system

Abstract

We provide the system. [Solution] Means for collecting data, A means of preprocessing the collected data, A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence, A means to output the generated issues and improvement proposals as a report, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order to improve the organizational performance of a company, it is important to quickly identify current problems and derive appropriate improvement measures. However, many companies have problems in that it takes a great deal of time and effort to collect, analyze data, and formulate improvement measures, and it is difficult to do so efficiently. In addition, when there are limitations in human resources and a lack of expertise in data analysis, sufficient improvement is often not possible. Furthermore, overwhelmed by the diversity and volume of data, it is difficult to obtain appropriate feedback and actionable insights. Against this background, there is a need to develop a system that automatically identifies organizational issues and provides improvement measures using generative artificial intelligence.

Means for Solving the Problems

[0005] This invention provides a system that includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, and means for outputting the generated issues and improvement proposals as a report.

[0006] Specifically, the server is equipped with means to collect user feedback data and performance indicator data. Next, the server cleans the collected feedback data and normalizes the performance indicator data. Then, using a generative artificial intelligence model, the server has the means to automatically generate organizational issues and improvement proposals from the pre-processed data. Finally, the server has the means to create a report based on the generated issues and improvement proposals and output it to the terminal. In this way, the effort required for manual analysis and improvement proposal formulation is significantly reduced, making it possible to improve organizational performance efficiently and effectively.

[0007] "Means of data collection" refers to devices or software for electronically acquiring user feedback data and corporate performance indicator data.

[0008] "Feedback data" refers to text data such as opinions, impressions, evaluations, and reviews obtained from customers and employees.

[0009] "Performance indicator data" refers to various types of data that indicate a company's business situation and performance, such as sales data, customer acquisition costs, and return rates.

[0010] "Means for preprocessing collected data" refers to devices or software used to prepare data into an appropriate format before analysis, such as cleaning collected feedback data or normalizing performance indicator data.

[0011] "Generative artificial intelligence" is an artificial intelligence technology that can generate natural language from input data and propose specific problems and improvement plans based on its content.

[0012] "Means for generating organizational challenges and improvement proposals" refers to a device or software that uses generative artificial intelligence to extract current problems within an organization from pre-processed data and propose solutions to those problems.

[0013] "Means of outputting as a report" refers to a device or software that organizes the generated issues and improvement proposals into an easy-to-read format and outputs them in PDF or other file formats.

[0014] A "system" is a set of devices, software, and combinations thereof that include all of the means described above and work together to achieve a specific objective (in this case, improving organizational performance). [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system for improving the organizational performance of companies. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence, and outputs them as a report. The specific processing of this system is performed by a server.

[0037] Program Processing Overview

[0038] Data collection

[0039] The server first collects user feedback data and company performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions. Performance metrics data includes sales data, customer acquisition costs, and return rates.

[0040] Specific example: The server collects customer reviews and monthly sales data for the past six months.

[0041] Data preprocessing

[0042] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data undergoes spell checking and sentiment analysis. Performance metric data is normalized, scaled, and outliers are handled.

[0043] Specific example: The server corrects spelling mistakes in feedback and converts sales data into a year-on-year percentage change.

[0044] Execution of generative AI models

[0045] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3(registered trademark).5-turbo) generates organizational challenges and proposed solutions from the input data.

[0046] Specific example: The server inputs user feedback and sales data into a generative AI model, which then generates specific suggestions such as "improve customer support response speed."

[0047] Identifying problems and generating improvement plans

[0048] The server extracts issues and improvement suggestions generated from generative artificial intelligence models and creates a detailed list. This clarifies the organization's current problems and proposes specific solutions for each problem.

[0049] Specific example: The server identifies problems such as "customer support response speed" and "new product marketing strategy," and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media."

[0050] Report generation and feedback

[0051] Finally, the server generates a report based on the identified issues and proposed improvements. The report is generated in PDF format and sent to the company's management and relevant personnel.

[0052] Specific example: Create a report generated by the server in PDF format and send it to management via email.

[0053] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This, in turn, can lead to a significant improvement in organizational performance.

[0054] The following describes the processing flow.

[0055] Step 1: Data Collection

[0056] The server collects user feedback data and corporate performance indicator data. It gathers customer reviews, survey results, and employee opinions provided by users. It also collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0057] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this data in a database.

[0058] Step 2: Cleaning Feedback Data

[0059] The server cleans the collected feedback data. This cleaning process includes spell checking and sentiment analysis of the text data.

[0060] Specific example: The server uses a natural language processing tool to correct spelling errors in customer reviews and categorize the sentiment of the reviews into three groups: positive, negative, and neutral.

[0061] Step 3: Normalize performance metrics data

[0062] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0063] Specific example: The server converts sales data into a year-on-year percentage change and detects and corrects abnormally high or low values.

[0064] Step 4: Combining the data

[0065] The server combines pre-processed feedback data and performance metric data. This forms the input dataset for the model.

[0066] Specific example: The server creates a data frame containing feedback data and sales data, and converts it into a format that can be input into a generative artificial intelligence model.

[0067] Step 5: Setting up and running the generative artificial intelligence model

[0068] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model then generates organizational challenges and proposed improvements.

[0069] Specific example: The server uses the Hugging Face transformers library to load a generative artificial intelligence model, inputs a combined dataset, and generates suggestions such as "improve product quality" and "improve customer support."

[0070] Step 6: Identifying issues and generating improvement plans

[0071] The server extracts a list of organizational issues and improvement proposals from text generated by a generative artificial intelligence model.

[0072] Specific example: The server extracts "slow response time for customer support" from the generated text and proposes "implementation of a 24 / 7 chatbot" as an improvement plan.

[0073] Step 7: Report Generation

[0074] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0075] Specific example: The server uses a report template, summarizing issues and suggested improvements in separate sections, and adding charts and graphs as needed.

[0076] Step 8: Report Distribution

[0077] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0078] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0079] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables organizations to quickly and efficiently identify problems and implement concrete improvement measures.

[0080] (Example 1)

[0081] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0082] Traditional systems for improving organizational performance suffered from the time and effort required for cleaning, normalizing, and analyzing collected data using generative artificial intelligence. Furthermore, the lack of effective methods for integrating and analyzing user feedback data and performance indicator data made it difficult to quickly provide clear improvement suggestions. As a result, companies struggled to efficiently identify problems and implement concrete countermeasures.

[0083] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0084] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence. This makes it possible to quickly clean and normalize the collected feedback data and performance indicator data, and efficiently analyze them using a generative artificial intelligence model, thereby quickly generating clear issues and specific improvement proposals.

[0085] "Means of collecting data" refers to functions for obtaining user feedback data and organizational performance indicator data. Specifically, this includes retrieving information from databases and collecting data from online survey forms.

[0086] "Means for preprocessing collected data" refer to functions for cleaning and sentiment analysis of collected feedback data, as well as normalizing and scaling performance indicator data. Specifically, this includes spell checking of text data and handling of data outliers.

[0087] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that uses a generative artificial intelligence model to analyze pre-processed data and automatically generate organizational issues and specific improvement proposals. Specifically, it uses generative artificial intelligence such as GPT-3.5-turbo.

[0088] "A means of outputting generated issues and improvement proposals as a report" refers to a function that generates a report based on the generated issues and improvement proposals, and saves and distributes that report in PDF format or other formats.

[0089] "Feedback data" refers to data that includes suggestions for improvement and opinions regarding the organization, such as customer reviews, survey results, and employee feedback obtained from users.

[0090] "Performance metrics data" refers to data used to measure an organization's performance, and includes sales data, customer acquisition costs, and return rates.

[0091] "Preprocessing" refers to a series of processes performed to prepare collected data into an analyzable format, and includes text data cleaning, sentiment analysis, normalization, and scaling.

[0092] This invention is a system for improving the organizational performance of a company, which generates specific problems and improvement proposals through multiple processing steps and outputs them as a report. The specific processing of this system is executed by a server and uses the following hardware and software.

[0093] The server first collects user feedback data and organizational performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions, while performance metrics data includes sales data, customer acquisition costs, and return rates. This data is retrieved from the company's internal database system (e.g., MySQL® or PostgreSQL) and received via HTTP requests. Specifically, it uses SQL queries to retrieve data and collects feedback data from online forms.

[0094] Next, the server preprocesses the collected data. For cleaning feedback data, natural language processing libraries such as NLTK and SpaCy are used to perform spell checking and sentiment analysis on text data. For performance metric data, the Python pandas library is used to normalize the data, scale it, and handle outliers.

[0095] The pre-processed data is input into a generative artificial intelligence model (e.g., OpenAI®'s GPT-3.5-turbo). The server uses the OpenAI library to pass the data to the generative AI model and generates a problem and suggested improvements. An example of a prompt message would be: "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]".

[0096] The server extracts problems and suggested improvements generated from a generative artificial intelligence model and creates a concrete list. This process uses regular expressions and natural language processing techniques to extract problems and suggestions from the generated text.

[0097] Finally, the server generates a report based on the identified issues and suggested improvements. The report is generated in PDF format using the Python reportlab library and then sent to the company's management and relevant personnel using the smtplib library. The report contains a detailed list of the identified issues and suggested improvements, enabling the company to respond quickly and efficiently.

[0098] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0099] Step 1: Data Collection

[0100] The server first collects user feedback data and organizational performance indicator data. Inputs include performance indicator data such as sales data, customer acquisition costs, and return rates retrieved from the company's database system (e.g., MySQL or PostgreSQL), and feedback data such as customer reviews and employee opinions collected from online survey forms. Specifically, the server executes SQL queries to retrieve the necessary performance indicator data from the database and collects feedback data from online forms via HTTP requests. The server then collects this data and passes it on to the next preprocessing step.

[0101] Step 2: Data Preprocessing

[0102] The server preprocesses the collected data. The inputs are collected feedback data and performance metric data. Preprocessing includes cleaning the feedback data, sentiment analysis, and normalization, scaling, and outlier handling of the performance metric data. Specifically, the server uses natural language processing libraries such as NLTK and SpaCy to spell-check and clean the text data, and performs sentiment analysis. It also uses the pandas library to normalize and handle outliers in the performance metric data. This generates preprocessed data, which is then passed to the next step in the execution of the generative AI model.

[0103] Step 3: Execute the generative AI model

[0104] The server combines cleaned and normalized data and inputs it into a generative artificial intelligence model (e.g., GPT-3.5-turbo). The input consists of pre-processed feedback data and performance metric data. Specifically, the server uses the OpenAI library to pass the data to the generative AI model and inputs prompts to generate organizational issues and improvement suggestions. For example, the prompts could be set in the form of "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]", and the AI ​​model would perform the analysis based on these prompts. This would then output the generated organizational issues and improvement suggestions.

[0105] Step 4: Identifying problems and generating improvement plans

[0106] The server analyzes text generated by a generative artificial intelligence model and extracts problems and suggested improvements. The input is the generated text obtained from the generative AI model. Specifically, the server uses regular expressions and natural language processing techniques to extract problems and suggested improvements from the generated text. For example, it uses regular expressions to extract sentences containing "Problem:" or "Suggested Improvement:" and creates separate lists for each. This outputs the problems and suggested improvements as concrete lists.

[0107] Step 5: Report generation and feedback

[0108] Finally, the server generates a report based on the identified issues and improvement suggestions and sends it to the company's management and relevant personnel. The input is a list of the generated issues and improvement suggestions. Specifically, the server uses the Python reportlab library to generate the report in PDF format, and then uses the smtplib library to send the generated report via email. The report contains detailed information on the generated issues and improvement suggestions, allowing the company to take quick and efficient action based on it.

[0109] (Application Example 1)

[0110] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0111] Conventional autonomous vehicles lack the means to identify specific issues and propose improvements to enhance vehicle performance and user satisfaction. Therefore, there is a need for a new system that effectively utilizes various operational data and user feedback to improve vehicle performance and the user experience.

[0112] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0113] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting sensor data and user feedback from in-vehicle devices, means for analyzing the collected sensor data and performing sentiment analysis of user feedback, means for generating issues and improvement proposals related to vehicle performance using generative artificial intelligence, and means for outputting the generated issues and improvement proposals related to vehicle performance as a report. This makes it possible to improve the performance and user experience of autonomous vehicles.

[0114] "Means of collecting data" refers to functions that collect sensor data and user feedback through in-vehicle devices and user interfaces.

[0115] "Means for preprocessing collected data" refers to functions that clean, normalize, and analyze collected sensor data and feedback data.

[0116] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that utilizes generative artificial intelligence models to generate organizational and system issues and corresponding improvement proposals from pre-processed data.

[0117] "A means of outputting generated issues and improvement proposals as a report" refers to a function that creates generated issues and improvement proposals in report format and provides them to administrators and relevant parties.

[0118] "Means for collecting sensor data and user feedback from in-vehicle devices" refers to functions that collect operational data and user feedback through various sensors and user interfaces installed in the vehicle.

[0119] "Means for analyzing collected sensor data and performing sentiment analysis of user feedback" refers to a function that analyzes collected sensor data and then performs sentiment analysis on user feedback.

[0120] "Means for generating vehicle performance issues and improvement proposals using generative artificial intelligence" refers to a function that automatically generates specific vehicle performance issues and improvement methods from data collected and analyzed using a generative artificial intelligence model.

[0121] "A means of outputting a report of issues and improvement suggestions regarding the performance of generated vehicles" refers to a function that compiles the issues and improvement suggestions for generated vehicles in a report format and provides them to the administrator.

[0122] This invention is a system for improving the performance and user experience of autonomous vehicles. This system analyzes various data collected from the vehicle and user feedback, automatically generates problems and improvement proposals using generative artificial intelligence, and provides them as a report.

[0123] Hardware and software used

[0124] The server plays a central role in the system and performs processing using the following hardware and software:

[0125] Hardware:

[0126] Various sensors in automotive devices (camera, LiDAR, GPS)

[0127] A smartphone or in-car infotainment system with a user interface.

[0128] software:

[0129] Python script for data cleaning and normalization

[0130] OpenAI's GPT-3.5-turbo for running generative AI models

[0131] Report generation requires a Python report generation library (e.g., ReportLab).

[0132] Data Acquisition and Preprocessing

[0133] The server collects sensor data from in-vehicle devices and simultaneously collects user feedback. Sensor data includes camera images, LiDAR data, and GPS data. User feedback includes satisfaction with ride comfort, response speed, and route selection. The collected data is first cleaned to remove noise and formatted into an appropriate format. Next, the text data undergoes spell checking and sentiment analysis.

[0134] Execution of generative AI models and generation of problems and improvement proposals.

[0135] The collected and pre-processed data is input into a generative AI model (e.g., GPT-3.5-turbo) to generate specific issues and improvement suggestions regarding vehicle performance. Examples include "identifying areas with high fuel consumption during operation" and "suggesting route optimizations to improve fuel efficiency."

[0136] Report generation

[0137] The generated issues and improvement suggestions are compiled into a report by the server and provided to the administrator. The report is generated in PDF format and can be sent via email or viewed on the in-car infotainment system.

[0138] Specific example

[0139] Examples of prompts for a generative AI model include:

[0140] Based on vehicle data and user feedback from the past six months, generate performance issues and suggested improvements for the vehicle.

[0141] data:

[0142] Operational data: [GPS data, time-series data, fuel consumption data]

[0143] Feedback: [User reviews, survey results]

[0144] We expect this system to enable rapid and efficient improvements in the performance and user experience of autonomous vehicles.

[0145] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0146] Step 1:

[0147] The server collects sensor data and user feedback from in-vehicle devices. Specifically, it collects sensor data such as camera images, LiDAR data, and GPS data, as well as feedback information from users regarding ride comfort, response speed, and satisfaction with route selection. The input data consists of sensor data and feedback data, while the output is the raw collected data.

[0148] Step 2:

[0149] The server preprocesses the collected sensor data and feedback data. Specifically, it cleans the data, removes noise, and formats it into an appropriate format. Spell checking and sentiment analysis are also performed on the feedback data. The input is the raw collected data, and the output is the cleaned and normalized data.

[0150] Step 3:

[0151] The server inputs pre-processed data into a generative artificial intelligence model. Specifically, it uses cleaned sensor data and sentiment-analyzed feedback data to create AI-based problem identification and improvement suggestion generation prompts. The input is pre-processed data, and the output is the analysis result from the generative AI model.

[0152] Step 4:

[0153] The server uses a generative artificial intelligence model to generate specific problems and improvement proposals from the input data. Specifically, it uses a generative AI model (e.g., GPT-3.5-turbo) to automatically generate problems and improvement proposals such as "identifying areas with high fuel consumption during operation" and "proposing route optimizations to improve fuel efficiency." The input consists of prompts and preprocessed data for the AI ​​model, and the output is a list of problems and improvement proposals.

[0154] Step 5:

[0155] The server generates and outputs a report containing the generated issues and improvement proposals. Specifically, it organizes the generated issues and improvement proposals, compiles them into a report format (e.g., PDF), and provides it to vehicle managers and other relevant parties. A report generation library (e.g., ReportLab) is used for this purpose. The input is a list of issues and improvement proposals, and the output is a report in PDF format.

[0156] Step 6:

[0157] The server distributes the generated report through the appropriate channel. Specifically, it either sends the PDF report via email or uploads it to the in-vehicle infotainment system for viewing. The input is a report in PDF format, and the output is the sent report.

[0158] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0159] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0160] Program Processing Overview

[0161] Data collection

[0162] The server first collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0163] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: positive, negative, and neutral.

[0164] Data preprocessing

[0165] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data is spell-checked and sentiment analyzed. Sentiment data analyzed by the sentiment engine is also included in the preprocessed data. Performance metric data is normalized, and data scaling and outlier handling are performed.

[0166] Specific examples: The server corrects spelling mistakes in feedback and converts sales data into year-over-year percentage changes. The sentiment engine analysis results include data such as "This review is negative."

[0167] Execution of generative AI models

[0168] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational issues and proposed solutions from the input data. The model also considers emotional data obtained from the emotion engine to generate more specific and appropriate issues and solutions.

[0169] Specific example: The server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0170] Identifying problems and generating improvement plans

[0171] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0172] Specific example: The server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from generated text, and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media." Furthermore, it identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0173] Report generation and feedback

[0174] Finally, the server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0175] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. Sentiment data is visualized to display sentiment trends for specific issues.

[0176] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0177] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0178] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This can lead to a significant improvement in organizational performance. By adding an emotion engine, more accurate suggestions that take user emotions into account become possible.

[0179] The following describes the processing flow.

[0180] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0181] Program Processing Overview

[0182] Step 1: Data Collection

[0183] The server collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0184] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: "positive," "negative," and "neutral."

[0185] Step 2: Cleaning Feedback Data

[0186] The server cleans the collected feedback data. This cleaning process includes spell checking and grammatical correction of the text data. Furthermore, it uses a sentiment engine to analyze the sentiment of the feedback and adds the results to the data.

[0187] Specific example: The server uses natural language processing tools to correct spelling and grammatical errors in reviews, and analyzes and adds a sentiment score for each review.

[0188] Step 3: Normalize performance metrics data

[0189] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0190] Specific example: The server normalizes sales data by comparing it to the same month of the previous year, and detects and corrects abnormally high or low values.

[0191] Step 4: Combining the data

[0192] The server combines pre-processed feedback data with performance metrics data. It integrates feedback data, including data from the emotion engine, with performance metrics data to create an input dataset for the model.

[0193] Specific example: The server combines feedback data (with sentiment scores) and sales data to create a dataset in a format suitable for generative artificial intelligence models.

[0194] Step 5: Setting up and running the generative artificial intelligence model

[0195] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model generates organizational challenges and proposed solutions. The model also considers emotional data obtained from an emotion engine.

[0196] Specific example: A server uses a generative AI model as input to a combined dataset and generates suggestions to identify areas where "product quality dissatisfaction" or "improvements to customer support" are needed.

[0197] Step 6: Identifying issues and generating improvement plans

[0198] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0199] Specific example: The server identifies "slow customer support response speed" from generated text and proposes "implementing a new CRM system" as an improvement. Furthermore, it identifies "the biggest customer complaint" from sentiment data and proposes specific countermeasures.

[0200] Step 7: Report Generation

[0201] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0202] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, and adds graphs and charts. Sentiment data is visualized to display sentiment trends for specific issues.

[0203] Step 8: Report Distribution

[0204] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0205] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0206] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables companies to quickly and efficiently identify problems and implement concrete improvement measures. Adding an emotion engine allows for more accurate suggestions that take user emotions into account.

[0207] (Example 2)

[0208] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0209] Modern businesses struggle to efficiently collect and analyze customer feedback and performance data. Furthermore, it's difficult to identify organizational challenges from the collected data and automatically generate concrete improvement plans. Additionally, extracting insights that take user emotions into account and creating improvement plans based on these insights presents another challenge.

[0210] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0211] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for analyzing the emotions of feedback data using an emotion analysis engine, and means for adding emotional data to the feedback data during preprocessing. This enables companies to quickly and efficiently collect and preprocess data and automatically generate specific issues and improvement proposals that take emotional data into account.

[0212] "Means of data collection" refers to devices and methods for efficiently collecting user feedback data and corporate performance indicator data.

[0213] "Methods for preprocessing collected data" refer to techniques for preparing collected data into a format suitable for subsequent analysis or input to generative models, such as text cleaning, normalization, data scaling, and handling of outliers.

[0214] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a technology that utilizes generative artificial intelligence models (e.g., generative AI models) to automatically generate organizational issues and specific improvement proposals based on pre-processed data.

[0215] "Means for outputting generated issues and improvement proposals as a report" refers to devices or methods that summarize the issues and improvement proposals generated from a generative artificial intelligence model into a visually easy-to-understand report format and output it in PDF format or similar.

[0216] "Methods for analyzing the sentiment of feedback data using a sentiment analysis engine" refers to technologies that automatically recognize and classify the sentiment (positive, negative, neutral, etc.) of the text contained in feedback data.

[0217] "Means for adding emotional data to feedback data in preprocessing" refers to a technique that adds emotional data analyzed by an emotional analysis engine to the feedback text data and further includes it in the preprocessed data.

[0218] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion analysis engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0219] First, the server collects user feedback data and corporate performance metrics data. Users provide customer reviews, survey results, employee opinions, etc. The server collects this feedback data and also retrieves performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems. Furthermore, it analyzes the sentiment of the feedback data using a sentiment analysis engine (e.g., IBM Watson®, Google® Cloud Natural Language API).

[0220] For example, the server collects customer reviews and monthly sales data for the past six months and stores them in a database. Using a sentiment analysis engine, it classifies the sentiment of customer reviews into three categories: positive, negative, and neutral.

[0221] Next, the server preprocesses the collected data. It cleans the feedback data, performing spell checks on text data and removing unnecessary symbols. It also adds sentiment data to the feedback data. For performance metric data, it normalizes the data, scales it, and handles outliers.

[0222] For example, the server corrects spelling mistakes in feedback and converts sales data into year-on-year percentage changes. The sentiment analysis engine includes information such as "this review is negative" as a result of its analysis.

[0223] The server integrates pre-processed data and inputs it into a generative artificial intelligence model. This generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data. The model also considers sentiment data to provide more specific and appropriate challenges and solutions.

[0224] For example, the server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0225] The server extracts a list of organizational issues and improvement proposals from the generated text. It also extracts insights based on sentiment data and proposes specific countermeasures.

[0226] For example, the server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from the generated text and proposes improvement plans such as "implementing a new CRM system" and "designing marketing campaigns using social media." It identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0227] Finally, the server generates a report based on the identified issues and proposed improvements. The report is formatted for easy viewing and output in PDF format. The generated report is distributed and shared with the company's management and relevant personnel.

[0228] As a concrete example, the server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. It visualizes sentiment data and displays sentiment trends for specific issues. The server emails the generated PDF report to the responsible party and saves it to cloud storage, making it shareable across the entire organization.

[0229] This system enables companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take emotional data into account. By adding an emotional analysis engine, it becomes possible to analyze users' emotions in detail and make more accurate recommendations.

[0230] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0231] Step 1: Data Collection

[0232] The server collects feedback data from users. Specifically, users input customer reviews, survey results, employee opinions, etc., into forms on their terminals and send them to the server. The server stores this data in a database. The server also automatically collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems. In this collection process, APIs are used to retrieve the necessary data from databases and ERP systems.

[0233] Input: Customer reviews, survey results, sales data

[0234] Output: Raw data stored in the database

[0235] Step 2: Sentiment analysis of feedback data

[0236] The server performs sentiment analysis on the collected feedback data. Specifically, it uses a sentiment analysis engine to analyze each review and survey response, and assigns positive, negative, or neutral sentiment tags. The server adds the analysis results to the feedback data and stores the updated data back into the database.

[0237] Input: Feedback data

[0238] Output: Feedback data with emotion tags

[0239] Step 3: Data Preprocessing

[0240] The server preprocesses the collected and sentiment-analyzed data. Feedback data undergoes spell checking and removal of unnecessary symbols. Performance metric data is normalized, scaled, and outliers are handled. The preprocessed data is then stored back into the database.

[0241] Input: Collected and sentiment-analyzed data

[0242] Output: Preprocessed data

[0243] Step 4: Preparing input for the generative AI model

[0244] The server integrates pre-processed data and converts it into a format that can be input into a generative artificial intelligence model. In this process, user feedback, sentiment analysis data, and performance data are appropriately combined and prepared in a format that the generative AI model (e.g., GPT-3.5-turbo) can understand.

[0245] Input: Preprocessed data

[0246] Output: Input data for generative AI models

[0247] Step 5: Execute the generative AI model

[0248] The server inputs integrated data into a generative artificial intelligence model. Based on the input data, the generative AI model generates organizational challenges and proposed solutions. A specific prompt might be, "Based on feedback and sales data from the past six months, please propose organizational challenges and solutions." The generated results are returned to the server as a series of text data.

[0249] Input: "Based on feedback and sales data from the past six months, please propose organizational challenges and improvement plans."

[0250] Output: Text data including organizational challenges and proposed improvements.

[0251] Step 6: Identifying issues and improvement proposals

[0252] The server analyzes text data obtained from generative AI models to extract specific problems and proposed solutions. Insights based on sentiment data are also added during this process. The server organizes the problems and solutions and compiles them into data for reporting.

[0253] Input: Text data from a generative AI model

[0254] Output: Organized data on issues and proposed improvements

[0255] Step 7: Generate the report

[0256] The server generates a report based on the identified issues and improvement suggestions. The report is formatted for easy viewing and organized into sections. Charts and graphs are added as needed to visualize sentiment data. The final report is output in PDF format, saved to the database, and then sent to relevant parties.

[0257] Input: Organized problem and improvement proposal data

[0258] Output: Generated PDF report

[0259] This process allows companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take sentiment data into account.

[0260] (Application Example 2)

[0261] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0262] In modern factory operations, it is essential to effectively collect and analyze data on equipment operation, maintenance issues, and worker feedback, and to implement improvements quickly. However, there is no system in place to efficiently aggregate and analyze this data to generate specific problems and improvement plans. As a result, factory operational efficiency declines, and productivity improvements are hindered.

[0263] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for pre-processing the collected data, means for generating organizational issues and improvement proposals from the pre-processed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting equipment operation data, maintenance history, and worker feedback data from sensors in the factory, means for cleaning the collected data, performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model, and means for visualizing the generated issues and improvement proposals using charts and graphs, outputting a report in PDF format, and distributing it. This makes it possible to efficiently collect and analyze data within the factory and to quickly generate and share specific issues and improvement proposals.

[0264] "Means of collecting data" refers to devices and systems that acquire equipment operation data, maintenance history, employee opinions, etc., from sensors within the factory or feedback from users.

[0265] "Means for preprocessing collected data" refer to methods and systems for improving data quality and maintaining consistency by cleaning acquired data and performing sentiment analysis.

[0266] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to the application of a generative artificial intelligence model to identify and propose current problems and improvement measures for an organization based on pre-processed data.

[0267] "Means for outputting generated issues and improvement proposals as a report" refers to methods or systems for formatting the generated information in an easy-to-understand manner and creating and outputting a report in a format such as PDF.

[0268] "Means for collecting equipment operation data, maintenance history, and worker feedback data from sensors within the factory" refers to a data collection mechanism based on various sensors installed within the factory and input from employees.

[0269] "Means for performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model" refers to processing procedures and methods for normalizing collected data, applying sentiment analysis, and inputting it into a generative artificial intelligence model in a format useful for that model.

[0270] "A method for visualizing data using charts and graphs, outputting reports in PDF format, and distributing them" refers to a system or method for visually presenting generated data and proposals in an easy-to-understand format, organizing them into a report, and then distributing them to administrators and relevant parties.

[0271] This invention provides a system aimed at automating data collection, analysis, visualization, and feedback in factory operations. Here, we describe specific embodiments for effectively collecting data and automatically generating organizational challenges and improvement proposals using generative artificial intelligence.

[0272] First, the server uses sensors within the factory to collect data on equipment operation, maintenance history, and feedback from workers. This includes data from IoT devices and online feedback forms filled out by employees. Specifically, the server uses an IoT platform (e.g., AWS® IoT Core) to collect data and stores it in a database (e.g., Amazon RDS).

[0273] Next, the server preprocesses the collected data. Specifically, it cleans the data and uses an emotion analysis engine (e.g., Hugging Face's Transformers model) to emotionally classify employee feedback. It also normalizes performance metric data and converts it into a consistent data format. The preprocessed data is then manipulated using the Python Pandas library.

[0274] The server then inputs the pre-processed data into a generative artificial intelligence model (e.g., GPT-3.5-turbo) to generate organizational challenges and improvement proposals. The generated information includes specific suggestions for improving work efficiency and optimizing equipment maintenance. Data is input to the generative AI using prompts such as the following:

[0275] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[0276] The issues and improvement proposals generated by the generative artificial intelligence model are visualized by the server. Specifically, a PDF report containing charts and graphs is generated using Python's Matplotlib and ReportLab libraries. This allows stakeholders to understand the current state of the organization in a visually easy-to-understand way and take appropriate improvement measures.

[0277] Finally, the server distributes the generated reports to administrators and relevant parties. This is done by sending the reports via email using a mail server (e.g., SendGrid) or by uploading them to a cloud storage service (e.g., Google Drive).

[0278] As described above, the system of the present invention automates a series of processes from data collection to analysis, report generation, and feedback, thereby improving the efficiency and performance of factory operations.

[0279] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0280] Step 1: Data Collection

[0281] The server collects data using various sensors placed throughout the factory and online feedback forms from employees. Inputs include equipment operation data, maintenance history, and worker feedback data, which are acquired through the IoT platform and stored in a database. Specifically, AWS IoT Core is used to collect various data and store it in Amazon RDS.

[0282] Step 2: Data Preprocessing

[0283] The server cleans the collected data and performs sentiment analysis. The input includes the data collected in the previous step. For data cleaning, the Pandas library in Python is used to correct incomplete data and spelling mistakes. For sentiment analysis, the Transformers model from Hugging Face is used to classify employees' feedback as "positive", "negative", or "neutral" sentimentally. Additionally, the performance indicator data is normalized and converted into a consistent data format.

[0284] Step 3: Data Integration and Input to the Generative AI Model

[0285] The server integrates the preprocessed data and inputs it into the generative AI model. Specifically, the Pandas library in Python is used to combine the preprocessed data as a data frame and input it into the generative AI model (GPT-3.5-turbo). Here, data input is performed using a prompt text. Examples of prompt texts are as follows:

[0286] "Based on the equipment operation data and operator feedback data for the past six months, please extract the problems in the factory and their improvement plans. Also, consider the analysis results of the sentiment engine and include specific proposals. The problems may include frequent overheating issues and excessive stress among workers. As solutions, please propose the introduction of a cooling system and improvement measures for the working environment."

[0287] Step 4: Generation of Problems and Improvement Plans

[0288] The server analyzes the output obtained from the generative AI model to identify the organization's problems and improvement plans. The input includes the text data obtained from the generative AI model in the previous step. The output includes a specific list of problems and improvement plans for them. For example, "equipment overheating" and "worker stress" are extracted as problems, and "introduction of a cooling system" and "improvement of the working environment" are generated as improvement plans.

[0289] Step 5: Report Generation

[0290] The server generates a report based on the generated issues and improvement suggestions. The input includes the list of issues and improvement suggestions obtained in the previous step. Using the Matplotlib and ReportLab libraries in Python, the issues and improvement suggestions are visualized using charts and graphs, and output as a report in PDF format.

[0291] Step 6: Report Distribution

[0292] The server distributes the generated report to the relevant parties. The input includes the generated PDF report. The report can be distributed via email using a mail server (e.g., SendGrid) or uploaded to a cloud storage service (e.g., Google Drive).

[0293] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0294] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0295] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0296] [Second Embodiment]

[0297] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0298] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0299] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0300] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0301] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0302] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0303] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0304] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0305] The specific processing program 56 is an example of the "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 operating as a specific processing unit 290 according to the specific processing program 56 executed by the processor 28 on the RAM 30.

[0306] 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 specific processing unit 290.

[0307] In the smart glasses 214, the processor 46 performs reception and output processing. The storage 50 stores a reception and output program 60. The processor 46 reads the reception and output program 60 from the storage 50 and executes the read reception and output program 60 on the RAM 48. The reception and output processing is realized by operating as a control unit 46A according to the reception and output program 60 executed by the processor 46 on the RAM 48.

[0308] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0309] The present invention is a system for improving the organizational performance of an enterprise, which preprocesses the collected data, automatically generates problems and improvement plans using generative artificial intelligence, and outputs them as a report. The specific processing of this system is executed by the server.

[0310] Processing Outline of the Program

[0311] Data Collection

[0312] The server first collects user feedback data and company performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions. Performance metrics data includes sales data, customer acquisition costs, and return rates.

[0313] Specific example: The server collects customer reviews and monthly sales data for the past six months.

[0314] Data preprocessing

[0315] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data undergoes spell checking and sentiment analysis. Performance metric data is normalized, scaled, and outliers are handled.

[0316] Specific example: The server corrects spelling mistakes in feedback and converts sales data into a year-on-year percentage change.

[0317] Execution of generative AI models

[0318] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data.

[0319] Specific example: The server inputs user feedback and sales data into a generative AI model, which then generates specific suggestions such as "improve customer support response speed."

[0320] Identifying problems and generating improvement plans

[0321] The server extracts issues and improvement suggestions generated from generative artificial intelligence models and creates a detailed list. This clarifies the organization's current problems and proposes specific solutions for each problem.

[0322] Specific example: The server identifies problems such as "customer support response speed" and "new product marketing strategy," and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media."

[0323] Report generation and feedback

[0324] Finally, the server generates a report based on the identified issues and proposed improvements. The report is generated in PDF format and sent to the company's management and relevant personnel.

[0325] Specific example: Create a report generated by the server in PDF format and send it to management via email.

[0326] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This, in turn, can lead to a significant improvement in organizational performance.

[0327] The following describes the processing flow.

[0328] Step 1: Data Collection

[0329] The server collects user feedback data and corporate performance indicator data. It gathers customer reviews, survey results, and employee opinions provided by users. It also collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0330] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this data in a database.

[0331] Step 2: Cleaning Feedback Data

[0332] The server cleans the collected feedback data. This cleaning process includes spell checking and sentiment analysis of the text data.

[0333] Specific example: The server uses a natural language processing tool to correct spelling errors in customer reviews and categorize the sentiment of the reviews into three groups: positive, negative, and neutral.

[0334] Step 3: Normalize performance metrics data

[0335] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0336] Specific example: The server converts sales data into a year-on-year percentage change and detects and corrects abnormally high or low values.

[0337] Step 4: Combining the data

[0338] The server combines pre-processed feedback data and performance metric data. This forms the input dataset for the model.

[0339] Specific example: The server creates a data frame containing feedback data and sales data, and converts it into a format that can be input into a generative artificial intelligence model.

[0340] Step 5: Setting up and running the generative artificial intelligence model

[0341] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model then generates organizational challenges and proposed improvements.

[0342] Specific example: The server uses the Hugging Face transformers library to load a generative artificial intelligence model, inputs a combined dataset, and generates suggestions such as "improve product quality" and "improve customer support."

[0343] Step 6: Identifying issues and generating improvement plans

[0344] The server extracts a list of organizational issues and improvement proposals from text generated by a generative artificial intelligence model.

[0345] Specific example: The server extracts "slow response time for customer support" from the generated text and proposes "implementation of a 24 / 7 chatbot" as an improvement plan.

[0346] Step 7: Report Generation

[0347] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0348] Specific example: The server uses a report template, summarizing issues and suggested improvements in separate sections, and adding charts and graphs as needed.

[0349] Step 8: Report Distribution

[0350] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0351] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0352] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables organizations to quickly and efficiently identify problems and implement concrete improvement measures.

[0353] (Example 1)

[0354] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0355] Traditional systems for improving organizational performance suffered from the time and effort required for cleaning, normalizing, and analyzing collected data using generative artificial intelligence. Furthermore, the lack of effective methods for integrating and analyzing user feedback data and performance indicator data made it difficult to quickly provide clear improvement suggestions. As a result, companies struggled to efficiently identify problems and implement concrete countermeasures.

[0356] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0357] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence. This makes it possible to quickly clean and normalize the collected feedback data and performance indicator data, and efficiently analyze them using a generative artificial intelligence model, thereby quickly generating clear issues and specific improvement proposals.

[0358] "Means of collecting data" refers to functions for obtaining user feedback data and organizational performance indicator data. Specifically, this includes retrieving information from databases and collecting data from online survey forms.

[0359] "Means for preprocessing collected data" refer to functions for cleaning and sentiment analysis of collected feedback data, as well as normalizing and scaling performance indicator data. Specifically, this includes spell checking of text data and handling of data outliers.

[0360] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that uses a generative artificial intelligence model to analyze pre-processed data and automatically generate organizational issues and specific improvement proposals. Specifically, it uses generative artificial intelligence such as GPT-3.5-turbo.

[0361] "A means of outputting generated issues and improvement proposals as a report" refers to a function that generates a report based on the generated issues and improvement proposals, and saves and distributes that report in PDF format or other formats.

[0362] "Feedback data" refers to data that includes suggestions for improvement and opinions regarding the organization, such as customer reviews, survey results, and employee feedback obtained from users.

[0363] "Performance metrics data" refers to data used to measure an organization's performance, and includes sales data, customer acquisition costs, and return rates.

[0364] "Preprocessing" refers to a series of processes performed to prepare collected data into an analyzable format, and includes text data cleaning, sentiment analysis, normalization, and scaling.

[0365] This invention is a system for improving the organizational performance of a company, which generates specific problems and improvement proposals through multiple processing steps and outputs them as a report. The specific processing of this system is executed by a server and uses the following hardware and software.

[0366] The server first collects user feedback data and organizational performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions, while performance metrics data includes sales data, customer acquisition costs, and return rates. This data is retrieved from the company's internal database system (e.g., MySQL or PostgreSQL) and received via HTTP requests. Specifically, it uses SQL queries to retrieve data and collects feedback data from online forms.

[0367] Next, the server preprocesses the collected data. For cleaning feedback data, natural language processing libraries such as NLTK and SpaCy are used to perform spell checking and sentiment analysis on text data. For performance metric data, the Python pandas library is used to normalize the data, scale it, and handle outliers.

[0368] The pre-processed data is input into a generative artificial intelligence model (e.g., OpenAI's GPT-3.5-turbo). The server uses the OpenAI library to pass the data to the generative AI model and generates the problem and suggested improvements. An example of a prompt message would be: "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]".

[0369] The server extracts problems and suggested improvements generated from a generative artificial intelligence model and creates a concrete list. This process uses regular expressions and natural language processing techniques to extract problems and suggestions from the generated text.

[0370] Finally, the server generates a report based on the identified issues and suggested improvements. The report is generated in PDF format using the Python reportlab library and then sent to the company's management and relevant personnel using the smtplib library. The report contains a detailed list of the identified issues and suggested improvements, enabling the company to respond quickly and efficiently.

[0371] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0372] Step 1: Data Collection

[0373] The server first collects user feedback data and organizational performance indicator data. Inputs include performance indicator data such as sales data, customer acquisition costs, and return rates retrieved from the company's database system (e.g., MySQL or PostgreSQL), and feedback data such as customer reviews and employee opinions collected from online survey forms. Specifically, the server executes SQL queries to retrieve the necessary performance indicator data from the database and collects feedback data from online forms via HTTP requests. The server then collects this data and passes it on to the next preprocessing step.

[0374] Step 2: Data Preprocessing

[0375] The server preprocesses the collected data. The inputs are collected feedback data and performance metric data. Preprocessing includes cleaning the feedback data, sentiment analysis, and normalization, scaling, and outlier handling of the performance metric data. Specifically, the server uses natural language processing libraries such as NLTK and SpaCy to spell-check and clean the text data, and performs sentiment analysis. It also uses the pandas library to normalize and handle outliers in the performance metric data. This generates preprocessed data, which is then passed to the next step in the execution of the generative AI model.

[0376] Step 3: Execute the generative AI model

[0377] The server combines cleaned and normalized data and inputs it into a generative artificial intelligence model (e.g., GPT-3.5-turbo). The input consists of pre-processed feedback data and performance metric data. Specifically, the server uses the OpenAI library to pass the data to the generative AI model and inputs prompts to generate organizational issues and improvement suggestions. For example, the prompts could be set in the form of "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]", and the AI ​​model would perform the analysis based on these prompts. This would then output the generated organizational issues and improvement suggestions.

[0378] Step 4: Identifying problems and generating improvement plans

[0379] The server analyzes text generated by a generative artificial intelligence model and extracts problems and suggested improvements. The input is the generated text obtained from the generative AI model. Specifically, the server uses regular expressions and natural language processing techniques to extract problems and suggested improvements from the generated text. For example, it uses regular expressions to extract sentences containing "Problem:" or "Suggested Improvement:" and creates separate lists for each. This outputs the problems and suggested improvements as concrete lists.

[0380] Step 5: Report generation and feedback

[0381] Finally, the server generates a report based on the identified issues and improvement suggestions and sends it to the company's management and relevant personnel. The input is a list of the generated issues and improvement suggestions. Specifically, the server uses the Python reportlab library to generate the report in PDF format, and then uses the smtplib library to send the generated report via email. The report contains detailed information on the generated issues and improvement suggestions, allowing the company to take quick and efficient action based on it.

[0382] (Application Example 1)

[0383] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0384] Conventional autonomous vehicles lack the means to identify specific issues and propose improvements to enhance vehicle performance and user satisfaction. Therefore, there is a need for a new system that effectively utilizes various operational data and user feedback to improve vehicle performance and the user experience.

[0385] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0386] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting sensor data and user feedback from in-vehicle devices, means for analyzing the collected sensor data and performing sentiment analysis of user feedback, means for generating issues and improvement proposals related to vehicle performance using generative artificial intelligence, and means for outputting the generated issues and improvement proposals related to vehicle performance as a report. This makes it possible to improve the performance and user experience of autonomous vehicles.

[0387] "Means of collecting data" refers to functions that collect sensor data and user feedback through in-vehicle devices and user interfaces.

[0388] "Means for preprocessing collected data" refers to functions that clean, normalize, and analyze collected sensor data and feedback data.

[0389] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that utilizes generative artificial intelligence models to generate organizational and system issues and corresponding improvement proposals from pre-processed data.

[0390] "A means of outputting generated issues and improvement proposals as a report" refers to a function that creates generated issues and improvement proposals in report format and provides them to administrators and relevant parties.

[0391] "Means for collecting sensor data and user feedback from in-vehicle devices" refers to functions that collect operational data and user feedback through various sensors and user interfaces installed in the vehicle.

[0392] "Means for analyzing collected sensor data and performing sentiment analysis of user feedback" refers to a function that analyzes collected sensor data and then performs sentiment analysis on user feedback.

[0393] "Means for generating vehicle performance issues and improvement proposals using generative artificial intelligence" refers to a function that automatically generates specific vehicle performance issues and improvement methods from data collected and analyzed using a generative artificial intelligence model.

[0394] "A means of outputting a report of issues and improvement suggestions regarding the performance of generated vehicles" refers to a function that compiles the issues and improvement suggestions for generated vehicles in a report format and provides them to the administrator.

[0395] This invention is a system for improving the performance and user experience of autonomous vehicles. This system analyzes various data collected from the vehicle and user feedback, automatically generates problems and improvement proposals using generative artificial intelligence, and provides them as a report.

[0396] Hardware and software used

[0397] The server plays a central role in the system and performs processing using the following hardware and software:

[0398] Hardware:

[0399] Various sensors in automotive devices (camera, LiDAR, GPS)

[0400] A smartphone or in-car infotainment system with a user interface.

[0401] software:

[0402] Python script for data cleaning and normalization

[0403] OpenAI's GPT-3.5-turbo for running generative AI models

[0404] Report generation requires a Python report generation library (e.g., ReportLab).

[0405] Data Acquisition and Preprocessing

[0406] The server collects sensor data from in-vehicle devices and simultaneously collects user feedback. Sensor data includes camera images, LiDAR data, and GPS data. User feedback includes satisfaction with ride comfort, response speed, and route selection. The collected data is first cleaned to remove noise and formatted into an appropriate format. Next, the text data undergoes spell checking and sentiment analysis.

[0407] Execution of generative AI models and generation of problems and improvement proposals.

[0408] The collected and pre-processed data is input into a generative AI model (e.g., GPT-3.5-turbo) to generate specific issues and improvement suggestions regarding vehicle performance. Examples include "identifying areas with high fuel consumption during operation" and "suggesting route optimizations to improve fuel efficiency."

[0409] Report generation

[0410] The generated issues and improvement suggestions are compiled into a report by the server and provided to the administrator. The report is generated in PDF format and can be sent via email or viewed on the in-car infotainment system.

[0411] Specific example

[0412] Examples of prompts for a generative AI model include:

[0413] Based on vehicle data and user feedback from the past six months, generate performance issues and suggested improvements for the vehicle.

[0414] data:

[0415] Operational data: [GPS data, time-series data, fuel consumption data]

[0416] Feedback: [User reviews, survey results]

[0417] We expect this system to enable rapid and efficient improvements in the performance and user experience of autonomous vehicles.

[0418] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0419] Step 1:

[0420] The server collects sensor data and user feedback from in-vehicle devices. Specifically, it collects sensor data such as camera images, LiDAR data, and GPS data, as well as feedback information from users regarding ride comfort, response speed, and satisfaction with route selection. The input data consists of sensor data and feedback data, while the output is the raw collected data.

[0421] Step 2:

[0422] The server preprocesses the collected sensor data and feedback data. Specifically, it cleans the data, removes noise, and formats it into an appropriate format. Spell checking and sentiment analysis are also performed on the feedback data. The input is the raw collected data, and the output is the cleaned and normalized data.

[0423] Step 3:

[0424] The server inputs pre-processed data into a generative artificial intelligence model. Specifically, it uses cleaned sensor data and sentiment-analyzed feedback data to create AI-based problem identification and improvement suggestion generation prompts. The input is pre-processed data, and the output is the analysis result from the generative AI model.

[0425] Step 4:

[0426] The server uses a generative artificial intelligence model to generate specific problems and improvement proposals from the input data. Specifically, it uses a generative AI model (e.g., GPT-3.5-turbo) to automatically generate problems and improvement proposals such as "identifying areas with high fuel consumption during operation" and "proposing route optimizations to improve fuel efficiency." The input consists of prompts and preprocessed data for the AI ​​model, and the output is a list of problems and improvement proposals.

[0427] Step 5:

[0428] The server generates and outputs a report containing the generated issues and improvement proposals. Specifically, it organizes the generated issues and improvement proposals, compiles them into a report format (e.g., PDF), and provides it to vehicle managers and other relevant parties. A report generation library (e.g., ReportLab) is used for this purpose. The input is a list of issues and improvement proposals, and the output is a report in PDF format.

[0429] Step 6:

[0430] The server distributes the generated report through the appropriate channel. Specifically, it either sends the PDF report via email or uploads it to the in-vehicle infotainment system for viewing. The input is a report in PDF format, and the output is the sent report.

[0431] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0432] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0433] Program Processing Overview

[0434] Data collection

[0435] The server first collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0436] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: positive, negative, and neutral.

[0437] Data preprocessing

[0438] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data is spell-checked and sentiment analyzed. Sentiment data analyzed by the sentiment engine is also included in the preprocessed data. Performance metric data is normalized, and data scaling and outlier handling are performed.

[0439] Specific examples: The server corrects spelling mistakes in feedback and converts sales data into year-over-year percentage changes. The sentiment engine analysis results include data such as "This review is negative."

[0440] Execution of generative AI models

[0441] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational issues and proposed solutions from the input data. The model also considers emotional data obtained from the emotion engine to generate more specific and appropriate issues and solutions.

[0442] Specific example: The server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0443] Identifying problems and generating improvement plans

[0444] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0445] Specific example: The server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from generated text, and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media." Furthermore, it identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0446] Report generation and feedback

[0447] Finally, the server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0448] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. Sentiment data is visualized to display sentiment trends for specific issues.

[0449] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0450] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0451] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This can lead to a significant improvement in organizational performance. By adding an emotion engine, more accurate suggestions that take user emotions into account become possible.

[0452] The following describes the processing flow.

[0453] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0454] Program Processing Overview

[0455] Step 1: Data Collection

[0456] The server collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0457] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: "positive," "negative," and "neutral."

[0458] Step 2: Cleaning Feedback Data

[0459] The server cleans the collected feedback data. This cleaning process includes spell checking and grammatical correction of the text data. Furthermore, it uses a sentiment engine to analyze the sentiment of the feedback and adds the results to the data.

[0460] Specific example: The server uses natural language processing tools to correct spelling and grammatical errors in reviews, and analyzes and adds a sentiment score for each review.

[0461] Step 3: Normalize performance metrics data

[0462] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0463] Specific example: The server normalizes sales data by comparing it to the same month of the previous year, and detects and corrects abnormally high or low values.

[0464] Step 4: Combining the data

[0465] The server combines pre-processed feedback data with performance metrics data. It integrates feedback data, including data from the emotion engine, with performance metrics data to create an input dataset for the model.

[0466] Specific example: The server combines feedback data (with sentiment scores) and sales data to create a dataset in a format suitable for generative artificial intelligence models.

[0467] Step 5: Setting up and running the generative artificial intelligence model

[0468] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model generates organizational challenges and proposed solutions. The model also considers emotional data obtained from an emotion engine.

[0469] Specific example: A server uses a generative AI model as input to a combined dataset and generates suggestions to identify areas where "product quality dissatisfaction" or "improvements to customer support" are needed.

[0470] Step 6: Identifying issues and generating improvement plans

[0471] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0472] Specific example: The server identifies "slow customer support response speed" from generated text and proposes "implementing a new CRM system" as an improvement. Furthermore, it identifies "the biggest customer complaint" from sentiment data and proposes specific countermeasures.

[0473] Step 7: Report Generation

[0474] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0475] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, and adds graphs and charts. Sentiment data is visualized to display sentiment trends for specific issues.

[0476] Step 8: Report Distribution

[0477] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0478] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0479] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables companies to quickly and efficiently identify problems and implement concrete improvement measures. Adding an emotion engine allows for more accurate suggestions that take user emotions into account.

[0480] (Example 2)

[0481] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0482] Modern businesses struggle to efficiently collect and analyze customer feedback and performance data. Furthermore, it's difficult to identify organizational challenges from the collected data and automatically generate concrete improvement plans. Additionally, extracting insights that take user emotions into account and creating improvement plans based on these insights presents another challenge.

[0483] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0484] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for analyzing the emotions of feedback data using an emotion analysis engine, and means for adding emotional data to the feedback data during preprocessing. This enables companies to quickly and efficiently collect and preprocess data and automatically generate specific issues and improvement proposals that take emotional data into account.

[0485] "Means of data collection" refers to devices and methods for efficiently collecting user feedback data and corporate performance indicator data.

[0486] "Methods for preprocessing collected data" refer to techniques for preparing collected data into a format suitable for subsequent analysis or input to generative models, such as text cleaning, normalization, data scaling, and handling of outliers.

[0487] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a technology that utilizes generative artificial intelligence models (e.g., generative AI models) to automatically generate organizational issues and specific improvement proposals based on pre-processed data.

[0488] "Means for outputting generated issues and improvement proposals as a report" refers to devices or methods that summarize the issues and improvement proposals generated from a generative artificial intelligence model into a visually easy-to-understand report format and output it in PDF format or similar.

[0489] "Methods for analyzing the sentiment of feedback data using a sentiment analysis engine" refers to technologies that automatically recognize and classify the sentiment (positive, negative, neutral, etc.) of the text contained in feedback data.

[0490] "Means for adding emotional data to feedback data in preprocessing" refers to a technique that adds emotional data analyzed by an emotional analysis engine to the feedback text data and further includes it in the preprocessed data.

[0491] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion analysis engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0492] First, the server collects user feedback data and company performance metrics data. Users provide customer reviews, survey results, employee opinions, etc. The server collects this feedback data and also retrieves performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems. Furthermore, it analyzes the sentiment of the feedback data using a sentiment analysis engine (e.g., IBM Watson, Google Cloud Natural Language API).

[0493] For example, the server collects customer reviews and monthly sales data for the past six months and stores them in a database. Using a sentiment analysis engine, it classifies the sentiment of customer reviews into three categories: positive, negative, and neutral.

[0494] Next, the server preprocesses the collected data. It cleans the feedback data, performing spell checks on text data and removing unnecessary symbols. It also adds sentiment data to the feedback data. For performance metric data, it normalizes the data, scales it, and handles outliers.

[0495] For example, the server corrects spelling mistakes in feedback and converts sales data into year-on-year percentage changes. The sentiment analysis engine includes information such as "this review is negative" as a result of its analysis.

[0496] The server integrates pre-processed data and inputs it into a generative artificial intelligence model. This generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data. The model also considers sentiment data to provide more specific and appropriate challenges and solutions.

[0497] For example, the server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0498] The server extracts a list of organizational issues and improvement proposals from the generated text. It also extracts insights based on sentiment data and proposes specific countermeasures.

[0499] For example, the server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from the generated text and proposes improvement plans such as "implementing a new CRM system" and "designing marketing campaigns using social media." It identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0500] Finally, the server generates a report based on the identified issues and proposed improvements. The report is formatted for easy viewing and output in PDF format. The generated report is distributed and shared with the company's management and relevant personnel.

[0501] As a concrete example, the server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. It visualizes sentiment data and displays sentiment trends for specific issues. The server emails the generated PDF report to the responsible party and saves it to cloud storage, making it shareable across the entire organization.

[0502] This system enables companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take emotional data into account. By adding an emotional analysis engine, it becomes possible to analyze users' emotions in detail and make more accurate recommendations.

[0503] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0504] Step 1: Data Collection

[0505] The server collects feedback data from users. Specifically, users input customer reviews, survey results, employee opinions, etc., into forms on their terminals and send them to the server. The server stores this data in a database. The server also automatically collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems. In this collection process, APIs are used to retrieve the necessary data from databases and ERP systems.

[0506] Input: Customer reviews, survey results, sales data

[0507] Output: Raw data stored in the database

[0508] Step 2: Sentiment analysis of feedback data

[0509] The server performs sentiment analysis on the collected feedback data. Specifically, it uses a sentiment analysis engine to analyze each review and survey response, and assigns positive, negative, or neutral sentiment tags. The server adds the analysis results to the feedback data and stores the updated data back into the database.

[0510] Input: Feedback data

[0511] Output: Feedback data with emotion tags

[0512] Step 3: Data Preprocessing

[0513] The server preprocesses the collected and sentiment-analyzed data. Feedback data undergoes spell checking and removal of unnecessary symbols. Performance metric data is normalized, scaled, and outliers are handled. The preprocessed data is then stored back into the database.

[0514] Input: Collected and sentiment-analyzed data

[0515] Output: Preprocessed data

[0516] Step 4: Preparing input for the generative AI model

[0517] The server integrates pre-processed data and converts it into a format that can be input into a generative artificial intelligence model. In this process, user feedback, sentiment analysis data, and performance data are appropriately combined and prepared in a format that the generative AI model (e.g., GPT-3.5-turbo) can understand.

[0518] Input: Preprocessed data

[0519] Output: Input data for generative AI models

[0520] Step 5: Execute the generative AI model

[0521] The server inputs integrated data into a generative artificial intelligence model. Based on the input data, the generative AI model generates organizational challenges and proposed solutions. A specific prompt might be, "Based on feedback and sales data from the past six months, please propose organizational challenges and solutions." The generated results are returned to the server as a series of text data.

[0522] Input: "Based on feedback and sales data from the past six months, please propose organizational challenges and improvement plans."

[0523] Output: Text data including organizational challenges and proposed improvements.

[0524] Step 6: Identifying issues and improvement proposals

[0525] The server analyzes text data obtained from generative AI models to extract specific problems and proposed solutions. Insights based on sentiment data are also added during this process. The server organizes the problems and solutions and compiles them into data for reporting.

[0526] Input: Text data from a generative AI model

[0527] Output: Organized data on issues and proposed improvements

[0528] Step 7: Generate the report

[0529] The server generates a report based on the identified issues and improvement suggestions. The report is formatted for easy viewing and organized into sections. Charts and graphs are added as needed to visualize sentiment data. The final report is output in PDF format, saved to the database, and then sent to relevant parties.

[0530] Input: Organized problem and improvement proposal data

[0531] Output: Generated PDF report

[0532] This process allows companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take sentiment data into account.

[0533] (Application Example 2)

[0534] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0535] In modern factory operations, it is essential to effectively collect and analyze data on equipment operation, maintenance issues, and worker feedback, and to implement improvements quickly. However, there is no system in place to efficiently aggregate and analyze this data to generate specific problems and improvement plans. As a result, factory operational efficiency declines, and productivity improvements are hindered.

[0536] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for pre-processing the collected data, means for generating organizational issues and improvement proposals from the pre-processed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting equipment operation data, maintenance history, and worker feedback data from sensors in the factory, means for cleaning the collected data, performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model, and means for visualizing the generated issues and improvement proposals using charts and graphs, outputting a report in PDF format, and distributing it. This makes it possible to efficiently collect and analyze data within the factory and to quickly generate and share specific issues and improvement proposals.

[0537] "Means of collecting data" refers to devices and systems that acquire equipment operation data, maintenance history, employee opinions, etc., from sensors within the factory or feedback from users.

[0538] "Means for preprocessing collected data" refer to methods and systems for improving data quality and maintaining consistency by cleaning acquired data and performing sentiment analysis.

[0539] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to the application of a generative artificial intelligence model to identify and propose current problems and improvement measures for an organization based on pre-processed data.

[0540] "Means for outputting generated issues and improvement proposals as a report" refers to methods or systems for formatting the generated information in an easy-to-understand manner and creating and outputting a report in a format such as PDF.

[0541] "Means for collecting equipment operation data, maintenance history, and worker feedback data from sensors within the factory" refers to a data collection mechanism based on various sensors installed within the factory and input from employees.

[0542] "Means for performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model" refers to processing procedures and methods for normalizing collected data, applying sentiment analysis, and inputting it into a generative artificial intelligence model in a format useful for that model.

[0543] "A method for visualizing data using charts and graphs, outputting reports in PDF format, and distributing them" refers to a system or method for visually presenting generated data and proposals in an easy-to-understand format, organizing them into a report, and then distributing them to administrators and relevant parties.

[0544] This invention provides a system aimed at automating data collection, analysis, visualization, and feedback in factory operations. Here, we describe specific embodiments for effectively collecting data and automatically generating organizational challenges and improvement proposals using generative artificial intelligence.

[0545] First, the server uses sensors within the factory to collect data on equipment operation, maintenance history, and feedback from workers. This includes data from IoT devices and online feedback forms filled out by employees. Specifically, the server uses an IoT platform (e.g., AWS IoT Core) to collect data and stores it in a database (e.g., Amazon RDS).

[0546] Next, the server preprocesses the collected data. Specifically, it cleans the data and uses an emotion analysis engine (e.g., Hugging Face's Transformers model) to emotionally classify employee feedback. It also normalizes performance metric data and converts it into a consistent data format. The preprocessed data is then manipulated using the Python Pandas library.

[0547] The server then inputs the pre-processed data into a generative artificial intelligence model (e.g., GPT-3.5-turbo) to generate organizational challenges and improvement proposals. The generated information includes specific suggestions for improving work efficiency and optimizing equipment maintenance. Data is input to the generative AI using prompts such as the following:

[0548] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[0549] The issues and improvement proposals generated by the generative artificial intelligence model are visualized by the server. Specifically, a PDF report containing charts and graphs is generated using Python's Matplotlib and ReportLab libraries. This allows stakeholders to understand the current state of the organization in a visually easy-to-understand way and take appropriate improvement measures.

[0550] Finally, the server distributes the generated reports to administrators and relevant parties. This is done by sending the reports via email using a mail server (e.g., SendGrid) or by uploading them to a cloud storage service (e.g., Google Drive).

[0551] As described above, the system of the present invention automates a series of processes from data collection to analysis, report generation, and feedback, thereby improving the efficiency and performance of factory operations.

[0552] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0553] Step 1: Data Collection

[0554] The server collects data using various sensors placed throughout the factory and online feedback forms from employees. Inputs include equipment operation data, maintenance history, and worker feedback data, which are acquired through the IoT platform and stored in a database. Specifically, AWS IoT Core is used to collect various data and store it in Amazon RDS.

[0555] Step 2: Data Preprocessing

[0556] The server cleans the collected data and performs sentiment analysis. The input includes the data collected in the previous step. Data cleaning uses the Python Pandas library to correct incomplete data and spelling errors. Sentiment analysis uses the Hugging Face Transformers model to classify employee feedback emotionally as "positive," "negative," or "neutral." Furthermore, performance metric data is normalized and converted into a consistent data format.

[0557] Step 3: Data integration and input into generative artificial intelligence models

[0558] The server integrates the preprocessed data and inputs it into a generative artificial intelligence model. Specifically, it uses the Python Pandas library to combine the preprocessed data into a dataframe and inputs it into the generative artificial intelligence model (GPT-3.5-turbo). Here, data input is performed using prompt statements. An example of a prompt statement is as follows:

[0559] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[0560] Step 4: Generating problems and improvement plans

[0561] The server analyzes the output obtained by the generative artificial intelligence model to identify organizational challenges and improvement suggestions. The input includes text data obtained from the generative artificial intelligence model in the previous step. The output includes a list of specific challenges and corresponding improvement suggestions. For example, "equipment overheating" and "worker stress" might be extracted as challenges, while "implementation of a cooling system" and "improvement of the work environment" might be generated as improvement suggestions.

[0562] Step 5: Report Generation

[0563] The server generates a report based on the generated issues and improvement suggestions. The input includes the list of issues and improvement suggestions obtained in the previous step. Using the Matplotlib and ReportLab libraries in Python, the issues and improvement suggestions are visualized using charts and graphs, and output as a report in PDF format.

[0564] Step 6: Report Distribution

[0565] The server distributes the generated report to the relevant parties. The input includes the generated PDF report. The report can be distributed via email using a mail server (e.g., SendGrid) or uploaded to a cloud storage service (e.g., Google Drive).

[0566] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0567] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0568] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0569] [Third Embodiment]

[0570] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0571] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0572] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0573] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0574] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0575] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0576] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0577] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0578] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0579] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0580] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0581] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0582] This invention is a system for improving the organizational performance of companies. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence, and outputs them as a report. The specific processing of this system is performed by a server.

[0583] Program Processing Overview

[0584] Data collection

[0585] The server first collects user feedback data and company performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions. Performance metrics data includes sales data, customer acquisition costs, and return rates.

[0586] Specific example: The server collects customer reviews and monthly sales data for the past six months.

[0587] Data preprocessing

[0588] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data undergoes spell checking and sentiment analysis. Performance metric data is normalized, scaled, and outliers are handled.

[0589] Specific example: The server corrects spelling mistakes in feedback and converts sales data into a year-on-year percentage change.

[0590] Execution of generative AI models

[0591] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data.

[0592] Specific example: The server inputs user feedback and sales data into a generative AI model, which then generates specific suggestions such as "improve customer support response speed."

[0593] Identifying problems and generating improvement plans

[0594] The server extracts issues and improvement suggestions generated from generative artificial intelligence models and creates a detailed list. This clarifies the organization's current problems and proposes specific solutions for each problem.

[0595] Specific example: The server identifies problems such as "customer support response speed" and "new product marketing strategy," and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media."

[0596] Report generation and feedback

[0597] Finally, the server generates a report based on the identified issues and proposed improvements. The report is generated in PDF format and sent to the company's management and relevant personnel.

[0598] Specific example: Create a report generated by the server in PDF format and send it to management via email.

[0599] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This, in turn, can lead to a significant improvement in organizational performance.

[0600] The following describes the processing flow.

[0601] Step 1: Data Collection

[0602] The server collects user feedback data and corporate performance indicator data. It gathers customer reviews, survey results, and employee opinions provided by users. It also collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0603] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this data in a database.

[0604] Step 2: Cleaning Feedback Data

[0605] The server cleans the collected feedback data. This cleaning process includes spell checking and sentiment analysis of the text data.

[0606] Specific example: The server uses a natural language processing tool to correct spelling errors in customer reviews and categorize the sentiment of the reviews into three groups: positive, negative, and neutral.

[0607] Step 3: Normalize performance metrics data

[0608] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0609] Specific example: The server converts sales data into a year-on-year percentage change and detects and corrects abnormally high or low values.

[0610] Step 4: Combining the data

[0611] The server combines pre-processed feedback data and performance metric data. This forms the input dataset for the model.

[0612] Specific example: The server creates a data frame containing feedback data and sales data, and converts it into a format that can be input into a generative artificial intelligence model.

[0613] Step 5: Setting up and running the generative artificial intelligence model

[0614] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model then generates organizational challenges and proposed improvements.

[0615] Specific example: The server uses the Hugging Face transformers library to load a generative artificial intelligence model, inputs a combined dataset, and generates suggestions such as "improve product quality" and "improve customer support."

[0616] Step 6: Identifying issues and generating improvement plans

[0617] The server extracts a list of organizational issues and improvement proposals from text generated by a generative artificial intelligence model.

[0618] Specific example: The server extracts "slow response time for customer support" from the generated text and proposes "implementation of a 24 / 7 chatbot" as an improvement plan.

[0619] Step 7: Report Generation

[0620] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0621] Specific example: The server uses a report template, summarizing issues and suggested improvements in separate sections, and adding charts and graphs as needed.

[0622] Step 8: Report Distribution

[0623] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0624] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0625] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables organizations to quickly and efficiently identify problems and implement concrete improvement measures.

[0626] (Example 1)

[0627] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0628] Traditional systems for improving organizational performance suffered from the time and effort required for cleaning, normalizing, and analyzing collected data using generative artificial intelligence. Furthermore, the lack of effective methods for integrating and analyzing user feedback data and performance indicator data made it difficult to quickly provide clear improvement suggestions. As a result, companies struggled to efficiently identify problems and implement concrete countermeasures.

[0629] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0630] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence. This makes it possible to quickly clean and normalize the collected feedback data and performance indicator data, and efficiently analyze them using a generative artificial intelligence model, thereby quickly generating clear issues and specific improvement proposals.

[0631] "Means of collecting data" refers to functions for obtaining user feedback data and organizational performance indicator data. Specifically, this includes retrieving information from databases and collecting data from online survey forms.

[0632] "Means for preprocessing collected data" refer to functions for cleaning and sentiment analysis of collected feedback data, as well as normalizing and scaling performance indicator data. Specifically, this includes spell checking of text data and handling of data outliers.

[0633] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that uses a generative artificial intelligence model to analyze pre-processed data and automatically generate organizational issues and specific improvement proposals. Specifically, it uses generative artificial intelligence such as GPT-3.5-turbo.

[0634] "A means of outputting generated issues and improvement proposals as a report" refers to a function that generates a report based on the generated issues and improvement proposals, and saves and distributes that report in PDF format or other formats.

[0635] "Feedback data" refers to data that includes suggestions for improvement and opinions regarding the organization, such as customer reviews, survey results, and employee feedback obtained from users.

[0636] "Performance metrics data" refers to data used to measure an organization's performance, and includes sales data, customer acquisition costs, and return rates.

[0637] "Preprocessing" refers to a series of processes performed to prepare collected data into an analyzable format, and includes text data cleaning, sentiment analysis, normalization, and scaling.

[0638] This invention is a system for improving the organizational performance of a company, which generates specific problems and improvement proposals through multiple processing steps and outputs them as a report. The specific processing of this system is executed by a server and uses the following hardware and software.

[0639] The server first collects user feedback data and organizational performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions, while performance metrics data includes sales data, customer acquisition costs, and return rates. This data is retrieved from the company's internal database system (e.g., MySQL or PostgreSQL) and received via HTTP requests. Specifically, it uses SQL queries to retrieve data and collects feedback data from online forms.

[0640] Next, the server preprocesses the collected data. For cleaning feedback data, natural language processing libraries such as NLTK and SpaCy are used to perform spell checking and sentiment analysis on text data. For performance metric data, the Python pandas library is used to normalize the data, scale it, and handle outliers.

[0641] The pre-processed data is input into a generative artificial intelligence model (e.g., OpenAI's GPT-3.5-turbo). The server uses the OpenAI library to pass the data to the generative AI model and generates the problem and suggested improvements. An example of a prompt message would be: "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]".

[0642] The server extracts problems and suggested improvements generated from a generative artificial intelligence model and creates a concrete list. This process uses regular expressions and natural language processing techniques to extract problems and suggestions from the generated text.

[0643] Finally, the server generates a report based on the identified issues and suggested improvements. The report is generated in PDF format using the Python reportlab library and then sent to the company's management and relevant personnel using the smtplib library. The report contains a detailed list of the identified issues and suggested improvements, enabling the company to respond quickly and efficiently.

[0644] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0645] Step 1: Data Collection

[0646] The server first collects user feedback data and organizational performance indicator data. Inputs include performance indicator data such as sales data, customer acquisition costs, and return rates retrieved from the company's database system (e.g., MySQL or PostgreSQL), and feedback data such as customer reviews and employee opinions collected from online survey forms. Specifically, the server executes SQL queries to retrieve the necessary performance indicator data from the database and collects feedback data from online forms via HTTP requests. The server then collects this data and passes it on to the next preprocessing step.

[0647] Step 2: Data Preprocessing

[0648] The server preprocesses the collected data. The inputs are collected feedback data and performance metric data. Preprocessing includes cleaning the feedback data, sentiment analysis, and normalization, scaling, and outlier handling of the performance metric data. Specifically, the server uses natural language processing libraries such as NLTK and SpaCy to spell-check and clean the text data, and performs sentiment analysis. It also uses the pandas library to normalize and handle outliers in the performance metric data. This generates preprocessed data, which is then passed to the next step in the execution of the generative AI model.

[0649] Step 3: Execute the generative AI model

[0650] The server combines cleaned and normalized data and inputs it into a generative artificial intelligence model (e.g., GPT-3.5-turbo). The input consists of pre-processed feedback data and performance metric data. Specifically, the server uses the OpenAI library to pass the data to the generative AI model and inputs prompts to generate organizational issues and improvement suggestions. For example, the prompts could be set in the form of "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]", and the AI ​​model would perform the analysis based on these prompts. This would then output the generated organizational issues and improvement suggestions.

[0651] Step 4: Identifying problems and generating improvement plans

[0652] The server analyzes text generated by a generative artificial intelligence model and extracts problems and suggested improvements. The input is the generated text obtained from the generative AI model. Specifically, the server uses regular expressions and natural language processing techniques to extract problems and suggested improvements from the generated text. For example, it uses regular expressions to extract sentences containing "Problem:" or "Suggested Improvement:" and creates separate lists for each. This outputs the problems and suggested improvements as concrete lists.

[0653] Step 5: Report generation and feedback

[0654] Finally, the server generates a report based on the identified issues and improvement suggestions and sends it to the company's management and relevant personnel. The input is a list of the generated issues and improvement suggestions. Specifically, the server uses the Python reportlab library to generate the report in PDF format, and then uses the smtplib library to send the generated report via email. The report contains detailed information on the generated issues and improvement suggestions, allowing the company to take quick and efficient action based on it.

[0655] (Application Example 1)

[0656] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0657] Conventional autonomous vehicles lack the means to identify specific issues and propose improvements to enhance vehicle performance and user satisfaction. Therefore, there is a need for a new system that effectively utilizes various operational data and user feedback to improve vehicle performance and the user experience.

[0658] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0659] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting sensor data and user feedback from in-vehicle devices, means for analyzing the collected sensor data and performing sentiment analysis of user feedback, means for generating issues and improvement proposals related to vehicle performance using generative artificial intelligence, and means for outputting the generated issues and improvement proposals related to vehicle performance as a report. This makes it possible to improve the performance and user experience of autonomous vehicles.

[0660] "Means of collecting data" refers to functions that collect sensor data and user feedback through in-vehicle devices and user interfaces.

[0661] "Means for preprocessing collected data" refers to functions that clean, normalize, and analyze collected sensor data and feedback data.

[0662] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that utilizes generative artificial intelligence models to generate organizational and system issues and corresponding improvement proposals from pre-processed data.

[0663] "A means of outputting generated issues and improvement proposals as a report" refers to a function that creates generated issues and improvement proposals in report format and provides them to administrators and relevant parties.

[0664] "Means for collecting sensor data and user feedback from in-vehicle devices" refers to functions that collect operational data and user feedback through various sensors and user interfaces installed in the vehicle.

[0665] "Means for analyzing collected sensor data and performing sentiment analysis of user feedback" refers to a function that analyzes collected sensor data and then performs sentiment analysis on user feedback.

[0666] "Means for generating vehicle performance issues and improvement proposals using generative artificial intelligence" refers to a function that automatically generates specific vehicle performance issues and improvement methods from data collected and analyzed using a generative artificial intelligence model.

[0667] "A means of outputting a report of issues and improvement suggestions regarding the performance of generated vehicles" refers to a function that compiles the issues and improvement suggestions for generated vehicles in a report format and provides them to the administrator.

[0668] This invention is a system for improving the performance and user experience of autonomous vehicles. This system analyzes various data collected from the vehicle and user feedback, automatically generates problems and improvement proposals using generative artificial intelligence, and provides them as a report.

[0669] Hardware and software used

[0670] The server plays a central role in the system and performs processing using the following hardware and software:

[0671] Hardware:

[0672] Various sensors in automotive devices (camera, LiDAR, GPS)

[0673] A smartphone or in-car infotainment system with a user interface.

[0674] software:

[0675] Python script for data cleaning and normalization

[0676] OpenAI's GPT-3.5-turbo for running generative AI models

[0677] Report generation requires a Python report generation library (e.g., ReportLab).

[0678] Data Acquisition and Preprocessing

[0679] The server collects sensor data from in-vehicle devices and simultaneously collects user feedback. Sensor data includes camera images, LiDAR data, and GPS data. User feedback includes satisfaction with ride comfort, response speed, and route selection. The collected data is first cleaned to remove noise and formatted into an appropriate format. Next, the text data undergoes spell checking and sentiment analysis.

[0680] Execution of generative AI models and generation of problems and improvement proposals.

[0681] The collected and pre-processed data is input into a generative AI model (e.g., GPT-3.5-turbo) to generate specific issues and improvement suggestions regarding vehicle performance. Examples include "identifying areas with high fuel consumption during operation" and "suggesting route optimizations to improve fuel efficiency."

[0682] Report generation

[0683] The generated issues and improvement suggestions are compiled into a report by the server and provided to the administrator. The report is generated in PDF format and can be sent via email or viewed on the in-car infotainment system.

[0684] Specific example

[0685] Examples of prompts for a generative AI model include:

[0686] Based on vehicle data and user feedback from the past six months, generate performance issues and suggested improvements for the vehicle.

[0687] data:

[0688] Operational data: [GPS data, time-series data, fuel consumption data]

[0689] Feedback: [User reviews, survey results]

[0690] We expect this system to enable rapid and efficient improvements in the performance and user experience of autonomous vehicles.

[0691] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0692] Step 1:

[0693] The server collects sensor data and user feedback from in-vehicle devices. Specifically, it collects sensor data such as camera images, LiDAR data, and GPS data, as well as feedback information from users regarding ride comfort, response speed, and satisfaction with route selection. The input data consists of sensor data and feedback data, while the output is the raw collected data.

[0694] Step 2:

[0695] The server preprocesses the collected sensor data and feedback data. Specifically, it cleans the data, removes noise, and formats it into an appropriate format. Spell checking and sentiment analysis are also performed on the feedback data. The input is the raw collected data, and the output is the cleaned and normalized data.

[0696] Step 3:

[0697] The server inputs pre-processed data into a generative artificial intelligence model. Specifically, it uses cleaned sensor data and sentiment-analyzed feedback data to create AI-based problem identification and improvement suggestion generation prompts. The input is pre-processed data, and the output is the analysis result from the generative AI model.

[0698] Step 4:

[0699] The server uses a generative artificial intelligence model to generate specific problems and improvement proposals from the input data. Specifically, it uses a generative AI model (e.g., GPT-3.5-turbo) to automatically generate problems and improvement proposals such as "identifying areas with high fuel consumption during operation" and "proposing route optimizations to improve fuel efficiency." The input consists of prompts and preprocessed data for the AI ​​model, and the output is a list of problems and improvement proposals.

[0700] Step 5:

[0701] The server generates and outputs a report containing the generated issues and improvement proposals. Specifically, it organizes the generated issues and improvement proposals, compiles them into a report format (e.g., PDF), and provides it to vehicle managers and other relevant parties. A report generation library (e.g., ReportLab) is used for this purpose. The input is a list of issues and improvement proposals, and the output is a report in PDF format.

[0702] Step 6:

[0703] The server distributes the generated report through the appropriate channel. Specifically, it either sends the PDF report via email or uploads it to the in-vehicle infotainment system for viewing. The input is a report in PDF format, and the output is the sent report.

[0704] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0705] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0706] Program Processing Overview

[0707] Data collection

[0708] The server first collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0709] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: positive, negative, and neutral.

[0710] Data preprocessing

[0711] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data is spell-checked and sentiment analyzed. Sentiment data analyzed by the sentiment engine is also included in the preprocessed data. Performance metric data is normalized, and data scaling and outlier handling are performed.

[0712] Specific examples: The server corrects spelling mistakes in feedback and converts sales data into year-over-year percentage changes. The sentiment engine analysis results include data such as "This review is negative."

[0713] Execution of generative AI models

[0714] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational issues and proposed solutions from the input data. The model also considers emotional data obtained from the emotion engine to generate more specific and appropriate issues and solutions.

[0715] Specific example: The server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0716] Identifying problems and generating improvement plans

[0717] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0718] Specific example: The server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from generated text, and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media." Furthermore, it identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0719] Report generation and feedback

[0720] Finally, the server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0721] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. Sentiment data is visualized to display sentiment trends for specific issues.

[0722] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0723] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0724] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This can lead to a significant improvement in organizational performance. By adding an emotion engine, more accurate suggestions that take user emotions into account become possible.

[0725] The following describes the processing flow.

[0726] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0727] Program Processing Overview

[0728] Step 1: Data Collection

[0729] The server collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0730] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: "positive," "negative," and "neutral."

[0731] Step 2: Cleaning Feedback Data

[0732] The server cleans the collected feedback data. This cleaning process includes spell checking and grammatical correction of the text data. Furthermore, it uses a sentiment engine to analyze the sentiment of the feedback and adds the results to the data.

[0733] Specific example: The server uses natural language processing tools to correct spelling and grammatical errors in reviews, and analyzes and adds a sentiment score for each review.

[0734] Step 3: Normalize performance metrics data

[0735] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0736] Specific example: The server normalizes sales data by comparing it to the same month of the previous year, and detects and corrects abnormally high or low values.

[0737] Step 4: Combining the data

[0738] The server combines pre-processed feedback data with performance metrics data. It integrates feedback data, including data from the emotion engine, with performance metrics data to create an input dataset for the model.

[0739] Specific example: The server combines feedback data (with sentiment scores) and sales data to create a dataset in a format suitable for generative artificial intelligence models.

[0740] Step 5: Setting up and running the generative artificial intelligence model

[0741] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model generates organizational challenges and proposed solutions. The model also considers emotional data obtained from an emotion engine.

[0742] Specific example: A server uses a generative AI model as input to a combined dataset and generates suggestions to identify areas where "product quality dissatisfaction" or "improvements to customer support" are needed.

[0743] Step 6: Identifying issues and generating improvement plans

[0744] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0745] Specific example: The server identifies "slow customer support response speed" from generated text and proposes "implementing a new CRM system" as an improvement. Furthermore, it identifies "the biggest customer complaint" from sentiment data and proposes specific countermeasures.

[0746] Step 7: Report Generation

[0747] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0748] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, and adds graphs and charts. Sentiment data is visualized to display sentiment trends for specific issues.

[0749] Step 8: Report Distribution

[0750] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0751] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0752] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables companies to quickly and efficiently identify problems and implement concrete improvement measures. Adding an emotion engine allows for more accurate suggestions that take user emotions into account.

[0753] (Example 2)

[0754] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0755] Modern businesses struggle to efficiently collect and analyze customer feedback and performance data. Furthermore, it's difficult to identify organizational challenges from the collected data and automatically generate concrete improvement plans. Additionally, extracting insights that take user emotions into account and creating improvement plans based on these insights presents another challenge.

[0756] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0757] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for analyzing the emotions of feedback data using an emotion analysis engine, and means for adding emotional data to the feedback data during preprocessing. This enables companies to quickly and efficiently collect and preprocess data and automatically generate specific issues and improvement proposals that take emotional data into account.

[0758] "Means of data collection" refers to devices and methods for efficiently collecting user feedback data and corporate performance indicator data.

[0759] "Methods for preprocessing collected data" refer to techniques for preparing collected data into a format suitable for subsequent analysis or input to generative models, such as text cleaning, normalization, data scaling, and handling of outliers.

[0760] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a technology that utilizes generative artificial intelligence models (e.g., generative AI models) to automatically generate organizational issues and specific improvement proposals based on pre-processed data.

[0761] "Means for outputting generated issues and improvement proposals as a report" refers to devices or methods that summarize the issues and improvement proposals generated from a generative artificial intelligence model into a visually easy-to-understand report format and output it in PDF format or similar.

[0762] "Methods for analyzing the sentiment of feedback data using a sentiment analysis engine" refers to technologies that automatically recognize and classify the sentiment (positive, negative, neutral, etc.) of the text contained in feedback data.

[0763] "Means for adding emotional data to feedback data in preprocessing" refers to a technique that adds emotional data analyzed by an emotional analysis engine to the feedback text data and further includes it in the preprocessed data.

[0764] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion analysis engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0765] First, the server collects user feedback data and company performance metrics data. Users provide customer reviews, survey results, employee opinions, etc. The server collects this feedback data and also retrieves performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems. Furthermore, it analyzes the sentiment of the feedback data using a sentiment analysis engine (e.g., IBM Watson, Google Cloud Natural Language API).

[0766] For example, the server collects customer reviews and monthly sales data for the past six months and stores them in a database. Using a sentiment analysis engine, it classifies the sentiment of customer reviews into three categories: positive, negative, and neutral.

[0767] Next, the server preprocesses the collected data. It cleans the feedback data, performing spell checks on text data and removing unnecessary symbols. It also adds sentiment data to the feedback data. For performance metric data, it normalizes the data, scales it, and handles outliers.

[0768] For example, the server corrects spelling mistakes in feedback and converts sales data into year-on-year percentage changes. The sentiment analysis engine includes information such as "this review is negative" as a result of its analysis.

[0769] The server integrates pre-processed data and inputs it into a generative artificial intelligence model. This generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data. The model also considers sentiment data to provide more specific and appropriate challenges and solutions.

[0770] For example, the server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0771] The server extracts a list of organizational issues and improvement proposals from the generated text. It also extracts insights based on sentiment data and proposes specific countermeasures.

[0772] For example, the server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from the generated text and proposes improvement plans such as "implementing a new CRM system" and "designing marketing campaigns using social media." It identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0773] Finally, the server generates a report based on the identified issues and proposed improvements. The report is formatted for easy viewing and output in PDF format. The generated report is distributed and shared with the company's management and relevant personnel.

[0774] As a concrete example, the server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. It visualizes sentiment data and displays sentiment trends for specific issues. The server emails the generated PDF report to the responsible party and saves it to cloud storage, making it shareable across the entire organization.

[0775] This system enables companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take emotional data into account. By adding an emotional analysis engine, it becomes possible to analyze users' emotions in detail and make more accurate recommendations.

[0776] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0777] Step 1: Data Collection

[0778] The server collects feedback data from users. Specifically, users input customer reviews, survey results, employee opinions, etc., into forms on their terminals and send them to the server. The server stores this data in a database. The server also automatically collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems. In this collection process, APIs are used to retrieve the necessary data from databases and ERP systems.

[0779] Input: Customer reviews, survey results, sales data

[0780] Output: Raw data stored in the database

[0781] Step 2: Sentiment analysis of feedback data

[0782] The server performs sentiment analysis on the collected feedback data. Specifically, it uses a sentiment analysis engine to analyze each review and survey response, and assigns positive, negative, or neutral sentiment tags. The server adds the analysis results to the feedback data and stores the updated data back into the database.

[0783] Input: Feedback data

[0784] Output: Feedback data with emotion tags

[0785] Step 3: Data Preprocessing

[0786] The server preprocesses the collected and sentiment-analyzed data. Feedback data undergoes spell checking and removal of unnecessary symbols. Performance metric data is normalized, scaled, and outliers are handled. The preprocessed data is then stored back into the database.

[0787] Input: Collected and sentiment-analyzed data

[0788] Output: Preprocessed data

[0789] Step 4: Preparing input for the generative AI model

[0790] The server integrates pre-processed data and converts it into a format that can be input into a generative artificial intelligence model. In this process, user feedback, sentiment analysis data, and performance data are appropriately combined and prepared in a format that the generative AI model (e.g., GPT-3.5-turbo) can understand.

[0791] Input: Preprocessed data

[0792] Output: Input data for generative AI models

[0793] Step 5: Execute the generative AI model

[0794] The server inputs integrated data into a generative artificial intelligence model. Based on the input data, the generative AI model generates organizational challenges and proposed solutions. A specific prompt might be, "Based on feedback and sales data from the past six months, please propose organizational challenges and solutions." The generated results are returned to the server as a series of text data.

[0795] Input: "Based on feedback and sales data from the past six months, please propose organizational challenges and improvement plans."

[0796] Output: Text data including organizational challenges and proposed improvements.

[0797] Step 6: Identifying issues and improvement proposals

[0798] The server analyzes text data obtained from generative AI models to extract specific problems and proposed solutions. Insights based on sentiment data are also added during this process. The server organizes the problems and solutions and compiles them into data for reporting.

[0799] Input: Text data from a generative AI model

[0800] Output: Organized data on issues and proposed improvements

[0801] Step 7: Generate the report

[0802] The server generates a report based on the identified issues and improvement suggestions. The report is formatted for easy viewing and organized into sections. Charts and graphs are added as needed to visualize sentiment data. The final report is output in PDF format, saved to the database, and then sent to relevant parties.

[0803] Input: Organized problem and improvement proposal data

[0804] Output: Generated PDF report

[0805] This process allows companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take sentiment data into account.

[0806] (Application Example 2)

[0807] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0808] In modern factory operations, it is essential to effectively collect and analyze data on equipment operation, maintenance issues, and worker feedback, and to implement improvements quickly. However, there is no system in place to efficiently aggregate and analyze this data to generate specific problems and improvement plans. As a result, factory operational efficiency declines, and productivity improvements are hindered.

[0809] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for pre-processing the collected data, means for generating organizational issues and improvement proposals from the pre-processed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting equipment operation data, maintenance history, and worker feedback data from sensors in the factory, means for cleaning the collected data, performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model, and means for visualizing the generated issues and improvement proposals using charts and graphs, outputting a report in PDF format, and distributing it. This makes it possible to efficiently collect and analyze data within the factory and to quickly generate and share specific issues and improvement proposals.

[0810] "Means of collecting data" refers to devices and systems that acquire equipment operation data, maintenance history, employee opinions, etc., from sensors within the factory or feedback from users.

[0811] "Means for preprocessing collected data" refer to methods and systems for improving data quality and maintaining consistency by cleaning acquired data and performing sentiment analysis.

[0812] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to the application of a generative artificial intelligence model to identify and propose current problems and improvement measures for an organization based on pre-processed data.

[0813] "Means for outputting generated issues and improvement proposals as a report" refers to methods or systems for formatting the generated information in an easy-to-understand manner and creating and outputting a report in a format such as PDF.

[0814] "Means for collecting equipment operation data, maintenance history, and worker feedback data from sensors within the factory" refers to a data collection mechanism based on various sensors installed within the factory and input from employees.

[0815] "Means for performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model" refers to processing procedures and methods for normalizing collected data, applying sentiment analysis, and inputting it into a generative artificial intelligence model in a format useful for that model.

[0816] "A method for visualizing data using charts and graphs, outputting reports in PDF format, and distributing them" refers to a system or method for visually presenting generated data and proposals in an easy-to-understand format, organizing them into a report, and then distributing them to administrators and relevant parties.

[0817] This invention provides a system aimed at automating data collection, analysis, visualization, and feedback in factory operations. Here, we describe specific embodiments for effectively collecting data and automatically generating organizational challenges and improvement proposals using generative artificial intelligence.

[0818] First, the server uses sensors within the factory to collect data on equipment operation, maintenance history, and feedback from workers. This includes data from IoT devices and online feedback forms filled out by employees. Specifically, the server uses an IoT platform (e.g., AWS IoT Core) to collect data and stores it in a database (e.g., Amazon RDS).

[0819] Next, the server preprocesses the collected data. Specifically, it cleans the data and uses an emotion analysis engine (e.g., Hugging Face's Transformers model) to emotionally classify employee feedback. It also normalizes performance metric data and converts it into a consistent data format. The preprocessed data is then manipulated using the Python Pandas library.

[0820] The server then inputs the pre-processed data into a generative artificial intelligence model (e.g., GPT-3.5-turbo) to generate organizational challenges and improvement proposals. The generated information includes specific suggestions for improving work efficiency and optimizing equipment maintenance. Data is input to the generative AI using prompts such as the following:

[0821] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[0822] The issues and improvement proposals generated by the generative artificial intelligence model are visualized by the server. Specifically, a PDF report containing charts and graphs is generated using Python's Matplotlib and ReportLab libraries. This allows stakeholders to understand the current state of the organization in a visually easy-to-understand way and take appropriate improvement measures.

[0823] Finally, the server distributes the generated reports to administrators and relevant parties. This is done by sending the reports via email using a mail server (e.g., SendGrid) or by uploading them to a cloud storage service (e.g., Google Drive).

[0824] As described above, the system of the present invention automates a series of processes from data collection to analysis, report generation, and feedback, thereby improving the efficiency and performance of factory operations.

[0825] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0826] Step 1: Data Collection

[0827] The server collects data using various sensors placed throughout the factory and online feedback forms from employees. Inputs include equipment operation data, maintenance history, and worker feedback data, which are acquired through the IoT platform and stored in a database. Specifically, AWS IoT Core is used to collect various data and store it in Amazon RDS.

[0828] Step 2: Data Preprocessing

[0829] The server cleans the collected data and performs sentiment analysis. The input includes the data collected in the previous step. Data cleaning uses the Python Pandas library to correct incomplete data and spelling errors. Sentiment analysis uses the Hugging Face Transformers model to classify employee feedback emotionally as "positive," "negative," or "neutral." Furthermore, performance metric data is normalized and converted into a consistent data format.

[0830] Step 3: Data integration and input into generative artificial intelligence models

[0831] The server integrates the preprocessed data and inputs it into a generative artificial intelligence model. Specifically, it uses the Python Pandas library to combine the preprocessed data into a dataframe and inputs it into the generative artificial intelligence model (GPT-3.5-turbo). Here, data input is performed using prompt statements. An example of a prompt statement is as follows:

[0832] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[0833] Step 4: Generating problems and improvement plans

[0834] The server analyzes the output obtained by the generative artificial intelligence model to identify organizational challenges and improvement suggestions. The input includes text data obtained from the generative artificial intelligence model in the previous step. The output includes a list of specific challenges and corresponding improvement suggestions. For example, "equipment overheating" and "worker stress" might be extracted as challenges, while "implementation of a cooling system" and "improvement of the work environment" might be generated as improvement suggestions.

[0835] Step 5: Report Generation

[0836] The server generates a report based on the generated issues and improvement suggestions. The input includes the list of issues and improvement suggestions obtained in the previous step. Using the Matplotlib and ReportLab libraries in Python, the issues and improvement suggestions are visualized using charts and graphs, and output as a report in PDF format.

[0837] Step 6: Report Distribution

[0838] The server distributes the generated report to the relevant parties. The input includes the generated PDF report. The report can be distributed via email using a mail server (e.g., SendGrid) or uploaded to a cloud storage service (e.g., Google Drive).

[0839] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0840] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0841] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0842] [Fourth Embodiment]

[0843] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0844] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0845] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0846] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0847] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0848] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0849] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0850] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0851] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0852] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0853] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0854] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0855] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0856] This invention is a system for improving the organizational performance of companies. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence, and outputs them as a report. The specific processing of this system is performed by a server.

[0857] Program Processing Overview

[0858] Data collection

[0859] The server first collects user feedback data and company performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions. Performance metrics data includes sales data, customer acquisition costs, and return rates.

[0860] Specific example: The server collects customer reviews and monthly sales data for the past six months.

[0861] Data preprocessing

[0862] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data undergoes spell checking and sentiment analysis. Performance metric data is normalized, scaled, and outliers are handled.

[0863] Specific example: The server corrects spelling mistakes in feedback and converts sales data into a year-on-year percentage change.

[0864] Execution of generative AI models

[0865] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data.

[0866] Specific example: The server inputs user feedback and sales data into a generative AI model, which then generates specific suggestions such as "improve customer support response speed."

[0867] Identifying problems and generating improvement plans

[0868] The server extracts issues and improvement suggestions generated from generative artificial intelligence models and creates a detailed list. This clarifies the organization's current problems and proposes specific solutions for each problem.

[0869] Specific example: The server identifies problems such as "customer support response speed" and "new product marketing strategy," and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media."

[0870] Report generation and feedback

[0871] Finally, the server generates a report based on the identified issues and proposed improvements. The report is generated in PDF format and sent to the company's management and relevant personnel.

[0872] Specific example: Create a report generated by the server in PDF format and send it to management via email.

[0873] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This, in turn, can lead to a significant improvement in organizational performance.

[0874] The following describes the processing flow.

[0875] Step 1: Data Collection

[0876] The server collects user feedback data and corporate performance indicator data. It gathers customer reviews, survey results, and employee opinions provided by users. It also collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0877] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this data in a database.

[0878] Step 2: Cleaning Feedback Data

[0879] The server cleans the collected feedback data. This cleaning process includes spell checking and sentiment analysis of the text data.

[0880] Specific example: The server uses a natural language processing tool to correct spelling errors in customer reviews and categorize the sentiment of the reviews into three groups: positive, negative, and neutral.

[0881] Step 3: Normalize performance metrics data

[0882] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[0883] Specific example: The server converts sales data into a year-on-year percentage change and detects and corrects abnormally high or low values.

[0884] Step 4: Combining the data

[0885] The server combines pre-processed feedback data and performance metric data. This forms the input dataset for the model.

[0886] Specific example: The server creates a data frame containing feedback data and sales data, and converts it into a format that can be input into a generative artificial intelligence model.

[0887] Step 5: Setting up and running the generative artificial intelligence model

[0888] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model then generates organizational challenges and proposed improvements.

[0889] Specific example: The server uses the Hugging Face transformers library to load a generative artificial intelligence model, inputs a combined dataset, and generates suggestions such as "improve product quality" and "improve customer support."

[0890] Step 6: Identifying issues and generating improvement plans

[0891] The server extracts a list of organizational issues and improvement proposals from text generated by a generative artificial intelligence model.

[0892] Specific example: The server extracts "slow response time for customer support" from the generated text and proposes "implementation of a 24 / 7 chatbot" as an improvement plan.

[0893] Step 7: Report Generation

[0894] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0895] Specific example: The server uses a report template, summarizing issues and suggested improvements in separate sections, and adding charts and graphs as needed.

[0896] Step 8: Report Distribution

[0897] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0898] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0899] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables organizations to quickly and efficiently identify problems and implement concrete improvement measures.

[0900] (Example 1)

[0901] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0902] Traditional systems for improving organizational performance suffered from the time and effort required for cleaning, normalizing, and analyzing collected data using generative artificial intelligence. Furthermore, the lack of effective methods for integrating and analyzing user feedback data and performance indicator data made it difficult to quickly provide clear improvement suggestions. As a result, companies struggled to efficiently identify problems and implement concrete countermeasures.

[0903] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0904] In this invention, the server includes means for collecting data, means for preprocessing the collected data, and means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence. This makes it possible to quickly clean and normalize the collected feedback data and performance indicator data, and efficiently analyze them using a generative artificial intelligence model, thereby quickly generating clear issues and specific improvement proposals.

[0905] "Means of collecting data" refers to functions for obtaining user feedback data and organizational performance indicator data. Specifically, this includes retrieving information from databases and collecting data from online survey forms.

[0906] "Means for preprocessing collected data" refer to functions for cleaning and sentiment analysis of collected feedback data, as well as normalizing and scaling performance indicator data. Specifically, this includes spell checking of text data and handling of data outliers.

[0907] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that uses a generative artificial intelligence model to analyze pre-processed data and automatically generate organizational issues and specific improvement proposals. Specifically, it uses generative artificial intelligence such as GPT-3.5-turbo.

[0908] "A means of outputting generated issues and improvement proposals as a report" refers to a function that generates a report based on the generated issues and improvement proposals, and saves and distributes that report in PDF format or other formats.

[0909] "Feedback data" refers to data that includes suggestions for improvement and opinions regarding the organization, such as customer reviews, survey results, and employee feedback obtained from users.

[0910] "Performance metrics data" refers to data used to measure an organization's performance, and includes sales data, customer acquisition costs, and return rates.

[0911] "Preprocessing" refers to a series of processes performed to prepare collected data into an analyzable format, and includes text data cleaning, sentiment analysis, normalization, and scaling.

[0912] This invention is a system for improving the organizational performance of a company, which generates specific problems and improvement proposals through multiple processing steps and outputs them as a report. The specific processing of this system is executed by a server and uses the following hardware and software.

[0913] The server first collects user feedback data and organizational performance metrics data. Feedback data includes customer reviews, survey results, and employee opinions, while performance metrics data includes sales data, customer acquisition costs, and return rates. This data is retrieved from the company's internal database system (e.g., MySQL or PostgreSQL) and received via HTTP requests. Specifically, it uses SQL queries to retrieve data and collects feedback data from online forms.

[0914] Next, the server preprocesses the collected data. For cleaning feedback data, natural language processing libraries such as NLTK and SpaCy are used to perform spell checking and sentiment analysis on text data. For performance metric data, the Python pandas library is used to normalize the data, scale it, and handle outliers.

[0915] The pre-processed data is input into a generative artificial intelligence model (e.g., OpenAI's GPT-3.5-turbo). The server uses the OpenAI library to pass the data to the generative AI model and generates the problem and suggested improvements. An example of a prompt message would be: "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]".

[0916] The server extracts problems and suggested improvements generated from a generative artificial intelligence model and creates a concrete list. This process uses regular expressions and natural language processing techniques to extract problems and suggestions from the generated text.

[0917] Finally, the server generates a report based on the identified issues and suggested improvements. The report is generated in PDF format using the Python reportlab library and then sent to the company's management and relevant personnel using the smtplib library. The report contains a detailed list of the identified issues and suggested improvements, enabling the company to respond quickly and efficiently.

[0918] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0919] Step 1: Data Collection

[0920] The server first collects user feedback data and organizational performance indicator data. Inputs include performance indicator data such as sales data, customer acquisition costs, and return rates retrieved from the company's database system (e.g., MySQL or PostgreSQL), and feedback data such as customer reviews and employee opinions collected from online survey forms. Specifically, the server executes SQL queries to retrieve the necessary performance indicator data from the database and collects feedback data from online forms via HTTP requests. The server then collects this data and passes it on to the next preprocessing step.

[0921] Step 2: Data Preprocessing

[0922] The server preprocesses the collected data. The inputs are collected feedback data and performance metric data. Preprocessing includes cleaning the feedback data, sentiment analysis, and normalization, scaling, and outlier handling of the performance metric data. Specifically, the server uses natural language processing libraries such as NLTK and SpaCy to spell-check and clean the text data, and performs sentiment analysis. It also uses the pandas library to normalize and handle outliers in the performance metric data. This generates preprocessed data, which is then passed to the next step in the execution of the generative AI model.

[0923] Step 3: Execute the generative AI model

[0924] The server combines cleaned and normalized data and inputs it into a generative artificial intelligence model (e.g., GPT-3.5-turbo). The input consists of pre-processed feedback data and performance metric data. Specifically, the server uses the OpenAI library to pass the data to the generative AI model and inputs prompts to generate organizational issues and improvement suggestions. For example, the prompts could be set in the form of "Analyze the following data and suggest improvements: Feedback: [Feedback data] Performance Metrics: [Performance data]", and the AI ​​model would perform the analysis based on these prompts. This would then output the generated organizational issues and improvement suggestions.

[0925] Step 4: Identifying problems and generating improvement plans

[0926] The server analyzes text generated by a generative artificial intelligence model and extracts problems and suggested improvements. The input is the generated text obtained from the generative AI model. Specifically, the server uses regular expressions and natural language processing techniques to extract problems and suggested improvements from the generated text. For example, it uses regular expressions to extract sentences containing "Problem:" or "Suggested Improvement:" and creates separate lists for each. This outputs the problems and suggested improvements as concrete lists.

[0927] Step 5: Report generation and feedback

[0928] Finally, the server generates a report based on the identified issues and improvement suggestions and sends it to the company's management and relevant personnel. The input is a list of the generated issues and improvement suggestions. Specifically, the server uses the Python reportlab library to generate the report in PDF format, and then uses the smtplib library to send the generated report via email. The report contains detailed information on the generated issues and improvement suggestions, allowing the company to take quick and efficient action based on it.

[0929] (Application Example 1)

[0930] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0931] Conventional autonomous vehicles lack the means to identify specific issues and propose improvements to enhance vehicle performance and user satisfaction. Therefore, there is a need for a new system that effectively utilizes various operational data and user feedback to improve vehicle performance and the user experience.

[0932] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0933] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting sensor data and user feedback from in-vehicle devices, means for analyzing the collected sensor data and performing sentiment analysis of user feedback, means for generating issues and improvement proposals related to vehicle performance using generative artificial intelligence, and means for outputting the generated issues and improvement proposals related to vehicle performance as a report. This makes it possible to improve the performance and user experience of autonomous vehicles.

[0934] "Means of collecting data" refers to functions that collect sensor data and user feedback through in-vehicle devices and user interfaces.

[0935] "Means for preprocessing collected data" refers to functions that clean, normalize, and analyze collected sensor data and feedback data.

[0936] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a function that utilizes generative artificial intelligence models to generate organizational and system issues and corresponding improvement proposals from pre-processed data.

[0937] "A means of outputting generated issues and improvement proposals as a report" refers to a function that creates generated issues and improvement proposals in report format and provides them to administrators and relevant parties.

[0938] "Means for collecting sensor data and user feedback from in-vehicle devices" refers to functions that collect operational data and user feedback through various sensors and user interfaces installed in the vehicle.

[0939] "Means for analyzing collected sensor data and performing sentiment analysis of user feedback" refers to a function that analyzes collected sensor data and then performs sentiment analysis on user feedback.

[0940] "Means for generating vehicle performance issues and improvement proposals using generative artificial intelligence" refers to a function that automatically generates specific vehicle performance issues and improvement methods from data collected and analyzed using a generative artificial intelligence model.

[0941] "A means of outputting a report of issues and improvement suggestions regarding the performance of generated vehicles" refers to a function that compiles the issues and improvement suggestions for generated vehicles in a report format and provides them to the administrator.

[0942] This invention is a system for improving the performance and user experience of autonomous vehicles. This system analyzes various data collected from the vehicle and user feedback, automatically generates problems and improvement proposals using generative artificial intelligence, and provides them as a report.

[0943] Hardware and software used

[0944] The server plays a central role in the system and performs processing using the following hardware and software:

[0945] Hardware:

[0946] Various sensors in automotive devices (camera, LiDAR, GPS)

[0947] A smartphone or in-car infotainment system with a user interface.

[0948] software:

[0949] Python script for data cleaning and normalization

[0950] OpenAI's GPT-3.5-turbo for running generative AI models

[0951] Report generation requires a Python report generation library (e.g., ReportLab).

[0952] Data Acquisition and Preprocessing

[0953] The server collects sensor data from in-vehicle devices and simultaneously collects user feedback. Sensor data includes camera images, LiDAR data, and GPS data. User feedback includes satisfaction with ride comfort, response speed, and route selection. The collected data is first cleaned to remove noise and formatted into an appropriate format. Next, the text data undergoes spell checking and sentiment analysis.

[0954] Execution of generative AI models and generation of problems and improvement proposals.

[0955] The collected and pre-processed data is input into a generative AI model (e.g., GPT-3.5-turbo) to generate specific issues and improvement suggestions regarding vehicle performance. Examples include "identifying areas with high fuel consumption during operation" and "suggesting route optimizations to improve fuel efficiency."

[0956] Report generation

[0957] The generated issues and improvement suggestions are compiled into a report by the server and provided to the administrator. The report is generated in PDF format and can be sent via email or viewed on the in-car infotainment system.

[0958] Specific example

[0959] Examples of prompts for a generative AI model include:

[0960] Based on vehicle data and user feedback from the past six months, generate performance issues and suggested improvements for the vehicle.

[0961] data:

[0962] Operational data: [GPS data, time-series data, fuel consumption data]

[0963] Feedback: [User reviews, survey results]

[0964] We expect this system to enable rapid and efficient improvements in the performance and user experience of autonomous vehicles.

[0965] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0966] Step 1:

[0967] The server collects sensor data and user feedback from in-vehicle devices. Specifically, it collects sensor data such as camera images, LiDAR data, and GPS data, as well as feedback information from users regarding ride comfort, response speed, and satisfaction with route selection. The input data consists of sensor data and feedback data, while the output is the raw collected data.

[0968] Step 2:

[0969] The server preprocesses the collected sensor data and feedback data. Specifically, it cleans the data, removes noise, and formats it into an appropriate format. Spell checking and sentiment analysis are also performed on the feedback data. The input is the raw collected data, and the output is the cleaned and normalized data.

[0970] Step 3:

[0971] The server inputs pre-processed data into a generative artificial intelligence model. Specifically, it uses cleaned sensor data and sentiment-analyzed feedback data to create AI-based problem identification and improvement suggestion generation prompts. The input is pre-processed data, and the output is the analysis result from the generative AI model.

[0972] Step 4:

[0973] The server uses a generative artificial intelligence model to generate specific problems and improvement proposals from the input data. Specifically, it uses a generative AI model (e.g., GPT-3.5-turbo) to automatically generate problems and improvement proposals such as "identifying areas with high fuel consumption during operation" and "proposing route optimizations to improve fuel efficiency." The input consists of prompts and preprocessed data for the AI ​​model, and the output is a list of problems and improvement proposals.

[0974] Step 5:

[0975] The server generates and outputs a report containing the generated issues and improvement proposals. Specifically, it organizes the generated issues and improvement proposals, compiles them into a report format (e.g., PDF), and provides it to vehicle managers and other relevant parties. A report generation library (e.g., ReportLab) is used for this purpose. The input is a list of issues and improvement proposals, and the output is a report in PDF format.

[0976] Step 6:

[0977] The server distributes the generated report through the appropriate channel. Specifically, it either sends the PDF report via email or uploads it to the in-vehicle infotainment system for viewing. The input is a report in PDF format, and the output is the sent report.

[0978] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0979] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[0980] Program Processing Overview

[0981] Data collection

[0982] The server first collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[0983] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: positive, negative, and neutral.

[0984] Data preprocessing

[0985] Next, the server preprocesses the collected data. Feedback data is cleaned, and text data is spell-checked and sentiment analyzed. Sentiment data analyzed by the sentiment engine is also included in the preprocessed data. Performance metric data is normalized, and data scaling and outlier handling are performed.

[0986] Specific examples: The server corrects spelling mistakes in feedback and converts sales data into year-over-year percentage changes. The sentiment engine analysis results include data such as "This review is negative."

[0987] Execution of generative AI models

[0988] The server combines the cleaned and normalized data and inputs it into a generative artificial intelligence model. The generative AI model (e.g., GPT-3.5-turbo) generates organizational issues and proposed solutions from the input data. The model also considers emotional data obtained from the emotion engine to generate more specific and appropriate issues and solutions.

[0989] Specific example: The server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[0990] Identifying problems and generating improvement plans

[0991] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[0992] Specific example: The server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from generated text, and proposes improvement measures such as "implementing a new CRM system" and "designing a marketing campaign using social media." Furthermore, it identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[0993] Report generation and feedback

[0994] Finally, the server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[0995] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. Sentiment data is visualized to display sentiment trends for specific issues.

[0996] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[0997] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[0998] This invention enables companies to quickly and efficiently identify organizational challenges and implement concrete improvement measures. This can lead to a significant improvement in organizational performance. By adding an emotion engine, more accurate suggestions that take user emotions into account become possible.

[0999] The following describes the processing flow.

[1000] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion engine, and outputs them as a report. The specific processing of this system is performed by a server.

[1001] Program Processing Overview

[1002] Step 1: Data Collection

[1003] The server collects user feedback data and corporate performance metrics data. It gathers customer reviews, survey results, and employee opinions provided by users. Furthermore, it uses an emotion engine to recognize user emotions within the feedback data. It also collects performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems.

[1004] Specific example: A server collects customer reviews and monthly sales data for the past six months and stores this in a database. An emotion engine is used to classify the emotions of customer reviews into three categories: "positive," "negative," and "neutral."

[1005] Step 2: Cleaning Feedback Data

[1006] The server cleans the collected feedback data. This cleaning process includes spell checking and grammatical correction of the text data. Furthermore, it uses a sentiment engine to analyze the sentiment of the feedback and adds the results to the data.

[1007] Specific example: The server uses natural language processing tools to correct spelling and grammatical errors in reviews, and analyzes and adds a sentiment score for each review.

[1008] Step 3: Normalize performance metrics data

[1009] The server normalizes the collected performance metric data, scales the data, and handles outliers.

[1010] Specific example: The server normalizes sales data by comparing it to the same month of the previous year, and detects and corrects abnormally high or low values.

[1011] Step 4: Combining the data

[1012] The server combines pre-processed feedback data with performance metrics data. It integrates feedback data, including data from the emotion engine, with performance metrics data to create an input dataset for the model.

[1013] Specific example: The server combines feedback data (with sentiment scores) and sales data to create a dataset in a format suitable for generative artificial intelligence models.

[1014] Step 5: Setting up and running the generative artificial intelligence model

[1015] The server sets up a generative artificial intelligence model (e.g., GPT-3.5-turbo) and inputs pre-processed data into the model. The model generates organizational challenges and proposed solutions. The model also considers emotional data obtained from an emotion engine.

[1016] Specific example: A server uses a generative AI model as input to a combined dataset and generates suggestions to identify areas where "product quality dissatisfaction" or "improvements to customer support" are needed.

[1017] Step 6: Identifying issues and generating improvement plans

[1018] The server extracts a list of organizational challenges and improvement proposals from text generated by a generative artificial intelligence model, including insights based on sentiment data.

[1019] Specific example: The server identifies "slow customer support response speed" from generated text and proposes "implementing a new CRM system" as an improvement. Furthermore, it identifies "the biggest customer complaint" from sentiment data and proposes specific countermeasures.

[1020] Step 7: Report Generation

[1021] The server generates a report based on the identified issues and suggested improvements. The report is formatted for easy viewing and output in PDF format.

[1022] Specific example: The server uses a report template to organize issues and improvement suggestions into sections, and adds graphs and charts. Sentiment data is visualized to display sentiment trends for specific issues.

[1023] Step 8: Report Distribution

[1024] The server sends the generated reports to the company's management and relevant personnel. The reports are delivered in formats such as email attachments.

[1025] Specific example: The server generates a PDF report, emails it to the responsible person, and saves it to cloud storage for sharing across the entire organization.

[1026] The above outlines the specific processing steps for a system designed to improve a company's organizational performance. This system enables companies to quickly and efficiently identify problems and implement concrete improvement measures. Adding an emotion engine allows for more accurate suggestions that take user emotions into account.

[1027] (Example 2)

[1028] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1029] Modern businesses struggle to efficiently collect and analyze customer feedback and performance data. Furthermore, it's difficult to identify organizational challenges from the collected data and automatically generate concrete improvement plans. Additionally, extracting insights that take user emotions into account and creating improvement plans based on these insights presents another challenge.

[1030] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1031] In this invention, the server includes means for collecting data, means for preprocessing the collected data, means for generating organizational issues and improvement proposals from the preprocessed data using generative artificial intelligence, means for analyzing the emotions of feedback data using an emotion analysis engine, and means for adding emotional data to the feedback data during preprocessing. This enables companies to quickly and efficiently collect and preprocess data and automatically generate specific issues and improvement proposals that take emotional data into account.

[1032] "Means of data collection" refers to devices and methods for efficiently collecting user feedback data and corporate performance indicator data.

[1033] "Methods for preprocessing collected data" refer to techniques for preparing collected data into a format suitable for subsequent analysis or input to generative models, such as text cleaning, normalization, data scaling, and handling of outliers.

[1034] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to a technology that utilizes generative artificial intelligence models (e.g., generative AI models) to automatically generate organizational issues and specific improvement proposals based on pre-processed data.

[1035] "Means for outputting generated issues and improvement proposals as a report" refers to devices or methods that summarize the issues and improvement proposals generated from a generative artificial intelligence model into a visually easy-to-understand report format and output it in PDF format or similar.

[1036] "Methods for analyzing the sentiment of feedback data using a sentiment analysis engine" refers to technologies that automatically recognize and classify the sentiment (positive, negative, neutral, etc.) of the text contained in feedback data.

[1037] "Means for adding emotional data to feedback data in preprocessing" refers to a technique that adds emotional data analyzed by an emotional analysis engine to the feedback text data and further includes it in the preprocessed data.

[1038] This invention is a system for improving the organizational performance of a company. It preprocesses collected data, automatically generates problems and improvement proposals using generative artificial intelligence and an emotion analysis engine, and outputs them as a report. The specific processing of this system is performed by a server.

[1039] First, the server collects user feedback data and company performance metrics data. Users provide customer reviews, survey results, employee opinions, etc. The server collects this feedback data and also retrieves performance metrics data such as sales data, customer acquisition costs, and return rates from the company's internal systems. Furthermore, it analyzes the sentiment of the feedback data using a sentiment analysis engine (e.g., IBM Watson, Google Cloud Natural Language API).

[1040] For example, the server collects customer reviews and monthly sales data for the past six months and stores them in a database. Using a sentiment analysis engine, it classifies the sentiment of customer reviews into three categories: positive, negative, and neutral.

[1041] Next, the server preprocesses the collected data. It cleans the feedback data, performing spell checks on text data and removing unnecessary symbols. It also adds sentiment data to the feedback data. For performance metric data, it normalizes the data, scales it, and handles outliers.

[1042] For example, the server corrects spelling mistakes in feedback and converts sales data into year-on-year percentage changes. The sentiment analysis engine includes information such as "this review is negative" as a result of its analysis.

[1043] The server integrates pre-processed data and inputs it into a generative artificial intelligence model. This generative AI model (e.g., GPT-3.5-turbo) generates organizational challenges and proposed solutions from the input data. The model also considers sentiment data to provide more specific and appropriate challenges and solutions.

[1044] For example, the server inputs user feedback, sentiment data, and sales data into a generative AI model to generate specific suggestions such as "improve customer support response speed."

[1045] The server extracts a list of organizational issues and improvement proposals from the generated text. It also extracts insights based on sentiment data and proposes specific countermeasures.

[1046] For example, the server extracts issues such as "slow response time for customer support" and "marketing strategy for new products" from the generated text and proposes improvement plans such as "implementing a new CRM system" and "designing marketing campaigns using social media." It identifies "customer dissatisfaction" from sentiment data and proposes specific countermeasures.

[1047] Finally, the server generates a report based on the identified issues and proposed improvements. The report is formatted for easy viewing and output in PDF format. The generated report is distributed and shared with the company's management and relevant personnel.

[1048] As a concrete example, the server uses a report template to organize issues and improvement suggestions into sections, adding charts and graphs as needed. It visualizes sentiment data and displays sentiment trends for specific issues. The server emails the generated PDF report to the responsible party and saves it to cloud storage, making it shareable across the entire organization.

[1049] This system enables companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take emotional data into account. By adding an emotional analysis engine, it becomes possible to analyze users' emotions in detail and make more accurate recommendations.

[1050] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1051] Step 1: Data Collection

[1052] The server collects feedback data from users. Specifically, users input customer reviews, survey results, employee opinions, etc., into forms on their terminals and send them to the server. The server stores this data in a database. The server also automatically collects performance indicator data such as sales data, customer acquisition costs, and return rates from the company's internal systems. In this collection process, APIs are used to retrieve the necessary data from databases and ERP systems.

[1053] Input: Customer reviews, survey results, sales data

[1054] Output: Raw data stored in the database

[1055] Step 2: Sentiment analysis of feedback data

[1056] The server performs sentiment analysis on the collected feedback data. Specifically, it uses a sentiment analysis engine to analyze each review and survey response, and assigns positive, negative, or neutral sentiment tags. The server adds the analysis results to the feedback data and stores the updated data back into the database.

[1057] Input: Feedback data

[1058] Output: Feedback data with emotion tags

[1059] Step 3: Data Preprocessing

[1060] The server preprocesses the collected and sentiment-analyzed data. Feedback data undergoes spell checking and removal of unnecessary symbols. Performance metric data is normalized, scaled, and outliers are handled. The preprocessed data is then stored back into the database.

[1061] Input: Collected and sentiment-analyzed data

[1062] Output: Preprocessed data

[1063] Step 4: Preparing input for the generative AI model

[1064] The server integrates pre-processed data and converts it into a format that can be input into a generative artificial intelligence model. In this process, user feedback, sentiment analysis data, and performance data are appropriately combined and prepared in a format that the generative AI model (e.g., GPT-3.5-turbo) can understand.

[1065] Input: Preprocessed data

[1066] Output: Input data for generative AI models

[1067] Step 5: Execute the generative AI model

[1068] The server inputs integrated data into a generative artificial intelligence model. Based on the input data, the generative AI model generates organizational challenges and proposed solutions. A specific prompt might be, "Based on feedback and sales data from the past six months, please propose organizational challenges and solutions." The generated results are returned to the server as a series of text data.

[1069] Input: "Based on feedback and sales data from the past six months, please propose organizational challenges and improvement plans."

[1070] Output: Text data including organizational challenges and proposed improvements.

[1071] Step 6: Identifying issues and improvement proposals

[1072] The server analyzes text data obtained from generative AI models to extract specific problems and proposed solutions. Insights based on sentiment data are also added during this process. The server organizes the problems and solutions and compiles them into data for reporting.

[1073] Input: Text data from a generative AI model

[1074] Output: Organized data on issues and proposed improvements

[1075] Step 7: Generate the report

[1076] The server generates a report based on the identified issues and improvement suggestions. The report is formatted for easy viewing and organized into sections. Charts and graphs are added as needed to visualize sentiment data. The final report is output in PDF format, saved to the database, and then sent to relevant parties.

[1077] Input: Organized problem and improvement proposal data

[1078] Output: Generated PDF report

[1079] This process allows companies to quickly and efficiently identify organizational challenges and implement specific improvement measures that take sentiment data into account.

[1080] (Application Example 2)

[1081] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1082] In modern factory operations, it is essential to effectively collect and analyze data on equipment operation, maintenance issues, and worker feedback, and to implement improvements quickly. However, there is no system in place to efficiently aggregate and analyze this data to generate specific problems and improvement plans. As a result, factory operational efficiency declines, and productivity improvements are hindered.

[1083] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data, means for pre-processing the collected data, means for generating organizational issues and improvement proposals from the pre-processed data using generative artificial intelligence, means for outputting the generated issues and improvement proposals as a report, means for collecting equipment operation data, maintenance history, and worker feedback data from sensors in the factory, means for cleaning the collected data, performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model, and means for visualizing the generated issues and improvement proposals using charts and graphs, outputting a report in PDF format, and distributing it. This makes it possible to efficiently collect and analyze data within the factory and to quickly generate and share specific issues and improvement proposals.

[1084] "Means of collecting data" refers to devices and systems that acquire equipment operation data, maintenance history, employee opinions, etc., from sensors within the factory or feedback from users.

[1085] "Means for preprocessing collected data" refer to methods and systems for improving data quality and maintaining consistency by cleaning acquired data and performing sentiment analysis.

[1086] "A means of generating organizational issues and improvement proposals from pre-processed data using generative artificial intelligence" refers to the application of a generative artificial intelligence model to identify and propose current problems and improvement measures for an organization based on pre-processed data.

[1087] "Means for outputting generated issues and improvement proposals as a report" refers to methods or systems for formatting the generated information in an easy-to-understand manner and creating and outputting a report in a format such as PDF.

[1088] "Means for collecting equipment operation data, maintenance history, and worker feedback data from sensors within the factory" refers to a data collection mechanism based on various sensors installed within the factory and input from employees.

[1089] "Means for performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model" refers to processing procedures and methods for normalizing collected data, applying sentiment analysis, and inputting it into a generative artificial intelligence model in a format useful for that model.

[1090] "A method for visualizing data using charts and graphs, outputting reports in PDF format, and distributing them" refers to a system or method for visually presenting generated data and proposals in an easy-to-understand format, organizing them into a report, and then distributing them to administrators and relevant parties.

[1091] This invention provides a system aimed at automating data collection, analysis, visualization, and feedback in factory operations. Here, we describe specific embodiments for effectively collecting data and automatically generating organizational challenges and improvement proposals using generative artificial intelligence.

[1092] First, the server uses sensors within the factory to collect data on equipment operation, maintenance history, and feedback from workers. This includes data from IoT devices and online feedback forms filled out by employees. Specifically, the server uses an IoT platform (e.g., AWS IoT Core) to collect data and stores it in a database (e.g., Amazon RDS).

[1093] Next, the server preprocesses the collected data. Specifically, it cleans the data and uses an emotion analysis engine (e.g., Hugging Face's Transformers model) to emotionally classify employee feedback. It also normalizes performance metric data and converts it into a consistent data format. The preprocessed data is then manipulated using the Python Pandas library.

[1094] The server then inputs the pre-processed data into a generative artificial intelligence model (e.g., GPT-3.5-turbo) to generate organizational challenges and improvement proposals. The generated information includes specific suggestions for improving work efficiency and optimizing equipment maintenance. Data is input to the generative AI using prompts such as the following:

[1095] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[1096] The issues and improvement proposals generated by the generative artificial intelligence model are visualized by the server. Specifically, a PDF report containing charts and graphs is generated using Python's Matplotlib and ReportLab libraries. This allows stakeholders to understand the current state of the organization in a visually easy-to-understand way and take appropriate improvement measures.

[1097] Finally, the server distributes the generated reports to administrators and relevant parties. This is done by sending the reports via email using a mail server (e.g., SendGrid) or by uploading them to a cloud storage service (e.g., Google Drive).

[1098] As described above, the system of the present invention automates a series of processes from data collection to analysis, report generation, and feedback, thereby improving the efficiency and performance of factory operations.

[1099] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1100] Step 1: Data Collection

[1101] The server collects data using various sensors placed throughout the factory and online feedback forms from employees. Inputs include equipment operation data, maintenance history, and worker feedback data, which are acquired through the IoT platform and stored in a database. Specifically, AWS IoT Core is used to collect various data and store it in Amazon RDS.

[1102] Step 2: Data Preprocessing

[1103] The server cleans the collected data and performs sentiment analysis. The input includes the data collected in the previous step. Data cleaning uses the Python Pandas library to correct incomplete data and spelling errors. Sentiment analysis uses the Hugging Face Transformers model to classify employee feedback emotionally as "positive," "negative," or "neutral." Furthermore, performance metric data is normalized and converted into a consistent data format.

[1104] Step 3: Data integration and input into generative artificial intelligence models

[1105] The server integrates the preprocessed data and inputs it into a generative artificial intelligence model. Specifically, it uses the Python Pandas library to combine the preprocessed data into a dataframe and inputs it into the generative artificial intelligence model (GPT-3.5-turbo). Here, data input is performed using prompt statements. An example of a prompt statement is as follows:

[1106] "Based on equipment operation data and worker feedback data from the past six months, identify challenges within the factory and propose solutions. Include specific suggestions, taking into account the results of the emotional engine analysis. These challenges may include frequent overheating issues and excessive worker stress. Propose solutions such as the implementation of cooling systems and improvements to the work environment."

[1107] Step 4: Generating problems and improvement plans

[1108] The server analyzes the output obtained by the generative artificial intelligence model to identify organizational challenges and improvement suggestions. The input includes text data obtained from the generative artificial intelligence model in the previous step. The output includes a list of specific challenges and corresponding improvement suggestions. For example, "equipment overheating" and "worker stress" might be extracted as challenges, while "implementation of a cooling system" and "improvement of the work environment" might be generated as improvement suggestions.

[1109] Step 5: Report Generation

[1110] The server generates a report based on the generated issues and improvement suggestions. The input includes the list of issues and improvement suggestions obtained in the previous step. Using the Matplotlib and ReportLab libraries in Python, the issues and improvement suggestions are visualized using charts and graphs, and output as a report in PDF format.

[1111] Step 6: Report Distribution

[1112] The server distributes the generated report to the relevant parties. The input includes the generated PDF report. The report can be distributed via email using a mail server (e.g., SendGrid) or uploaded to a cloud storage service (e.g., Google Drive).

[1113] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1114] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1115] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1116] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1117] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1118] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1119] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1120] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1121] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1122] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1123] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1124] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1125] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1126] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1127] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1128] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1129] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1130] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1131] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1132] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1133] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1134] The following is further disclosed regarding the embodiments described above.

[1135] (Claim 1)

[1136] Means of collecting data,

[1137] A means of preprocessing the collected data,

[1138] A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence,

[1139] A means to output the generated issues and improvement proposals as a report,

[1140] A system that includes this.

[1141] (Claim 2)

[1142] The system according to claim 1, which collects user feedback data and performance indicator data.

[1143] (Claim 3)

[1144] The system according to claim 1, which performs cleaning of feedback data and normalization of performance indicator data in the preprocessing stage.

[1145] "Example 1"

[1146] (Claim 1)

[1147] Means of collecting data,

[1148] A means of preprocessing the collected data,

[1149] A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence,

[1150] A means to output the generated issues and improvement proposals as a report,

[1151] A system that includes this.

[1152] (Claim 2)

[1153] The system according to claim 1, which collects user feedback data and organizational performance indicator data.

[1154] (Claim 3)

[1155] The system according to claim 1, which, in the preprocessing stage, cleans and performs sentiment analysis on the text data of the feedback data and normalizes the performance indicator data.

[1156] "Application Example 1"

[1157] (Claim 1)

[1158] Means of collecting data,

[1159] A means of preprocessing the collected data,

[1160] A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence,

[1161] A means to output the generated issues and improvement proposals as a report,

[1162] A means for collecting sensor data and user feedback from in-vehicle devices,

[1163] A means of analyzing collected sensor data and performing sentiment analysis of user feedback,

[1164] A means of generating vehicle performance issues and improvement proposals using generative artificial intelligence,

[1165] A means of outputting a report outlining the performance issues and improvement suggestions related to the generated vehicles,

[1166] A system that includes this.

[1167] (Claim 2)

[1168] The system according to claim 1, which collects user feedback data and performance indicator data.

[1169] (Claim 3)

[1170] The system according to claim 1, which includes collected sensor data, with the preprocessing performed by cleaning the feedback data and normalizing the performance indicator data.

[1171] "Example 2 of combining an emotion engine"

[1172] (Claim 1)

[1173] Means of collecting data,

[1174] A means of preprocessing the collected data,

[1175] A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence,

[1176] A means to output the generated issues and improvement proposals as a report,

[1177] A means of analyzing the emotions in feedback data using an emotion analysis engine,

[1178] A means of adding emotional data to feedback data in preprocessing,

[1179] A system that includes this.

[1180] (Claim 2)

[1181] The system according to claim 1, which collects user feedback data and performance indicator data.

[1182] (Claim 3)

[1183] The system according to claim 1, wherein the preprocessing involves cleaning the feedback data and normalizing the performance indicator data, and integrating the emotional data obtained by the emotional engine.

[1184] "Application example 2 when combining with an emotional engine"

[1185] (Claim 1)

[1186] Means of collecting data,

[1187] A means of preprocessing the collected data,

[1188] A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence,

[1189] A means to output the generated issues and improvement proposals as a report,

[1190] A means of collecting equipment operation data, maintenance history, and worker feedback data from sensors within the factory,

[1191] A method for cleaning collected data, performing sentiment analysis, normalizing performance indicator data, and inputting it into a generative artificial intelligence model,

[1192] Based on the generated issues and improvement proposals, a method is provided to visualize them using charts and graphs, output a report in PDF format, and distribute it.

[1193] A system that includes this.

[1194] (Claim 2)

[1195] The system according to claim 1, which collects user feedback data and performance indicator data.

[1196] (Claim 3)

[1197] The system according to claim 1, which performs cleaning and sentiment analysis of feedback data and normalizes performance indicator data in the preprocessing stage. [Explanation of Symbols]

[1198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting data, A means of preprocessing the collected data, A method for generating organizational challenges and improvement proposals from pre-processed data using generative artificial intelligence, A means to output the generated issues and improvement proposals as a report, A system that includes this.

2. The system according to claim 1, which collects user feedback data and performance indicator data.

3. The system according to claim 1, wherein the preprocessing involves cleaning the feedback data and normalizing the performance indicator data.

Images