for your hard work, everyone!", the server collects this email and analyzes it using natural language processing technology. As a result of the sentiment analysis, the email is recognized as having a positive sentiment (compound score: 0.8).

[0467] Prompt Sentence Examples

[0468] An example of a prompt sentence to input to the generative AI model is as follows:

[0469] Develop a system that collects email and chat content from within the factory and analyzes it using natural language processing technology and an emotion engine. Specifically, create a program that meets the following requirements:

[0470] 1. Collect emails and chat messages within the factory.

[0471] 2. Analyze the collected data using natural language processing technology to recognize emotions.

[0472] 3. Extract indicators of organizational culture.

[0473] 4. Visualize sentiment and organizational culture indicators.

[0474] In this way, it is possible to monitor the level of communication within the factory and the emotional state of employees in real time and propose appropriate improvement actions.

[0475] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0476] Step 1:

[0477] The server collects the contents of emails and chats within the factory. Specifically, it acquires data in text file format from each terminal in the factory and stores it in a central database. The input is the text data of emails and chats from each terminal, and the output is the text data stored in the database.

[0478] Step 2:

[0479] The server analyzes the collected text data using natural language processing technology. Specifically, it uses Python's NLTK library to tokenize the text data and calculates sentiment scores using an emotion engine (SentimentIntensityAnalyzer). The input is the text data stored in the database, and the output is the sentiment score for each piece of text data.

[0480] Step 3:

[0481] The server recognizes the emotional state of employees based on the emotion scores. Specifically, it aggregates the emotion scores and classifies them into positive, negative, and neutral emotional states. The input is the emotion score, and the output is the classification result of the emotional state of each employee.

[0482] Step 4:

[0483] The server extracts indicators of organizational culture. Specifically, it vectorizes the text data using TfidfVectorizer and performs dimensionality reduction using PCA. The input is the text data, and the output is a dimension-reduced indicator of organizational culture.

[0484] Step 5:

[0485] The server visualizes the emotional state and organizational culture indicators. Specifically, it uses Matplotlib to create a two-dimensional plot and visually display the emotional state and organizational culture indicators. The input is the classification results of the emotional state and the organizational culture indicators, and the output is a visualized graph.

[0486] Step 6:

[0487] The server proposes improvement actions based on the visualized data. Specifically, it uses a generative AI model to generate appropriate improvement actions based on prompt statements. The inputs are the visualized data and the prompt statements, and the output is the proposed improvement actions.

[0488] Step 7:

[0489] The user executes an improvement cycle based on the proposed improvement actions. Specifically, the user executes the proposed course of action and sends the results to the server as feedback. The input is the proposed improvement action, and the output is feedback of the execution results.

[0490] Example 2

[0491] Next, a description will be given of Example 2 of Form 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."

[0492] Conventional organizational culture diagnostic systems were limited to analyzing the content of emails and chats, and were unable to directly utilize user emotional data. As a result, the accuracy of organizational culture diagnostics was low, and the proposals for improvement actions were ineffective. Furthermore, the construction of a database for comparing diagnostic results with other organizations was insufficient. This led to the issue of the organizational culture improvement cycle not functioning effectively.

[0493] 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.

[0494] In this invention, the server includes means for a user to input emotional data, means for transmitting the input emotional data to the server, means for the server to analyze the emotional data, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for storing the diagnosis results in a database and comparing them with other organizations, means for proposing improvement actions based on the diagnosis results, and means for supporting the improvement cycle based on the proposed improvement actions. This makes it possible to diagnose organizational culture with high accuracy by directly using user emotional data and to propose effective improvement actions.

[0495] A "user" is an individual or group that uses the system to input emotion data.

[0496] "Emotion data" is data such as text and numerical values ​​entered by the user, which represents the user's emotional state.

[0497] A "server" is a computer system that receives and analyzes emotion data and stores the diagnostic results in a database.

[0498] An "emotion engine" is software used by the server to analyze and classify emotional data as positive or negative.

[0499] A "database" is a system that stores diagnostic results and preserves information to enable comparison with other organizations.

[0500] "Organizational culture" refers to the values, behavioral patterns, and communication characteristics of a particular organization (department / section).

[0501] The "diagnosis result" is information indicating the state of organizational culture evaluated based on the analysis results of emotion data.

[0502] "Improvement actions" are specific guidelines for improving organizational culture that are proposed based on the diagnostic results.

[0503] An "improvement cycle" is a series of processes in which a proposed improvement action is implemented, the results are reevaluated, and the next improvement action is proposed.

[0504] The present invention relates to a system for diagnosing organizational culture based on user emotion data and proposing improvement actions. Specific embodiments of this system will be described below.

[0505] Hardware and software used

[0506] Hardware: Servers, terminals

[0507] Software: emotion engine, database management system (e.g., MySQL), generative AI model

[0508] System Overview

[0509] 1. Entering emotion data

[0510] The user inputs their own emotional data into the emotion engine using a terminal. Specifically, the user inputs text such as "I had a lot of fun today" or "I'm stressed because things aren't going well at work."

[0511] 2. Sending Emotional Data

[0512] The device sends the input emotion data to the server. Specifically, the device sends the emotion data to the server using an HTTP request.

[0513] 3. Emotion Data Analysis

[0514] The server passes the received emotion data to the emotion engine for analysis. Specifically, the server calls the emotion engine's API and classifies the emotion data as positive or negative. For example, data such as "I had a lot of fun today" is analyzed as positive, and data such as "I felt stressed because things weren't going well at work" is analyzed as negative.

[0515] 4. Diagnosis of organizational culture

[0516] Based on the analysis results, the server diagnoses the culture of the organization to which the user belongs. Specifically, if there are many positive emotions, the server diagnoses that the culture of the organization is good, and if there are many negative emotions, it diagnoses that the culture of the organization has problems. For example, if the user's emotional data is positive, such as "I had a lot of fun today," it diagnoses that the culture of the organization is good.

[0517] 5. Storing diagnostic results in a database

[0518] The server stores the results of the assessment in a database. Specifically, the server uses a database management system (e.g., MySQL) to save the results in a format that allows comparison with other organizations. For example, the assessment result that organization A has a good culture can be stored in the database so that it can be compared with other organizations B and C.

[0519] Specific examples

[0520] A user types into the emotion engine, "I had a lot of fun today."

[0521] The terminal sends this input to the server.

[0522] The server uses an emotion engine to analyze the emotion "it was fun" as positive.

[0523] Based on this positive emotion, the server diagnoses the culture of the organization to which the user belongs as being good.

[0524] The server stores the diagnostic results in a database, allowing comparison with other organizations.

[0525] Example prompts for generative AI models

[0526] "Please explain a system that diagnoses organizational culture based on user emotional data. Please explain in detail how the emotional engine, database, server, and terminal are used to collect and analyze data and store the diagnostic results."

[0527] In this way, the system diagnoses organizational culture based on users' emotional data and stores the results in a database that allows comparison with other organizations.

[0528] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0529] Step 1:

[0530] The user inputs their own emotional data into the emotion engine using a terminal. Specifically, the user inputs text such as "I had a lot of fun today" or "I'm stressed because things aren't going well at work." The input data is sent to the emotion engine.

[0531] Step 2:

[0532] The device sends the input emotion data to the server. Specifically, the device sends emotion data to the server using an HTTP request. The input is the user's emotion data, and the output is data sent to the server.

[0533] Step 3:

[0534] The server passes the received emotion data to the emotion engine for analysis. Specifically, the server calls the emotion engine's API to classify the emotion data as positive or negative. The input is emotion data, and the output is the analysis result: positive or negative.

[0535] Step 4:

[0536] The server then uses the analysis results to diagnose the culture of the organization to which the user belongs. Specifically, if there are many positive emotions, the server diagnoses that the culture of the organization is good, and if there are many negative emotions, it diagnoses that there are problems with the culture of the organization. The input is the analysis results, and the output is the diagnosis of the organizational culture.

[0537] Step 5:

[0538] The server stores the diagnosis results in a database. Specifically, the server uses a database management system (e.g., MySQL) to save the diagnosis results in a format that allows comparison with other organizations. The input is the diagnosis results of organizational culture, and the output is storage in the database.

[0539] Step 6:

[0540] The server proposes improvement actions based on the diagnosis results. Specifically, the server uses a generative AI model to generate specific action guidelines for improving organizational culture. The input is the diagnosis results of organizational culture, and the output is proposals for improvement actions.

[0541] Step 7:

[0542] The server supports the improvement cycle based on the proposed improvement actions. Specifically, the server monitors the execution status of the improvement actions and proposes the next improvement action as necessary. The input is the execution status of the improvement action, and the output is a proposal for the next improvement action.

[0543] (Application example 2)

[0544] Next, a description will be given of Application Example 2 of Form 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."

[0545] Conventional organizational culture diagnostic systems were limited to analyzing organizational culture based on the content of emails and chats, and were unable to reflect changes in employee emotions in real time. As a result, the diagnosis of organizational culture was one-sided, making it difficult to accurately grasp the actual state of the organization. In addition, there was a lack of means to compare diagnostic results based on emotional data with other organizations, and suggestions for improvement actions and support for improvement cycles were not adequately provided.

[0546] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0547] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for analyzing employee emotions in real time, means for storing the emotion analysis results in a database, means for diagnosing organizational culture based on the emotion data, and means for displaying the diagnosis results. This makes it possible to diagnose organizational culture that reflects changes in employee emotions in real time, enabling a more accurate and multifaceted evaluation of organizational culture.

[0548] "Email" means a digital message sent or received over the Internet.

[0549] "Chat" is a means of communication in which text messages are exchanged in real time.

[0550] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[0551] "Analysis" is the process of examining data in detail to reveal its structure and meaning.

[0552] "Diagnosis" is the act of evaluating the current situation based on data and information and identifying problems and areas for improvement.

[0553] "Comparison" is the act of contrasting multiple objects and revealing their differences and similarities.

[0554] "Improvement actions" are specific actions or measures to solve current problems and improve the situation.

[0555] The "improvement cycle" is a method of continuously improving the situation by repeating the process of planning, doing, evaluating, and improving.

[0556] "Emotions" are psychological responses that humans have to certain situations or stimuli.

[0557] "Real-time" refers to processing or reaction occurring immediately, without delay.

[0558] A "database" is a system for efficiently storing, searching, and managing data.

[0559] "Display" is the act of visually showing data or information.

[0560] As an embodiment of the present invention, a robot for diagnosing organizational culture in a factory will be described as an example. The system includes a program for analyzing the emotions of employees in real time and diagnosing the organizational culture.

[0561] The server uses the following hardware and software:

[0562] camera

[0563] Robot body (e.g. Pepper)

[0564] Image processing library (e.g. OpenCV)

[0565] Sentiment Analysis Engine

[0566] Database Management Systems

[0567] The server uses a camera to capture employees' faces and analyzes their emotions using an emotion analysis engine. The analyzed emotion data is stored in a database management system. The server then aggregates the emotion data over a certain period of time and calculates the percentage of positive emotions to diagnose the organizational culture. The diagnosis results are displayed on the robot's display or on the manager's terminal.

[0568] For example, when a factory worker talks to a robot, the robot analyzes their facial expressions and tone of voice to collect emotional data. The data is compiled weekly and the results of the organizational culture diagnosis are reported to the factory manager.

[0569] An example of a prompt is as follows:

[0570] Design a robot that analyzes the emotions of employees in a factory in real time and diagnoses the organizational culture. The robot will analyze employees' facial expressions and tone of voice using an emotion engine and store the data in a database. It will compile data over a certain period of time and diagnose the organizational culture on a three-point scale: "Good," "Average," or "Problematic."

[0571] In this way, the server diagnoses organizational culture in a way that reflects changes in employee sentiment in real time, enabling a more accurate and multifaceted evaluation of organizational culture.

[0572] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0573] Step 1:

[0574] The server captures the employee's face using a camera. The input is video data from the camera, and the output is the captured image frame. Specifically, the server acquires video data from the camera at regular intervals and saves it as an image frame.

[0575] Step 2:

[0576] The server uses a sentiment analysis engine to analyze employee emotions from captured image frames. The input is the image frame, and the output is the analyzed emotion data (e.g., positive, negative). Specifically, the server passes the image frame to the sentiment analysis engine and performs sentiment analysis.

[0577] Step 3:

[0578] The server stores the analyzed emotion data in a database management system. The input is emotion data and employee identification information, and the output is emotion data stored in the database. Specifically, the server pairs emotion data with employee IDs and stores them in the database.

[0579] Step 4:

[0580] The server aggregates emotion data over a certain period of time and calculates the percentage of positive emotions. The input is emotion data obtained from the database, and the output is the percentage of positive emotions. Specifically, the server obtains emotion data from the database, counts positive and negative emotion data, and calculates the percentage.

[0581] Step 5:

[0582] The server diagnoses organizational culture based on the calculated percentage of positive emotions. The input is the percentage of positive emotions, and the output is the organizational culture diagnosis result (e.g., good, average, problematic). Specifically, the server applies diagnostic criteria based on the percentage of positive emotions to evaluate organizational culture.

[0583] Step 6:

[0584] The server displays the diagnostic results on the robot's display or the administrator's terminal. The input is the organizational culture diagnostic results, and the output is the displayed diagnostic results. Specifically, the server converts the diagnostic results into text format and sends them to the robot's display or the administrator's terminal for display.

[0585] Step 7:

[0586] The user (administrator) checks the displayed diagnostic results and takes improvement actions as necessary. The input is the diagnostic results, and the output is the implemented improvement actions. In concrete terms, the user considers improvement measures for the organization based on the diagnostic results and puts them into action.

[0587] Example 3

[0588] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0589] Conventional organizational culture analysis systems can analyze organizational culture from the content of electronic communications and suggest improvement actions based on the diagnostic results, but they have the problem of not being able to suggest improvement actions that take into account user emotional data. This has resulted in a lack of concrete improvement measures to improve the quality of communication within an organization and employee satisfaction.

[0590] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0591] In this invention, the server includes means for analyzing organizational culture from the content of electronic communications, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting an improvement cycle based on the proposed improvement actions, means for collecting and analyzing user emotion data, means for proposing improvement actions based on changes in the emotion data, and means for notifying relevant parties of the proposed improvement actions. This makes it possible to propose specific improvement actions that take user emotion data into consideration, thereby improving the quality of communication within the organization and employee satisfaction.

[0592] "Electronic communications" are means of communication that take place in a digital format, such as email or chat.

[0593] "Organizational culture" is the collection of values, beliefs, and codes of conduct shared within an organization.

[0594] "Analysis" is the process of collecting data and analyzing its content for a specific purpose.

[0595] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[0596] "Improvement actions" are specific guidelines and measures proposed based on the diagnostic results.

[0597] An "improvement cycle" is a series of processes in which improvement actions are implemented, the results are evaluated, and the next improvement plan is planned.

[0598] "Emotion data" is data that indicates the emotional state of the user, and includes an emotion score extracted from text data.

[0599] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate and analyze data.

[0600] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0601] "Notification" is a communication method used to inform stakeholders of proposed improvement actions.

[0602] The present invention relates to a system that analyzes communication within an organization and user emotion data and proposes improvement actions. A specific embodiment of this system is described below.

[0603] First, the server uses specific software to collect user emotion data. For example, it uses an emotion analysis API to analyze text data entered by the user on the device and extract an emotion score. If the user enters "Work hasn't been going well lately," the server sends this text data to the emotion analysis API and obtains a negative emotion score.

[0604] The server then stores the analyzed emotion data in a database, which contains information such as user IDs, text data, and emotion scores (positive, negative, or neutral). For example, a MySQL database is used to manage the data.

[0605] The server then periodically analyzes the emotion data in the database and uses a generative AI model (e.g., GPT-4) to identify changes in the user's emotion. Specifically, it compares past emotion data with current emotion data to determine whether there are any negative changes.

[0606] The server proposes improvement actions based on the analysis results of the emotion data. For example, if the user's emotion is changing negatively, the cause is identified and a prompt sentence is input into the AI ​​model to suggest appropriate improvement actions. An example of a prompt sentence could be, "Please identify the cause of the user's emotion changing negatively and propose improvement actions to resolve that cause."

[0607] Finally, the server notifies relevant parties within the organization of the proposed improvement actions. Notifications are sent via email or chat tools (e.g., Slack or Microsoft Teams). The notification includes details of the proposed improvement actions and how to implement them. For example, the notification might say, "User sentiment has become negative, so we suggest holding regular meetings and team-building activities."

[0608] In this way, the system can suggest appropriate improvement actions based on changes in the user's emotions and support a cycle of improving communication within an organization. The flow of the identification process in the third embodiment will be described with reference to FIG. 21.

[0609] Step 1:

[0610] The user inputs text data from the terminal.

[0611] Input: A user types into a terminal, "Work hasn't been going well lately."

[0612] Specific operation: The user enters text into the input field on the terminal and presses the send button.

[0613] Output: The terminal sends the entered text data to the server.

[0614] Step 2:

[0615] The server sends the received text data to the sentiment analysis API and obtains a sentiment score.

[0616] Input: Text data sent from the device: "Work hasn't been going well lately."

[0617] Specific operation: The server sends text data to the sentiment analysis API and receives a sentiment score (negative) from the API.

[0618] Output: Sentiment score (negative).

[0619] Step 3:

[0620] The server stores the obtained emotion scores in a database.

[0621] Input: Sentiment score (negative), user ID, text data.

[0622] Specific operation: The server stores user IDs, text data, and emotion scores in a MySQL database.

[0623] Output: Emotion data stored in a database.

[0624] Step 4:

[0625] The server periodically analyzes the emotion data in the database.

[0626] Input: Past and current emotion data stored in the database.

[0627] Specific operation: The server uses a generative AI model (GPT-4) to compare past and current emotional data and identify changes in emotions.

[0628] Output: Emotional change (from positive to negative).

[0629] Step 5:

[0630] The server suggests improvement actions based on changes in the emotion data.

[0631] Input: Emotional change (from positive to negative).

[0632] Specific operation: The server inputs a prompt to the generative AI model: "Please identify the cause of the user's negative emotion change and propose an improvement action to resolve that cause." The generative AI model then outputs an appropriate improvement action.

[0633] Output: Improvement actions (holding regular meetings and team building activities).

[0634] Step 6:

[0635] The server notifies the interested parties of the proposed remedial actions.

[0636] Input: Improvement actions (holding regular meetings and team building activities).

[0637] Specific behavior: The server notifies relevant parties of proposed improvement actions via email and chat tools (Slack and Microsoft Teams).

[0638] Output: Notification sent to stakeholders ("User sentiment is changing negatively, we suggest holding regular meetings and team building activities.").

[0639] (Application example 3)

[0640] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0641] Conventional organizational culture analysis systems can analyze organizational culture from email and chat content and suggest improvement actions, but they have the problem of not being able to suggest real-time improvement actions based on changes in worker emotions. Also, there was a lack of a way to quickly notify relevant parties of the proposed improvement actions, which could delay the start of the improvement cycle.

[0642] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for monitoring the emotions of workers in real time, means for proposing improvement actions based on changes in emotions, and means for notifying relevant parties of the proposed improvement actions. This enables real-time proposal of improvement actions based on changes in workers' emotions and rapid notification.

[0643] "Email" is a means of communication for sending and receiving text and files over the Internet.

[0644] "Chat" is a means of communication for exchanging text messages in real time.

[0645] "Organizational culture" is a general term for the values, beliefs, and codes of behavior shared within an organization.

[0646] "Analysis" is the process of collecting data, extracting information from that data, and understanding it.

[0647] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[0648] "Comparison" is the process of contrasting different data or information to reveal their differences and similarities.

[0649] "Improvement actions" are specific actions or measures taken to solve a specific problem or improve a situation.

[0650] An "improvement cycle" is a repeated process of identifying problems, implementing improvement actions, and evaluating the results.

[0651] "Monitoring" is the process of continuously observing and collecting data on a specific object.

[0652] An "emotion" is a psychological response that a person has to a particular situation or stimulus.

[0653] "Real-time" refers to processing or reaction occurring immediately, without delay.

[0654] "Notification" is the process of communicating specific information to interested parties.

[0655] A system for carrying out this invention is configured as follows: The server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for monitoring the emotions of workers in real time, means for proposing improvement actions based on changes in emotions, and means for notifying relevant parties of the proposed improvement actions.

[0656] Hardware and software used

[0657] Hardware: Factory robots, cameras, microphones, sensors

[0658] Software: Emotion recognition AI model, data analysis tools, notification system

[0659] Program processing procedure

[0660] 1. Data Collection:

[0661] Cameras and microphones mounted on factory robots are used to collect workers' facial expressions and tone of voice in real time.

[0662] Sensors are also used to collect data on the work environment (temperature, humidity, noise levels, etc.).

[0663] 2. Emotion recognition:

[0664] The collected data is input into an emotion recognition AI model to analyze the emotions of workers.

[0665] The emotion recognition AI model uses, for example, "Cloud Vision API" and "Tone Analyzer."

[0666] 3. Identifying the cause:

[0667] If your emotions are shifting negatively, identify the cause.

[0668] Use data analysis tools (e.g., Python's Pandas or Scikit-learn) to compare with historical data and identify causes of negative sentiment.

[0669] 4. Suggested improvement actions:

[0670] Based on the identified causes, suggest appropriate improvement actions.

[0671] For example, if the problem is a lack of communication, suggest holding regular meetings and team-building activities.

[0672] 5. Notice:

[0673] Communicate proposed improvement actions to relevant parties within the organization.

[0674] Use notification systems (e.g., Slack API or email notification systems) to notify relevant parties in real time.

[0675] Specific examples

[0676] Scenario: Worker A is feeling stressed in a factory.

[0677] Data collection: Worker A's facial expressions and tone of voice were collected using a camera and microphone.

[0678] Emotion recognition: The emotion recognition AI model determines that Worker A's emotion is "stress."

[0679] Identifying the cause: Data analysis tools compare with past data and identify the cause of stress as "increased workload."

[0680] Suggested improvement actions: Workload adjustments and break suggestions.

[0681] Notification: Proposal details are notified to factory managers via Slack.

[0682] Prompt Sentence Examples

[0683] "Develop a system that monitors the emotions of workers in factories in real time, and if their emotions change negatively, identifies the cause and suggests appropriate improvement actions. For example, if a worker is feeling stressed, identify the cause and suggest a break or rearrange work. The hardware used would be cameras, microphones, and sensors, and the software would be emotion recognition AI models, data analysis tools, and notification systems."

[0684] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0685] Step 1:

[0686] The server uses cameras and microphones installed on factory robots to collect the facial expressions and tone of voice of workers in real time. The input is video and audio data from the camera and microphone, and the output is a stream of these data. Specifically, the camera captures the worker's face, and the microphone records the tone of voice.

[0687] Step 2:

[0688] The server uses sensors to collect data about the working environment (such as temperature, humidity, and noise level). The input is the environmental data from the sensors, and the output is a stream of these data. Specifically, the temperature sensor measures the temperature of the environment, and the noise sensor records the noise level.

[0689] Step 3:

[0690] The server inputs the collected video and audio data into an emotion recognition AI model to analyze the worker's emotions. The input is video and audio data, and the output is the emotion analysis result. Specifically, the AI ​​model uses an expression recognition algorithm to analyze facial expressions and an audio analysis algorithm to analyze the tone of voice.

[0691] Step 4:

[0692] The server uses a data analysis tool to identify the cause of negative sentiment changes. The input is the sentiment analysis results and past data, and the output is the cause of the negative sentiment. Specifically, the data analysis tool compares past data with current data to identify outliers and patterns.

[0693] Step 5:

[0694] The server proposes appropriate improvement actions based on the identified causes. The input is the cause of the negative emotion, and the output is the proposed improvement action. Specifically, the server selects and proposes an appropriate action from a database of improvement actions.

[0695] Step 6:

[0696] The server notifies relevant parties within the organization of proposed improvement actions. The input is the proposed improvement action, and the output is a notification message. Specifically, the notification system uses the Slack API or email notification system to send notifications to relevant parties in real time.

[0697] 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.

[0698] 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> ) 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.

[0699] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0700] 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.

[0701] [Second embodiment]

[0702] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0703] 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.

[0704] 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).

[0705] 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.

[0706] 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.

[0707] 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).

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0714] "Example 1"

[0715] In one embodiment of the present invention, the contents of emails and chats within an organization are collected. The collected data is analyzed using natural language processing technology to extract elements that serve as indicators of organizational culture (e.g., the level of active communication, whether specific values ​​are being adopted, etc.).

[0716] "Example 2"

[0717] Next, the culture of each organization (department / section) is diagnosed based on the extracted elements. The results are stored in a database that allows comparison with other organizations.

[0718] "Example 3"

[0719] Furthermore, improvement actions are proposed based on the results of the diagnosis. The proposed improvement actions are notified to relevant parties within the organization to help start the improvement cycle. Specifically, for departments where communication is sluggish, actions such as holding regular meetings or proposing team-building activities could be considered.

[0720] The processing flow of each embodiment will be described below.

[0721] "Example 1"

[0722] Step 1: Collect email and chat content from within the organization. Specifically, obtain data from the organization's email server and chat tools.

[0723] Step 2: Analyze the collected data using natural language processing technology. Specifically, using techniques such as text mining and sentiment analysis, extract elements such as the level of communication activity and whether specific values ​​are being calculated.

[0724] "Example 2"

[0725] Step 1: Diagnose the culture of each organization (department / section) based on the extracted elements. Specifically, evaluate the extracted elements as indicators of organizational culture and diagnose the culture of each organization.

[0726] Step 2: The diagnostic results are stored in a database. Specifically, the diagnostic results are classified by organization and stored in a database that allows comparison with other organizations.

[0727] "Example 3"

[0728] Step 1: Propose improvement actions based on the diagnosis results. Specifically, for departments where communication is sluggish, consider actions such as holding regular meetings or proposing team-building activities.

[0729] Step 2: Notify the relevant parties within the organization of the proposed improvement actions. Specifically, communicate the improvement actions to the relevant parties via email or chat tools and help start the improvement cycle.

[0730] Example 1

[0731] Next, a description will be given of Example 1 of Form 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."

[0732] Conventional organizational culture analysis systems have had difficulty effectively collecting and analyzing email and chat content to extract indicators of organizational culture. Furthermore, they lacked a means to display the extracted indicators in an easy-to-understand manner for users, making it difficult to propose specific guidelines for action aimed at improving organizational culture. This made it impossible to accurately evaluate the level of communication within an organization or the degree to which values ​​are shared, and to take appropriate action to improve it.

[0733] 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.

[0734] In this invention, the server includes means for collecting email and chat content, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology, means for extracting indicators of organizational culture from the analysis results, and means for displaying the extracted indicators to the user. This makes it possible to accurately evaluate the level of communication within the organization and the degree of shared values, and to provide the user with specific guidelines for action.

[0735] "Email" means a digital message sent or received over the Internet or other computer network.

[0736] "Chat" is a means of communication for exchanging text messages in real time.

[0737] "Means of collection" refers to the technology and process used to capture email and chat content and store it in a database.

[0738] "Preprocessing means" refers to techniques and processes such as data cleaning and tokenization that prepare collected data in a form that is easier to analyze.

[0739] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language.

[0740] "Analysis means" are techniques or processes that use pre-processed data to extract specific information or patterns.

[0741] "Organizational culture indicators" are specific indicators for evaluating an organization's culture, such as the level of communication within the organization and the degree of shared values.

[0742] "Means of extraction" refers to the techniques and processes used to extract useful information and indicators from the analysis results.

[0743] The "display means" refers to the techniques and processes for visually presenting the extracted indicators to the user.

[0744] A "generative AI model" is a model that uses artificial intelligence to generate new information and indicators from data.

[0745] This invention is a system that collects the contents of emails and chats within an organization, analyzes them using natural language processing technology, extracts indicators of organizational culture, and provides users with specific guidelines for action.

[0746] Data collection

[0747] The server collects email and chat content. Specifically, it uses common communication platforms such as Microsoft Exchange Server and Slack API to obtain email and chat history within the organization. This allows the communication data within the organization to be stored in a database.

[0748] Data Preprocessing

[0749] The server pre-processes the collected data, which includes text cleaning (removing unnecessary characters and spaces), tokenization (splitting words and sentences), and stop-word removal (removing common words), using natural language processing libraries such as Python's NLTK and spaCy.

[0750] Natural Language Processing (NLP)

[0751] The server then analyzes the preprocessed data using natural language processing techniques. Specifically, it performs sentiment analysis and topic modeling to extract useful information from the text data. Sentiment analysis is performed using the Python spaCy library, and topic modeling is performed using LDA (Latent Dirichlet Allocation).

[0752] Extracting indicators

[0753] The server extracts indicators of organizational culture from the analysis results. For example, it evaluates the level of active communication or the extent to which specific values ​​are shared. A generative AI model (e.g., OpenAI's GPT-4) is used for this evaluation. Using the generative AI model, specific indicators of organizational culture are generated based on the analysis results.

[0754] Displaying the results

[0755] The terminal displays the extracted indicators to the user. The user can log in to the system and check the indicators of organizational culture. For example, when the user types "Tell me how active communication was last month" into the terminal, the server retrieves the corresponding indicators from the database and sends them to the terminal. The terminal displays the retrieved indicators to the user.

[0756] Specific examples

[0757] Suppose a user logs into the system and wants to check how active communication is within their organization. The user types in "Tell me how active communication was last month" on their terminal. The server analyzes the collected email and chat data and generates a result using a generative AI model. The result is displayed as "Communication was very active last month, with particularly a lot of discussion about Project X."

[0758] Prompt Sentence Examples

[0759] "Analyze email and chat content within your organization to assess communication intensity and shared values."

[0760] In this way, the server is a system that consistently performs data collection, analysis, and indicator extraction, providing users with specific indicators of organizational culture.

[0761] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0762] Step 1: Data collection

[0763] The server collects email and chat content. Specifically, it retrieves data from email servers and chat platforms through APIs. The input is raw data retrieved from the email and chat APIs, and the output is unprocessed text data stored in a database. Specifically, the server periodically calls the API to retrieve new messages and store them in the database.

[0764] Step 2: Data Preprocessing

[0765] The server preprocesses the collected data. The input is raw text data stored in a database, and the output is preprocessed, clean text data. Specifically, the server uses Python's NLTK and spaCy libraries to tokenize the text data, remove unnecessary characters and spaces, and remove stop words.

[0766] Step 3: Natural Language Processing (NLP)

[0767] The server analyzes the preprocessed data using natural language processing technology. The input is preprocessed clean text data, and the output is a sentiment score and topic model as the analysis results. Specifically, the server performs sentiment analysis using the Python spaCy library and performs topic modeling using LDA (Latent Dirichlet Allocation).

[0768] Step 4: Extracting metrics

[0769] The server extracts organizational culture indicators from the analysis results. The input is the analysis results such as sentiment scores and topic models, and the output is the organizational culture indicators. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate specific organizational culture indicators based on the analysis results.

[0770] Step 5: View the results

[0771] The terminal displays the extracted indicators to the user. The input is the indicators of organizational culture, and the output is specific indicator information displayed to the user. In concrete terms, when the user types "Tell me how active communication was last month" into the terminal, the server retrieves the corresponding indicators from the database and sends them to the terminal. The terminal then displays the retrieved indicators to the user.

[0772] (Application example 1)

[0773] Next, a description will be given of Application Example 1 of Form 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."

[0774] Conventional organizational culture analysis systems primarily target email and chat content in office environments, and do not provide information on improving communication, work efficiency, or safety within factories. Furthermore, they lack real-time feedback functionality, making it difficult to take immediate action to improve. This has resulted in insufficient efforts to improve work efficiency and safety within factories.

[0775] 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.

[0776] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for analyzing communication within the factory and providing information useful for improving work efficiency and safety, and means for providing feedback to managers and workers in real time, thereby enabling improvements in work efficiency and safety within the factory.

[0777] "Email" means a digital message sent or received over the Internet or other network.

[0778] "Chat" is a means of communication for exchanging text messages in real time.

[0779] "Organizational culture" is the set of values, beliefs, and behaviors shared within an organization.

[0780] An "analytical means" is a method or device for collecting data and analyzing that data using specific algorithms or techniques.

[0781] A "diagnostic means" is a method or device for assessing a particular condition or problem based on the results of an analysis.

[0782] A "comparison tool" is a method or device for contrasting different data sets or results to find differences and commonalities.

[0783] "Proposal means" refers to a method or device for suggesting specific actions or improvement measures based on the results of analysis or diagnosis.

[0784] "Supporting measures" are methods or devices that provide the necessary support and resources in implementing the proposed actions or improvements.

[0785] "Communication within the factory" refers to the exchange of information and communication between workers and managers within the factory.

[0786] "Work efficiency" is an index that indicates how much work can be completed within a certain time.

[0787] "Safety" is an indicator of how safe the work environment and work processes are to avoid accidents and dangers.

[0788] A "means for providing feedback" is a method or device for returning information in real time based on the results of analysis or diagnosis.

[0789] A system for carrying out the present invention includes a program that collects the contents of emails and chats and analyzes them using natural language processing technology. A specific embodiment of this system is described below.

[0790] The server first collects email and chat content, which involves connecting to a mail server such as an IMAP server and retrieving all emails from the user's mailbox. The retrieved email content is collected in text format.

[0791] Next, the server uses natural language processing technology to analyze the collected email and chat content. Specifically, it uses NLTK's VADER Sentiment Analyzer to perform sentiment analysis on each email. It also performs TF-IDF vectorization to convert the email content into a numerical vector. Finally, it clusters the email content using KMeans clustering.

[0792] Based on the analysis results, the server diagnoses the culture of each organization (department / section) and compares the results with other organizations, making it possible to evaluate the level of communication within the organization and whether specific values ​​are being adopted.

[0793] Furthermore, the server proposes improvement actions based on the diagnosis results, including specific guidelines for improving organizational culture. Based on the proposed improvement actions, the server supports the improvement cycle.

[0794] The server analyzes communications within the factory and provides real-time feedback to managers and workers to provide information that will help improve work efficiency and safety. This feedback is based on the results of analysis and diagnosis.

[0795] As a concrete example, the following prompt sentence could be input to a generative AI model:

[0796] "I want to develop an application that analyzes communications within a factory and provides information that will help improve work efficiency and safety. I want to apply technology that collects email and chat content and analyzes it using natural language processing technology to extract elements that serve as indicators of organizational culture."

[0797] By inputting this prompt into a generative AI model, more specific analysis results and ideas for how to provide feedback can be obtained.

[0798] The hardware used is a mail server (e.g., IMAP server) and a computer that performs analysis. The software used is Python, NLTK, and Scikit-learn. This will enable improved work efficiency and safety within the factory.

[0799] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0800] Step 1:

[0801] The server collects emails and chat messages. Specifically, it connects to the IMAP server and retrieves all messages from the user's mailbox. The input is the user's email account information, and the output is the email message in text format.

[0802] Step 2:

[0803] The server saves the collected email and chat content in text format. The input is the email content acquired in step 1, and the output is the email content saved in a text file or database.

[0804] Step 3:

[0805] The server uses natural language processing technology to analyze the content of collected emails and chats. Specifically, it uses NLTK's VADER Sentiment Analyzer to perform sentiment analysis of each email. The input is the text content of the email, and the output is a sentiment score for each email.

[0806] Step 4:

[0807] The server performs TF-IDF vectorization to convert the email content into a numerical vector. The input is the email content in text format, and the output is a numerical vector.

[0808] Step 5:

[0809] The server clusters the email content using KMeans clustering. The input is a numeric vector, and the output is a cluster label for each email.

[0810] Step 6:

[0811] The server diagnoses the culture of each organization (department / section) based on the analysis results. The input is the emotion score and cluster label, and the output is the organizational culture diagnosis result.

[0812] Step 7:

[0813] The server compares the diagnosis results with other organizations. The input is the diagnosis results of the organizational culture, and the output is the comparison results with other organizations.

[0814] Step 8:

[0815] The server proposes improvement actions based on the diagnosis results. The input is the organizational culture diagnosis results and the results of comparison with other organizations, and the output is a proposal of specific improvement actions.

[0816] Step 9:

[0817] The server supports an improvement cycle based on the proposed improvement actions, with the input being the proposed improvement actions and the output being support information for the improvement cycle.

[0818] Step 10:

[0819] The server analyzes communications within the factory and provides information useful for improving work efficiency and safety. The input is the analysis results of emails and chats, and the output is information related to work efficiency and safety.

[0820] Step 11:

[0821] The server provides real-time feedback to managers and workers. The input is information about work efficiency and safety, and the output is feedback to managers and workers.

[0822] Example 2

[0823] Next, a description will be given of Example 2 of Form 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."

[0824] Conventional organizational culture diagnostic systems analyze organizational culture solely from email and chat content, which can result in biased and incomplete data. Furthermore, the criteria for comparing diagnostic results with other organizations are often vague, and suggested improvement actions often lack specificity. This makes it difficult to accurately diagnose organizational culture and make effective improvements.

[0825] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for extracting cultural elements from the preprocessed data, a means for diagnosing the culture of each organization based on the extracted cultural elements, a means for comparing the diagnosis results with other organizations, and a means for storing the diagnosis results in a database. This enables accurate diagnosis of organizational culture and comparison with other organizations, and makes it possible to propose specific improvement actions.

[0826] "Means for collecting data" refers to a device or method for collecting data such as feedback from users and survey results.

[0827] "Means for pre-processing collected data" refers to a device or method for pre-processing collected data, such as cleaning and tokenizing it.

[0828] A "means for extracting cultural elements" is a device or method for extracting organizational cultural elements from data preprocessed using a generative AI model.

[0829] The "means for diagnosing the culture of each organization" is a device or method for diagnosing the culture of each organization based on the extracted cultural elements.

[0830] "Means for comparing diagnostic results with other tissues" refers to a device or method for comparing diagnostic results with diagnostic results of other tissues.

[0831] The "means for storing diagnostic results in a database" refers to a device or method for storing the generated diagnostic results in a database.

[0832] A "generative AI model" is a model that uses artificial intelligence to generate specific information from data.

[0833] A "prompt" is an instruction sentence input to a generative AI model, which contains a question or command to extract specific information.

[0834] The present invention relates to a system for diagnosing the culture of an organization and comparing it with other organizations. A specific embodiment of this system will be described below.

[0835] First, the user collects data about the organization's culture, such as employee feedback and survey results. The user then sends this data to the server via their device. The data is often sent in CSV or JSON format.

[0836] Next, the server preprocesses the received data. Specifically, it cleans the data (removes unnecessary characters and noise) and tokenizes it (divides the text into words). The server preprocesses the text data using the Python libraries NLTK and spaCy.

[0837] The server then uses a generative AI model (e.g., a model using artificial intelligence) to extract cultural elements from the preprocessed data. The server inputs prompt sentences into the generative AI model to extract cultural elements. Specific examples of prompt sentences include the following:

[0838] "Please extract organizational culture elements from the following feedback data:

[0839] 1. There is active communication between team members.

[0840] 2. New ideas are frequently proposed.

[0841] 3. Cooperation among employees is emphasized.

[0842] By inputting this prompt into a generative AI model, the model extracts cultural elements such as "communication," "innovation," and "cooperation."

[0843] Next, the server generates a cultural diagnosis of the organization based on the extracted cultural elements. The diagnosis results are formatted in a format that allows comparison with other organizations. For example, the server may generate a diagnosis result such as, "This organization has active communication and frequent innovation."

[0844] Finally, the server stores the generated diagnostic results in a database, which makes it easy to compare with other organizations. The server stores data using an RDBMS such as MySQL or PostgreSQL.

[0845] This system enables accurate diagnosis of organizational culture and comparison with other organizations, enabling proposals for specific improvement actions.

[0846] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0847] Step 1: Data collection

[0848] Users collect data about their organization's culture, including employee feedback and survey results.

[0849] Input: Feedback and survey result data.

[0850] Output: Collected data.

[0851] Specific operation: The terminal receives the data entered by the user into the questionnaire form and sends it to the server.

[0852] Step 2: Data Preprocessing

[0853] The server preprocesses the received data, specifically cleaning the data (removing unnecessary characters and noise) and tokenizing (dividing the text into words).

[0854] Input: Collected data.

[0855] Output: Preprocessed data.

[0856] Specific operation: Remove unnecessary spaces and special characters from the feedback data received by the server and split it into words. Uses Python libraries NLTK and spaCy.

[0857] Step 3: Extracting cultural elements

[0858] The server uses a generative AI model to extract cultural elements from the pre-processed data.

[0859] Input: Preprocessed data.

[0860] Output: Extracted cultural elements.

[0861] Specific operation: The server inputs the prompt statement, "Please extract organizational cultural elements from the following feedback data: 1. Communication between team members is active. 2. New ideas are frequently proposed. 3. Cooperation between employees is emphasized," into the generative AI model, and extracts cultural elements such as "communication," "innovation," and "cooperation."

[0862] Step 4: Generate diagnostic results

[0863] The server generates a cultural diagnosis result for the organization based on the extracted cultural elements.

[0864] Input: Extracted cultural elements.

[0865] Output: Organizational culture diagnostic results.

[0866] Specific operation: Based on the extracted cultural elements, the server generates diagnostic results such as "This organization has active communication and frequent innovation."

[0867] Step 5: Store in the database

[0868] The server stores the generated diagnostic results in a database.

[0869] Input: Organizational culture diagnostic results.

[0870] Output: Diagnostic results stored in a database.

[0871] Specific operation: The diagnostic results generated by the server are saved in a database in the form of "organization ID," "cultural elements," "diagnosis results," etc. RDBMS such as MySQL or PostgreSQL is used.

[0872] (Application example 2)

[0873] Next, a description will be given of Application Example 2 of Form 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."

[0874] Conventional organizational culture diagnostic systems were limited to analyzing organizational culture based on the content of emails and chats, making it difficult to diagnose the work patterns and communication styles of each department within a factory in real time.In addition, they lacked the functionality to propose an efficient work environment based on the diagnostic results, making it difficult to contribute to improving productivity throughout the organization.

[0875] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0876] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for collecting data from sensors and cameras, means for inputting the collected data into a generative AI model to diagnose the culture of each department, means for storing the diagnosis results in a database and comparing them with other departments, and means for generating a report proposing an efficient work environment. This makes it possible to diagnose the work patterns and communication styles of each department in a factory in real time and propose an efficient work environment.

[0877] "Email" means a digital message sent or received over the Internet.

[0878] "Chat" is a means of communication for exchanging text messages in real time.

[0879] "Organizational culture" is the set of values, beliefs, and behaviors shared within an organization.

[0880] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[0881] "Diagnosis" is the act of identifying a specific condition or problem based on data.

[0882] "Comparison" is the act of contrasting two or more objects and revealing their differences and similarities.

[0883] An "improvement action" is a specific action or measure taken to solve a specific problem.

[0884] An "improvement cycle" is a series of processes for continuous improvement.

[0885] A "sensor" is a device that detects physical phenomena and converts them into data.

[0886] A "camera" is a device that captures images or videos.

[0887] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information or predictions from data.

[0888] A "database" is a system for efficiently storing, managing, and retrieving data.

[0889] A "report" is a document that organizes and reports information on a specific topic.

[0890] "Work environment" is the collective term for the physical and psychological environment in which work takes place.

[0891] A system for carrying out the present invention has the following configuration: The server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for collecting data from sensors and cameras, means for inputting the collected data into a generative AI model to diagnose the culture of each department, means for storing the diagnosis results in a database and comparing them with other departments, and means for generating a report that proposes an efficient work environment.

[0892] First, the server uses sensors and cameras installed in the factory to collect real-time data on the work patterns and communication styles of each department. The collected data is preprocessed using OpenCV, an image processing library, to extract features. Next, the extracted features are input into a generative AI model to diagnose the culture of each department. This generative AI model is built using scikit-learn, a machine learning library.

[0893] The results of the diagnosis are stored in a database and compared with those of other departments. The database stores past data and best practices for proposing efficient work environments. The server generates reports that suggest efficient work environments based on this data. These reports are provided in dashboard format for users to view.

[0894] As a concrete example, consider the case of diagnosing the culture of the assembly department and the inspection department and proposing an efficient work environment. The server diagnoses the work patterns and communication style of the assembly department and inputs prompt sentences to the generative AI model to propose an efficient work environment. An example of a prompt sentence is as follows:

[0895] "Please diagnose the work patterns and communication styles of the assembly department and propose an efficient work environment."

[0896] This prompt can be used to input data into the generative AI model to obtain diagnostic results. Based on the diagnostic results, the server generates a report suggesting an efficient work environment and provides it to the user.

[0897] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0898] Step 1:

[0899] The server uses sensors and cameras installed in the factory to collect real-time data on the work patterns and communication styles of each department. The input is data from the sensors and cameras, and the output is the collected raw data. Specifically, the cameras periodically capture images, and the sensors collect environmental data (temperature, humidity, volume, etc.).

[0900] Step 2:

[0901] The server preprocesses the collected data using OpenCV, an image processing library. The input is the raw data collected in step 1, and the output is the preprocessed data. Specifically, the image data is converted to grayscale, and noise removal and edge detection are performed.

[0902] Step 3:

[0903] The server extracts features from the preprocessed data. The input is the preprocessed data, and the output is the extracted features. Specifically, it uses the SIFT (Scale-Invariant Feature Transform) algorithm to detect feature points in the image and generate a feature vector.

[0904] Step 4:

[0905] The server inputs the extracted features into a generative AI model to diagnose the culture of each department. The input is the features, and the output is the diagnosis result. Specifically, the generative AI model is built using the scikit-learn library, and performs clustering and classification based on the features.

[0906] Step 5:

[0907] The server stores the diagnostic results in a database. The input is the diagnostic results, and the output is the diagnostic results stored in the database. Specifically, the server inserts the diagnostic results into the appropriate tables using a database management system (DBMS).

[0908] Step 6:

[0909] The server compares the results with those of other departments based on the diagnostic results stored in the database. The input is the diagnostic results stored in the database, and the output is the comparison results. Specifically, it uses SQL queries to compare with the diagnostic results of other departments and perform statistical analysis.

[0910] Step 7:

[0911] The server generates a report proposing an efficient work environment. The input is the comparison result, and the output is a proposal report. Specifically, the server uses a report generation tool to create a document proposing an efficient work environment based on the comparison result.

[0912] Step 8:

[0913] The user views the report generated by the server in the form of a dashboard. The input is the proposal report, and the output is the dashboard that the user views. Specifically, the user accesses the dashboard using a web browser and checks the proposal report.

[0914] Example 3

[0915] Next, a description will be given of Example 3 of Form Example 3. 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."

[0916] Conventional organizational culture analysis systems simply analyze the content of emails and chats, but are inadequate in proposing specific improvement actions or supporting their implementation. Furthermore, there is a lack of a way to effectively communicate the analysis results to relevant parties, which often delays the start of the improvement cycle. This creates the problem of not improving the quality and efficiency of communication throughout the organization.

[0917] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0918] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for performing sentiment analysis and topic modeling of text data using a generative AI model, and means for notifying relevant parties of the proposed improvement actions using a notification system. This makes it possible to perform a detailed analysis of the communication situation within an organization and quickly propose and notify specific improvement actions.

[0919] "Email" is a means of communication for sending and receiving text and files over the Internet.

[0920] "Chat" is a means of communication for exchanging text messages in real time.

[0921] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[0922] "Analysis" is the process of examining data in detail to understand its meaning and structure.

[0923] "Diagnosis" is a means of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[0924] "Comparison" is a means of contrasting different data or results and revealing their differences and similarities.

[0925] "Improvement actions" are specific guidelines and measures proposed based on the diagnostic results.

[0926] An "improvement cycle" is a series of processes in which improvement actions are carried out, the results are evaluated, and the results are used to lead to the next improvement.

[0927] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze and generate text data.

[0928] "Sentiment analysis" is a method of extracting emotions and feelings from text data and evaluating their trends.

[0929] "Topic modeling" is a method for extracting major themes and topics from text data and understanding their structure.

[0930] A "notification system" is a communication method or platform for quickly conveying specific information to relevant parties.

[0931] The present invention is a system for analyzing the communication situation within an organization and proposing improvement actions. A specific embodiment of this system is described below.

[0932] Hardware and software used

[0933] Hardware: Servers, terminals (PCs, smartphones)

[0934] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), notification systems (e.g., Slack, email)

[0935] System Overview

[0936] In this system, the server collects email and chat content within the organization and analyzes it using a generative AI model. Based on the analysis results, the system diagnoses the communication situation in each department and proposes improvement actions. The proposed improvement actions are notified to relevant parties using a notification system, helping to start the improvement cycle.

[0937] Specific actions

[0938] 1. Data Collection

[0939] The server collects communication data from the email server and chat system (e.g., Slack, Microsoft Teams) for the past month. Specifically, it uses an API to obtain email sending and receiving history and chat logs, and stores them in a database.

[0940] 2. Data analysis

[0941] The server analyzes the collected data. Generative AI models (e.g., GPT-4) are used to perform sentiment analysis and topic modeling on the text data. For example, email content can be analyzed to determine whether it contains more positive or negative interactions.

[0942] 3. Generating diagnostic results

[0943] The server then uses the analysis results to diagnose the communication situation in each department, generating a diagnosis such as, "Department A has a lot of positive interactions, while Department B has a lot of negative interactions."

[0944] 4. Proposal of improvement actions

[0945] Based on the results of the diagnosis, the server uses a generative AI model to propose improvement actions. For example, it generates specific actions such as "Propose regular meetings to Department B."

[0946] 5. Notification

[0947] The server notifies the relevant parties of the proposed improvement action. The server notifies the relevant parties of the improvement action using a notification system (e.g., Slack, email). For example, using the Slack API, a message is sent to the manager of Department B suggesting "holding regular meetings."

[0948] 6. Start the improvement cycle

[0949] Users (stakeholders) receive notifications and take suggested improvement actions, for example, the manager of department B schedules and runs a regular meeting.

[0950] Examples of concrete examples and prompts

[0951] Specific examples

[0952] Data collection: The server collects email sending and receiving history for the past month from the email server.

[0953] Data analysis: The server uses the generated AI model to analyze the sentiment of the email content and evaluate whether it contains a lot of positive or negative interactions.

[0954] Generating diagnostic results: Department A is diagnosed as having many positive interactions, while Department B is diagnosed as having many negative interactions.

[0955] Proposal for improvement action: Propose to Department B that they hold regular meetings.

[0956] Notification: The server uses Slack to notify the manager of department B of the improvement action.

[0957] Initiating the improvement cycle: Department B's manager schedules and conducts regular meetings.

[0958] Prompt Sentence Examples

[0959] "Communication within Department B is lacking. Please suggest some action to improve it."

[0960] In this way, the system diagnoses the communication situation within the organization and proposes appropriate improvement actions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0961] Step 1:

[0962] Data collection

[0963] The server collects communication data from the mail server and chat system for the past month. Specifically, it uses an API to obtain email sending and receiving history and chat logs and stores them in a database.

[0964] Input: Communication data from mail servers and chat systems

[0965] Output: Communication data stored in a database

[0966] Step 2:

[0967] Data Preprocessing

[0968] The server preprocesses the collected data, specifically cleaning the text data (removing unnecessary characters and spaces), tokenizing it (dividing it into words), and removing stop words (removing frequently occurring but meaningless words).

[0969] Input: Communication data stored in a database

[0970] Output: Preprocessed text data

[0971] Step 3:

[0972] Data analysis

[0973] The server analyzes the preprocessed data. It uses a generative AI model (e.g., GPT-4) to perform sentiment analysis and topic modeling on the text data. For example, it analyzes the content of emails and evaluates whether they contain a lot of positive or negative interactions.

[0974] Input: Preprocessed text data

[0975] Output: Sentiment analysis and topic modeling results

[0976] Step 4:

[0977] Generating diagnostic results

[0978] The server then uses the analysis results to diagnose the communication situation in each department, generating a diagnosis such as, "Department A has a lot of positive interactions, while Department B has a lot of negative interactions."

[0979] Input: Sentiment analysis results and topic modeling results

[0980] Output: Diagnostic results regarding the communication status of each department

[0981] Step 5:

[0982] Proposal of improvement actions

[0983] Based on the results of the diagnosis, the server uses a generative AI model to propose improvement actions. For example, it generates specific actions such as "Propose regular meetings to Department B."

[0984] Input: Diagnostic results regarding the communication status of each department

[0985] Output: Suggested improvement actions

[0986] Step 6:

[0987] notification

[0988] The server notifies the relevant parties of the proposed improvement action. The server notifies the relevant parties of the improvement action using a notification system (e.g., Slack, email). For example, using the Slack API, a message is sent to the manager of Department B suggesting "holding regular meetings."

[0989] Input: Proposed improvement action

[0990] Output: Notification message sent to interested parties

[0991] Step 7:

[0992] Start of the improvement cycle

[0993] Users (stakeholders) receive notifications and take suggested improvement actions, for example, the manager of department B schedules and runs a regular meeting.

[0994] Input: Notification message sent to interested parties

[0995] Output: Improvement actions taken

[0996] (Application example 3)

[0997] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0998] Conventional organizational culture analysis systems can propose improvement actions based on the analysis results, but these proposals are not properly communicated to the relevant parties, which means that the improvement cycle is not carried out effectively. In addition, the proposed improvement actions are not presented as concrete guidelines, so it is unclear how the relevant parties should act, and they often do not lead to actual improvements. This has led to the issue of insufficient improvement in communication and efficiency throughout the organization.

[0999] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1000] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for notifying relevant parties of the improvement actions based on the diagnosis results, means for generating specific action guidelines for executing the proposed improvement actions, and means for notifying relevant parties of the generated action guidelines.As a result, specific improvement actions based on the diagnosis results are appropriately notified to relevant parties and executed, thereby enabling improvement of communication and efficiency throughout the organization.

[1001] "Email" means a digital message sent or received over the Internet or other computer network.

[1002] "Chat" is a means of communication for exchanging text messages in real time.

[1003] "Organizational culture" refers to the values, beliefs, and codes of behavior shared within an organization.

[1004] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[1005] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[1006] "Comparison" is the process of contrasting different elements to reveal their differences and similarities.

[1007] "Improvement actions" are specific improvement measures proposed based on the results of the diagnosis.

[1008] "Notification" is the process of communicating information to interested parties.

[1009] A "code of conduct" is an instruction or guideline that indicates specific behavior.

[1010] "Stakeholders" are people or groups within or outside an organization who are involved in a particular project or task.

[1011] A "server" is a computer system that provides data and services over a network.

[1012] The system for implementing this invention consists of three main elements: a server, terminals, and users. The server plays a central role in analyzing the content of emails and chats and diagnosing organizational culture. The terminals are devices through which users interface with the server, and users are the entities that operate the system and take action to improve it.

[1013] Server Roles and Operations

[1014] The server analyzes and calculates data using the following hardware and software.

[1015] Hardware: A server machine with a powerful processor, sufficient memory, and ample storage.

[1016] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning frameworks (e.g., TensorFlow, PyTorch), database management systems (e.g., MySQL, PostgreSQL).

[1017] The server first collects email and chat content and analyzes this data using natural language processing technology. Based on the analysis results, it diagnoses the culture of each organization (department / section) and compares it with other organizations. Based on the diagnosis results, a generative AI model is used to propose specific improvement actions. The proposed improvement actions are notified to the relevant parties and are then generated as specific guidelines for action.

[1018] Terminal roles and processing

[1019] A terminal is a device through which a user interfaces with a server, and uses the following hardware and software:

[1020] Hardware: Devices such as computers, tablets, and smartphones.

[1021] Software: web browsers, email clients, chat applications.

[1022] The device receives notifications and action guidelines sent from the server and displays them to the user, who can then take specific action to improve the situation.

[1023] User Roles and Actions

[1024] Users are the ones who operate the system and take action to improve it. They receive notifications and guidelines from the server via their devices and take specific actions based on them. For example, they hold regular meetings or carry out team-building activities.

[1025] Specific examples

[1026] For example, if communication in a particular department within a factory is diagnosed as being sluggish, the server will suggest the following improvement actions:

[1027] Suggest holding regular meetings.

[1028] Suggest team-building activities.

[1029] These suggestions are communicated to relevant parties via the terminal, and users then take action to improve the situation in accordance with specific guidelines.

[1030] Prompt Sentence Examples

[1031] An example of a prompt sentence to input to the generative AI model is as follows:

[1032] Develop a system that diagnoses the communication situation within a factory and proposes improvement actions. Based on the results of the diagnosis, it should propose regular meetings and team building activities, and include a function to notify relevant parties by email.

[1033] In this way, providing specific modes for carrying out the invention can improve communication and efficiency throughout an organization.

[1034] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1035] Step 1:

[1036] The server collects email and chat content. This involves retrieving data from mail and chat servers. The input is raw email and chat data, and the output is text data for analysis. Specifically, it retrieves emails using IMAP and SMTP protocols and collects chat data using APIs.

[1037] Step 2:

[1038] The server analyzes the collected text data using natural language processing technology. The input is the text data collected in step 1, and the output is the analysis results. Specifically, it uses natural language processing libraries such as NLTK and spaCy to perform text tokenization, part-of-speech tagging, sentiment analysis, etc.

[1039] Step 3:

[1040] The server diagnoses the culture of each organization (department / section) based on the analysis results. The input is the analysis results obtained in step 2, and the output is the diagnosis results. Specifically, a machine learning model is used to reverse-calculate the level of communication activity and specific values.

[1041] Step 4:

[1042] The server compares the diagnosis results with those of other organizations. The input is the diagnosis results obtained in step 3, and the output is the comparison results. Specifically, the results are compared with the diagnosis results of other organizations stored in the database and a relative evaluation is performed.

[1043] Step 5:

[1044] The server proposes improvement actions based on the diagnosis results. The input is the comparison result obtained in step 4, and the output is the proposed improvement actions. Specifically, a generative AI model is used to generate specific improvement actions. Prompt statements are used to give appropriate instructions to the model.

[1045] Step 6:

[1046] The server notifies the stakeholders of the proposed remediation actions. The input is the remediation action generated in step 5, and the output is the sending of a notification. Specifically, it sends an email using the SMTP protocol and a chat message using an API.

[1047] Step 7:

[1048] The server generates a specific action plan for implementing the proposed improvement actions. The input is the improvement action generated in step 5, and the output is a specific action plan. Specifically, a generative AI model is used to create a detailed action plan.

[1049] Step 8:

[1050] The server notifies the relevant parties of the generated action plan. The input is the action plan generated in step 7, and the output is sending a notification. Specifically, it sends an email using the SMTP protocol and a chat message using an API.

[1051] Step 9:

[1052] The user receives notifications and action guidelines from the server through their terminal and takes specific improvement actions based on them. The input is the notifications and action guidelines sent in step 8, and the output is the implemented improvement actions. Specifically, this involves holding regular meetings and carrying out team-building activities.

[1053] 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.

[1054] "Example 1"

[1055] In one embodiment of the present invention, an emotion engine is used to analyze a user's emotions from the content of emails and chats. Specifically, the emotion engine uses natural language processing and machine learning techniques to recognize a user's emotions and track changes in those emotions. For example, the emotion engine infers a user's emotional state from the words, expressions, emoticons, and other elements used by the user in emails and chats.

[1056] "Example 2"

[1057] The analysis results of the emotion engine are also reflected in the diagnosis of organizational culture. Specifically, changes in user emotions are evaluated as an indicator of organizational culture, and the culture of each organization is diagnosed. For example, if the user's emotions are changing positively, the organization's culture is diagnosed as being good. Conversely, if the user's emotions are changing negatively, the organization's culture is diagnosed as having problems.

[1058] "Example 3"

[1059] Furthermore, the system suggests improvement actions based on changes in the user's emotions. Specifically, if the user's emotions are changing negatively, the system identifies the cause and suggests improvement actions to resolve the cause. For example, if the system determines that the cause of the user's negative emotions is a lack of communication, it suggests holding regular meetings or team-building activities.

[1060] The processing flow of each embodiment will be described below.

[1061] "Example 1"

[1062] Step 1: The emotion engine collects email and chat content from users.

[1063] Step 2: Recognize the user's emotions from the collected information using natural language processing and machine learning technologies.

[1064] Step 3: Track the user's emotional changes and save the results.

[1065] "Example 2"

[1066] Step 1: Obtain the analysis results of the emotion engine.

[1067] Step 2: Evaluate the analysis results as indicators of organizational culture.

[1068] Step 3: Based on the assessment results, diagnose the organization's culture and save the results.

[1069] "Example 3"

[1070] Step 1: Obtain diagnostic results of changes in user sentiment and organizational culture.

[1071] Step 2: If the emotional change is negative, identify its cause.

[1072] Step 3: Propose improvement actions to eliminate the causes and save the results.

[1073] Example 1

[1074] Next, a description will be given of Example 1 of Form 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."

[1075] In modern organizations, communication via email and chat is extremely important, but there is a lack of effective ways to analyze the content of email and chat and use it to diagnose and improve organizational culture. It is also difficult to analyze user sentiment and understand the health of the organization. This poses a challenge, delaying improvements to the quality of organizational communication and culture.

[1076] 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.

[1077] In this invention, the server includes means for collecting the contents of emails and chats, means for preprocessing the collected data, and means for analyzing the preprocessed data using natural language processing technology, which makes it possible to analyze the level of communication activity within an organization, whether specific values ​​are being calculated, and to analyze user emotions.

[1078] "Email" means a digital message sent or received over the Internet.

[1079] "Chat" is a means of communication for exchanging text messages in real time.

[1080] "Means of collection" refers to the methods and technologies used to obtain email and chat content.

[1081] "Preprocessing means" refers to methods and techniques for converting collected data into a format that is easy to analyze.

[1082] "Natural language processing technology" is a technology that allows computers to analyze, understand, and generate human language.

[1083] "Analytical means" are methods and techniques for analyzing data and extracting meaning and patterns.

[1084] "Organizational culture" is the collection of values, beliefs, and codes of conduct shared within an organization.

[1085] A "diagnostic means" is a method or technique for assessing the state of tissue based on the results of an analysis.

[1086] "Comparative means" are methods or techniques for comparing diagnostic results with results from other tissues.

[1087] "Improvement actions" are specific actions taken to solve organizational problems and improve performance.

[1088] "Proposal means" are methods and techniques for proposing improvement actions.

[1089] "Supporting measures" are methods and techniques to support the implementation of the proposed improvement actions.

[1090] An "emotion engine" is software or algorithms for analyzing user emotions from text data.

[1091] A "user" is an individual or member of an organization who uses email or chat.

[1092] The present invention is a system for collecting the contents of emails and chats within an organization and analyzing them using natural language processing technology. A specific embodiment of this system will be described below.

[1093] Data collection

[1094] The server collects email and chat content within the organization. Specifically, it uses the APIs of mail servers and chat platforms to obtain users' email and chat messages. For example, it can use the APIs of Microsoft Exchange and Slack. The server periodically accesses these platforms to collect new messages.

[1095] Data Preprocessing

[1096] The server preprocesses the collected data by using the Python libraries NLTK and spaCy to tokenize the text data, remove unnecessary symbols and spaces, and clean up email and chat metadata (sender, recipient, timestamp, etc.).

[1097] Analysis using natural language processing

[1098] The server then uses natural language processing technology to analyze the preprocessed data. Specifically, it performs grammatical analysis of the text and extracts keywords. For example, it uses spaCy to identify parts of speech such as nouns and verbs and extract important keywords. This allows it to extract elements that serve as indicators of organizational culture (for example, how active communication is, or whether specific values ​​are being worked out).

[1099] Emotion analysis

[1100] The server uses an emotion engine to analyze the user's emotions from the content of emails and chats. The emotion engine uses Google Cloud Natural Language API and IBM Watson Natural Language Understanding. Using these tools, the server infers the user's emotional state from the words, expressions, and emojis used in emails and chats, and tracks changes in that state.

[1101] Saving and displaying results

[1102] The server stores the analysis results in a database. Specifically, a relational database such as MySQL or PostgreSQL is used. The stored data is displayed on a dashboard that can be accessed by administrators and users. The dashboard is built using a web framework such as Django or Flask.

[1103] Specific examples

[1104] For example, if a user reports "the project is progressing smoothly" by email, the server collects and preprocesses this email. Next, it uses natural language processing technology to extract keywords such as "project," "smooth," and "progressing." It then uses an emotion engine to recognize positive emotions and stores the results in a database. Finally, administrators can view the results through a dashboard.

[1105] Prompt Sentence Examples

[1106] Examples of prompts to be input to a generative AI model include:

[1107] "Please analyze the user's sentiment from the following text:

[1108] 1. 'The project is progressing smoothly'

[1109] 2. 'This task is very difficult'

[1110] Using this prompt, the generative AI model can analyze the user's emotions from the text and return the results.

[1111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1112] Step 1:

[1113] The server collects email and chat content. Specifically, it uses the API of a mail server or chat platform to obtain user email and chat messages. For example, it uses the API of Microsoft Exchange or Slack. The input is the raw message data obtained from the API, and the output is the collected message data.

[1114] Step 2:

[1115] The server preprocesses the collected data. Specifically, it uses the Python libraries NLTK and spaCy to tokenize the text data and remove unnecessary symbols and spaces. It also organizes email and chat metadata (sender, recipient, timestamp, etc.). The input is the collected message data, and the output is the preprocessed, clean text data.

[1116] Step 3:

[1117] The server analyzes the preprocessed data using natural language processing technology. Specifically, it performs grammatical analysis of the text and extracts keywords. For example, it uses spaCy to identify parts of speech such as nouns and verbs and extract important keywords. The input is the preprocessed, clean text data, and the output is the analyzed keywords and grammatical information.

[1118] Step 4:

[1119] The server uses an emotion engine to analyze the user's emotions from the content of emails and chats. The emotion engine uses Google Cloud Natural Language API and IBM Watson Natural Language Understanding. These tools are used to estimate the user's emotional state from the words, expressions, and emojis used by the user in emails and chats, and track changes in that state. The input is the analyzed keywords and grammatical information, and the output is the estimated result of the user's emotional state.

[1120] Step 5:

[1121] The server stores the analysis results in a database. Specifically, a relational database such as MySQL or PostgreSQL is used. The stored data is displayed on a dashboard that can be accessed by administrators and users. The dashboard is built using a web framework such as Django or Flask. The input is the estimation result of the user's emotional state, and the output is the analysis results stored in the database.

[1122] Step 6:

[1123] Users check the analysis results through a dashboard. Specifically, they access the dashboard using a web browser and view information such as the level of communication activity in the organization, whether specific values ​​are being calculated, and the user's emotional state. The input is the analysis results stored in the database, and the output is the display of the analysis results that the user views.

[1124] (Application example 1)

[1125] Next, a description will be given of Application Example 1 of Form 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."

[1126] Conventional organizational culture analysis systems analyze email and chat content to diagnose organizational culture and suggest improvement actions, but they were unable to monitor specific factory environments or employee emotional states in real time. This made it difficult to grasp the level of communication within a factory and the emotional state of employees, and to suggest appropriate improvement actions.

[1127] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting an improvement cycle based on the proposed improvement actions, means for collecting the content of emails and chats within the factory, means for analyzing the collected data using natural language processing technology and recognizing emotions, means for extracting indicators of organizational culture, and means for visualizing the emotions and indicators of organizational culture. This makes it possible to monitor the activity of communication within the factory and the emotional states of employees in real time and propose appropriate improvement actions.

[1128] "Email" means a digital message sent or received over the Internet or other network.

[1129] "Chat" is a means of communication for exchanging text messages in real time.

[1130] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[1131] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[1132] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[1133] "Comparison" is the process of contrasting different data or results to reveal similarities and differences.

[1134] "Improvement actions" are specific actions or measures proposed based on the diagnostic results.

[1135] An "improvement cycle" is a series of processes in which improvement actions are carried out, the results are evaluated, and the next improvement action is planned and executed.

[1136] "Natural language processing technology" is a technology that uses computers to understand, analyze, and generate human language.

[1137] An "emotion engine" is software that analyzes and recognizes user emotions from text data.

[1138] An "indicator" is a standard or measure for quantitatively evaluating a specific phenomenon or condition.

[1139] "Visualization" is the process of visually representing data or information to make it easier to understand.

[1140] The system for implementing this invention collects the contents of emails and chats within a factory and analyzes them using natural language processing technology and an emotion engine to monitor indicators of organizational culture and the emotional state of employees in real time. Specific embodiments are described below.

[1141] Hardware and software used

[1142] Hardware: Robots in factories (e.g. general-purpose robots)

[1143] Software: Python, NLTK, Scikit-learn, Matplotlib

[1144] Data collection

[1145] The server collects email and chat content from within the factory as text files, allowing for centralized management of communication data within the factory.

[1146] Natural Language Processing and Sentiment Analysis

[1147] The server analyzes the collected data using natural language processing technology and recognizes the user's emotions using an emotion engine. Specifically, it uses NLTK's SentimentIntensityAnalyzer to analyze the emotions in each email and chat.

[1148] Extracting indicators of organizational culture

[1149] The server extracts indicators of organizational culture by vectorizing the text data using TfidfVectorizer and reducing the dimensions using PCA, which allows us to evaluate the level of communication within the factory and whether specific values ​​are being adopted.

[1150] Data Visualization

[1151] The server uses Matplotlib to visualize the sentiment and organizational culture indicators in a two-dimensional plot, allowing users to visually grasp the state of communication within the factory and the emotional state of employees.

[1152] Specific examples

[1153] For example, if an email sent within a factory contains the content "Today's production line is going smoothly. Thank you for your hard work, everyone!", the server collects this email and analyzes it using natural language processing technology. As a result of the sentiment analysis, the email is recognized as having a positive sentiment (compound score: 0.8).

[1154] Prompt Sentence Examples

[1155] An example of a prompt sentence to input to the generative AI model is as follows:

[1156] Develop a system that collects email and chat content from within the factory and analyzes it using natural language processing technology and an emotion engine. Specifically, create a program that meets the following requirements:

[1157] 1. Collect emails and chat messages within the factory.

[1158] 2. Analyze the collected data using natural language processing technology to recognize emotions.

[1159] 3. Extract indicators of organizational culture.

[1160] 4. Visualize sentiment and organizational culture indicators.

[1161] In this way, it is possible to monitor the level of communication within the factory and the emotional state of employees in real time and propose appropriate improvement actions.

[1162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1163] Step 1:

[1164] The server collects the contents of emails and chats within the factory. Specifically, it acquires data in text file format from each terminal in the factory and stores it in a central database. The input is the text data of emails and chats from each terminal, and the output is the text data stored in the database.

[1165] Step 2:

[1166] The server analyzes the collected text data using natural language processing technology. Specifically, it uses Python's NLTK library to tokenize the text data and calculates sentiment scores using an emotion engine (SentimentIntensityAnalyzer). The input is the text data stored in the database, and the output is the sentiment score for each piece of text data.

[1167] Step 3:

[1168] The server recognizes the emotional state of employees based on the emotion scores. Specifically, it aggregates the emotion scores and classifies them into positive, negative, and neutral emotional states. The input is the emotion score, and the output is the classification result of the emotional state of each employee.

[1169] Step 4:

[1170] The server extracts indicators of organizational culture. Specifically, it vectorizes the text data using TfidfVectorizer and performs dimensionality reduction using PCA. The input is the text data, and the output is a dimension-reduced indicator of organizational culture.

[1171] Step 5:

[1172] The server visualizes the emotional state and organizational culture indicators. Specifically, it uses Matplotlib to create a two-dimensional plot and visually display the emotional state and organizational culture indicators. The input is the classification results of the emotional state and the organizational culture indicators, and the output is a visualized graph.

[1173] Step 6:

[1174] The server proposes improvement actions based on the visualized data. Specifically, it uses a generative AI model to generate appropriate improvement actions based on prompt statements. The inputs are the visualized data and the prompt statements, and the output is the proposed improvement actions.

[1175] Step 7:

[1176] The user executes an improvement cycle based on the proposed improvement actions. Specifically, the user executes the proposed course of action and sends the results to the server as feedback. The input is the proposed improvement action, and the output is feedback of the execution results.

[1177] Example 2

[1178] Next, a description will be given of Example 2 of Form 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."

[1179] Conventional organizational culture diagnostic systems were limited to analyzing the content of emails and chats, and were unable to directly utilize user emotional data. As a result, the accuracy of organizational culture diagnostics was low, and the proposals for improvement actions were ineffective. Furthermore, the construction of a database for comparing diagnostic results with other organizations was insufficient. This led to the issue of the organizational culture improvement cycle not functioning effectively.

[1180] 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.

[1181] In this invention, the server includes means for a user to input emotional data, means for transmitting the input emotional data to the server, means for the server to analyze the emotional data, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for storing the diagnosis results in a database and comparing them with other organizations, means for proposing improvement actions based on the diagnosis results, and means for supporting the improvement cycle based on the proposed improvement actions. This makes it possible to diagnose organizational culture with high accuracy by directly using user emotional data and to propose effective improvement actions.

[1182] A "user" is an individual or group that uses the system to input emotion data.

[1183] "Emotion data" is data such as text and numerical values ​​entered by the user, which represents the user's emotional state.

[1184] A "server" is a computer system that receives and analyzes emotion data and stores the diagnostic results in a database.

[1185] An "emotion engine" is software used by the server to analyze and classify emotional data as positive or negative.

[1186] A "database" is a system that stores diagnostic results and preserves information to enable comparison with other organizations.

[1187] "Organizational culture" refers to the values, behavioral patterns, and communication characteristics of a particular organization (department / section).

[1188] The "diagnosis result" is information indicating the state of organizational culture evaluated based on the analysis results of emotion data.

[1189] "Improvement actions" are specific guidelines for improving organizational culture that are proposed based on the diagnostic results.

[1190] An "improvement cycle" is a series of processes in which a proposed improvement action is implemented, the results are reevaluated, and the next improvement action is proposed.

[1191] The present invention relates to a system for diagnosing organizational culture based on user emotion data and proposing improvement actions. Specific embodiments of this system will be described below.

[1192] Hardware and software used

[1193] Hardware: Servers, terminals

[1194] Software: emotion engine, database management system (e.g., MySQL), generative AI model

[1195] System Overview

[1196] 1. Entering emotion data

[1197] The user inputs their own emotional data into the emotion engine using a terminal. Specifically, the user inputs text such as "I had a lot of fun today" or "I'm stressed because things aren't going well at work."

[1198] 2. Sending Emotional Data

[1199] The device sends the input emotion data to the server. Specifically, the device sends the emotion data to the server using an HTTP request.

[1200] 3. Emotion Data Analysis

[1201] The server passes the received emotion data to the emotion engine for analysis. Specifically, the server calls the emotion engine's API and classifies the emotion data as positive or negative. For example, data such as "I had a lot of fun today" is analyzed as positive, and data such as "I felt stressed because things weren't going well at work" is analyzed as negative.

[1202] 4. Diagnosis of organizational culture

[1203] Based on the analysis results, the server diagnoses the culture of the organization to which the user belongs. Specifically, if there are many positive emotions, the server diagnoses that the culture of the organization is good, and if there are many negative emotions, it diagnoses that the culture of the organization has problems. For example, if the user's emotional data is positive, such as "I had a lot of fun today," it diagnoses that the culture of the organization is good.

[1204] 5. Storing diagnostic results in a database

[1205] The server stores the results of the assessment in a database. Specifically, the server uses a database management system (e.g., MySQL) to save the results in a format that allows comparison with other organizations. For example, the assessment result that organization A has a good culture can be stored in the database so that it can be compared with other organizations B and C.

[1206] Specific examples

[1207] A user types into the emotion engine, "I had a lot of fun today."

[1208] The terminal sends this input to the server.

[1209] The server uses an emotion engine to analyze the emotion "it was fun" as positive.

[1210] Based on this positive emotion, the server diagnoses the culture of the organization to which the user belongs as being good.

[1211] The server stores the diagnostic results in a database, allowing comparison with other organizations.

[1212] Example prompts for generative AI models

[1213] "Please explain a system that diagnoses organizational culture based on user emotional data. Please explain in detail how the emotional engine, database, server, and terminal are used to collect and analyze data and store the diagnostic results."

[1214] In this way, the system diagnoses organizational culture based on users' emotional data and stores the results in a database that allows comparison with other organizations.

[1215] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1216] Step 1:

[1217] The user inputs their own emotional data into the emotion engine using a terminal. Specifically, the user inputs text such as "I had a lot of fun today" or "I'm stressed because things aren't going well at work." The input data is sent to the emotion engine.

[1218] Step 2:

[1219] The device sends the input emotion data to the server. Specifically, the device sends emotion data to the server using an HTTP request. The input is the user's emotion data, and the output is data sent to the server.

[1220] Step 3:

[1221] The server passes the received emotion data to the emotion engine for analysis. Specifically, the server calls the emotion engine's API to classify the emotion data as positive or negative. The input is emotion data, and the output is the analysis result: positive or negative.

[1222] Step 4:

[1223] The server then uses the analysis results to diagnose the culture of the organization to which the user belongs. Specifically, if there are many positive emotions, the server diagnoses that the culture of the organization is good, and if there are many negative emotions, it diagnoses that there are problems with the culture of the organization. The input is the analysis results, and the output is the diagnosis of the organizational culture.

[1224] Step 5:

[1225] The server stores the diagnosis results in a database. Specifically, the server uses a database management system (e.g., MySQL) to save the diagnosis results in a format that allows comparison with other organizations. The input is the diagnosis results of organizational culture, and the output is storage in the database.

[1226] Step 6:

[1227] The server proposes improvement actions based on the diagnosis results. Specifically, the server uses a generative AI model to generate specific action guidelines for improving organizational culture. The input is the diagnosis results of organizational culture, and the output is proposals for improvement actions.

[1228] Step 7:

[1229] The server supports the improvement cycle based on the proposed improvement actions. Specifically, the server monitors the execution status of the improvement actions and proposes the next improvement action as necessary. The input is the execution status of the improvement action, and the output is a proposal for the next improvement action.

[1230] (Application example 2)

[1231] Next, a description will be given of Application Example 2 of Form 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."

[1232] Conventional organizational culture diagnostic systems were limited to analyzing organizational culture based on the content of emails and chats, and were unable to reflect changes in employee emotions in real time. As a result, the diagnosis of organizational culture was one-sided, making it difficult to accurately grasp the actual state of the organization. In addition, there was a lack of means to compare diagnostic results based on emotional data with other organizations, and suggestions for improvement actions and support for improvement cycles were not adequately provided.

[1233] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1234] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for analyzing employee emotions in real time, means for storing the emotion analysis results in a database, means for diagnosing organizational culture based on the emotion data, and means for displaying the diagnosis results. This makes it possible to diagnose organizational culture that reflects changes in employee emotions in real time, enabling a more accurate and multifaceted evaluation of organizational culture.

[1235] "Email" means a digital message sent or received over the Internet.

[1236] "Chat" is a means of communication in which text messages are exchanged in real time.

[1237] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[1238] "Analysis" is the process of examining data in detail to reveal its structure and meaning.

[1239] "Diagnosis" is the act of evaluating the current situation based on data and information and identifying problems and areas for improvement.

[1240] "Comparison" is the act of contrasting multiple objects and revealing their differences and similarities.

[1241] "Improvement actions" are specific actions or measures to solve current problems and improve the situation.

[1242] The "improvement cycle" is a method of continuously improving the situation by repeating the process of planning, doing, evaluating, and improving.

[1243] "Emotions" are psychological responses that humans have to certain situations or stimuli.

[1244] "Real-time" refers to processing or reaction occurring immediately, without delay.

[1245] A "database" is a system for efficiently storing, searching, and managing data.

[1246] "Display" is the act of visually showing data or information.

[1247] As an embodiment of the present invention, a robot for diagnosing organizational culture in a factory will be described as an example. The system includes a program for analyzing the emotions of employees in real time and diagnosing the organizational culture.

[1248] The server uses the following hardware and software:

[1249] camera

[1250] Robot body (e.g. Pepper)

[1251] Image processing library (e.g. OpenCV)

[1252] Sentiment Analysis Engine

[1253] Database Management Systems

[1254] The server uses a camera to capture employees' faces and analyzes their emotions using an emotion analysis engine. The analyzed emotion data is stored in a database management system. The server then aggregates the emotion data over a certain period of time and calculates the percentage of positive emotions to diagnose the organizational culture. The diagnosis results are displayed on the robot's display or on the manager's terminal.

[1255] For example, when a factory worker talks to a robot, the robot analyzes their facial expressions and tone of voice to collect emotional data. The data is compiled weekly and the results of the organizational culture diagnosis are reported to the factory manager.

[1256] An example of a prompt is as follows:

[1257] Design a robot that analyzes the emotions of employees in a factory in real time and diagnoses the organizational culture. The robot will analyze employees' facial expressions and tone of voice using an emotion engine and store the data in a database. It will compile data over a certain period of time and diagnose the organizational culture on a three-point scale: "Good," "Average," or "Problematic."

[1258] In this way, the server diagnoses organizational culture in a way that reflects changes in employee sentiment in real time, enabling a more accurate and multifaceted evaluation of organizational culture.

[1259] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1260] Step 1:

[1261] The server captures the employee's face using a camera. The input is video data from the camera, and the output is the captured image frame. Specifically, the server acquires video data from the camera at regular intervals and saves it as an image frame.

[1262] Step 2:

[1263] The server uses a sentiment analysis engine to analyze employee emotions from captured image frames. The input is the image frame, and the output is the analyzed emotion data (e.g., positive, negative). Specifically, the server passes the image frame to the sentiment analysis engine and performs sentiment analysis.

[1264] Step 3:

[1265] The server stores the analyzed emotion data in a database management system. The input is emotion data and employee identification information, and the output is emotion data stored in the database. Specifically, the server pairs emotion data with employee IDs and stores them in the database.

[1266] Step 4:

[1267] The server aggregates emotion data over a certain period of time and calculates the percentage of positive emotions. The input is emotion data obtained from the database, and the output is the percentage of positive emotions. Specifically, the server obtains emotion data from the database, counts positive and negative emotion data, and calculates the percentage.

[1268] Step 5:

[1269] The server diagnoses organizational culture based on the calculated percentage of positive emotions. The input is the percentage of positive emotions, and the output is the organizational culture diagnosis result (e.g., good, average, problematic). Specifically, the server applies diagnostic criteria based on the percentage of positive emotions to evaluate organizational culture.

[1270] Step 6:

[1271] The server displays the diagnostic results on the robot's display or the administrator's terminal. The input is the organizational culture diagnostic results, and the output is the displayed diagnostic results. Specifically, the server converts the diagnostic results into text format and sends them to the robot's display or the administrator's terminal for display.

[1272] Step 7:

[1273] The user (administrator) checks the displayed diagnostic results and takes improvement actions as necessary. The input is the diagnostic results, and the output is the implemented improvement actions. In concrete terms, the user considers improvement measures for the organization based on the diagnostic results and puts them into action.

[1274] Example 3

[1275] Next, a description will be given of Example 3 of Form Example 3. 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."

[1276] Conventional organizational culture analysis systems can analyze organizational culture from the content of electronic communications and suggest improvement actions based on the diagnostic results, but they have the problem of not being able to suggest improvement actions that take into account user emotional data. This has resulted in a lack of concrete improvement measures to improve the quality of communication within an organization and employee satisfaction.

[1277] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1278] In this invention, the server includes means for analyzing organizational culture from the content of electronic communications, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting an improvement cycle based on the proposed improvement actions, means for collecting and analyzing user emotion data, means for proposing improvement actions based on changes in the emotion data, and means for notifying relevant parties of the proposed improvement actions. This makes it possible to propose specific improvement actions that take user emotion data into consideration, thereby improving the quality of communication within the organization and employee satisfaction.

[1279] "Electronic communications" are means of communication that take place in a digital format, such as email or chat.

[1280] "Organizational culture" is the collection of values, beliefs, and codes of conduct shared within an organization.

[1281] "Analysis" is the process of collecting data and analyzing its content for a specific purpose.

[1282] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[1283] "Improvement actions" are specific guidelines and measures proposed based on the diagnostic results.

[1284] An "improvement cycle" is a series of processes in which improvement actions are implemented, the results are evaluated, and the next improvement plan is planned.

[1285] "Emotion data" is data that indicates the emotional state of the user, and includes an emotion score extracted from text data.

[1286] A "generative AI model" is an algorithm or system that uses artificial intelligence to generate and analyze data.

[1287] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[1288] "Notification" is a communication method used to inform stakeholders of proposed improvement actions.

[1289] The present invention relates to a system that analyzes communication within an organization and user emotion data and proposes improvement actions. A specific embodiment of this system is described below.

[1290] First, the server uses specific software to collect user emotion data. For example, it uses an emotion analysis API to analyze text data entered by the user on the device and extract an emotion score. If the user enters "Work hasn't been going well lately," the server sends this text data to the emotion analysis API and obtains a negative emotion score.

[1291] The server then stores the analyzed emotion data in a database, which contains information such as user IDs, text data, and emotion scores (positive, negative, or neutral). For example, a MySQL database is used to manage the data.

[1292] The server then periodically analyzes the emotion data in the database and uses a generative AI model (e.g., GPT-4) to identify changes in the user's emotion. Specifically, it compares past emotion data with current emotion data to determine whether there are any negative changes.

[1293] The server proposes improvement actions based on the analysis results of the emotion data. For example, if the user's emotion is changing negatively, the cause is identified and a prompt sentence is input into the AI ​​model to suggest appropriate improvement actions. An example of a prompt sentence could be, "Please identify the cause of the user's emotion changing negatively and propose improvement actions to resolve that cause."

[1294] Finally, the server notifies relevant parties within the organization of the proposed improvement actions. Notifications are sent via email or chat tools (e.g., Slack or Microsoft Teams). The notification includes details of the proposed improvement actions and how to implement them. For example, the notification might say, "User sentiment has become negative, so we suggest holding regular meetings and team-building activities."

[1295] In this way, the system can suggest appropriate improvement actions based on changes in the user's emotions and support a cycle of improving communication within an organization. The flow of the identification process in the third embodiment will be described with reference to FIG. 21.

[1296] Step 1:

[1297] The user inputs text data from the terminal.

[1298] Input: A user types into a terminal, "Work hasn't been going well lately."

[1299] Specific operation: The user enters text into the input field on the terminal and presses the send button.

[1300] Output: The terminal sends the entered text data to the server.

[1301] Step 2:

[1302] The server sends the received text data to the sentiment analysis API and obtains a sentiment score.

[1303] Input: Text data sent from the device: "Work hasn't been going well lately."

[1304] Specific operation: The server sends text data to the sentiment analysis API and receives a sentiment score (negative) from the API.

[1305] Output: Sentiment score (negative).

[1306] Step 3:

[1307] The server stores the obtained emotion scores in a database.

[1308] Input: Sentiment score (negative), user ID, text data.

[1309] Specific operation: The server stores user IDs, text data, and emotion scores in a MySQL database.

[1310] Output: Emotion data stored in a database.

[1311] Step 4:

[1312] The server periodically analyzes the emotion data in the database.

[1313] Input: Past and current emotion data stored in the database.

[1314] Specific operation: The server uses a generative AI model (GPT-4) to compare past and current emotional data and identify changes in emotions.

[1315] Output: Emotional change (from positive to negative).

[1316] Step 5:

[1317] The server suggests improvement actions based on changes in the emotion data.

[1318] Input: Emotional change (from positive to negative).

[1319] Specific operation: The server inputs a prompt to the generative AI model: "Please identify the cause of the user's negative emotion change and propose an improvement action to resolve that cause." The generative AI model then outputs an appropriate improvement action.

[1320] Output: Improvement actions (holding regular meetings and team building activities).

[1321] Step 6:

[1322] The server notifies the interested parties of the proposed remedial actions.

[1323] Input: Improvement actions (holding regular meetings and team building activities).

[1324] Specific behavior: The server notifies relevant parties of proposed improvement actions via email and chat tools (Slack and Microsoft Teams).

[1325] Output: Notification sent to stakeholders ("User sentiment is changing negatively, we suggest holding regular meetings and team building activities.").

[1326] (Application example 3)

[1327] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1328] Conventional organizational culture analysis systems can analyze organizational culture from email and chat content and suggest improvement actions, but they have the problem of not being able to suggest real-time improvement actions based on changes in worker emotions. Also, there was a lack of a way to quickly notify relevant parties of the proposed improvement actions, which could delay the start of the improvement cycle.

[1329] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for monitoring the emotions of workers in real time, means for proposing improvement actions based on changes in emotions, and means for notifying relevant parties of the proposed improvement actions. This enables real-time proposal of improvement actions based on changes in workers' emotions and rapid notification.

[1330] "Email" is a means of communication for sending and receiving text and files over the Internet.

[1331] "Chat" is a means of communication for exchanging text messages in real time.

[1332] "Organizational culture" is a general term for the values, beliefs, and codes of behavior shared within an organization.

[1333] "Analysis" is the process of collecting data, extracting information from that data, and understanding it.

[1334] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[1335] "Comparison" is the process of contrasting different data or information to reveal their differences and similarities.

[1336] "Improvement actions" are specific actions or measures taken to solve a specific problem or improve a situation.

[1337] An "improvement cycle" is a repeated process of identifying problems, implementing improvement actions, and evaluating the results.

[1338] "Monitoring" is the process of continuously observing and collecting data on a specific object.

[1339] An "emotion" is a psychological response that a person has to a particular situation or stimulus.

[1340] "Real-time" refers to processing or reaction occurring immediately, without delay.

[1341] "Notification" is the process of communicating specific information to interested parties.

[1342] A system for carrying out this invention is configured as follows: The server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for monitoring the emotions of workers in real time, means for proposing improvement actions based on changes in emotions, and means for notifying relevant parties of the proposed improvement actions.

[1343] Hardware and software used

[1344] Hardware: Factory robots, cameras, microphones, sensors

[1345] Software: Emotion recognition AI model, data analysis tools, notification system

[1346] Program processing procedure

[1347] 1. Data Collection:

[1348] Cameras and microphones mounted on factory robots are used to collect workers' facial expressions and tone of voice in real time.

[1349] Sensors are also used to collect data on the work environment (temperature, humidity, noise levels, etc.).

[1350] 2. Emotion recognition:

[1351] The collected data is input into an emotion recognition AI model to analyze the emotions of workers.

[1352] The emotion recognition AI model uses, for example, "Cloud Vision API" and "Tone Analyzer."

[1353] 3. Identifying the cause:

[1354] If your emotions are shifting negatively, identify the cause.

[1355] Use data analysis tools (e.g., Python's Pandas or Scikit-learn) to compare with historical data and identify causes of negative sentiment.

[1356] 4. Suggested improvement actions:

[1357] Based on the identified causes, suggest appropriate improvement actions.

[1358] For example, if the problem is a lack of communication, suggest holding regular meetings and team-building activities.

[1359] 5. Notice:

[1360] Communicate proposed improvement actions to relevant parties within the organization.

[1361] Use notification systems (e.g., Slack API or email notification systems) to notify relevant parties in real time.

[1362] Specific examples

[1363] Scenario: Worker A is feeling stressed in a factory.

[1364] Data collection: Worker A's facial expressions and tone of voice were collected using a camera and microphone.

[1365] Emotion recognition: The emotion recognition AI model determines that Worker A's emotion is "stress."

[1366] Identifying the cause: Data analysis tools compare with past data and identify the cause of stress as "increased workload."

[1367] Suggested improvement actions: Workload adjustments and break suggestions.

[1368] Notification: Proposal details are notified to factory managers via Slack.

[1369] Prompt Sentence Examples

[1370] "Develop a system that monitors the emotions of workers in factories in real time, and if their emotions change negatively, identifies the cause and suggests appropriate improvement actions. For example, if a worker is feeling stressed, identify the cause and suggest a break or rearrange work. The hardware used would be cameras, microphones, and sensors, and the software would be emotion recognition AI models, data analysis tools, and notification systems."

[1371] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1372] Step 1:

[1373] The server uses cameras and microphones installed on factory robots to collect the facial expressions and tone of voice of workers in real time. The input is video and audio data from the camera and microphone, and the output is a stream of these data. Specifically, the camera captures the worker's face, and the microphone records the tone of voice.

[1374] Step 2:

[1375] The server uses sensors to collect data about the working environment (such as temperature, humidity, and noise level). The input is the environmental data from the sensors, and the output is a stream of these data. Specifically, the temperature sensor measures the temperature of the environment, and the noise sensor records the noise level.

[1376] Step 3:

[1377] The server inputs the collected video and audio data into an emotion recognition AI model to analyze the worker's emotions. The input is video and audio data, and the output is the emotion analysis result. Specifically, the AI ​​model uses an expression recognition algorithm to analyze facial expressions and an audio analysis algorithm to analyze the tone of voice.

[1378] Step 4:

[1379] The server uses a data analysis tool to identify the cause of negative sentiment changes. The input is the sentiment analysis results and past data, and the output is the cause of the negative sentiment. Specifically, the data analysis tool compares past data with current data to identify outliers and patterns.

[1380] Step 5:

[1381] The server proposes appropriate improvement actions based on the identified causes. The input is the cause of the negative emotion, and the output is the proposed improvement action. Specifically, the server selects and proposes an appropriate action from a database of improvement actions.

[1382] Step 6:

[1383] The server notifies relevant parties within the organization of proposed improvement actions. The input is the proposed improvement action, and the output is a notification message. Specifically, the notification system uses the Slack API or email notification system to send notifications to relevant parties in real time.

[1384] 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.

[1385] 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> ) 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.

[1386] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1387] 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.

[1388] [Third embodiment]

[1389] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1390] 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.

[1391] 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).

[1392] 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.

[1393] 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.

[1394] 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).

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1401] "Example 1"

[1402] In one embodiment of the present invention, the contents of emails and chats within an organization are collected. The collected data is analyzed using natural language processing technology to extract elements that serve as indicators of organizational culture (e.g., the level of active communication, whether specific values ​​are being adopted, etc.).

[1403] "Example 2"

[1404] Next, the culture of each organization (department / section) is diagnosed based on the extracted elements. The results are stored in a database that allows comparison with other organizations.

[1405] "Example 3"

[1406] Furthermore, improvement actions are proposed based on the results of the diagnosis. The proposed improvement actions are notified to relevant parties within the organization to help start the improvement cycle. Specifically, for departments where communication is sluggish, actions such as holding regular meetings or proposing team-building activities could be considered.

[1407] The processing flow of each embodiment will be described below.

[1408] "Example 1"

[1409] Step 1: Collect email and chat content from within the organization. Specifically, obtain data from the organization's email server and chat tools.

[1410] Step 2: Analyze the collected data using natural language processing technology. Specifically, using techniques such as text mining and sentiment analysis, extract elements such as the level of communication activity and whether specific values ​​are being calculated.

[1411] "Example 2"

[1412] Step 1: Diagnose the culture of each organization (department / section) based on the extracted elements. Specifically, evaluate the extracted elements as indicators of organizational culture and diagnose the culture of each organization.

[1413] Step 2: The diagnostic results are stored in a database. Specifically, the diagnostic results are classified by organization and stored in a database that allows comparison with other organizations.

[1414] "Example 3"

[1415] Step 1: Propose improvement actions based on the diagnosis results. Specifically, for departments where communication is sluggish, consider actions such as holding regular meetings or proposing team-building activities.

[1416] Step 2: Notify the relevant parties within the organization of the proposed improvement actions. Specifically, communicate the improvement actions to the relevant parties via email or chat tools and help start the improvement cycle.

[1417] Example 1

[1418] Next, a description will be given of Example 1 of Form 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."

[1419] Conventional organizational culture analysis systems have had difficulty effectively collecting and analyzing email and chat content to extract indicators of organizational culture. Furthermore, they lacked a means to display the extracted indicators in an easy-to-understand manner for users, making it difficult to propose specific guidelines for action aimed at improving organizational culture. This made it impossible to accurately evaluate the level of communication within an organization or the degree to which values ​​are shared, and to take appropriate action to improve it.

[1420] 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.

[1421] In this invention, the server includes means for collecting email and chat content, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology, means for extracting indicators of organizational culture from the analysis results, and means for displaying the extracted indicators to the user. This makes it possible to accurately evaluate the level of communication within the organization and the degree of shared values, and to provide the user with specific guidelines for action.

[1422] "Email" means a digital message sent or received over the Internet or other computer network.

[1423] "Chat" is a means of communication for exchanging text messages in real time.

[1424] "Means of collection" refers to the technology and process used to capture email and chat content and store it in a database.

[1425] "Preprocessing means" refers to techniques and processes such as data cleaning and tokenization that prepare collected data in a form that is easier to analyze.

[1426] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language.

[1427] "Analysis means" are techniques or processes that use pre-processed data to extract specific information or patterns.

[1428] "Organizational culture indicators" are specific indicators for evaluating an organization's culture, such as the level of communication within the organization and the degree of shared values.

[1429] "Means of extraction" refers to the techniques and processes used to extract useful information and indicators from the analysis results.

[1430] The "display means" refers to the techniques and processes for visually presenting the extracted indicators to the user.

[1431] A "generative AI model" is a model that uses artificial intelligence to generate new information and indicators from data.

[1432] This invention is a system that collects the contents of emails and chats within an organization, analyzes them using natural language processing technology, extracts indicators of organizational culture, and provides users with specific guidelines for action.

[1433] Data collection

[1434] The server collects email and chat content. Specifically, it uses common communication platforms such as Microsoft Exchange Server and Slack API to obtain email and chat history within the organization. This allows the communication data within the organization to be stored in a database.

[1435] Data Preprocessing

[1436] The server pre-processes the collected data, which includes text cleaning (removing unnecessary characters and spaces), tokenization (splitting words and sentences), and stop-word removal (removing common words), using natural language processing libraries such as Python's NLTK and spaCy.

[1437] Natural Language Processing (NLP)

[1438] The server then analyzes the preprocessed data using natural language processing techniques. Specifically, it performs sentiment analysis and topic modeling to extract useful information from the text data. Sentiment analysis is performed using the Python spaCy library, and topic modeling is performed using LDA (Latent Dirichlet Allocation).

[1439] Extracting indicators

[1440] The server extracts indicators of organizational culture from the analysis results. For example, it evaluates the level of active communication or the extent to which specific values ​​are shared. A generative AI model (e.g., OpenAI's GPT-4) is used for this evaluation. Using the generative AI model, specific indicators of organizational culture are generated based on the analysis results.

[1441] Displaying the results

[1442] The terminal displays the extracted indicators to the user. The user can log in to the system and check the indicators of organizational culture. For example, when the user types "Tell me how active communication was last month" into the terminal, the server retrieves the corresponding indicators from the database and sends them to the terminal. The terminal displays the retrieved indicators to the user.

[1443] Specific examples

[1444] Suppose a user logs into the system and wants to check how active communication is within their organization. The user types in "Tell me how active communication was last month" on their terminal. The server analyzes the collected email and chat data and generates a result using a generative AI model. The result is displayed as "Communication was very active last month, with particularly a lot of discussion about Project X."

[1445] Prompt Sentence Examples

[1446] "Analyze email and chat content within your organization to assess communication intensity and shared values."

[1447] In this way, the server is a system that consistently performs data collection, analysis, and indicator extraction, providing users with specific indicators of organizational culture.

[1448] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1449] Step 1: Data collection

[1450] The server collects email and chat content. Specifically, it retrieves data from email servers and chat platforms through APIs. The input is raw data retrieved from the email and chat APIs, and the output is unprocessed text data stored in a database. Specifically, the server periodically calls the API to retrieve new messages and store them in the database.

[1451] Step 2: Data Preprocessing

[1452] The server preprocesses the collected data. The input is raw text data stored in a database, and the output is preprocessed, clean text data. Specifically, the server uses Python's NLTK and spaCy libraries to tokenize the text data, remove unnecessary characters and spaces, and remove stop words.

[1453] Step 3: Natural Language Processing (NLP)

[1454] The server analyzes the preprocessed data using natural language processing technology. The input is preprocessed clean text data, and the output is a sentiment score and topic model as the analysis results. Specifically, the server performs sentiment analysis using the Python spaCy library and performs topic modeling using LDA (Latent Dirichlet Allocation).

[1455] Step 4: Extracting metrics

[1456] The server extracts organizational culture indicators from the analysis results. The input is the analysis results such as sentiment scores and topic models, and the output is the organizational culture indicators. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-4) to generate specific organizational culture indicators based on the analysis results.

[1457] Step 5: View the results

[1458] The terminal displays the extracted indicators to the user. The input is the indicators of organizational culture, and the output is specific indicator information displayed to the user. In concrete terms, when the user types "Tell me how active communication was last month" into the terminal, the server retrieves the corresponding indicators from the database and sends them to the terminal. The terminal then displays the retrieved indicators to the user.

[1459] (Application example 1)

[1460] Next, a description will be given of Application Example 1 of Form 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."

[1461] Conventional organizational culture analysis systems primarily target email and chat content in office environments, and do not provide information on improving communication, work efficiency, or safety within factories. Furthermore, they lack real-time feedback functionality, making it difficult to take immediate action to improve. This has resulted in insufficient efforts to improve work efficiency and safety within factories.

[1462] 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.

[1463] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for analyzing communication within the factory and providing information useful for improving work efficiency and safety, and means for providing feedback to managers and workers in real time, thereby enabling improvements in work efficiency and safety within the factory.

[1464] "Email" means a digital message sent or received over the Internet or other network.

[1465] "Chat" is a means of communication for exchanging text messages in real time.

[1466] "Organizational culture" is the set of values, beliefs, and behaviors shared within an organization.

[1467] An "analytical means" is a method or device for collecting data and analyzing that data using specific algorithms or techniques.

[1468] A "diagnostic means" is a method or device for assessing a particular condition or problem based on the results of an analysis.

[1469] A "comparison tool" is a method or device for contrasting different data sets or results to find differences and commonalities.

[1470] "Proposal means" refers to a method or device for suggesting specific actions or improvement measures based on the results of analysis or diagnosis.

[1471] "Supporting measures" are methods or devices that provide the necessary support and resources in implementing the proposed actions or improvements.

[1472] "Communication within the factory" refers to the exchange of information and communication between workers and managers within the factory.

[1473] "Work efficiency" is an index that indicates how much work can be completed within a certain time.

[1474] "Safety" is an indicator of how safe the work environment and work processes are to avoid accidents and dangers.

[1475] A "means for providing feedback" is a method or device for returning information in real time based on the results of analysis or diagnosis.

[1476] A system for carrying out the present invention includes a program that collects the contents of emails and chats and analyzes them using natural language processing technology. A specific embodiment of this system is described below.

[1477] The server first collects email and chat content, which involves connecting to a mail server such as an IMAP server and retrieving all emails from the user's mailbox. The retrieved email content is collected in text format.

[1478] Next, the server uses natural language processing technology to analyze the collected email and chat content. Specifically, it uses NLTK's VADER Sentiment Analyzer to perform sentiment analysis on each email. It also performs TF-IDF vectorization to convert the email content into a numerical vector. Finally, it clusters the email content using KMeans clustering.

[1479] Based on the analysis results, the server diagnoses the culture of each organization (department / section) and compares the results with other organizations, making it possible to evaluate the level of communication within the organization and whether specific values ​​are being adopted.

[1480] Furthermore, the server proposes improvement actions based on the diagnosis results, including specific guidelines for improving organizational culture. Based on the proposed improvement actions, the server supports the improvement cycle.

[1481] The server analyzes communications within the factory and provides real-time feedback to managers and workers to provide information that will help improve work efficiency and safety. This feedback is based on the results of analysis and diagnosis.

[1482] As a concrete example, the following prompt sentence could be input to a generative AI model:

[1483] "I want to develop an application that analyzes communications within a factory and provides information that will help improve work efficiency and safety. I want to apply technology that collects email and chat content and analyzes it using natural language processing technology to extract elements that serve as indicators of organizational culture."

[1484] By inputting this prompt into a generative AI model, more specific analysis results and ideas for how to provide feedback can be obtained.

[1485] The hardware used is a mail server (e.g., IMAP server) and a computer that performs analysis. The software used is Python, NLTK, and Scikit-learn. This will enable improved work efficiency and safety within the factory.

[1486] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1487] Step 1:

[1488] The server collects emails and chat messages. Specifically, it connects to the IMAP server and retrieves all messages from the user's mailbox. The input is the user's email account information, and the output is the email message in text format.

[1489] Step 2:

[1490] The server saves the collected email and chat content in text format. The input is the email content acquired in step 1, and the output is the email content saved in a text file or database.

[1491] Step 3:

[1492] The server uses natural language processing technology to analyze the content of collected emails and chats. Specifically, it uses NLTK's VADER Sentiment Analyzer to perform sentiment analysis of each email. The input is the text content of the email, and the output is a sentiment score for each email.

[1493] Step 4:

[1494] The server performs TF-IDF vectorization to convert the email content into a numerical vector. The input is the email content in text format, and the output is a numerical vector.

[1495] Step 5:

[1496] The server clusters the email content using KMeans clustering. The input is a numeric vector, and the output is a cluster label for each email.

[1497] Step 6:

[1498] The server diagnoses the culture of each organization (department / section) based on the analysis results. The input is the emotion score and cluster label, and the output is the organizational culture diagnosis result.

[1499] Step 7:

[1500] The server compares the diagnosis results with other organizations. The input is the diagnosis results of the organizational culture, and the output is the comparison results with other organizations.

[1501] Step 8:

[1502] The server proposes improvement actions based on the diagnosis results. The input is the organizational culture diagnosis results and the results of comparison with other organizations, and the output is a proposal of specific improvement actions.

[1503] Step 9:

[1504] The server supports an improvement cycle based on the proposed improvement actions, with the input being the proposed improvement actions and the output being support information for the improvement cycle.

[1505] Step 10:

[1506] The server analyzes communications within the factory and provides information useful for improving work efficiency and safety. The input is the analysis results of emails and chats, and the output is information related to work efficiency and safety.

[1507] Step 11:

[1508] The server provides real-time feedback to managers and workers. The input is information about work efficiency and safety, and the output is feedback to managers and workers.

[1509] Example 2

[1510] Next, a description will be given of Example 2 of Form 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."

[1511] Conventional organizational culture diagnostic systems analyze organizational culture solely from email and chat content, which can result in biased and incomplete data. Furthermore, the criteria for comparing diagnostic results with other organizations are often vague, and suggested improvement actions often lack specificity. This makes it difficult to accurately diagnose organizational culture and make effective improvements.

[1512] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for extracting cultural elements from the preprocessed data, a means for diagnosing the culture of each organization based on the extracted cultural elements, a means for comparing the diagnosis results with other organizations, and a means for storing the diagnosis results in a database. This enables accurate diagnosis of organizational culture and comparison with other organizations, and makes it possible to propose specific improvement actions.

[1513] "Means for collecting data" refers to a device or method for collecting data such as feedback from users and survey results.

[1514] "Means for pre-processing collected data" refers to a device or method for pre-processing collected data, such as cleaning and tokenizing it.

[1515] A "means for extracting cultural elements" is a device or method for extracting organizational cultural elements from data preprocessed using a generative AI model.

[1516] The "means for diagnosing the culture of each organization" is a device or method for diagnosing the culture of each organization based on the extracted cultural elements.

[1517] "Means for comparing diagnostic results with other tissues" refers to a device or method for comparing diagnostic results with diagnostic results of other tissues.

[1518] The "means for storing diagnostic results in a database" refers to a device or method for storing the generated diagnostic results in a database.

[1519] A "generative AI model" is a model that uses artificial intelligence to generate specific information from data.

[1520] A "prompt" is an instruction sentence input to a generative AI model, which contains a question or command to extract specific information.

[1521] The present invention relates to a system for diagnosing the culture of an organization and comparing it with other organizations. A specific embodiment of this system will be described below.

[1522] First, the user collects data about the organization's culture, such as employee feedback and survey results. The user then sends this data to the server via their device. The data is often sent in CSV or JSON format.

[1523] Next, the server preprocesses the received data. Specifically, it cleans the data (removes unnecessary characters and noise) and tokenizes it (divides the text into words). The server preprocesses the text data using the Python libraries NLTK and spaCy.

[1524] The server then uses a generative AI model (e.g., a model using artificial intelligence) to extract cultural elements from the preprocessed data. The server inputs prompt sentences into the generative AI model to extract cultural elements. Specific examples of prompt sentences include the following:

[1525] "Please extract organizational culture elements from the following feedback data:

[1526] 1. There is active communication between team members.

[1527] 2. New ideas are frequently proposed.

[1528] 3. Cooperation among employees is emphasized.

[1529] By inputting this prompt into a generative AI model, the model extracts cultural elements such as "communication," "innovation," and "cooperation."

[1530] Next, the server generates a cultural diagnosis of the organization based on the extracted cultural elements. The diagnosis results are formatted in a format that allows comparison with other organizations. For example, the server may generate a diagnosis result such as, "This organization has active communication and frequent innovation."

[1531] Finally, the server stores the generated diagnostic results in a database, which makes it easy to compare with other organizations. The server stores data using an RDBMS such as MySQL or PostgreSQL.

[1532] This system enables accurate diagnosis of organizational culture and comparison with other organizations, enabling proposals for specific improvement actions.

[1533] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1534] Step 1: Data collection

[1535] Users collect data about their organization's culture, including employee feedback and survey results.

[1536] Input: Feedback and survey result data.

[1537] Output: Collected data.

[1538] Specific operation: The terminal receives the data entered by the user into the questionnaire form and sends it to the server.

[1539] Step 2: Data Preprocessing

[1540] The server preprocesses the received data, specifically cleaning the data (removing unnecessary characters and noise) and tokenizing (dividing the text into words).

[1541] Input: Collected data.

[1542] Output: Preprocessed data.

[1543] Specific operation: Remove unnecessary spaces and special characters from the feedback data received by the server and split it into words. Uses Python libraries NLTK and spaCy.

[1544] Step 3: Extracting cultural elements

[1545] The server uses a generative AI model to extract cultural elements from the pre-processed data.

[1546] Input: Preprocessed data.

[1547] Output: Extracted cultural elements.

[1548] Specific operation: The server inputs the prompt statement, "Please extract organizational cultural elements from the following feedback data: 1. Communication between team members is active. 2. New ideas are frequently proposed. 3. Cooperation between employees is emphasized," into the generative AI model, and extracts cultural elements such as "communication," "innovation," and "cooperation."

[1549] Step 4: Generate diagnostic results

[1550] The server generates a cultural diagnosis result for the organization based on the extracted cultural elements.

[1551] Input: Extracted cultural elements.

[1552] Output: Organizational culture diagnostic results.

[1553] Specific operation: Based on the extracted cultural elements, the server generates diagnostic results such as "This organization has active communication and frequent innovation."

[1554] Step 5: Store in the database

[1555] The server stores the generated diagnostic results in a database.

[1556] Input: Organizational culture diagnostic results.

[1557] Output: Diagnostic results stored in a database.

[1558] Specific operation: The diagnostic results generated by the server are saved in a database in the form of "organization ID," "cultural elements," "diagnosis results," etc. RDBMS such as MySQL or PostgreSQL is used.

[1559] (Application example 2)

[1560] Next, a description will be given of Application Example 2 of Form 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."

[1561] Conventional organizational culture diagnostic systems were limited to analyzing organizational culture based on the content of emails and chats, making it difficult to diagnose the work patterns and communication styles of each department within a factory in real time.In addition, they lacked the functionality to propose an efficient work environment based on the diagnostic results, making it difficult to contribute to improving productivity throughout the organization.

[1562] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1563] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for collecting data from sensors and cameras, means for inputting the collected data into a generative AI model to diagnose the culture of each department, means for storing the diagnosis results in a database and comparing them with other departments, and means for generating a report proposing an efficient work environment. This makes it possible to diagnose the work patterns and communication styles of each department in a factory in real time and propose an efficient work environment.

[1564] "Email" means a digital message sent or received over the Internet.

[1565] "Chat" is a means of communication for exchanging text messages in real time.

[1566] "Organizational culture" is the set of values, beliefs, and behaviors shared within an organization.

[1567] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[1568] "Diagnosis" is the act of identifying a specific condition or problem based on data.

[1569] "Comparison" is the act of contrasting two or more objects and revealing their differences and similarities.

[1570] An "improvement action" is a specific action or measure taken to solve a specific problem.

[1571] An "improvement cycle" is a series of processes for continuous improvement.

[1572] A "sensor" is a device that detects physical phenomena and converts them into data.

[1573] A "camera" is a device that captures images or videos.

[1574] A "generative AI model" is an algorithm that uses artificial intelligence to generate new information or predictions from data.

[1575] A "database" is a system for efficiently storing, managing, and retrieving data.

[1576] A "report" is a document that organizes and reports information on a specific topic.

[1577] "Work environment" is the collective term for the physical and psychological environment in which work takes place.

[1578] A system for carrying out the present invention has the following configuration: The server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for collecting data from sensors and cameras, means for inputting the collected data into a generative AI model to diagnose the culture of each department, means for storing the diagnosis results in a database and comparing them with other departments, and means for generating a report that proposes an efficient work environment.

[1579] First, the server uses sensors and cameras installed in the factory to collect real-time data on the work patterns and communication styles of each department. The collected data is preprocessed using OpenCV, an image processing library, to extract features. Next, the extracted features are input into a generative AI model to diagnose the culture of each department. This generative AI model is built using scikit-learn, a machine learning library.

[1580] The results of the diagnosis are stored in a database and compared with those of other departments. The database stores past data and best practices for proposing efficient work environments. The server generates reports that suggest efficient work environments based on this data. These reports are provided in dashboard format for users to view.

[1581] As a concrete example, consider the case of diagnosing the culture of the assembly department and the inspection department and proposing an efficient work environment. The server diagnoses the work patterns and communication style of the assembly department and inputs prompt sentences to the generative AI model to propose an efficient work environment. An example of a prompt sentence is as follows:

[1582] "Please diagnose the work patterns and communication styles of the assembly department and propose an efficient work environment."

[1583] This prompt can be used to input data into the generative AI model to obtain diagnostic results. Based on the diagnostic results, the server generates a report suggesting an efficient work environment and provides it to the user.

[1584] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1585] Step 1:

[1586] The server uses sensors and cameras installed in the factory to collect real-time data on the work patterns and communication styles of each department. The input is data from the sensors and cameras, and the output is the collected raw data. Specifically, the cameras periodically capture images, and the sensors collect environmental data (temperature, humidity, volume, etc.).

[1587] Step 2:

[1588] The server preprocesses the collected data using OpenCV, an image processing library. The input is the raw data collected in step 1, and the output is the preprocessed data. Specifically, the image data is converted to grayscale, and noise removal and edge detection are performed.

[1589] Step 3:

[1590] The server extracts features from the preprocessed data. The input is the preprocessed data, and the output is the extracted features. Specifically, it uses the SIFT (Scale-Invariant Feature Transform) algorithm to detect feature points in the image and generate a feature vector.

[1591] Step 4:

[1592] The server inputs the extracted features into a generative AI model to diagnose the culture of each department. The input is the features, and the output is the diagnosis result. Specifically, the generative AI model is built using the scikit-learn library, and performs clustering and classification based on the features.

[1593] Step 5:

[1594] The server stores the diagnostic results in a database. The input is the diagnostic results, and the output is the diagnostic results stored in the database. Specifically, the server inserts the diagnostic results into the appropriate tables using a database management system (DBMS).

[1595] Step 6:

[1596] The server compares the results with those of other departments based on the diagnostic results stored in the database. The input is the diagnostic results stored in the database, and the output is the comparison results. Specifically, it uses SQL queries to compare with the diagnostic results of other departments and perform statistical analysis.

[1597] Step 7:

[1598] The server generates a report proposing an efficient work environment. The input is the comparison result, and the output is a proposal report. Specifically, the server uses a report generation tool to create a document proposing an efficient work environment based on the comparison result.

[1599] Step 8:

[1600] The user views the report generated by the server in the form of a dashboard. The input is the proposal report, and the output is the dashboard that the user views. Specifically, the user accesses the dashboard using a web browser and checks the proposal report.

[1601] Example 3

[1602] Next, a third embodiment of the third embodiment will be described. 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."

[1603] Conventional organizational culture analysis systems simply analyze the content of emails and chats, but are inadequate in proposing specific improvement actions or supporting their implementation. Furthermore, there is a lack of a way to effectively communicate the analysis results to relevant parties, which often delays the start of the improvement cycle. This creates the problem of not improving the quality and efficiency of communication throughout the organization.

[1604] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1605] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for performing sentiment analysis and topic modeling of text data using a generative AI model, and means for notifying relevant parties of the proposed improvement actions using a notification system. This makes it possible to perform a detailed analysis of the communication situation within an organization and quickly propose and notify specific improvement actions.

[1606] "Email" is a means of communication for sending and receiving text and files over the Internet.

[1607] "Chat" is a means of communication for exchanging text messages in real time.

[1608] "Organizational culture" is the set of values, beliefs, and codes of behavior shared within an organization.

[1609] "Analysis" is the process of examining data in detail to understand its meaning and structure.

[1610] "Diagnosis" is a means of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[1611] "Comparison" is a means of contrasting different data or results and revealing their differences and similarities.

[1612] "Improvement actions" are specific guidelines and measures proposed based on the diagnostic results.

[1613] An "improvement cycle" is a series of processes in which improvement actions are carried out, the results are evaluated, and the results are used to lead to the next improvement.

[1614] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to analyze and generate text data.

[1615] "Sentiment analysis" is a method of extracting emotions and feelings from text data and evaluating their trends.

[1616] "Topic modeling" is a method for extracting major themes and topics from text data and understanding their structure.

[1617] A "notification system" is a communication method or platform for quickly conveying specific information to relevant parties.

[1618] The present invention is a system for analyzing the communication situation within an organization and proposing improvement actions. A specific embodiment of this system is described below.

[1619] Hardware and software used

[1620] Hardware: Servers, terminals (PCs, smartphones)

[1621] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), notification systems (e.g., Slack, email)

[1622] System Overview

[1623] In this system, the server collects email and chat content within the organization and analyzes it using a generative AI model. Based on the analysis results, the system diagnoses the communication situation in each department and proposes improvement actions. The proposed improvement actions are notified to relevant parties using a notification system, helping to start the improvement cycle.

[1624] Specific actions

[1625] 1. Data Collection

[1626] The server collects communication data from the email server and chat system (e.g., Slack, Microsoft Teams) for the past month. Specifically, it uses an API to obtain email sending and receiving history and chat logs, and stores them in a database.

[1627] 2. Data analysis

[1628] The server analyzes the collected data. Generative AI models (e.g., GPT-4) are used to perform sentiment analysis and topic modeling on the text data. For example, email content can be analyzed to determine whether it contains more positive or negative interactions.

[1629] 3. Generating diagnostic results

[1630] The server then uses the analysis results to diagnose the communication situation in each department, generating a diagnosis such as, "Department A has a lot of positive interactions, while Department B has a lot of negative interactions."

[1631] 4. Proposal of improvement actions

[1632] Based on the results of the diagnosis, the server uses a generative AI model to propose improvement actions. For example, it generates specific actions such as "Propose regular meetings to Department B."

[1633] 5. Notification

[1634] The server notifies the relevant parties of the proposed improvement action. The server notifies the relevant parties of the improvement action using a notification system (e.g., Slack, email). For example, using the Slack API, a message is sent to the manager of Department B suggesting "holding regular meetings."

[1635] 6. Start the improvement cycle

[1636] Users (stakeholders) receive notifications and take suggested improvement actions, for example, the manager of department B schedules and runs a regular meeting.

[1637] Examples of concrete examples and prompts

[1638] Specific examples

[1639] Data collection: The server collects email sending and receiving history for the past month from the email server.

[1640] Data analysis: The server uses the generated AI model to analyze the sentiment of the email content and evaluate whether it contains a lot of positive or negative interactions.

[1641] Generating diagnostic results: Department A is diagnosed as having many positive interactions, while Department B is diagnosed as having many negative interactions.

[1642] Proposal for improvement action: Propose to Department B that they hold regular meetings.

[1643] Notification: The server uses Slack to notify the manager of department B of the improvement action.

[1644] Initiating the improvement cycle: Department B's manager schedules and conducts regular meetings.

[1645] Prompt Sentence Examples

[1646] "Communication within Department B is lacking. Please suggest some action to improve it."

[1647] In this way, the system diagnoses the communication situation within the organization and proposes appropriate improvement actions. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1648] Step 1:

[1649] Data collection

[1650] The server collects communication data from the mail server and chat system for the past month. Specifically, it uses an API to obtain email sending and receiving history and chat logs and stores them in a database.

[1651] Input: Communication data from mail servers and chat systems

[1652] Output: Communication data stored in a database

[1653] Step 2:

[1654] Data Preprocessing

[1655] The server preprocesses the collected data, specifically cleaning the text data (removing unnecessary characters and spaces), tokenizing it (dividing it into words), and removing stop words (removing frequently occurring but meaningless words).

[1656] Input: Communication data stored in a database

[1657] Output: Preprocessed text data

[1658] Step 3:

[1659] Data analysis

[1660] The server analyzes the preprocessed data. It uses a generative AI model (e.g., GPT-4) to perform sentiment analysis and topic modeling on the text data. For example, it analyzes the content of emails and evaluates whether they contain a lot of positive or negative interactions.

[1661] Input: Preprocessed text data

[1662] Output: Sentiment analysis and topic modeling results

[1663] Step 4:

[1664] Generating diagnostic results

[1665] The server then uses the analysis results to diagnose the communication situation in each department, generating a diagnosis such as, "Department A has a lot of positive interactions, while Department B has a lot of negative interactions."

[1666] Input: Sentiment analysis results and topic modeling results

[1667] Output: Diagnostic results regarding the communication status of each department

[1668] Step 5:

[1669] Proposal of improvement actions

[1670] Based on the results of the diagnosis, the server uses a generative AI model to propose improvement actions. For example, it generates specific actions such as "Propose regular meetings to Department B."

[1671] Input: Diagnostic results regarding the communication status of each department

[1672] Output: Suggested improvement actions

[1673] Step 6:

[1674] notification

[1675] The server notifies the relevant parties of the proposed improvement action. The server notifies the relevant parties of the improvement action using a notification system (e.g., Slack, email). For example, using the Slack API, a message is sent to the manager of Department B suggesting "holding regular meetings."

[1676] Input: Proposed improvement action

[1677] Output: Notification message sent to interested parties

[1678] Step 7:

[1679] Start of the improvement cycle

[1680] Users (stakeholders) receive notifications and take suggested improvement actions, for example, the manager of department B schedules and runs a regular meeting.

[1681] Input: Notification message sent to interested parties

[1682] Output: Improvement actions taken

[1683] (Application example 3)

[1684] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1685] Conventional organizational culture analysis systems can propose improvement actions based on the analysis results, but these proposals are not properly communicated to the relevant parties, which means that the improvement cycle is not carried out effectively. In addition, the proposed improvement actions are not presented as concrete guidelines, so it is unclear how the relevant parties should act, and they often do not lead to actual improvements. This has led to the issue of insufficient improvement in communication and efficiency throughout the organization.

[1686] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1687] In this invention, the server includes means for analyzing organizational culture from the content of emails and chats, means for diagnosing the culture of each organization (department / section) based on the analysis results, means for comparing the diagnosis results with other organizations, means for proposing improvement actions based on the diagnosis results, means for supporting the improvement cycle based on the proposed improvement actions, means for notifying relevant parties of the improvement actions based on the diagnosis results, means for generating specific action guidelines for executing the proposed improvement actions, and means for notifying relevant parties of the generated action guidelines.As a result, specific improvement actions based on the diagnosis results are appropriately notified to relevant parties and executed, thereby enabling improvement of communication and efficiency throughout the organization.

[1688] "Email" means a digital message sent or received over the Internet or other computer network.

[1689] "Chat" is a means of communication for exchanging text messages in real time.

[1690] "Organizational culture" refers to the values, beliefs, and codes of behavior shared within an organization.

[1691] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[1692] "Diagnosis" is the process of evaluating the current situation based on the analysis results and identifying problems and areas for improvement.

[1693] "Comparison" is the process of contrasting different elements to reveal their differences and similarities.

[1694] "Improvement actions" are specific improvement measures proposed based on the results of the diagnosis.

[1695] "Notification" is the process of communicating information to interested parties.

[1696] A "code of conduct" is an instruction or guideline that indicates specific behavior.

[1697] "Stakeholders" are people or groups within or outside an organization who are involved in a particular project or task.

[1698] A "server" is a computer system that provides data and services over a network.

[1699] The system for implementing this invention consists of three main elements: a server, terminals, and users. The server plays a central role in analyzing the content of emails and chats and diagnosing organizational culture. The terminals are devices through which users interface with the server, and users are the entities that operate the system and take action to improve it.

[1700] Server Roles and Operations

[1701] The server analyzes and calculates data using the following hardware and software.

[1702] Hardware: A server machine with a powerful processor, sufficient memory, and ample storage.

[1703] Software: Natural language processing libraries (e.g., NLTK, spaCy), machine learning frameworks (e.g., TensorFlow, PyTorch), database management systems (e.g., MySQL, PostgreSQL).

[1704] The server first collects email and chat content and analyzes this data using natural language processing technology. Based on the analysis results, it diagnoses the culture of each organization (department / section) and compares it with other organizations. Based on the diagnosis results, a generative AI model is used to propose specific improvement actions. The proposed improvement actions are notified to the relevant parties and are then generated as specific guidelines for action.

[1705] Terminal roles and processing

[1706] A terminal is a device through which a user interfaces with a server, and uses the following hardware and software:

[1707] Hardware: Devices such as computers, tablets, and smartphones.

[1708] Software: web browsers, email clients, chat applications.

[1709] The device receives notifications and action guidelines sent from the server and displays them to the user, who can then take specific action to improve the situation.

[1710] User Roles and Actions

[1711] Users are the ones who operate the system and take action to improve it. They receive notifications and guidelines from the server via their devices and take specific actions based on them. For example, they hold regular meetings or carry out team-building activities.

[1712] Specific examples

[1713] For example, if communication in a particular department within a factory is diagnosed as being sluggish, the server will suggest the following improvement actions:

[1714] Suggest holding regular meetings.

[1715] Suggest team-building activities.

[1716] These suggestions are communicated to relevant parties via the terminal, and users then take action to improve the situation in accordance with specific guidelines.

[1717] Prompt Sentence Examples

[1718] An example of a prompt sentence to input to the generative AI model is as follows:

[1719] Develop a system that diagnoses the communication situation within a factory and proposes improvement actions. Based on the results of the diagnosis, it should propose regular meetings and team building activities, and include a function to notify relevant parties by email.

[1720] In this way, providing specific modes for carrying out the invention can improve communication and efficiency throughout an organization.

[1721] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1722] Step 1:

[1723] The server collects email and chat content. This involves retrieving data from mail and chat servers. The input is raw email and chat data, and the output is text data for analysis. Specifically, it retrieves emails using IMAP and SMTP protocols and collects chat data using APIs.

[1724] Step 2:

[1725] The server analyzes the collected text data using natural language processing technology. The input is the text data collected in step 1, and the output is the analysis results. Specifically, it uses natural language processing libraries such as NLTK and spaCy to perform text tokenization, part-of-speech tagging, sentiment analysis, etc.

[1726] Step 3:

[1727] The server diagnoses the culture of each organization (department / section) based on the analysis results. The input is the analysis results obtained in step 2, and the output is the diagnosis results. Specifically, a machine learning model is used to reverse-calculate the level of communication activity and specific values.

[1728] Step 4:

[1729] The server compares the diagnosis results with those of other organizations. The input is the diagnosis results obtained in step 3, and the output is the comparison results. Specifically, the results are compared with the diagnosis results of other organizations stored in the database and a relative evaluation is performed.

[1730] Step 5:

[1731] The server proposes improvement actions based on the diagnosis results. The input is the comparison result obtained in step 4, and the output is the proposed improvement actions. Specifically, a generative AI model is used to generate specific improvement actions. Prompt statements are used to give appropriate instructions to the model.

[1732] Step 6:

[1733] The server notifies the stakeholders of the proposed remediation actions. The input is the remediation action generated in step 5, and the output is the sending of a notification. Specifically, it sends an email using the SMTP protocol and a chat message using an API.

[1734] Step 7:

[1735] The server generates a specific action plan for implementing the proposed improvement actions. The input is the improvement action generated in step 5, and the output is a specific action plan. Specifically, a generative AI model is used to create a detailed action plan.

[1736] Step 8:

[1737] The server notifies the relevant parties of the generated action plan. The input is the action plan generated in step 7, and the output is sending a notification. Specifically, it sends an email using the SMTP protocol and a chat message using an API.

[1738] Step 9:

[1739] The user receives notifications and action guidelines from the server through their terminal and takes specific improvement actions based on them. The input is the notifications and action guidelines sent in step 8, and the output is the implemented improvement actions. Specifically, this involves holding regular meetings and carrying out team-building activities.

[1740] 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 iden...

Claims

1. A means of analyzing organizational culture from the content of electronic communications; a means for diagnosing the organizational culture based on the analysis result of the organizational culture; A means for comparing the diagnostic result of the organizational culture with the diagnostic result of the organizational culture of another organization; means for comparing the diagnostic results and proposing improvement actions based on the comparison results; means for supporting an improvement cycle based on said proposed improvement actions; A system including:

2. means for collecting and analyzing user emotion data; The suggesting means suggests the improvement action based on the analyzed change in the emotion data of the user. The system of claim 1 .

3. The proposed means proposes specific action plans for improving the organizational culture. The system of claim 1 .

Images