system

Abstract

We provide the system. [Solution] Data collection means, A data integration method that standardizes and integrates the collected data, Data analysis tools that perform analysis based on integrated data, A report generation method that generates a report using the analysis results, A report distribution method for distributing the generated 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] The "problems to be solved" and "means for solving the problems" will be described.

[0005] In order to effectively formulate a business strategy, it is necessary to collect, integrate, analyze a wide variety of data, and then create a report based on it. However, in the conventional method, there are problems that these processes take a huge amount of time and labor. In particular, data processing such as data standardization, removal of duplicate data, and completion of missing values takes time, and as a result, the accuracy and speed of analysis may be impaired. In addition, the work of appropriately summarizing the analysis results in a report format is also laborious. Therefore, there is a demand to automate and streamline the series of processes from data collection to report generation.

Means for Solving the Problems

[0006] To solve the above problems, the present invention provides the following means. The present invention provides a system including a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, and a report distribution means for distributing the generated report. Furthermore, in the present invention, the data collection means includes means for automatically acquiring data from multiple external data sources via APIs. The data analysis means also includes means for analyzing data using machine learning algorithms and statistical analysis methods. This makes it possible to automate and streamline the entire process from data collection to analysis, report generation, and distribution.

[0007] "Data collection means" refers to a function or device for collecting data necessary for business strategy from various internal and external data sources.

[0008] A "data integration means" is a function or device for standardizing collected data into a common format, removing duplicate data and imputing missing values ​​as needed, and generating an integrated dataset.

[0009] "Data analysis tools" refer to functions or devices that perform analysis based on integrated data and extract information or patterns useful for business strategy.

[0010] A "report generation means" is a function or device for creating visually easy-to-understand reports or presentation materials using the analysis results obtained by data analysis means.

[0011] "Report distribution means" refers to a function or device for automatically distributing generated reports to designated recipients.

[0012] "API" stands for Application Programming Interface, and it refers to a set of rules or protocols for exchanging data and functions between different software programs.

[0013] A "machine learning algorithm" is a mathematical method or process that learns from a large dataset and automatically performs tasks such as prediction, classification, and optimization.

[0014] "Statistical analysis methods" are mathematical techniques and processes for collecting, organizing, analyzing, and interpreting data, and they form the basis for making data-driven decisions. [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] This shows an emotion map where multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 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 the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

[0019] In the following embodiments, the labeled 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 relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0037] Data collection

[0038] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0039] Data Integration

[0040] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. In the case of collected customer data, if the same customer has been registered multiple times, these entries are integrated into a single record.

[0041] Data Analysis

[0042] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0043] Report generation

[0044] Based on the data analysis results, the server uses a report generation system to create a visually easy-to-understand report. The generated report is in PowerPoint format and includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0045] Report distribution

[0046] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For marketing teams, this eliminates the need for manual report creation and distribution, as they automatically receive weekly market trend reports.

[0047] For example, if a user requires a report to help them develop their next sales strategy, the following process will be performed.

[0048] 1. The user accesses the system and specifies the data they want to collect and its source.

[0049] 2. The server connects to the specified API and collects customer data and market trend data.

[0050] 3. The server standardizes the data, removes duplicate data, and performs necessary interpolation before creating an integrated dataset.

[0051] 4. The server uses data analysis tools to perform clustering and predictive analytics.

[0052] 5. The server automatically generates a report in PowerPoint format based on the analysis results obtained.

[0053] 6. The server delivers the report to the user and uploads it to cloud storage.

[0054] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0055] The following describes the processing flow.

[0056] Step 1:

[0057] The user accesses the system and specifies the type of data they want to collect (e.g., customer data, market trend data) and the data source (e.g., customer relationship management system, market research company).

[0058] Step 2:

[0059] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, to retrieve customer data from a customer management system, the server connects to the system's API and retrieves the latest customer information. The same applies when retrieving market trend data from a market research company.

[0060] Step 3:

[0061] The server stores the collected data in temporary storage. This storage is used to retain the information until the data processing and analysis are complete.

[0062] Step 4:

[0063] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is named differently (e.g., "name" and "full_name"), this will be unified. Additionally, numerical data in text format will be converted to numerical types.

[0064] Step 5:

[0065] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are merged into a single record. If there are missing values, they are imputed using the mean or median.

[0066] Step 6:

[0067] The server analyzes the integrated data using data analysis tools. This process involves extracting meaningful information and patterns from the data using machine learning algorithms and statistical analysis techniques. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0068] Step 7:

[0069] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0070] Step 8:

[0071] The server sends the generated report to the designated recipient's device or email address using the report distribution method. Furthermore, it uploads to cloud storage and generates a sharing link as needed. For example, it can automatically send a weekly market trend report to all members of the marketing department.

[0072] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently.

[0073] (Example 1)

[0074] 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."

[0075] Traditional business strategy planning systems involved separate processes for data collection, integration, analysis, report generation, and distribution, often requiring manual intervention between these steps, resulting in inefficiencies. In particular, the time and effort required for standardizing data collected from different sources, removing duplicates, and imputing missing values ​​made rapid data analysis and timely report distribution difficult, ultimately hindering the rapid development of business strategies.

[0076] 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.

[0077] In this invention, the server includes data collection means, data integration means for standardizing the collected data into a common format, removing duplicate data, and imputing missing values, data analysis means for diagnosing the integrated data and performing clustering and predictive analysis, report generation means for generating reports that visually display the analysis results, and report distribution means for automatically distributing the generated reports. This automates the entire process from data collection to report distribution, enabling the rapid and highly efficient formulation of business strategies.

[0078] "Data collection means" refers to a function that automatically retrieves data from external data sources via an API.

[0079] A "data integration method" is a function that standardizes collected data into a common format, removes duplicate data, and imputes missing values.

[0080] "Data analysis tools" refer to functions that perform clustering and predictive analysis using machine learning algorithms and statistical analysis methods based on integrated data.

[0081] A "report generation method" is a function that automatically generates reports that visually display the results of data analysis.

[0082] A "report distribution method" is a function that automatically distributes generated reports to designated recipients.

[0083] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0084] This system is configured as follows:

[0085] Data collection

[0086] The server automatically retrieves data from various data sources specified by the user using data collection methods. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to APIs of customer relationship management (CRM) systems and market research organizations to collect the necessary data.

[0087] Data Integration

[0088] Since the collected data is typically provided in different formats, the server uses data integration mechanisms to standardize this data into a common format. For example, field names are unified, data types are converted, and duplicate data is removed. In addition, missing values ​​are imputed in an appropriate manner. This allows the server to create a consistent dataset. For example, if the same customer is registered multiple times from multiple data sources, these are integrated into one, retaining the necessary information.

[0089] Data Analysis

[0090] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server clusters customer data to identify customer segments and analyzes purchasing trends for each segment. It also forecasts future sales based on market trend data.

[0091] Report generation

[0092] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report is in PowerPoint format and includes various graphs, charts, and text comments. For example, the report may include bar graphs showing clustering results and line graphs showing market trend analysis results.

[0093] Report distribution

[0094] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. If necessary, they can also be uploaded to cloud storage and a sharing link can be generated. For example, marketing team members can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0095] As a concrete example, consider a scenario where a user needs a report to formulate their next sales strategy. By using the following prompt, the system will automatically perform the necessary processing.

[0096] Example prompt: "Collect customer data and market trend data, and create a report that includes sales forecasts for the next period."

[0097] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

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

[0099] Data collection

[0100] Step 1:

[0101] The user accesses the system from their terminal and specifies the data they want to collect and its data source. As input, the user provides the API endpoint URL and authentication information (such as API key, user ID, and password) for each data source. As output, this information is sent to the server, completing the data collection setup.

[0102] Specific actions:

[0103] Access the user's system data collection settings screen.

[0104] Enter the API information and authentication details for each data source into the form, and then click the "Save Settings" button.

[0105] Step 2:

[0106] The server connects to the API of the data source specified by the user and automatically collects the data. The server sends a GET request to the configured API endpoint and stores the obtained data in temporary storage. As input, the server uses the API endpoint URL and authentication information, and as output, it obtains the collected data.

[0107] Specific actions:

[0108] The server connects to the configured API endpoint.

[0109] Make an API request using authentication credentials.

[0110] The acquired data is saved to temporary storage.

[0111] Data Integration

[0112] Step 3:

[0113] The server standardizes the collected data into a common format. As input, the server reads the collected data and applies standardization rules. As output, it obtains standardized data. This process includes unifying field names and converting data types.

[0114] Specific actions:

[0115] The server reads the data stored in temporary storage.

[0116] Apply mapping rules to standardize field names.

[0117] Convert data types as needed (e.g., convert a string to a number).

[0118] Standardized data is stored in a temporary database.

[0119] Step 4:

[0120] The server removes duplicate data and imputes missing values ​​from standardized data. As input, the server uses standardized data and applies duplicate detection and missing value imputation rules. The output is a clean dataset.

[0121] Specific actions:

[0122] A duplicate detection algorithm is applied to identify duplicate records.

[0123] It merges duplicate records into one and retains the necessary field information.

[0124] For fields with missing values, imputation rules are applied (such as inserting the mean).

[0125] Data Analysis

[0126] Step 5:

[0127] The server performs data analysis using integrated data. As input, the server obtains an integrated dataset and applies machine learning algorithms and statistical analysis techniques. As output, it obtains analysis results, such as customer clustering and sales forecasting.

[0128] Specific actions:

[0129] Load the integrated dataset into the analysis tool.

[0130] Apply the configured machine learning model and statistical methods.

[0131] Save the analysis results.

[0132] Report generation

[0133] Step 6:

[0134] The server automatically generates a report that visually displays the analysis results. As input, the server retrieves the analysis results and inserts the data into a report template. As output, a report in PowerPoint format is generated.

[0135] Specific actions:

[0136] Obtain the analysis results and insert the data into the report template.

[0137] Create visuals using libraries that automatically generate graphs and charts.

[0138] Save the completed report in PowerPoint format.

[0139] Report distribution

[0140] Step 7:

[0141] The server automatically distributes the generated reports to users. As input, the server retrieves user email addresses and recipient lists. As output, the reports are distributed to the specified recipients.

[0142] Specific actions:

[0143] Retrieve the user's email address and subscription list.

[0144] Send the report using the mail server.

[0145] Upload reports using the cloud storage API as needed and generate a sharing link.

[0146] The above is a detailed explanation of each processing step in the system's program. This flow allows users to automate the entire process from data collection to report generation and distribution, enabling them to formulate business strategies with high efficiency.

[0147] (Application Example 1)

[0148] 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."

[0149] In modern business operations, data collection, integration, analysis, and the generation and distribution of reports based on those results are essential. However, effectively performing these processes requires considerable time and effort, and carries a high risk of errors. Furthermore, insufficient mechanisms for quickly sharing generated reports within teams often lead to delayed decision-making. In addition, the integration of data from different data sources and the need for specialized knowledge to perform complex analyses can result in inefficiencies. A system is needed to solve these challenges and enable efficient and rapid data processing and report distribution.

[0150] 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.

[0151] In this invention, the server includes data collection means, data integration means for standardizing and integrating the collected data, data analysis means for performing analysis based on the integrated data, presentation generation means for generating a presentation using the analysis results, presentation distribution means for distributing the generated presentation, and cloud distribution means for uploading the generated presentation to the cloud. This makes it possible to automatically collect data from multiple external data sources via APIs, analyze the data using machine learning algorithms and statistical analysis methods based on the integrated data, automatically generate a presentation based on the results, send the generated presentation to a specified terminal or email address, and further upload it to cloud storage to generate a sharing link.

[0152] A "data collection method" is a means that has the function of automatically acquiring necessary data from external data sources.

[0153] A "data integration method" is a means of standardizing the formats of diverse collected data and combining them into a single integrated dataset.

[0154] "Data analysis methods" refer to methods for performing data analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[0155] A "presentation generation method" is a means of generating presentation materials in a visually easy-to-understand format based on analysis results.

[0156] A "presentation distribution method" is a means of sending a generated presentation to the device or email address of a designated recipient.

[0157] "Cloud distribution method" refers to a method of uploading a generated presentation to cloud storage and creating a sharing link.

[0158] This invention relates to an integrated data processing system for efficiently supporting the formulation of business strategies on e-commerce websites. This system can consistently automate data collection, data integration, data analysis, presentation generation, and presentation distribution.

[0159] Data collection

[0160] The server automatically retrieves data from various external data sources specified by the user using data collection methods. In this case, external data sources include various APIs. For example, the server connects to customer management system APIs and market research APIs to obtain customer purchase data and market trend data.

[0161] Data Integration

[0162] Because the collected data is provided in various formats, the server uses data integration tools to standardize and integrate this data. This process includes unifying field names, converting data types, removing duplicate data, and imputing missing values. The server might use the Pandas library, for example, to integrate the data.

[0163] Data Analysis

[0164] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server uses the scikit-learn library to perform KMeans clustering and customer segmentation.

[0165] Presentation generation

[0166] Based on the data analysis results, the server uses a presentation generation tool to create a visually easy-to-understand report. The generated presentation is in PowerPoint format and includes various graphs, charts, and text comments. For example, graphs generated by the Matplotlib library can be incorporated using the Python-pptx library.

[0167] Presentation delivery

[0168] The generated presentation is sent by the server to the designated recipient's device or email address using a presentation delivery method. Furthermore, it is also possible to upload it to cloud storage using a cloud delivery method and generate a sharing link.

[0169] As a concrete example, consider a scenario where a marketing manager at an e-commerce site plans the next promotional strategy. The server collects customer purchase data and market trend information from a specified API. Next, it integrates the collected data using the Pandas library and performs data analysis using scikit-learn. Based on the results, it generates a PowerPoint presentation using Python-pptx. The generated presentation is sent via email through an SMTP server and uploaded to an FTP server.

[0170] Example prompts for generative AI models

[0171] Create a Python program that uses KMeans clustering to segment customers based on purchase data obtained from an API endpoint, generates a report in PowerPoint format, and distributes it via email.

[0172] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0173] Step 1:

[0174] The user accesses the system and specifies the data they want to collect and its source. The server then receives a list of API endpoints based on the user's specifications as input.

[0175] Step 2:

[0176] The server accesses API endpoints to retrieve data. This process uses the requests library to send HTTP requests to each endpoint and receives data in JSON format. The retrieved data is stored in list format.

[0177] Step 3:

[0178] The server standardizes and integrates the acquired data. Here, the Pandas library is used to convert multiple JSON data sets into a DataFrame, unifying field names, converting data types, removing duplicate data, and imputing missing values. As a result, an integrated, standardized DataFrame is output.

[0179] Step 4:

[0180] The server performs data analysis based on the integrated data. In this step, KMeans clustering is performed using the scikit-learn library to segment customers. The integrated dataframe is taken as input, and a dataframe with each cluster labeled is output.

[0181] Step 5:

[0182] The server generates a presentation based on the analysis results. In this step, the Matplotlib library is used to generate graphs showing the distribution of each cluster, and these are incorporated into a PowerPoint presentation using the Python-pptx library. The output is a completed PowerPoint file.

[0183] Step 6:

[0184] The server delivers the generated presentation to the designated recipients and uploads it to the cloud. It is stored in cloud storage by sending an email using an SMTP server and uploading it to an FTP server. The output includes the email delivery status and a sharing link.

[0185] 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.

[0186] This invention combines a system that automates data collection, data integration, data analysis, report generation, and report distribution—all essential for business strategy planning—with an emotion engine that recognizes user sentiment. This system efficiently performs complex data processing and sentiment analysis by having the server, terminal, and user each fulfill their respective roles.

[0187] Data collection

[0188] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0189] Data Integration

[0190] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. For example, if the same customer has been registered multiple times in customer data, these entries are consolidated into a single record.

[0191] Data Analysis

[0192] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0193] Emotional engine integration

[0194] The server uses an emotion engine to analyze and recognize the user's emotions from voice and facial expression data. This engine can identify emotions in real time while the user is using the system. For example, it can monitor what emotions the user is experiencing during data collection or report generation processes.

[0195] Emotion-based feedback

[0196] The server provides the emotion identification results obtained by the emotion engine as feedback to the report generation system. Based on this feedback, the report content can be optimized. For example, if the user is dissatisfied, the format and content of the generated report can be changed to adjust it to meet the user's needs.

[0197] Data collection optimization

[0198] The server can select which data to collect based on the user's emotions identified by the emotion engine. For example, if a user shows a strong interest in a particular market trend, the server can adjust its settings to prioritize the collection of data in that area.

[0199] Report generation

[0200] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0201] Report distribution

[0202] The generated reports are sent by the server to the designated recipient's device or email address using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0203] As a concrete example, if a user needs a report to develop their next sales strategy, the process would be as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses an API to collect, standardize, and integrate the data, and then performs data analysis. The sentiment engine analyzes the user's emotions in real time and incorporates the feedback into report generation. Finally, the server generates a tailored report and delivers it to the user. This allows the user to develop business strategies efficiently and quickly.

[0204] The following describes the processing flow.

[0205] Step 1:

[0206] The user accesses the system and specifies the type of data they want to collect and the data source. For example, they might specify that they want to collect customer data from a customer relationship management system and market trend data from a market research company.

[0207] Step 2:

[0208] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, it might retrieve the latest customer information from a customer management system or the latest market trend data from a market research company.

[0209] Step 3:

[0210] The server temporarily stores the acquired data in storage. This storage is used to hold the data until processing and analysis are complete.

[0211] Step 4:

[0212] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is different (e.g., "name" and "full_name"), it will be unified. It will also convert numerical data in text format to numerical types.

[0213] Step 5:

[0214] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are consolidated into a single record. Also, if the data contains missing values, the server uses the mean or median to impute them.

[0215] Step 6:

[0216] The server analyzes the integrated data using data analysis tools. This process involves using machine learning algorithms and statistical analysis techniques to extract meaningful information and patterns from the data. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0217] Step 7:

[0218] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's voice and facial expression data to identify, for example, whether the user is interested or dissatisfied during the data collection process.

[0219] Step 8:

[0220] The server incorporates the emotion identification results obtained from the emotion engine as feedback into report generation. For example, if a user is interested in specific data, detailed analysis results based on that data will be added to the report.

[0221] Step 9:

[0222] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. The generated report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0223] Step 10:

[0224] The server sends the generated reports to the designated recipients' devices or email addresses using the report distribution method. Furthermore, it uploads them to cloud storage and generates sharing links as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0225] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently. Furthermore, considering user sentiment allows for more appropriate data analysis and report generation.

[0226] (Example 2)

[0227] 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".

[0228] While conventional data collection and analysis systems could integrate and analyze data from multiple external data sources, they failed to reflect user sentiment in real time, thus failing to adequately enhance user satisfaction and efficiency. Furthermore, the content and format of generated reports were not optimized based on user sentiment, remaining static in their information provision, making it difficult to respond to dynamic business needs. Additionally, the inability to dynamically change the priority of collected data based on user interests made it difficult to provide timely information.

[0229] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion analysis means for analyzing the user's emotions in real time, and a feedback provision means for providing feedback based on the results of the emotion analysis. This makes it possible to collect, analyze, generate and distribute data that reflects the user's emotions in real time, improving user satisfaction and efficiency, and enabling the provision of information that responds to dynamic business needs.

[0230] "Data acquisition means" refers to devices or systems for automatically acquiring data from external data sources.

[0231] "Data integration means" refers to programs or devices used to standardize and integrate collected data.

[0232] "Data analysis tools" refer to programs or devices that perform analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[0233] "Report generation means" refers to programs or devices that generate visually easy-to-understand reports based on the results of data analysis.

[0234] "Report distribution means" refers to a program or device for distributing generated reports to designated recipients.

[0235] "Emotion analysis means" refers to programs or devices that analyze a user's emotions in real time from their voice data and facial expression data.

[0236] "Feedback provision means" refers to programs or devices used to optimize the content and format of reports based on the results of sentiment analysis.

[0237] "External data sources" refer to data providers that exist outside of the system, such as customer management systems or market research companies.

[0238] A "machine learning algorithm" refers to a technology that automatically learns patterns and rules from data and uses them to make predictions and classifications on new data.

[0239] "Statistical analysis techniques" refer to the techniques used to analyze a set of data using statistical methods.

[0240] These definitions will deepen our understanding of the key elements of the patent claims.

[0241] This invention relates to a system that analyzes user emotions in real time and optimizes data collection, integration, analysis, report generation, and distribution based on that analysis. In this system, the server, terminal, and user each have their own roles to perform comprehensive data processing and emotion analysis.

[0242] First, the user logs into the system using a terminal. The user specifies the type of data they want to collect and the data source. Data sources include external data sources such as customer relationship management systems and market research companies.

[0243] The server accesses specified external data sources via APIs (Application Programming Interfaces) and automatically retrieves the necessary data. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to the APIs of customer management systems or market research companies to retrieve data in real time.

[0244] Next, the server standardizes and integrates the collected data using data integration mechanisms. This involves unifying field names and converting data types. It also removes duplicate data and imputes missing values ​​to create a consistent dataset. For example, in the case of customer data, if the same customer is registered as multiple records, these are integrated into a single record.

[0245] The integrated data is analyzed by the server using data analysis tools. Machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. Specifically, customer data is clustered to identify customer segments, and purchasing trends for each segment are analyzed. Furthermore, sales forecasts for the next period are made based on market trend data.

[0246] The system incorporates emotion analysis capabilities that analyze user emotions in real time. It analyzes user voice and facial expression data to identify emotions. For example, if a user experiences joy or dissatisfaction during data collection or report generation, it can be detected immediately.

[0247] The results of the sentiment analysis are provided to the server through a feedback system. Based on this feedback, the server optimizes the content and format of the generated report. If the user is dissatisfied, the visual elements and report content can be improved. It is also possible to dynamically change settings to prioritize the collection of data of high user interest.

[0248] Finally, the server generates a visually easy-to-understand report based on the analysis results and sentiment feedback. The report includes various graphs, charts, and text comments. For example, a bar graph showing customer segmentation results and a line graph showing market trend analysis results are automatically generated and incorporated into the report.

[0249] The generated reports are delivered by the server to the recipient's device or email address. They can also be uploaded to cloud storage and a sharing link can be generated as needed. This reduces the manual effort required for report creation and distribution, as marketing teams receive weekly market trend reports.

[0250] As a concrete example, if a user requires a report for their next sales strategy, the following steps would be taken: The user accesses the system and specifies the type and source of data to be collected. The server uses an API to collect, standardize, and integrate the data, and performs data analysis. Simultaneously, the sentiment engine analyzes the user's emotions in real time and incorporates this feedback into report generation. Finally, the server generates a tailored report and delivers it to the user.

[0251] An example of a prompt is, "Collect data from the customer management system and generate customer segmentation and market trend reports."

[0252] As a result, this system efficiently and quickly automates data collection, integration, analysis, report generation, and distribution, and further improves user satisfaction and efficiency by integrating sentiment analysis.

[0253] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0254] Step 1: Data Collection

[0255] The user logs into the system using a terminal and specifies the type of data to be collected and the data source. As input, they provide API information for customer management systems or market research companies. The server generates and sends API requests to the specified data sources. Specifically, the server retrieves data in JSON or CSV format from the external data sources. As output, the collected data is stored on the server.

[0256] Step 2: Data Integration

[0257] The server stores the collected data in a database. Since input data is often provided in different formats, the server uses data integration tools to standardize this data. Specifically, this involves unifying field names, converting data types, detecting and removing duplicate data, and imputing missing values. For example, it might unify field names like "name" and "full_name" to "name". The output is a consistent dataset.

[0258] Step 3: Data Analysis

[0259] The server takes integrated data stored in the database as input and performs data analysis using machine learning algorithms and statistical analysis techniques. Specifically, it performs clustering, classification, and regression analysis to extract important information. For example, it identifies the results of customer segmentation and analyzes the purchasing trends of each segment. The analysis results are generated as output.

[0260] Step 4: Emotion Analysis

[0261] The server uses emotion analysis tools to analyze the user's emotions in real time, taking their voice and facial expression data as input. Specifically, it analyzes voice and video data collected through microphones and cameras to identify the user's emotions. For example, it detects emotions such as joy or dissatisfaction from changes in voice tone and facial expressions. The emotion analysis results are generated as output.

[0262] Step 5: Provide feedback

[0263] Based on the sentiment analysis results, the server provides feedback to the report generation system using a feedback provision mechanism. Specifically, it optimizes the report content and format based on the user's emotions obtained through sentiment analysis. For example, if the user is dissatisfied, it improves the visual elements and content of the report. As output, an optimized report generation instruction is provided.

[0264] Step 6: Optimizing Data Collection

[0265] The server dynamically changes the priority of data to collect based on sentiment analysis results. It uses data on topics of high user interest as input. Specifically, if a user is interested in a particular market trend, the settings are changed to prioritize data collection in that area. The output is a data collection request with the set priority.

[0266] Step 7: Report Generation

[0267] The server generates a visually easy-to-understand report using a report generation method based on the analysis results and feedback from sentiment analysis. It uses integrated data and feedback information as input. Specifically, it automatically generates various graphs (e.g., bar graphs, line graphs) and charts, and adds text comments. The output is a completed report.

[0268] Step 8: Report Distribution

[0269] The server uses the generated report as input and distributes it to the specified recipient's device or email address. Specifically, it uses the report distribution method to send emails or upload to cloud storage. If necessary, it generates and provides a sharing link. The output consists of the distributed report and the sharing link.

[0270] Through these steps, the system efficiently and quickly automates the entire process from data collection to report delivery, and by integrating sentiment analysis, it can provide optimal feedback based on the user's emotions.

[0271] (Application Example 2)

[0272] 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".

[0273] Traditional systems automate data collection, integration, analysis, and report generation, but they lack dynamic report adjustments based on user emotions, resulting in insufficient user satisfaction and effective decision-making. Furthermore, the absence of mechanisms to reflect user emotions during use prevents improvements in the user experience. Therefore, there is a particular need for efficient and highly satisfying report generation and distribution, especially in the management of physical stores.

[0274] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion engine for recognizing the user's emotions, and a feedback means for dynamically adjusting the content of the report based on the user's emotions. This makes it possible to generate and distribute reports that are dynamically adjusted based on the user's emotions, thereby improving the user experience and achieving effective decision-making.

[0275] "Data acquisition means" refers to a device or software that automatically acquires necessary data from an external data source.

[0276] "Data integration means" refers to a device or software that standardizes the collected data and integrates it in a common format.

[0277] "Data analysis means" refers to a device or software that analyzes the integrated data using machine learning algorithms or statistical analysis methods.

[0278] "Report generation means" refers to a device or software that generates a visually easy-to-understand report based on the results of data analysis.

[0279] "Report distribution means" refers to a device or software that distributes the generated report to specific recipients.

[0280] "Emotion engine" refers to a system that analyzes the user's voice and expression and identifies their emotions in real time.

[0281] "Feedback means" refers to a device or software that dynamically adjusts the content of the report based on the user's emotions identified by the emotion engine.

[0282] These definition texts clarify the meaning of each technical element included in the invention.

[0283] The "Smart Report Assistant" of the present invention is a system that collects, integrates, and analyzes sales data of physical stores, customer feedback, inventory status, regional market trends, etc., and generates and distributes an optimal report for store managers. It also incorporates an emotion engine that recognizes the emotions of users and dynamically adjusts the report content according to the emotions of store managers.

[0284] System Configuration

[0285] 1. The server automatically acquires data from external data sources as data collection means. This includes a POS system, a customer questionnaire system, an ERP system, and a market trend API.

[0286] The server uses data integration means to standardize and integrate the collected data. For example, it performs operations such as unifying field names, converting data types, removing duplicate data, and complementing missing values.

[0287] 3. The server analyzes the integrated data using data analysis means. At this time, machine learning algorithms and statistical analysis methods are used. For example, sales trends, customer segmentation, inventory forecasting, etc. are carried out.

[0288] 4. The server uses an emotion engine to analyze and recognize emotions from the user's voice and expression in real time. This analysis result is used as feedback means to dynamically adjust the report content based on the user's emotions.

[0289] 5. The server uses report generation means to create a visually easy-to-understand report based on the results of data analysis and emotion feedback. Visualization includes various graphs and charts.

[0290] 6. The server distributes the generated report to the specified recipients using report distribution means. Distribution methods include emails and shared links to cloud storage.

[0291] Details of the System

[0292] To implement this invention, the server uses the following specific software and hardware.

[0293] EmotionEngine: Library for recognizing voice and expression (such as Microsoft's (registered trademark) Emotion API and Google's (registered trademark) Cloud Speech-to-Text, etc.)

[0294] <关于将特定软件和硬件用于服务器以实现发明的相关说明,此处英文原文似乎不完整,翻译可能会受影响。]] Data integration library: Software for performing data integration processing

[0295] Report generation library: Software for creating reports

[0296] API access libraries: such as the requests library for retrieving data from external data sources.

[0297] Explanation using specific examples

[0298] For example, if a user needs a report to develop their next sales strategy, the system works as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses APIs to collect, standardize, and integrate data from POS systems, customer survey systems, ERP systems, and market trend APIs. Next, machine learning algorithms and statistical analysis techniques are used to analyze the data and extract information such as sales trends, customer segments, and inventory forecasts. The sentiment engine analyzes the user's emotions in real time while they are using the system and provides feedback based on the results. Finally, the server generates a tailored report and delivers it to the specified recipients.

[0299] Example of a prompt

[0300] "Retrieve sales data from the POS system and collect inventory information from the ERP system. Then, integrate this data and perform data analysis based on customer feedback. Additionally, analyze store managers' emotions using an emotion engine and adjust the report content accordingly."

[0301] As a result, users can make strategic decisions efficiently and with high satisfaction.

[0302] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0303] Step 1:

[0304] The server receives a data collection request specified by the user. The user specifies the type of data to be collected (e.g., sales data, inventory data, customer feedback, market trends) and the data source. The input is the user's specification, based on which the server prepares an API call to access the external data source. The output is the URL and parameter settings of the API call.

[0305] Step 2:

[0306] The server executes the prepared API call and collects data from each data source. This includes a POS system, a customer questionnaire system, an ERP system, and a market trends API. The input is the API call settings, and the output is the collected data. The server temporarily stores the collected data in JSON format.

[0307] Step 3:

[0308] The server standardizes the collected data and integrates it using data integration means. Specifically, it performs tasks such as unifying field names, converting data types, removing duplicate data, and filling in missing values. The input is the collected data, and the output is a standardized integrated dataset.

[0309] Step 4:

[0310] The server analyzes the integrated data using data analysis means. It uses machine learning algorithms and statistical analysis methods to extract information such as sales trends, customer segmentation, and inventory forecasts. The input is the integrated dataset, and the output is the generated report data of the analysis results.

[0311] Step 5:

[0312] The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. The input is audio or video data, and the output is the emotion recognition result. Specifically, the emotion engine performs spectral analysis of the audio waveform and facial expression analysis from the video.

[0313] Step 6:

[0314] The server uses the emotion recognition results obtained from the emotion engine as a feedback mechanism to dynamically adjust the report content. The input is the report data of the emotion recognition results and analysis results, and the output is the adjusted report that reflects the emotion feedback.

[0315] Step 7:

[0316] The server uses a report generation mechanism to create the adjusted report in a visually easy-to-understand format. This visualization includes various graphs and charts. The input is the adjusted report data, and the output is the final report document.

[0317] Step 8:

[0318] The server distributes the generated final report to the designated recipients using a report distribution method. Distribution methods include email and shared links to cloud storage. The input is the final report document, and the output is a delivery completion notification.

[0319] The above describes the specific processing steps and details of each operation for carrying out the present invention.

[0320] 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.

[0321] 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.

[0322] 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.

[0323] [Second Embodiment]

[0324] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0325] 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.

[0326] 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).

[0327] 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.

[0328] 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.

[0329] 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).

[0330] 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.

[0331] 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.

[0332] 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.

[0333] 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.

[0334] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0335] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0336] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0337] Data collection

[0338] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0339] Data Integration

[0340] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. In the case of collected customer data, if the same customer has been registered multiple times, these entries are integrated into a single record.

[0341] Data Analysis

[0342] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0343] Report generation

[0344] Based on the data analysis results, the server uses a report generation system to create a visually easy-to-understand report. The generated report is in PowerPoint format and includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0345] Report distribution

[0346] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For marketing teams, this eliminates the need for manual report creation and distribution, as they automatically receive weekly market trend reports.

[0347] For example, if a user requires a report to help them develop their next sales strategy, the following process will be performed.

[0348] 1. The user accesses the system and specifies the data they want to collect and its source.

[0349] 2. The server connects to the specified API and collects customer data and market trend data.

[0350] 3. The server standardizes the data, removes duplicate data, and performs necessary interpolation before creating an integrated dataset.

[0351] 4. The server uses data analysis tools to perform clustering and predictive analytics.

[0352] 5. The server automatically generates a report in PowerPoint format based on the analysis results obtained.

[0353] 6. The server delivers the report to the user and uploads it to cloud storage.

[0354] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0355] The following describes the processing flow.

[0356] Step 1:

[0357] The user accesses the system and specifies the type of data they want to collect (e.g., customer data, market trend data) and the data source (e.g., customer relationship management system, market research company).

[0358] Step 2:

[0359] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, to retrieve customer data from a customer management system, the server connects to the system's API and retrieves the latest customer information. The same applies when retrieving market trend data from a market research company.

[0360] Step 3:

[0361] The server stores the collected data in temporary storage. This storage is used to retain the information until the data processing and analysis are complete.

[0362] Step 4:

[0363] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is named differently (e.g., "name" and "full_name"), this will be unified. Additionally, numerical data in text format will be converted to numerical types.

[0364] Step 5:

[0365] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are merged into a single record. If there are missing values, they are imputed using the mean or median.

[0366] Step 6:

[0367] The server analyzes the integrated data using data analysis tools. This process involves extracting meaningful information and patterns from the data using machine learning algorithms and statistical analysis techniques. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0368] Step 7:

[0369] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0370] Step 8:

[0371] The server sends the generated report to the designated recipient's device or email address using the report distribution method. Furthermore, it uploads to cloud storage and generates a sharing link as needed. For example, it can automatically send a weekly market trend report to all members of the marketing department.

[0372] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently.

[0373] (Example 1)

[0374] 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."

[0375] Traditional business strategy planning systems involved separate processes for data collection, integration, analysis, report generation, and distribution, often requiring manual intervention between these steps, resulting in inefficiencies. In particular, the time and effort required for standardizing data collected from different sources, removing duplicates, and imputing missing values ​​made rapid data analysis and timely report distribution difficult, ultimately hindering the rapid development of business strategies.

[0376] 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.

[0377] In this invention, the server includes data collection means, data integration means for standardizing the collected data into a common format, removing duplicate data, and imputing missing values, data analysis means for diagnosing the integrated data and performing clustering and predictive analysis, report generation means for generating reports that visually display the analysis results, and report distribution means for automatically distributing the generated reports. This automates the entire process from data collection to report distribution, enabling the rapid and highly efficient formulation of business strategies.

[0378] "Data collection means" refers to a function that automatically retrieves data from external data sources via an API.

[0379] A "data integration method" is a function that standardizes collected data into a common format, removes duplicate data, and imputes missing values.

[0380] "Data analysis tools" refer to functions that perform clustering and predictive analysis using machine learning algorithms and statistical analysis methods based on integrated data.

[0381] A "report generation method" is a function that automatically generates reports that visually display the results of data analysis.

[0382] A "report distribution method" is a function that automatically distributes generated reports to designated recipients.

[0383] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0384] This system is configured as follows:

[0385] Data collection

[0386] The server automatically retrieves data from various data sources specified by the user using data collection methods. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to APIs of customer relationship management (CRM) systems and market research organizations to collect the necessary data.

[0387] Data Integration

[0388] Since the collected data is typically provided in different formats, the server uses data integration mechanisms to standardize this data into a common format. For example, field names are unified, data types are converted, and duplicate data is removed. In addition, missing values ​​are imputed in an appropriate manner. This allows the server to create a consistent dataset. For example, if the same customer is registered multiple times from multiple data sources, these are integrated into one, retaining the necessary information.

[0389] Data Analysis

[0390] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server clusters customer data to identify customer segments and analyzes purchasing trends for each segment. It also forecasts future sales based on market trend data.

[0391] Report generation

[0392] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report is in PowerPoint format and includes various graphs, charts, and text comments. For example, the report may include bar graphs showing clustering results and line graphs showing market trend analysis results.

[0393] Report distribution

[0394] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. If necessary, they can also be uploaded to cloud storage and a sharing link can be generated. For example, marketing team members can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0395] As a concrete example, consider a scenario where a user needs a report to formulate their next sales strategy. By using the following prompt, the system will automatically perform the necessary processing.

[0396] Example prompt: "Collect customer data and market trend data, and create a report that includes sales forecasts for the next period."

[0397] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0398] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0399] Data collection

[0400] Step 1:

[0401] The user accesses the system from their terminal and specifies the data they want to collect and its data source. As input, the user provides the API endpoint URL and authentication information (such as API key, user ID, and password) for each data source. As output, this information is sent to the server, completing the data collection setup.

[0402] Specific actions:

[0403] Access the user's system data collection settings screen.

[0404] Enter the API information and authentication details for each data source into the form, and then click the "Save Settings" button.

[0405] Step 2:

[0406] The server connects to the API of the data source specified by the user and automatically collects the data. The server sends a GET request to the configured API endpoint and stores the obtained data in temporary storage. As input, the server uses the API endpoint URL and authentication information, and as output, it obtains the collected data.

[0407] Specific actions:

[0408] The server connects to the configured API endpoint.

[0409] Make an API request using authentication credentials.

[0410] The acquired data is saved to temporary storage.

[0411] Data Integration

[0412] Step 3:

[0413] The server standardizes the collected data into a common format. As input, the server reads the collected data and applies standardization rules. As output, it obtains standardized data. This process includes unifying field names and converting data types.

[0414] Specific actions:

[0415] The server reads the data stored in temporary storage.

[0416] Apply mapping rules to standardize field names.

[0417] Convert data types as needed (e.g., convert a string to a number).

[0418] Standardized data is stored in a temporary database.

[0419] Step 4:

[0420] The server removes duplicate data and imputes missing values ​​from standardized data. As input, the server uses standardized data and applies duplicate detection and missing value imputation rules. The output is a clean dataset.

[0421] Specific actions:

[0422] A duplicate detection algorithm is applied to identify duplicate records.

[0423] It merges duplicate records into one and retains the necessary field information.

[0424] For fields with missing values, imputation rules are applied (such as inserting the mean).

[0425] Data Analysis

[0426] Step 5:

[0427] The server performs data analysis using integrated data. As input, the server obtains an integrated dataset and applies machine learning algorithms and statistical analysis techniques. As output, it obtains analysis results, such as customer clustering and sales forecasting.

[0428] Specific actions:

[0429] Load the integrated dataset into the analysis tool.

[0430] Apply the configured machine learning model and statistical methods.

[0431] Save the analysis results.

[0432] Report generation

[0433] Step 6:

[0434] The server automatically generates a report that visually displays the analysis results. As input, the server retrieves the analysis results and inserts the data into a report template. As output, a report in PowerPoint format is generated.

[0435] Specific actions:

[0436] Obtain the analysis results and insert the data into the report template.

[0437] Create visuals using libraries that automatically generate graphs and charts.

[0438] Save the completed report in PowerPoint format.

[0439] Report distribution

[0440] Step 7:

[0441] The server automatically distributes the generated reports to users. As input, the server retrieves user email addresses and recipient lists. As output, the reports are distributed to the specified recipients.

[0442] Specific actions:

[0443] Retrieve the user's email address and subscription list.

[0444] Send the report using the mail server.

[0445] Upload reports using the cloud storage API as needed and generate a sharing link.

[0446] The above is a detailed explanation of each processing step in the system's program. This flow allows users to automate the entire process from data collection to report generation and distribution, enabling them to formulate business strategies with high efficiency.

[0447] (Application Example 1)

[0448] 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."

[0449] In modern business operations, data collection, integration, analysis, and the generation and distribution of reports based on those results are essential. However, effectively performing these processes requires considerable time and effort, and carries a high risk of errors. Furthermore, insufficient mechanisms for quickly sharing generated reports within teams often lead to delayed decision-making. In addition, the integration of data from different data sources and the need for specialized knowledge to perform complex analyses can result in inefficiencies. A system is needed to solve these challenges and enable efficient and rapid data processing and report distribution.

[0450] 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.

[0451] In this invention, the server includes data collection means, data integration means for standardizing and integrating the collected data, data analysis means for performing analysis based on the integrated data, presentation generation means for generating a presentation using the analysis results, presentation distribution means for distributing the generated presentation, and cloud distribution means for uploading the generated presentation to the cloud. This makes it possible to automatically collect data from multiple external data sources via APIs, analyze the data using machine learning algorithms and statistical analysis methods based on the integrated data, automatically generate a presentation based on the results, send the generated presentation to a specified terminal or email address, and further upload it to cloud storage to generate a sharing link.

[0452] A "data collection method" is a means that has the function of automatically acquiring necessary data from external data sources.

[0453] A "data integration method" is a means of standardizing the formats of diverse collected data and combining them into a single integrated dataset.

[0454] "Data analysis methods" refer to methods for performing data analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[0455] A "presentation generation method" is a means of generating presentation materials in a visually easy-to-understand format based on analysis results.

[0456] A "presentation distribution method" is a means of sending a generated presentation to the device or email address of a designated recipient.

[0457] "Cloud distribution method" refers to a method of uploading a generated presentation to cloud storage and creating a sharing link.

[0458] This invention relates to an integrated data processing system for efficiently supporting the formulation of business strategies on e-commerce websites. This system can consistently automate data collection, data integration, data analysis, presentation generation, and presentation distribution.

[0459] Data collection

[0460] The server automatically retrieves data from various external data sources specified by the user using data collection methods. In this case, external data sources include various APIs. For example, the server connects to customer management system APIs and market research APIs to obtain customer purchase data and market trend data.

[0461] Data Integration

[0462] Because the collected data is provided in various formats, the server uses data integration tools to standardize and integrate this data. This process includes unifying field names, converting data types, removing duplicate data, and imputing missing values. The server might use the Pandas library, for example, to integrate the data.

[0463] Data Analysis

[0464] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server uses the scikit-learn library to perform KMeans clustering and customer segmentation.

[0465] Presentation generation

[0466] Based on the data analysis results, the server uses a presentation generation tool to create a visually easy-to-understand report. The generated presentation is in PowerPoint format and includes various graphs, charts, and text comments. For example, graphs generated by the Matplotlib library can be incorporated using the Python-pptx library.

[0467] Presentation delivery

[0468] The generated presentation is sent by the server to the designated recipient's device or email address using a presentation delivery method. Furthermore, it is also possible to upload it to cloud storage using a cloud delivery method and generate a sharing link.

[0469] As a concrete example, consider a scenario where a marketing manager at an e-commerce site plans the next promotional strategy. The server collects customer purchase data and market trend information from a specified API. Next, it integrates the collected data using the Pandas library and performs data analysis using scikit-learn. Based on the results, it generates a PowerPoint presentation using Python-pptx. The generated presentation is sent via email through an SMTP server and uploaded to an FTP server.

[0470] Example prompts for generative AI models

[0471] Create a Python program that uses KMeans clustering to segment customers based on purchase data obtained from an API endpoint, generates a report in PowerPoint format, and distributes it via email.

[0472] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0473] Step 1:

[0474] The user accesses the system and specifies the data they want to collect and its source. The server then receives a list of API endpoints based on the user's specifications as input.

[0475] Step 2:

[0476] The server accesses API endpoints to retrieve data. This process uses the requests library to send HTTP requests to each endpoint and receives data in JSON format. The retrieved data is stored in list format.

[0477] Step 3:

[0478] The server standardizes and integrates the acquired data. Here, the Pandas library is used to convert multiple JSON data sets into a DataFrame, unifying field names, converting data types, removing duplicate data, and imputing missing values. As a result, an integrated, standardized DataFrame is output.

[0479] Step 4:

[0480] The server performs data analysis based on the integrated data. In this step, KMeans clustering is performed using the scikit-learn library to segment customers. The integrated dataframe is taken as input, and a dataframe with each cluster labeled is output.

[0481] Step 5:

[0482] The server generates a presentation based on the analysis results. In this step, the Matplotlib library is used to generate graphs showing the distribution of each cluster, and these are incorporated into a PowerPoint presentation using the Python-pptx library. The output is a completed PowerPoint file.

[0483] Step 6:

[0484] The server delivers the generated presentation to the designated recipients and uploads it to the cloud. It is stored in cloud storage by sending an email using an SMTP server and uploading it to an FTP server. The output includes the email delivery status and a sharing link.

[0485] 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.

[0486] This invention combines a system that automates data collection, data integration, data analysis, report generation, and report distribution—all essential for business strategy planning—with an emotion engine that recognizes user sentiment. This system efficiently performs complex data processing and sentiment analysis by having the server, terminal, and user each fulfill their respective roles.

[0487] Data collection

[0488] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0489] Data Integration

[0490] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. For example, if the same customer has been registered multiple times in customer data, these entries are consolidated into a single record.

[0491] Data Analysis

[0492] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0493] Emotional engine integration

[0494] The server uses an emotion engine to analyze and recognize the user's emotions from voice and facial expression data. This engine can identify emotions in real time while the user is using the system. For example, it can monitor what emotions the user is experiencing during data collection or report generation processes.

[0495] Emotion-based feedback

[0496] The server provides the emotion identification results obtained by the emotion engine as feedback to the report generation system. Based on this feedback, the report content can be optimized. For example, if the user is dissatisfied, the format and content of the generated report can be changed to adjust it to meet the user's needs.

[0497] Data collection optimization

[0498] The server can select which data to collect based on the user's emotions identified by the emotion engine. For example, if a user shows a strong interest in a particular market trend, the server can adjust its settings to prioritize the collection of data in that area.

[0499] Report generation

[0500] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0501] Report distribution

[0502] The generated reports are sent by the server to the designated recipient's device or email address using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0503] As a concrete example, if a user needs a report to develop their next sales strategy, the process would be as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses an API to collect, standardize, and integrate the data, and then performs data analysis. The sentiment engine analyzes the user's emotions in real time and incorporates the feedback into report generation. Finally, the server generates a tailored report and delivers it to the user. This allows the user to develop business strategies efficiently and quickly.

[0504] The following describes the processing flow.

[0505] Step 1:

[0506] The user accesses the system and specifies the type of data they want to collect and the data source. For example, they might specify that they want to collect customer data from a customer relationship management system and market trend data from a market research company.

[0507] Step 2:

[0508] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, it might retrieve the latest customer information from a customer management system or the latest market trend data from a market research company.

[0509] Step 3:

[0510] The server temporarily stores the acquired data in storage. This storage is used to hold the data until processing and analysis are complete.

[0511] Step 4:

[0512] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is different (e.g., "name" and "full_name"), it will be unified. It will also convert numerical data in text format to numerical types.

[0513] Step 5:

[0514] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are consolidated into a single record. Also, if the data contains missing values, the server uses the mean or median to impute them.

[0515] Step 6:

[0516] The server analyzes the integrated data using data analysis tools. This process involves using machine learning algorithms and statistical analysis techniques to extract meaningful information and patterns from the data. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0517] Step 7:

[0518] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's voice and facial expression data to identify, for example, whether the user is interested or dissatisfied during the data collection process.

[0519] Step 8:

[0520] The server incorporates the emotion identification results obtained from the emotion engine as feedback into report generation. For example, if a user is interested in specific data, detailed analysis results based on that data will be added to the report.

[0521] Step 9:

[0522] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. The generated report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0523] Step 10:

[0524] The server sends the generated reports to the designated recipients' devices or email addresses using the report distribution method. Furthermore, it uploads them to cloud storage and generates sharing links as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0525] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently. Furthermore, considering user sentiment allows for more appropriate data analysis and report generation.

[0526] (Example 2)

[0527] 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".

[0528] While conventional data collection and analysis systems could integrate and analyze data from multiple external data sources, they failed to reflect user sentiment in real time, thus failing to adequately enhance user satisfaction and efficiency. Furthermore, the content and format of generated reports were not optimized based on user sentiment, remaining static in their information provision, making it difficult to respond to dynamic business needs. Additionally, the inability to dynamically change the priority of collected data based on user interests made it difficult to provide timely information.

[0529] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion analysis means for analyzing the user's emotions in real time, and a feedback provision means for providing feedback based on the results of the emotion analysis. This makes it possible to collect, analyze, generate and distribute data that reflects the user's emotions in real time, improving user satisfaction and efficiency, and enabling the provision of information that responds to dynamic business needs.

[0530] "Data acquisition means" refers to devices or systems for automatically acquiring data from external data sources.

[0531] "Data integration means" refers to programs or devices used to standardize and integrate collected data.

[0532] "Data analysis tools" refer to programs or devices that perform analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[0533] "Report generation means" refers to programs or devices that generate visually easy-to-understand reports based on the results of data analysis.

[0534] "Report distribution means" refers to a program or device for distributing generated reports to designated recipients.

[0535] "Emotion analysis means" refers to programs or devices that analyze a user's emotions in real time from their voice data and facial expression data.

[0536] "Feedback provision means" refers to programs or devices used to optimize the content and format of reports based on the results of sentiment analysis.

[0537] "External data sources" refer to data providers that exist outside of the system, such as customer management systems or market research companies.

[0538] A "machine learning algorithm" refers to a technology that automatically learns patterns and rules from data and uses them to make predictions and classifications on new data.

[0539] "Statistical analysis techniques" refer to the techniques used to analyze a set of data using statistical methods.

[0540] These definitions will deepen our understanding of the key elements of the patent claims.

[0541] This invention relates to a system that analyzes user emotions in real time and optimizes data collection, integration, analysis, report generation, and distribution based on that analysis. In this system, the server, terminal, and user each have their own roles to perform comprehensive data processing and emotion analysis.

[0542] First, the user logs into the system using a terminal. The user specifies the type of data they want to collect and the data source. Data sources include external data sources such as customer relationship management systems and market research companies.

[0543] The server accesses specified external data sources via APIs (Application Programming Interfaces) and automatically retrieves the necessary data. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to the APIs of customer management systems or market research companies to retrieve data in real time.

[0544] Next, the server standardizes and integrates the collected data using data integration mechanisms. This involves unifying field names and converting data types. It also removes duplicate data and imputes missing values ​​to create a consistent dataset. For example, in the case of customer data, if the same customer is registered as multiple records, these are integrated into a single record.

[0545] The integrated data is analyzed by the server using data analysis tools. Machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. Specifically, customer data is clustered to identify customer segments, and purchasing trends for each segment are analyzed. Furthermore, sales forecasts for the next period are made based on market trend data.

[0546] The system incorporates emotion analysis capabilities that analyze user emotions in real time. It analyzes user voice and facial expression data to identify emotions. For example, if a user experiences joy or dissatisfaction during data collection or report generation, it can be detected immediately.

[0547] The results of the sentiment analysis are provided to the server through a feedback system. Based on this feedback, the server optimizes the content and format of the generated report. If the user is dissatisfied, the visual elements and report content can be improved. It is also possible to dynamically change settings to prioritize the collection of data of high user interest.

[0548] Finally, the server generates a visually easy-to-understand report based on the analysis results and sentiment feedback. The report includes various graphs, charts, and text comments. For example, a bar graph showing customer segmentation results and a line graph showing market trend analysis results are automatically generated and incorporated into the report.

[0549] The generated reports are delivered by the server to the recipient's device or email address. They can also be uploaded to cloud storage and a sharing link can be generated as needed. This reduces the manual effort required for report creation and distribution, as marketing teams receive weekly market trend reports.

[0550] As a concrete example, if a user requires a report for their next sales strategy, the following steps would be taken: The user accesses the system and specifies the type and source of data to be collected. The server uses an API to collect, standardize, and integrate the data, and performs data analysis. Simultaneously, the sentiment engine analyzes the user's emotions in real time and incorporates this feedback into report generation. Finally, the server generates a tailored report and delivers it to the user.

[0551] An example of a prompt is, "Collect data from the customer management system and generate customer segmentation and market trend reports."

[0552] As a result, this system efficiently and quickly automates data collection, integration, analysis, report generation, and distribution, and further improves user satisfaction and efficiency by integrating sentiment analysis.

[0553] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0554] Step 1: Data Collection

[0555] The user logs into the system using a terminal and specifies the type of data to be collected and the data source. As input, they provide API information for customer management systems or market research companies. The server generates and sends API requests to the specified data sources. Specifically, the server retrieves data in JSON or CSV format from the external data sources. As output, the collected data is stored on the server.

[0556] Step 2: Data Integration

[0557] The server stores the collected data in a database. Since input data is often provided in different formats, the server uses data integration tools to standardize this data. Specifically, this involves unifying field names, converting data types, detecting and removing duplicate data, and imputing missing values. For example, it might unify field names like "name" and "full_name" to "name". The output is a consistent dataset.

[0558] Step 3: Data Analysis

[0559] The server takes integrated data stored in the database as input and performs data analysis using machine learning algorithms and statistical analysis techniques. Specifically, it performs clustering, classification, and regression analysis to extract important information. For example, it identifies the results of customer segmentation and analyzes the purchasing trends of each segment. The analysis results are generated as output.

[0560] Step 4: Emotion Analysis

[0561] The server uses emotion analysis tools to analyze the user's emotions in real time, taking their voice and facial expression data as input. Specifically, it analyzes voice and video data collected through microphones and cameras to identify the user's emotions. For example, it detects emotions such as joy or dissatisfaction from changes in voice tone and facial expressions. The emotion analysis results are generated as output.

[0562] Step 5: Provide feedback

[0563] Based on the sentiment analysis results, the server provides feedback to the report generation system using a feedback provision mechanism. Specifically, it optimizes the report content and format based on the user's emotions obtained through sentiment analysis. For example, if the user is dissatisfied, it improves the visual elements and content of the report. As output, an optimized report generation instruction is provided.

[0564] Step 6: Optimizing Data Collection

[0565] The server dynamically changes the priority of data to collect based on sentiment analysis results. It uses data on topics of high user interest as input. Specifically, if a user is interested in a particular market trend, the settings are changed to prioritize data collection in that area. The output is a data collection request with the set priority.

[0566] Step 7: Report Generation

[0567] The server generates a visually easy-to-understand report using a report generation method based on the analysis results and feedback from sentiment analysis. It uses integrated data and feedback information as input. Specifically, it automatically generates various graphs (e.g., bar graphs, line graphs) and charts, and adds text comments. The output is a completed report.

[0568] Step 8: Report Distribution

[0569] The server uses the generated report as input and distributes it to the specified recipient's device or email address. Specifically, it uses the report distribution method to send emails or upload to cloud storage. If necessary, it generates and provides a sharing link. The output consists of the distributed report and the sharing link.

[0570] Through these steps, the system efficiently and quickly automates the entire process from data collection to report delivery, and by integrating sentiment analysis, it can provide optimal feedback based on the user's emotions.

[0571] (Application Example 2)

[0572] 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."

[0573] Traditional systems automate data collection, integration, analysis, and report generation, but they lack dynamic report adjustments based on user emotions, resulting in insufficient user satisfaction and effective decision-making. Furthermore, the absence of mechanisms to reflect user emotions during use prevents improvements in the user experience. Therefore, there is a particular need for efficient and highly satisfying report generation and distribution, especially in the management of physical stores.

[0574] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion engine for recognizing the user's emotions, and a feedback means for dynamically adjusting the content of the report based on the user's emotions. This makes it possible to generate and distribute reports that are dynamically adjusted based on the user's emotions, thereby improving the user experience and achieving effective decision-making.

[0575] "Data acquisition means" refers to a device or software that automatically acquires necessary data from an external data source.

[0576] "Data integration means" refers to a device or software that standardizes collected data and integrates it in a common format.

[0577] "Data analysis tools" refer to devices or software that perform analysis on integrated data using machine learning algorithms or statistical analysis methods.

[0578] A "report generation means" is a device or software that generates a visually easy-to-understand report based on the results of data analysis.

[0579] "Report distribution means" refers to a device or software that distributes generated reports to specific recipients.

[0580] An "emotion engine" is a system that analyzes a user's voice and facial expressions to identify their emotions in real time.

[0581] A "feedback mechanism" is a device or software that dynamically adjusts the content of a report based on the user's emotions identified by the emotion engine.

[0582] These definitions clarify the meaning of each technical element included in the invention.

[0583] The "Smart Report Assistant" of this invention is a system that collects, integrates, and analyzes sales data from physical stores, customer feedback, inventory status, and regional market trends, and generates and delivers optimal reports for store managers. It also incorporates an emotion engine that recognizes user emotions and dynamically adjusts the report content based on the store manager's feelings.

[0584] System Configuration

[0585] 1. The server automatically acquires data from external data sources as a means of data collection. This includes POS systems, customer survey systems, ERP systems, and market trend APIs.

[0586] 2. The server uses data integration means to standardize and integrate the collected data. For example, this includes unifying field names, converting data types, removing duplicate data, and imputing missing values.

[0587] 3. The server analyzes the integrated data using data analysis tools. This involves using machine learning algorithms and statistical analysis techniques. For example, it may analyze sales trends, perform customer segmentation, and forecast inventory.

[0588] 4. The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. This analysis result is used as feedback to dynamically adjust the report content based on the user's emotions.

[0589] 5. The server uses a report generation mechanism to create a visually easy-to-understand report based on the data analysis results and sentiment feedback. This visualization includes various graphs and charts.

[0590] 6. The server distributes the generated report to the designated recipient using a report distribution method. Distribution methods include email and shared links to cloud storage.

[0591] System details

[0592] To realize this invention, the server uses the following specific software and hardware.

[0593] EmotionEngine: A voice and facial expression recognition library (similar to Microsoft's Emotion API and Google's Cloud Speech-to-Text).

[0594] Data Integration Library: Software that performs data integration processing.

[0595] Report generation library: Software for creating reports

[0596] API access libraries: such as the requests library for retrieving data from external data sources.

[0597] Explanation using specific examples

[0598] For example, if a user needs a report to develop their next sales strategy, the system works as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses APIs to collect, standardize, and integrate data from POS systems, customer survey systems, ERP systems, and market trend APIs. Next, machine learning algorithms and statistical analysis techniques are used to analyze the data and extract information such as sales trends, customer segments, and inventory forecasts. The sentiment engine analyzes the user's emotions in real time while they are using the system and provides feedback based on the results. Finally, the server generates a tailored report and delivers it to the specified recipients.

[0599] Example of a prompt

[0600] "Retrieve sales data from the POS system and collect inventory information from the ERP system. Then, integrate this data and perform data analysis based on customer feedback. Additionally, analyze store managers' emotions using an emotion engine and adjust the report content accordingly."

[0601] As a result, users can make strategic decisions efficiently and with high satisfaction.

[0602] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0603] Step 1:

[0604] The server receives a data collection request specified by the user. The user specifies the type of data to be collected (e.g., sales data, inventory data, customer feedback, market trends) and the data source. The input is the user's specifications, and based on this, the server prepares an API call to access the external data source. The output is the URL and parameter settings of the API call.

[0605] Step 2:

[0606] The server executes the prepared API calls and collects data from each data source. This includes POS systems, customer survey systems, ERP systems, and market trend APIs. The input is the API call configuration, and the output is the retrieved data. The server temporarily stores the collected data in JSON format.

[0607] Step 3:

[0608] The server standardizes the collected data and integrates it using data integration tools. Specifically, it unifies field names, converts data types, removes duplicate data, and imputes missing values. The input is the collected data, and the output is a standardized, integrated dataset.

[0609] Step 4:

[0610] The server analyzes the integrated data using data analysis tools. It employs machine learning algorithms and statistical analysis techniques to extract information such as sales trends, customer segmentation, and inventory forecasts. The input is the integrated dataset, and the output is the generated report data of the analysis results.

[0611] Step 5:

[0612] The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. The input is audio or video data, and the output is the emotion recognition result. Specifically, the emotion engine performs spectral analysis of the audio waveform and facial expression analysis from the video.

[0613] Step 6:

[0614] The server uses the emotion recognition results obtained from the emotion engine as a feedback mechanism to dynamically adjust the report content. The input is the report data of the emotion recognition results and analysis results, and the output is the adjusted report that reflects the emotion feedback.

[0615] Step 7:

[0616] The server uses a report generation mechanism to create the adjusted report in a visually easy-to-understand format. This visualization includes various graphs and charts. The input is the adjusted report data, and the output is the final report document.

[0617] Step 8:

[0618] The server distributes the generated final report to the designated recipients using a report distribution method. Distribution methods include email and shared links to cloud storage. The input is the final report document, and the output is a delivery completion notification.

[0619] The above describes the specific processing steps and details of each operation for carrying out the present invention.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] [Third Embodiment]

[0624] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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".

[0636] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0637] Data collection

[0638] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0639] Data Integration

[0640] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. In the case of collected customer data, if the same customer has been registered multiple times, these entries are integrated into a single record.

[0641] Data Analysis

[0642] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0643] Report generation

[0644] Based on the data analysis results, the server uses a report generation system to create a visually easy-to-understand report. The generated report is in PowerPoint format and includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0645] Report distribution

[0646] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For marketing teams, this eliminates the need for manual report creation and distribution, as they automatically receive weekly market trend reports.

[0647] For example, if a user requires a report to help them develop their next sales strategy, the following process will be performed.

[0648] 1. The user accesses the system and specifies the data they want to collect and its source.

[0649] 2. The server connects to the specified API and collects customer data and market trend data.

[0650] 3. The server standardizes the data, removes duplicate data, and performs necessary interpolation before creating an integrated dataset.

[0651] 4. The server uses data analysis tools to perform clustering and predictive analytics.

[0652] 5. The server automatically generates a report in PowerPoint format based on the analysis results obtained.

[0653] 6. The server delivers the report to the user and uploads it to cloud storage.

[0654] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] The user accesses the system and specifies the type of data they want to collect (e.g., customer data, market trend data) and the data source (e.g., customer relationship management system, market research company).

[0658] Step 2:

[0659] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, to retrieve customer data from a customer management system, the server connects to the system's API and retrieves the latest customer information. The same applies when retrieving market trend data from a market research company.

[0660] Step 3:

[0661] The server stores the collected data in temporary storage. This storage is used to retain the information until the data processing and analysis are complete.

[0662] Step 4:

[0663] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is named differently (e.g., "name" and "full_name"), this will be unified. Additionally, numerical data in text format will be converted to numerical types.

[0664] Step 5:

[0665] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are merged into a single record. If there are missing values, they are imputed using the mean or median.

[0666] Step 6:

[0667] The server analyzes the integrated data using data analysis tools. This process involves extracting meaningful information and patterns from the data using machine learning algorithms and statistical analysis techniques. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0668] Step 7:

[0669] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0670] Step 8:

[0671] The server sends the generated report to the designated recipient's device or email address using the report distribution method. Furthermore, it uploads to cloud storage and generates a sharing link as needed. For example, it can automatically send a weekly market trend report to all members of the marketing department.

[0672] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently.

[0673] (Example 1)

[0674] 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."

[0675] Traditional business strategy planning systems involved separate processes for data collection, integration, analysis, report generation, and distribution, often requiring manual intervention between these steps, resulting in inefficiencies. In particular, the time and effort required for standardizing data collected from different sources, removing duplicates, and imputing missing values ​​made rapid data analysis and timely report distribution difficult, ultimately hindering the rapid development of business strategies.

[0676] 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.

[0677] In this invention, the server includes data collection means, data integration means for standardizing the collected data into a common format, removing duplicate data, and imputing missing values, data analysis means for diagnosing the integrated data and performing clustering and predictive analysis, report generation means for generating reports that visually display the analysis results, and report distribution means for automatically distributing the generated reports. This automates the entire process from data collection to report distribution, enabling the rapid and highly efficient formulation of business strategies.

[0678] "Data collection means" refers to a function that automatically retrieves data from external data sources via an API.

[0679] A "data integration method" is a function that standardizes collected data into a common format, removes duplicate data, and imputes missing values.

[0680] "Data analysis tools" refer to functions that perform clustering and predictive analysis using machine learning algorithms and statistical analysis methods based on integrated data.

[0681] A "report generation method" is a function that automatically generates reports that visually display the results of data analysis.

[0682] A "report distribution method" is a function that automatically distributes generated reports to designated recipients.

[0683] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0684] This system is configured as follows:

[0685] Data collection

[0686] The server automatically retrieves data from various data sources specified by the user using data collection methods. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to APIs of customer relationship management (CRM) systems and market research organizations to collect the necessary data.

[0687] Data Integration

[0688] Since the collected data is typically provided in different formats, the server uses data integration mechanisms to standardize this data into a common format. For example, field names are unified, data types are converted, and duplicate data is removed. In addition, missing values ​​are imputed in an appropriate manner. This allows the server to create a consistent dataset. For example, if the same customer is registered multiple times from multiple data sources, these are integrated into one, retaining the necessary information.

[0689] Data Analysis

[0690] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server clusters customer data to identify customer segments and analyzes purchasing trends for each segment. It also forecasts future sales based on market trend data.

[0691] Report generation

[0692] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report is in PowerPoint format and includes various graphs, charts, and text comments. For example, the report may include bar graphs showing clustering results and line graphs showing market trend analysis results.

[0693] Report distribution

[0694] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. If necessary, they can also be uploaded to cloud storage and a sharing link can be generated. For example, marketing team members can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0695] As a concrete example, consider a scenario where a user needs a report to formulate their next sales strategy. By using the following prompt, the system will automatically perform the necessary processing.

[0696] Example prompt: "Collect customer data and market trend data, and create a report that includes sales forecasts for the next period."

[0697] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0698] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0699] Data collection

[0700] Step 1:

[0701] The user accesses the system from their terminal and specifies the data they want to collect and its data source. As input, the user provides the API endpoint URL and authentication information (such as API key, user ID, and password) for each data source. As output, this information is sent to the server, completing the data collection setup.

[0702] Specific actions:

[0703] Access the user's system data collection settings screen.

[0704] Enter the API information and authentication details for each data source into the form, and then click the "Save Settings" button.

[0705] Step 2:

[0706] The server connects to the API of the data source specified by the user and automatically collects the data. The server sends a GET request to the configured API endpoint and stores the obtained data in temporary storage. As input, the server uses the API endpoint URL and authentication information, and as output, it obtains the collected data.

[0707] Specific actions:

[0708] The server connects to the configured API endpoint.

[0709] Make an API request using authentication credentials.

[0710] The acquired data is saved to temporary storage.

[0711] Data Integration

[0712] Step 3:

[0713] The server standardizes the collected data into a common format. As input, the server reads the collected data and applies standardization rules. As output, it obtains standardized data. This process includes unifying field names and converting data types.

[0714] Specific actions:

[0715] The server reads the data stored in temporary storage.

[0716] Apply mapping rules to standardize field names.

[0717] Convert data types as needed (e.g., convert a string to a number).

[0718] Standardized data is stored in a temporary database.

[0719] Step 4:

[0720] The server removes duplicate data and imputes missing values ​​from standardized data. As input, the server uses standardized data and applies duplicate detection and missing value imputation rules. The output is a clean dataset.

[0721] Specific actions:

[0722] A duplicate detection algorithm is applied to identify duplicate records.

[0723] It merges duplicate records into one and retains the necessary field information.

[0724] For fields with missing values, imputation rules are applied (such as inserting the mean).

[0725] Data Analysis

[0726] Step 5:

[0727] The server performs data analysis using integrated data. As input, the server obtains an integrated dataset and applies machine learning algorithms and statistical analysis techniques. As output, it obtains analysis results, such as customer clustering and sales forecasting.

[0728] Specific actions:

[0729] Load the integrated dataset into the analysis tool.

[0730] Apply the configured machine learning model and statistical methods.

[0731] Save the analysis results.

[0732] Report generation

[0733] Step 6:

[0734] The server automatically generates a report that visually displays the analysis results. As input, the server retrieves the analysis results and inserts the data into a report template. As output, a report in PowerPoint format is generated.

[0735] Specific actions:

[0736] Obtain the analysis results and insert the data into the report template.

[0737] Create visuals using libraries that automatically generate graphs and charts.

[0738] Save the completed report in PowerPoint format.

[0739] Report distribution

[0740] Step 7:

[0741] The server automatically distributes the generated reports to users. As input, the server retrieves user email addresses and recipient lists. As output, the reports are distributed to the specified recipients.

[0742] Specific actions:

[0743] Retrieve the user's email address and subscription list.

[0744] Send the report using the mail server.

[0745] Upload reports using the cloud storage API as needed and generate a sharing link.

[0746] The above is a detailed explanation of each processing step in the system's program. This flow allows users to automate the entire process from data collection to report generation and distribution, enabling them to formulate business strategies with high efficiency.

[0747] (Application Example 1)

[0748] 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."

[0749] In modern business operations, data collection, integration, analysis, and the generation and distribution of reports based on those results are essential. However, effectively performing these processes requires considerable time and effort, and carries a high risk of errors. Furthermore, insufficient mechanisms for quickly sharing generated reports within teams often lead to delayed decision-making. In addition, the integration of data from different data sources and the need for specialized knowledge to perform complex analyses can result in inefficiencies. A system is needed to solve these challenges and enable efficient and rapid data processing and report distribution.

[0750] 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.

[0751] In this invention, the server includes data collection means, data integration means for standardizing and integrating the collected data, data analysis means for performing analysis based on the integrated data, presentation generation means for generating a presentation using the analysis results, presentation distribution means for distributing the generated presentation, and cloud distribution means for uploading the generated presentation to the cloud. This makes it possible to automatically collect data from multiple external data sources via APIs, analyze the data using machine learning algorithms and statistical analysis methods based on the integrated data, automatically generate a presentation based on the results, send the generated presentation to a specified terminal or email address, and further upload it to cloud storage to generate a sharing link.

[0752] A "data collection method" is a means that has the function of automatically acquiring necessary data from external data sources.

[0753] A "data integration method" is a means of standardizing the formats of diverse collected data and combining them into a single integrated dataset.

[0754] "Data analysis methods" refer to methods for performing data analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[0755] A "presentation generation method" is a means of generating presentation materials in a visually easy-to-understand format based on analysis results.

[0756] A "presentation distribution method" is a means of sending a generated presentation to the device or email address of a designated recipient.

[0757] "Cloud distribution method" refers to a method of uploading a generated presentation to cloud storage and creating a sharing link.

[0758] This invention relates to an integrated data processing system for efficiently supporting the formulation of business strategies on e-commerce websites. This system can consistently automate data collection, data integration, data analysis, presentation generation, and presentation distribution.

[0759] Data collection

[0760] The server automatically retrieves data from various external data sources specified by the user using data collection methods. In this case, external data sources include various APIs. For example, the server connects to customer management system APIs and market research APIs to obtain customer purchase data and market trend data.

[0761] Data Integration

[0762] Because the collected data is provided in various formats, the server uses data integration tools to standardize and integrate this data. This process includes unifying field names, converting data types, removing duplicate data, and imputing missing values. The server might use the Pandas library, for example, to integrate the data.

[0763] Data Analysis

[0764] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server uses the scikit-learn library to perform KMeans clustering and customer segmentation.

[0765] Presentation generation

[0766] Based on the data analysis results, the server uses a presentation generation tool to create a visually easy-to-understand report. The generated presentation is in PowerPoint format and includes various graphs, charts, and text comments. For example, graphs generated by the Matplotlib library can be incorporated using the Python-pptx library.

[0767] Presentation delivery

[0768] The generated presentation is sent by the server to the designated recipient's device or email address using a presentation delivery method. Furthermore, it is also possible to upload it to cloud storage using a cloud delivery method and generate a sharing link.

[0769] As a concrete example, consider a scenario where a marketing manager at an e-commerce site plans the next promotional strategy. The server collects customer purchase data and market trend information from a specified API. Next, it integrates the collected data using the Pandas library and performs data analysis using scikit-learn. Based on the results, it generates a PowerPoint presentation using Python-pptx. The generated presentation is sent via email through an SMTP server and uploaded to an FTP server.

[0770] Example prompts for generative AI models

[0771] Create a Python program that uses KMeans clustering to segment customers based on purchase data obtained from an API endpoint, generates a report in PowerPoint format, and distributes it via email.

[0772] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0773] Step 1:

[0774] The user accesses the system and specifies the data they want to collect and its source. The server then receives a list of API endpoints based on the user's specifications as input.

[0775] Step 2:

[0776] The server accesses API endpoints to retrieve data. This process uses the requests library to send HTTP requests to each endpoint and receives data in JSON format. The retrieved data is stored in list format.

[0777] Step 3:

[0778] The server standardizes and integrates the acquired data. Here, the Pandas library is used to convert multiple JSON data sets into a DataFrame, unifying field names, converting data types, removing duplicate data, and imputing missing values. As a result, an integrated, standardized DataFrame is output.

[0779] Step 4:

[0780] The server performs data analysis based on the integrated data. In this step, KMeans clustering is performed using the scikit-learn library to segment customers. The integrated dataframe is taken as input, and a dataframe with each cluster labeled is output.

[0781] Step 5:

[0782] The server generates a presentation based on the analysis results. In this step, the Matplotlib library is used to generate graphs showing the distribution of each cluster, and these are incorporated into a PowerPoint presentation using the Python-pptx library. The output is a completed PowerPoint file.

[0783] Step 6:

[0784] The server delivers the generated presentation to the designated recipients and uploads it to the cloud. It is stored in cloud storage by sending an email using an SMTP server and uploading it to an FTP server. The output includes the email delivery status and a sharing link.

[0785] 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.

[0786] This invention combines a system that automates data collection, data integration, data analysis, report generation, and report distribution—all essential for business strategy planning—with an emotion engine that recognizes user sentiment. This system efficiently performs complex data processing and sentiment analysis by having the server, terminal, and user each fulfill their respective roles.

[0787] Data collection

[0788] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0789] Data Integration

[0790] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. For example, if the same customer has been registered multiple times in customer data, these entries are consolidated into a single record.

[0791] Data Analysis

[0792] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0793] Emotional engine integration

[0794] The server uses an emotion engine to analyze and recognize the user's emotions from voice and facial expression data. This engine can identify emotions in real time while the user is using the system. For example, it can monitor what emotions the user is experiencing during data collection or report generation processes.

[0795] Emotion-based feedback

[0796] The server provides the emotion identification results obtained by the emotion engine as feedback to the report generation system. Based on this feedback, the report content can be optimized. For example, if the user is dissatisfied, the format and content of the generated report can be changed to adjust it to meet the user's needs.

[0797] Data collection optimization

[0798] The server can select which data to collect based on the user's emotions identified by the emotion engine. For example, if a user shows a strong interest in a particular market trend, the server can adjust its settings to prioritize the collection of data in that area.

[0799] Report generation

[0800] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0801] Report distribution

[0802] The generated reports are sent by the server to the designated recipient's device or email address using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0803] As a concrete example, if a user needs a report to develop their next sales strategy, the process would be as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses an API to collect, standardize, and integrate the data, and then performs data analysis. The sentiment engine analyzes the user's emotions in real time and incorporates the feedback into report generation. Finally, the server generates a tailored report and delivers it to the user. This allows the user to develop business strategies efficiently and quickly.

[0804] The following describes the processing flow.

[0805] Step 1:

[0806] The user accesses the system and specifies the type of data they want to collect and the data source. For example, they might specify that they want to collect customer data from a customer relationship management system and market trend data from a market research company.

[0807] Step 2:

[0808] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, it might retrieve the latest customer information from a customer management system or the latest market trend data from a market research company.

[0809] Step 3:

[0810] The server temporarily stores the acquired data in storage. This storage is used to hold the data until processing and analysis are complete.

[0811] Step 4:

[0812] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is different (e.g., "name" and "full_name"), it will be unified. It will also convert numerical data in text format to numerical types.

[0813] Step 5:

[0814] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are consolidated into a single record. Also, if the data contains missing values, the server uses the mean or median to impute them.

[0815] Step 6:

[0816] The server analyzes the integrated data using data analysis tools. This process involves using machine learning algorithms and statistical analysis techniques to extract meaningful information and patterns from the data. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0817] Step 7:

[0818] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's voice and facial expression data to identify, for example, whether the user is interested or dissatisfied during the data collection process.

[0819] Step 8:

[0820] The server incorporates the emotion identification results obtained from the emotion engine as feedback into report generation. For example, if a user is interested in specific data, detailed analysis results based on that data will be added to the report.

[0821] Step 9:

[0822] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. The generated report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0823] Step 10:

[0824] The server sends the generated reports to the designated recipients' devices or email addresses using the report distribution method. Furthermore, it uploads them to cloud storage and generates sharing links as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0825] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently. Furthermore, considering user sentiment allows for more appropriate data analysis and report generation.

[0826] (Example 2)

[0827] 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."

[0828] While conventional data collection and analysis systems could integrate and analyze data from multiple external data sources, they failed to reflect user sentiment in real time, thus failing to adequately enhance user satisfaction and efficiency. Furthermore, the content and format of generated reports were not optimized based on user sentiment, remaining static in their information provision, making it difficult to respond to dynamic business needs. Additionally, the inability to dynamically change the priority of collected data based on user interests made it difficult to provide timely information.

[0829] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion analysis means for analyzing the user's emotions in real time, and a feedback provision means for providing feedback based on the results of the emotion analysis. This makes it possible to collect, analyze, generate and distribute data that reflects the user's emotions in real time, improving user satisfaction and efficiency, and enabling the provision of information that responds to dynamic business needs.

[0830] "Data acquisition means" refers to devices or systems for automatically acquiring data from external data sources.

[0831] "Data integration means" refers to programs or devices used to standardize and integrate collected data.

[0832] "Data analysis tools" refer to programs or devices that perform analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[0833] "Report generation means" refers to programs or devices that generate visually easy-to-understand reports based on the results of data analysis.

[0834] "Report distribution means" refers to a program or device for distributing generated reports to designated recipients.

[0835] "Emotion analysis means" refers to programs or devices that analyze a user's emotions in real time from their voice data and facial expression data.

[0836] "Feedback provision means" refers to programs or devices used to optimize the content and format of reports based on the results of sentiment analysis.

[0837] "External data sources" refer to data providers that exist outside of the system, such as customer management systems or market research companies.

[0838] A "machine learning algorithm" refers to a technology that automatically learns patterns and rules from data and uses them to make predictions and classifications on new data.

[0839] "Statistical analysis techniques" refer to the techniques used to analyze a set of data using statistical methods.

[0840] These definitions will deepen our understanding of the key elements of the patent claims.

[0841] This invention relates to a system that analyzes user emotions in real time and optimizes data collection, integration, analysis, report generation, and distribution based on that analysis. In this system, the server, terminal, and user each have their own roles to perform comprehensive data processing and emotion analysis.

[0842] First, the user logs into the system using a terminal. The user specifies the type of data they want to collect and the data source. Data sources include external data sources such as customer relationship management systems and market research companies.

[0843] The server accesses specified external data sources via APIs (Application Programming Interfaces) and automatically retrieves the necessary data. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to the APIs of customer management systems or market research companies to retrieve data in real time.

[0844] Next, the server standardizes and integrates the collected data using data integration mechanisms. This involves unifying field names and converting data types. It also removes duplicate data and imputes missing values ​​to create a consistent dataset. For example, in the case of customer data, if the same customer is registered as multiple records, these are integrated into a single record.

[0845] The integrated data is analyzed by the server using data analysis tools. Machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. Specifically, customer data is clustered to identify customer segments, and purchasing trends for each segment are analyzed. Furthermore, sales forecasts for the next period are made based on market trend data.

[0846] The system incorporates emotion analysis capabilities that analyze user emotions in real time. It analyzes user voice and facial expression data to identify emotions. For example, if a user experiences joy or dissatisfaction during data collection or report generation, it can be detected immediately.

[0847] The results of the sentiment analysis are provided to the server through a feedback system. Based on this feedback, the server optimizes the content and format of the generated report. If the user is dissatisfied, the visual elements and report content can be improved. It is also possible to dynamically change settings to prioritize the collection of data of high user interest.

[0848] Finally, the server generates a visually easy-to-understand report based on the analysis results and sentiment feedback. The report includes various graphs, charts, and text comments. For example, a bar graph showing customer segmentation results and a line graph showing market trend analysis results are automatically generated and incorporated into the report.

[0849] The generated reports are delivered by the server to the recipient's device or email address. They can also be uploaded to cloud storage and a sharing link can be generated as needed. This reduces the manual effort required for report creation and distribution, as marketing teams receive weekly market trend reports.

[0850] As a concrete example, if a user requires a report for their next sales strategy, the following steps would be taken: The user accesses the system and specifies the type and source of data to be collected. The server uses an API to collect, standardize, and integrate the data, and performs data analysis. Simultaneously, the sentiment engine analyzes the user's emotions in real time and incorporates this feedback into report generation. Finally, the server generates a tailored report and delivers it to the user.

[0851] An example of a prompt is, "Collect data from the customer management system and generate customer segmentation and market trend reports."

[0852] As a result, this system efficiently and quickly automates data collection, integration, analysis, report generation, and distribution, and further improves user satisfaction and efficiency by integrating sentiment analysis.

[0853] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0854] Step 1: Data Collection

[0855] The user logs into the system using a terminal and specifies the type of data to be collected and the data source. As input, they provide API information for customer management systems or market research companies. The server generates and sends API requests to the specified data sources. Specifically, the server retrieves data in JSON or CSV format from the external data sources. As output, the collected data is stored on the server.

[0856] Step 2: Data Integration

[0857] The server stores the collected data in a database. Since input data is often provided in different formats, the server uses data integration tools to standardize this data. Specifically, this involves unifying field names, converting data types, detecting and removing duplicate data, and imputing missing values. For example, it might unify field names like "name" and "full_name" to "name". The output is a consistent dataset.

[0858] Step 3: Data Analysis

[0859] The server takes integrated data stored in the database as input and performs data analysis using machine learning algorithms and statistical analysis techniques. Specifically, it performs clustering, classification, and regression analysis to extract important information. For example, it identifies the results of customer segmentation and analyzes the purchasing trends of each segment. The analysis results are generated as output.

[0860] Step 4: Emotion Analysis

[0861] The server uses emotion analysis tools to analyze the user's emotions in real time, taking their voice and facial expression data as input. Specifically, it analyzes voice and video data collected through microphones and cameras to identify the user's emotions. For example, it detects emotions such as joy or dissatisfaction from changes in voice tone and facial expressions. The emotion analysis results are generated as output.

[0862] Step 5: Provide feedback

[0863] Based on the sentiment analysis results, the server provides feedback to the report generation system using a feedback provision mechanism. Specifically, it optimizes the report content and format based on the user's emotions obtained through sentiment analysis. For example, if the user is dissatisfied, it improves the visual elements and content of the report. As output, an optimized report generation instruction is provided.

[0864] Step 6: Optimizing Data Collection

[0865] The server dynamically changes the priority of data to collect based on sentiment analysis results. It uses data on topics of high user interest as input. Specifically, if a user is interested in a particular market trend, the settings are changed to prioritize data collection in that area. The output is a data collection request with the set priority.

[0866] Step 7: Report Generation

[0867] The server generates a visually easy-to-understand report using a report generation method based on the analysis results and feedback from sentiment analysis. It uses integrated data and feedback information as input. Specifically, it automatically generates various graphs (e.g., bar graphs, line graphs) and charts, and adds text comments. The output is a completed report.

[0868] Step 8: Report Distribution

[0869] The server uses the generated report as input and distributes it to the specified recipient's device or email address. Specifically, it uses the report distribution method to send emails or upload to cloud storage. If necessary, it generates and provides a sharing link. The output consists of the distributed report and the sharing link.

[0870] Through these steps, the system efficiently and quickly automates the entire process from data collection to report delivery, and by integrating sentiment analysis, it can provide optimal feedback based on the user's emotions.

[0871] (Application Example 2)

[0872] 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."

[0873] Traditional systems automate data collection, integration, analysis, and report generation, but they lack dynamic report adjustments based on user emotions, resulting in insufficient user satisfaction and effective decision-making. Furthermore, the absence of mechanisms to reflect user emotions during use prevents improvements in the user experience. Therefore, there is a particular need for efficient and highly satisfying report generation and distribution, especially in the management of physical stores.

[0874] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion engine for recognizing the user's emotions, and a feedback means for dynamically adjusting the content of the report based on the user's emotions. This makes it possible to generate and distribute reports that are dynamically adjusted based on the user's emotions, thereby improving the user experience and achieving effective decision-making.

[0875] "Data acquisition means" refers to a device or software that automatically acquires necessary data from an external data source.

[0876] "Data integration means" refers to a device or software that standardizes collected data and integrates it in a common format.

[0877] "Data analysis tools" refer to devices or software that perform analysis on integrated data using machine learning algorithms or statistical analysis methods.

[0878] A "report generation means" is a device or software that generates a visually easy-to-understand report based on the results of data analysis.

[0879] "Report distribution means" refers to a device or software that distributes generated reports to specific recipients.

[0880] An "emotion engine" is a system that analyzes a user's voice and facial expressions to identify their emotions in real time.

[0881] A "feedback mechanism" is a device or software that dynamically adjusts the content of a report based on the user's emotions identified by the emotion engine.

[0882] These definitions clarify the meaning of each technical element included in the invention.

[0883] The "Smart Report Assistant" of this invention is a system that collects, integrates, and analyzes sales data from physical stores, customer feedback, inventory status, and regional market trends, and generates and delivers optimal reports for store managers. It also incorporates an emotion engine that recognizes user emotions and dynamically adjusts the report content based on the store manager's feelings.

[0884] System Configuration

[0885] 1. The server automatically acquires data from external data sources as a means of data collection. This includes POS systems, customer survey systems, ERP systems, and market trend APIs.

[0886] 2. The server uses data integration means to standardize and integrate the collected data. For example, this includes unifying field names, converting data types, removing duplicate data, and imputing missing values.

[0887] 3. The server analyzes the integrated data using data analysis tools. This involves using machine learning algorithms and statistical analysis techniques. For example, it may analyze sales trends, perform customer segmentation, and forecast inventory.

[0888] 4. The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. This analysis result is used as feedback to dynamically adjust the report content based on the user's emotions.

[0889] 5. The server uses a report generation mechanism to create a visually easy-to-understand report based on the data analysis results and sentiment feedback. This visualization includes various graphs and charts.

[0890] 6. The server distributes the generated report to the designated recipient using a report distribution method. Distribution methods include email and shared links to cloud storage.

[0891] System details

[0892] To realize this invention, the server uses the following specific software and hardware.

[0893] EmotionEngine: A voice and facial expression recognition library (similar to Microsoft's Emotion API and Google's Cloud Speech-to-Text).

[0894] Data Integration Library: Software that performs data integration processing.

[0895] Report generation library: Software for creating reports

[0896] API access libraries: such as the requests library for retrieving data from external data sources.

[0897] Explanation using specific examples

[0898] For example, if a user needs a report to develop their next sales strategy, the system works as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses APIs to collect, standardize, and integrate data from POS systems, customer survey systems, ERP systems, and market trend APIs. Next, machine learning algorithms and statistical analysis techniques are used to analyze the data and extract information such as sales trends, customer segments, and inventory forecasts. The sentiment engine analyzes the user's emotions in real time while they are using the system and provides feedback based on the results. Finally, the server generates a tailored report and delivers it to the specified recipients.

[0899] Example of a prompt

[0900] "Retrieve sales data from the POS system and collect inventory information from the ERP system. Then, integrate this data and perform data analysis based on customer feedback. Additionally, analyze store managers' emotions using an emotion engine and adjust the report content accordingly."

[0901] As a result, users can make strategic decisions efficiently and with high satisfaction.

[0902] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0903] Step 1:

[0904] The server receives a data collection request specified by the user. The user specifies the type of data to be collected (e.g., sales data, inventory data, customer feedback, market trends) and the data source. The input is the user's specifications, and based on this, the server prepares an API call to access the external data source. The output is the URL and parameter settings of the API call.

[0905] Step 2:

[0906] The server executes the prepared API calls and collects data from each data source. This includes POS systems, customer survey systems, ERP systems, and market trend APIs. The input is the API call configuration, and the output is the retrieved data. The server temporarily stores the collected data in JSON format.

[0907] Step 3:

[0908] The server standardizes the collected data and integrates it using data integration tools. Specifically, it unifies field names, converts data types, removes duplicate data, and imputes missing values. The input is the collected data, and the output is a standardized, integrated dataset.

[0909] Step 4:

[0910] The server analyzes the integrated data using data analysis tools. It employs machine learning algorithms and statistical analysis techniques to extract information such as sales trends, customer segmentation, and inventory forecasts. The input is the integrated dataset, and the output is the generated report data of the analysis results.

[0911] Step 5:

[0912] The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. The input is audio or video data, and the output is the emotion recognition result. Specifically, the emotion engine performs spectral analysis of the audio waveform and facial expression analysis from the video.

[0913] Step 6:

[0914] The server uses the emotion recognition results obtained from the emotion engine as a feedback mechanism to dynamically adjust the report content. The input is the report data of the emotion recognition results and analysis results, and the output is the adjusted report that reflects the emotion feedback.

[0915] Step 7:

[0916] The server uses a report generation mechanism to create the adjusted report in a visually easy-to-understand format. This visualization includes various graphs and charts. The input is the adjusted report data, and the output is the final report document.

[0917] Step 8:

[0918] The server distributes the generated final report to the designated recipients using a report distribution method. Distribution methods include email and shared links to cloud storage. The input is the final report document, and the output is a delivery completion notification.

[0919] The above describes the specific processing steps and details of each operation for carrying out the present invention.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] [Fourth Embodiment]

[0924] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0925] 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.

[0926] 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).

[0927] 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.

[0928] 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.

[0929] 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).

[0930] 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.

[0931] 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.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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".

[0937] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0938] Data collection

[0939] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[0940] Data Integration

[0941] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. In the case of collected customer data, if the same customer has been registered multiple times, these entries are integrated into a single record.

[0942] Data Analysis

[0943] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[0944] Report generation

[0945] Based on the data analysis results, the server uses a report generation system to create a visually easy-to-understand report. The generated report is in PowerPoint format and includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[0946] Report distribution

[0947] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For marketing teams, this eliminates the need for manual report creation and distribution, as they automatically receive weekly market trend reports.

[0948] For example, if a user requires a report to help them develop their next sales strategy, the following process will be performed.

[0949] 1. The user accesses the system and specifies the data they want to collect and its source.

[0950] 2. The server connects to the specified API and collects customer data and market trend data.

[0951] 3. The server standardizes the data, removes duplicate data, and performs necessary interpolation before creating an integrated dataset.

[0952] 4. The server uses data analysis tools to perform clustering and predictive analytics.

[0953] 5. The server automatically generates a report in PowerPoint format based on the analysis results obtained.

[0954] 6. The server delivers the report to the user and uploads it to cloud storage.

[0955] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0956] The following describes the processing flow.

[0957] Step 1:

[0958] The user accesses the system and specifies the type of data they want to collect (e.g., customer data, market trend data) and the data source (e.g., customer relationship management system, market research company).

[0959] Step 2:

[0960] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, to retrieve customer data from a customer management system, the server connects to the system's API and retrieves the latest customer information. The same applies when retrieving market trend data from a market research company.

[0961] Step 3:

[0962] The server stores the collected data in temporary storage. This storage is used to retain the information until the data processing and analysis are complete.

[0963] Step 4:

[0964] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is named differently (e.g., "name" and "full_name"), this will be unified. Additionally, numerical data in text format will be converted to numerical types.

[0965] Step 5:

[0966] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are merged into a single record. If there are missing values, they are imputed using the mean or median.

[0967] Step 6:

[0968] The server analyzes the integrated data using data analysis tools. This process involves extracting meaningful information and patterns from the data using machine learning algorithms and statistical analysis techniques. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[0969] Step 7:

[0970] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[0971] Step 8:

[0972] The server sends the generated report to the designated recipient's device or email address using the report distribution method. Furthermore, it uploads to cloud storage and generates a sharing link as needed. For example, it can automatically send a weekly market trend report to all members of the marketing department.

[0973] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently.

[0974] (Example 1)

[0975] 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".

[0976] Traditional business strategy planning systems involved separate processes for data collection, integration, analysis, report generation, and distribution, often requiring manual intervention between these steps, resulting in inefficiencies. In particular, the time and effort required for standardizing data collected from different sources, removing duplicates, and imputing missing values ​​made rapid data analysis and timely report distribution difficult, ultimately hindering the rapid development of business strategies.

[0977] 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.

[0978] In this invention, the server includes data collection means, data integration means for standardizing the collected data into a common format, removing duplicate data, and imputing missing values, data analysis means for diagnosing the integrated data and performing clustering and predictive analysis, report generation means for generating reports that visually display the analysis results, and report distribution means for automatically distributing the generated reports. This automates the entire process from data collection to report distribution, enabling the rapid and highly efficient formulation of business strategies.

[0979] "Data collection means" refers to a function that automatically retrieves data from external data sources via an API.

[0980] A "data integration method" is a function that standardizes collected data into a common format, removes duplicate data, and imputes missing values.

[0981] "Data analysis tools" refer to functions that perform clustering and predictive analysis using machine learning algorithms and statistical analysis methods based on integrated data.

[0982] A "report generation method" is a function that automatically generates reports that visually display the results of data analysis.

[0983] A "report distribution method" is a function that automatically distributes generated reports to designated recipients.

[0984] This invention relates to a system that consistently automates data collection, data integration, data analysis, report generation, and report distribution necessary for formulating business strategies. This system efficiently performs complex data processing by having the server, terminal, and user each fulfill their respective roles.

[0985] This system is configured as follows:

[0986] Data collection

[0987] The server automatically retrieves data from various data sources specified by the user using data collection methods. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to APIs of customer relationship management (CRM) systems and market research organizations to collect the necessary data.

[0988] Data Integration

[0989] Since the collected data is typically provided in different formats, the server uses data integration mechanisms to standardize this data into a common format. For example, field names are unified, data types are converted, and duplicate data is removed. In addition, missing values ​​are imputed in an appropriate manner. This allows the server to create a consistent dataset. For example, if the same customer is registered multiple times from multiple data sources, these are integrated into one, retaining the necessary information.

[0990] Data Analysis

[0991] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server clusters customer data to identify customer segments and analyzes purchasing trends for each segment. It also forecasts future sales based on market trend data.

[0992] Report generation

[0993] Based on the analysis results, the server uses a report generation system to create a visually easy-to-understand report. This report is in PowerPoint format and includes various graphs, charts, and text comments. For example, the report may include bar graphs showing clustering results and line graphs showing market trend analysis results.

[0994] Report distribution

[0995] The generated reports are automatically sent by the server to the designated recipients' devices or email addresses using the report distribution method. If necessary, they can also be uploaded to cloud storage and a sharing link can be generated. For example, marketing team members can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[0996] As a concrete example, consider a scenario where a user needs a report to formulate their next sales strategy. By using the following prompt, the system will automatically perform the necessary processing.

[0997] Example prompt: "Collect customer data and market trend data, and create a report that includes sales forecasts for the next period."

[0998] This system automates the entire process from data collection to report generation and distribution, enabling users to develop business strategies efficiently and quickly.

[0999] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1000] Data collection

[1001] Step 1:

[1002] The user accesses the system from their terminal and specifies the data they want to collect and its data source. As input, the user provides the API endpoint URL and authentication information (such as API key, user ID, and password) for each data source. As output, this information is sent to the server, completing the data collection setup.

[1003] Specific actions:

[1004] Access the user's system data collection settings screen.

[1005] Enter the API information and authentication details for each data source into the form, and then click the "Save Settings" button.

[1006] Step 2:

[1007] The server connects to the API of the data source specified by the user and automatically collects the data. The server sends a GET request to the configured API endpoint and stores the obtained data in temporary storage. As input, the server uses the API endpoint URL and authentication information, and as output, it obtains the collected data.

[1008] Specific actions:

[1009] The server connects to the configured API endpoint.

[1010] Make an API request using authentication credentials.

[1011] The acquired data is saved to temporary storage.

[1012] Data Integration

[1013] Step 3:

[1014] The server standardizes the collected data into a common format. As input, the server reads the collected data and applies standardization rules. As output, it obtains standardized data. This process includes unifying field names and converting data types.

[1015] Specific actions:

[1016] The server reads the data stored in temporary storage.

[1017] Apply mapping rules to standardize field names.

[1018] Convert data types as needed (e.g., convert a string to a number).

[1019] Standardized data is stored in a temporary database.

[1020] Step 4:

[1021] The server removes duplicate data and imputes missing values ​​from standardized data. As input, the server uses standardized data and applies duplicate detection and missing value imputation rules. The output is a clean dataset.

[1022] Specific actions:

[1023] A duplicate detection algorithm is applied to identify duplicate records.

[1024] It merges duplicate records into one and retains the necessary field information.

[1025] For fields with missing values, imputation rules are applied (such as inserting the mean).

[1026] Data Analysis

[1027] Step 5:

[1028] The server performs data analysis using integrated data. As input, the server obtains an integrated dataset and applies machine learning algorithms and statistical analysis techniques. As output, it obtains analysis results, such as customer clustering and sales forecasting.

[1029] Specific actions:

[1030] Load the integrated dataset into the analysis tool.

[1031] Apply the configured machine learning model and statistical methods.

[1032] Save the analysis results.

[1033] Report generation

[1034] Step 6:

[1035] The server automatically generates a report that visually displays the analysis results. As input, the server retrieves the analysis results and inserts the data into a report template. As output, a report in PowerPoint format is generated.

[1036] Specific actions:

[1037] Obtain the analysis results and insert the data into the report template.

[1038] Create visuals using libraries that automatically generate graphs and charts.

[1039] Save the completed report in PowerPoint format.

[1040] Report distribution

[1041] Step 7:

[1042] The server automatically distributes the generated reports to users. As input, the server retrieves user email addresses and recipient lists. As output, the reports are distributed to the specified recipients.

[1043] Specific actions:

[1044] Retrieve the user's email address and subscription list.

[1045] Send the report using the mail server.

[1046] Upload reports using the cloud storage API as needed and generate a sharing link.

[1047] The above is a detailed explanation of each processing step in the system's program. This flow allows users to automate the entire process from data collection to report generation and distribution, enabling them to formulate business strategies with high efficiency.

[1048] (Application Example 1)

[1049] 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".

[1050] In modern business operations, data collection, integration, analysis, and the generation and distribution of reports based on those results are essential. However, effectively performing these processes requires considerable time and effort, and carries a high risk of errors. Furthermore, insufficient mechanisms for quickly sharing generated reports within teams often lead to delayed decision-making. In addition, the integration of data from different data sources and the need for specialized knowledge to perform complex analyses can result in inefficiencies. A system is needed to solve these challenges and enable efficient and rapid data processing and report distribution.

[1051] 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.

[1052] In this invention, the server includes data collection means, data integration means for standardizing and integrating the collected data, data analysis means for performing analysis based on the integrated data, presentation generation means for generating a presentation using the analysis results, presentation distribution means for distributing the generated presentation, and cloud distribution means for uploading the generated presentation to the cloud. This makes it possible to automatically collect data from multiple external data sources via APIs, analyze the data using machine learning algorithms and statistical analysis methods based on the integrated data, automatically generate a presentation based on the results, send the generated presentation to a specified terminal or email address, and further upload it to cloud storage to generate a sharing link.

[1053] A "data collection method" is a means that has the function of automatically acquiring necessary data from external data sources.

[1054] A "data integration method" is a means of standardizing the formats of diverse collected data and combining them into a single integrated dataset.

[1055] "Data analysis methods" refer to methods for performing data analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[1056] A "presentation generation method" is a means of generating presentation materials in a visually easy-to-understand format based on analysis results.

[1057] A "presentation distribution method" is a means of sending a generated presentation to the device or email address of a designated recipient.

[1058] "Cloud distribution method" refers to a method of uploading a generated presentation to cloud storage and creating a sharing link.

[1059] This invention relates to an integrated data processing system for efficiently supporting the formulation of business strategies on e-commerce websites. This system can consistently automate data collection, data integration, data analysis, presentation generation, and presentation distribution.

[1060] Data collection

[1061] The server automatically retrieves data from various external data sources specified by the user using data collection methods. In this case, external data sources include various APIs. For example, the server connects to customer management system APIs and market research APIs to obtain customer purchase data and market trend data.

[1062] Data Integration

[1063] Because the collected data is provided in various formats, the server uses data integration tools to standardize and integrate this data. This process includes unifying field names, converting data types, removing duplicate data, and imputing missing values. The server might use the Pandas library, for example, to integrate the data.

[1064] Data Analysis

[1065] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, the server uses the scikit-learn library to perform KMeans clustering and customer segmentation.

[1066] Presentation generation

[1067] Based on the data analysis results, the server uses a presentation generation tool to create a visually easy-to-understand report. The generated presentation is in PowerPoint format and includes various graphs, charts, and text comments. For example, graphs generated by the Matplotlib library can be incorporated using the Python-pptx library.

[1068] Presentation delivery

[1069] The generated presentation is sent by the server to the designated recipient's device or email address using a presentation delivery method. Furthermore, it is also possible to upload it to cloud storage using a cloud delivery method and generate a sharing link.

[1070] As a concrete example, consider a scenario where a marketing manager at an e-commerce site plans the next promotional strategy. The server collects customer purchase data and market trend information from a specified API. Next, it integrates the collected data using the Pandas library and performs data analysis using scikit-learn. Based on the results, it generates a PowerPoint presentation using Python-pptx. The generated presentation is sent via email through an SMTP server and uploaded to an FTP server.

[1071] Example prompts for generative AI models

[1072] Create a Python program that uses KMeans clustering to segment customers based on purchase data obtained from an API endpoint, generates a report in PowerPoint format, and distributes it via email.

[1073] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1074] Step 1:

[1075] The user accesses the system and specifies the data they want to collect and its source. The server then receives a list of API endpoints based on the user's specifications as input.

[1076] Step 2:

[1077] The server accesses API endpoints to retrieve data. This process uses the requests library to send HTTP requests to each endpoint and receives data in JSON format. The retrieved data is stored in list format.

[1078] Step 3:

[1079] The server standardizes and integrates the acquired data. Here, the Pandas library is used to convert multiple JSON data sets into a DataFrame, unifying field names, converting data types, removing duplicate data, and imputing missing values. As a result, an integrated, standardized DataFrame is output.

[1080] Step 4:

[1081] The server performs data analysis based on the integrated data. In this step, KMeans clustering is performed using the scikit-learn library to segment customers. The integrated dataframe is taken as input, and a dataframe with each cluster labeled is output.

[1082] Step 5:

[1083] The server generates a presentation based on the analysis results. In this step, the Matplotlib library is used to generate graphs showing the distribution of each cluster, and these are incorporated into a PowerPoint presentation using the Python-pptx library. The output is a completed PowerPoint file.

[1084] Step 6:

[1085] The server delivers the generated presentation to the designated recipients and uploads it to the cloud. It is stored in cloud storage by sending an email using an SMTP server and uploading it to an FTP server. The output includes the email delivery status and a sharing link.

[1086] 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.

[1087] This invention combines a system that automates data collection, data integration, data analysis, report generation, and report distribution—all essential for business strategy planning—with an emotion engine that recognizes user sentiment. This system efficiently performs complex data processing and sentiment analysis by having the server, terminal, and user each fulfill their respective roles.

[1088] Data collection

[1089] The server automatically retrieves data from various data sources specified by the user using data collection methods. Here, it accesses multiple external data sources via APIs to collect the necessary data. For example, if a user in the marketing department wants to collect customer data or market trend data, the server connects to APIs of customer management systems and market research companies to retrieve data in real time.

[1090] Data Integration

[1091] The collected data is typically provided in a variety of formats. The server uses data integration tools to standardize this data into a common format. Standardization includes unifying field names and converting data types. Furthermore, it creates a consistent dataset by removing duplicate data and imputing missing values. For example, if the same customer has been registered multiple times in customer data, these entries are consolidated into a single record.

[1092] Data Analysis

[1093] The integrated data is analyzed by the server using data analysis tools. During this process, machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. For example, customer data is clustered to identify customer segments, and purchasing trends are analyzed for each segment. Furthermore, sales forecasts for the next period are made based on the collected market trend data.

[1094] Emotional engine integration

[1095] The server uses an emotion engine to analyze and recognize the user's emotions from voice and facial expression data. This engine can identify emotions in real time while the user is using the system. For example, it can monitor what emotions the user is experiencing during data collection or report generation processes.

[1096] Emotion-based feedback

[1097] The server provides the emotion identification results obtained by the emotion engine as feedback to the report generation system. Based on this feedback, the report content can be optimized. For example, if the user is dissatisfied, the format and content of the generated report can be changed to adjust it to meet the user's needs.

[1098] Data collection optimization

[1099] The server can select which data to collect based on the user's emotions identified by the emotion engine. For example, if a user shows a strong interest in a particular market trend, the server can adjust its settings to prioritize the collection of data in that area.

[1100] Report generation

[1101] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. This report includes various graphs, charts, and text comments. For example, it automatically generates and incorporates bar graphs showing customer segmentation results and line graphs showing market trend analysis results into the report.

[1102] Report distribution

[1103] The generated reports are sent by the server to the designated recipient's device or email address using the report distribution method. They can also be uploaded to cloud storage and a sharing link can be generated as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[1104] As a concrete example, if a user needs a report to develop their next sales strategy, the process would be as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses an API to collect, standardize, and integrate the data, and then performs data analysis. The sentiment engine analyzes the user's emotions in real time and incorporates the feedback into report generation. Finally, the server generates a tailored report and delivers it to the user. This allows the user to develop business strategies efficiently and quickly.

[1105] The following describes the processing flow.

[1106] Step 1:

[1107] The user accesses the system and specifies the type of data they want to collect and the data source. For example, they might specify that they want to collect customer data from a customer relationship management system and market trend data from a market research company.

[1108] Step 2:

[1109] The server accesses the API of the specified data source and retrieves the data using the necessary authentication information (API key, token, etc.). For example, it might retrieve the latest customer information from a customer management system or the latest market trend data from a market research company.

[1110] Step 3:

[1111] The server temporarily stores the acquired data in storage. This storage is used to hold the data until processing and analysis are complete.

[1112] Step 4:

[1113] The server uses data integration tools to standardize the collected data into a common format. This standardization process includes unifying field names from different sources and converting data types. For example, if the "Name" field in customer data is different (e.g., "name" and "full_name"), it will be unified. It will also convert numerical data in text format to numerical types.

[1114] Step 5:

[1115] The server integrates standardized data. This process includes removing duplicate data and imputing missing values. For example, if the same customer has registered multiple times, these entries are consolidated into a single record. Also, if the data contains missing values, the server uses the mean or median to impute them.

[1116] Step 6:

[1117] The server analyzes the integrated data using data analysis tools. This process involves using machine learning algorithms and statistical analysis techniques to extract meaningful information and patterns from the data. For example, it might cluster customer data to identify customer segments and analyze purchasing trends for each segment. It might also analyze market trend data to forecast future sales.

[1118] Step 7:

[1119] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's voice and facial expression data to identify, for example, whether the user is interested or dissatisfied during the data collection process.

[1120] Step 8:

[1121] The server incorporates the emotion identification results obtained from the emotion engine as feedback into report generation. For example, if a user is interested in specific data, detailed analysis results based on that data will be added to the report.

[1122] Step 9:

[1123] Based on the results of data analysis and feedback from the sentiment engine, the server uses report generation tools to create a visually easy-to-understand report. The generated report includes various graphs, charts, and text comments. For example, it generates and incorporates bar graphs showing customer segmentation results and line graphs showing sales forecast results into the report.

[1124] Step 10:

[1125] The server sends the generated reports to the designated recipients' devices or email addresses using the report distribution method. Furthermore, it uploads them to cloud storage and generates sharing links as needed. For example, users in a marketing team can automatically receive weekly market trend reports, reducing the effort required for manual report creation and distribution.

[1126] In this way, users can automate the entire process from data collection to report generation and distribution, enabling them to develop business strategies quickly and efficiently. Furthermore, considering user sentiment allows for more appropriate data analysis and report generation.

[1127] (Example 2)

[1128] 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".

[1129] While conventional data collection and analysis systems could integrate and analyze data from multiple external data sources, they failed to reflect user sentiment in real time, thus failing to adequately enhance user satisfaction and efficiency. Furthermore, the content and format of generated reports were not optimized based on user sentiment, remaining static in their information provision, making it difficult to respond to dynamic business needs. Additionally, the inability to dynamically change the priority of collected data based on user interests made it difficult to provide timely information.

[1130] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion analysis means for analyzing the user's emotions in real time, and a feedback provision means for providing feedback based on the results of the emotion analysis. This makes it possible to collect, analyze, generate and distribute data that reflects the user's emotions in real time, improving user satisfaction and efficiency, and enabling the provision of information that responds to dynamic business needs.

[1131] "Data acquisition means" refers to devices or systems for automatically acquiring data from external data sources.

[1132] "Data integration means" refers to programs or devices used to standardize and integrate collected data.

[1133] "Data analysis tools" refer to programs or devices that perform analysis using machine learning algorithms and statistical analysis techniques based on integrated data.

[1134] "Report generation means" refers to programs or devices that generate visually easy-to-understand reports based on the results of data analysis.

[1135] "Report distribution means" refers to a program or device for distributing generated reports to designated recipients.

[1136] "Emotion analysis means" refers to programs or devices that analyze a user's emotions in real time from their voice data and facial expression data.

[1137] "Feedback provision means" refers to programs or devices used to optimize the content and format of reports based on the results of sentiment analysis.

[1138] "External data sources" refer to data providers that exist outside of the system, such as customer management systems or market research companies.

[1139] A "machine learning algorithm" refers to a technology that automatically learns patterns and rules from data and uses them to make predictions and classifications on new data.

[1140] "Statistical analysis techniques" refer to the techniques used to analyze a set of data using statistical methods.

[1141] These definitions will deepen our understanding of the key elements of the patent claims.

[1142] This invention relates to a system that analyzes user emotions in real time and optimizes data collection, integration, analysis, report generation, and distribution based on that analysis. In this system, the server, terminal, and user each have their own roles to perform comprehensive data processing and emotion analysis.

[1143] First, the user logs into the system using a terminal. The user specifies the type of data they want to collect and the data source. Data sources include external data sources such as customer relationship management systems and market research companies.

[1144] The server accesses specified external data sources via APIs (Application Programming Interfaces) and automatically retrieves the necessary data. For example, if a user in the marketing department wants to collect customer data and market trend data, the server connects to the APIs of customer management systems or market research companies to retrieve data in real time.

[1145] Next, the server standardizes and integrates the collected data using data integration mechanisms. This involves unifying field names and converting data types. It also removes duplicate data and imputes missing values ​​to create a consistent dataset. For example, in the case of customer data, if the same customer is registered as multiple records, these are integrated into a single record.

[1146] The integrated data is analyzed by the server using data analysis tools. Machine learning algorithms and statistical analysis techniques are used to extract meaningful information from the data. Specifically, customer data is clustered to identify customer segments, and purchasing trends for each segment are analyzed. Furthermore, sales forecasts for the next period are made based on market trend data.

[1147] The system incorporates emotion analysis capabilities that analyze user emotions in real time. It analyzes user voice and facial expression data to identify emotions. For example, if a user experiences joy or dissatisfaction during data collection or report generation, it can be detected immediately.

[1148] The results of the sentiment analysis are provided to the server through a feedback system. Based on this feedback, the server optimizes the content and format of the generated report. If the user is dissatisfied, the visual elements and report content can be improved. It is also possible to dynamically change settings to prioritize the collection of data of high user interest.

[1149] Finally, the server generates a visually easy-to-understand report based on the analysis results and sentiment feedback. The report includes various graphs, charts, and text comments. For example, a bar graph showing customer segmentation results and a line graph showing market trend analysis results are automatically generated and incorporated into the report.

[1150] The generated reports are delivered by the server to the recipient's device or email address. They can also be uploaded to cloud storage and a sharing link can be generated as needed. This reduces the manual effort required for report creation and distribution, as marketing teams receive weekly market trend reports.

[1151] As a concrete example, if a user requires a report for their next sales strategy, the following steps would be taken: The user accesses the system and specifies the type and source of data to be collected. The server uses an API to collect, standardize, and integrate the data, and performs data analysis. Simultaneously, the sentiment engine analyzes the user's emotions in real time and incorporates this feedback into report generation. Finally, the server generates a tailored report and delivers it to the user.

[1152] An example of a prompt is, "Collect data from the customer management system and generate customer segmentation and market trend reports."

[1153] As a result, this system efficiently and quickly automates data collection, integration, analysis, report generation, and distribution, and further improves user satisfaction and efficiency by integrating sentiment analysis.

[1154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1155] Step 1: Data Collection

[1156] The user logs into the system using a terminal and specifies the type of data to be collected and the data source. As input, they provide API information for customer management systems or market research companies. The server generates and sends API requests to the specified data sources. Specifically, the server retrieves data in JSON or CSV format from the external data sources. As output, the collected data is stored on the server.

[1157] Step 2: Data Integration

[1158] The server stores the collected data in a database. Since input data is often provided in different formats, the server uses data integration tools to standardize this data. Specifically, this involves unifying field names, converting data types, detecting and removing duplicate data, and imputing missing values. For example, it might unify field names like "name" and "full_name" to "name". The output is a consistent dataset.

[1159] Step 3: Data Analysis

[1160] The server takes integrated data stored in the database as input and performs data analysis using machine learning algorithms and statistical analysis techniques. Specifically, it performs clustering, classification, and regression analysis to extract important information. For example, it identifies the results of customer segmentation and analyzes the purchasing trends of each segment. The analysis results are generated as output.

[1161] Step 4: Emotion Analysis

[1162] The server uses emotion analysis tools to analyze the user's emotions in real time, taking their voice and facial expression data as input. Specifically, it analyzes voice and video data collected through microphones and cameras to identify the user's emotions. For example, it detects emotions such as joy or dissatisfaction from changes in voice tone and facial expressions. The emotion analysis results are generated as output.

[1163] Step 5: Provide feedback

[1164] Based on the sentiment analysis results, the server provides feedback to the report generation system using a feedback provision mechanism. Specifically, it optimizes the report content and format based on the user's emotions obtained through sentiment analysis. For example, if the user is dissatisfied, it improves the visual elements and content of the report. As output, an optimized report generation instruction is provided.

[1165] Step 6: Optimizing Data Collection

[1166] The server dynamically changes the priority of data to collect based on sentiment analysis results. It uses data on topics of high user interest as input. Specifically, if a user is interested in a particular market trend, the settings are changed to prioritize data collection in that area. The output is a data collection request with the set priority.

[1167] Step 7: Report Generation

[1168] The server generates a visually easy-to-understand report using a report generation method based on the analysis results and feedback from sentiment analysis. It uses integrated data and feedback information as input. Specifically, it automatically generates various graphs (e.g., bar graphs, line graphs) and charts, and adds text comments. The output is a completed report.

[1169] Step 8: Report Distribution

[1170] The server uses the generated report as input and distributes it to the specified recipient's device or email address. Specifically, it uses the report distribution method to send emails or upload to cloud storage. If necessary, it generates and provides a sharing link. The output consists of the distributed report and the sharing link.

[1171] Through these steps, the system efficiently and quickly automates the entire process from data collection to report delivery, and by integrating sentiment analysis, it can provide optimal feedback based on the user's emotions.

[1172] (Application Example 2)

[1173] 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".

[1174] Traditional systems automate data collection, integration, analysis, and report generation, but they lack dynamic report adjustments based on user emotions, resulting in insufficient user satisfaction and effective decision-making. Furthermore, the absence of mechanisms to reflect user emotions during use prevents improvements in the user experience. Therefore, there is a particular need for efficient and highly satisfying report generation and distribution, especially in the management of physical stores.

[1175] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a data collection means, a data integration means for standardizing and integrating the collected data, a data analysis means for performing analysis based on the integrated data, a report generation means for generating a report using the analysis results, a report distribution means for distributing the generated report, an emotion engine for recognizing the user's emotions, and a feedback means for dynamically adjusting the content of the report based on the user's emotions. This makes it possible to generate and distribute reports that are dynamically adjusted based on the user's emotions, thereby improving the user experience and achieving effective decision-making.

[1176] "Data acquisition means" refers to a device or software that automatically acquires necessary data from an external data source.

[1177] "Data integration means" refers to a device or software that standardizes collected data and integrates it in a common format.

[1178] "Data analysis tools" refer to devices or software that perform analysis on integrated data using machine learning algorithms or statistical analysis methods.

[1179] A "report generation means" is a device or software that generates a visually easy-to-understand report based on the results of data analysis.

[1180] "Report distribution means" refers to a device or software that distributes generated reports to specific recipients.

[1181] An "emotion engine" is a system that analyzes a user's voice and facial expressions to identify their emotions in real time.

[1182] A "feedback mechanism" is a device or software that dynamically adjusts the content of a report based on the user's emotions identified by the emotion engine.

[1183] These definitions clarify the meaning of each technical element included in the invention.

[1184] The "Smart Report Assistant" of this invention is a system that collects, integrates, and analyzes sales data from physical stores, customer feedback, inventory status, and regional market trends, and generates and delivers optimal reports for store managers. It also incorporates an emotion engine that recognizes user emotions and dynamically adjusts the report content based on the store manager's feelings.

[1185] System Configuration

[1186] 1. The server automatically acquires data from external data sources as a means of data collection. This includes POS systems, customer survey systems, ERP systems, and market trend APIs.

[1187] 2. The server uses data integration means to standardize and integrate the collected data. For example, this includes unifying field names, converting data types, removing duplicate data, and imputing missing values.

[1188] 3. The server analyzes the integrated data using data analysis tools. This involves using machine learning algorithms and statistical analysis techniques. For example, it may analyze sales trends, perform customer segmentation, and forecast inventory.

[1189] 4. The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. This analysis result is used as feedback to dynamically adjust the report content based on the user's emotions.

[1190] 5. The server uses a report generation mechanism to create a visually easy-to-understand report based on the data analysis results and sentiment feedback. This visualization includes various graphs and charts.

[1191] 6. The server distributes the generated report to the designated recipient using a report distribution method. Distribution methods include email and shared links to cloud storage.

[1192] System details

[1193] To realize this invention, the server uses the following specific software and hardware.

[1194] EmotionEngine: A voice and facial expression recognition library (similar to Microsoft's Emotion API and Google's Cloud Speech-to-Text).

[1195] Data Integration Library: Software that performs data integration processing.

[1196] Report generation library: Software for creating reports

[1197] API access libraries: such as the requests library for retrieving data from external data sources.

[1198] Explanation using specific examples

[1199] For example, if a user needs a report to develop their next sales strategy, the system works as follows: The user accesses the system and specifies the type and source of data they want to collect. The server uses APIs to collect, standardize, and integrate data from POS systems, customer survey systems, ERP systems, and market trend APIs. Next, machine learning algorithms and statistical analysis techniques are used to analyze the data and extract information such as sales trends, customer segments, and inventory forecasts. The sentiment engine analyzes the user's emotions in real time while they are using the system and provides feedback based on the results. Finally, the server generates a tailored report and delivers it to the specified recipients.

[1200] Example of a prompt

[1201] "Retrieve sales data from the POS system and collect inventory information from the ERP system. Then, integrate this data and perform data analysis based on customer feedback. Additionally, analyze store managers' emotions using an emotion engine and adjust the report content accordingly."

[1202] As a result, users can make strategic decisions efficiently and with high satisfaction.

[1203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1204] Step 1:

[1205] The server receives a data collection request specified by the user. The user specifies the type of data to be collected (e.g., sales data, inventory data, customer feedback, market trends) and the data source. The input is the user's specifications, and based on this, the server prepares an API call to access the external data source. The output is the URL and parameter settings of the API call.

[1206] Step 2:

[1207] The server executes the prepared API calls and collects data from each data source. This includes POS systems, customer survey systems, ERP systems, and market trend APIs. The input is the API call configuration, and the output is the retrieved data. The server temporarily stores the collected data in JSON format.

[1208] Step 3:

[1209] The server standardizes the collected data and integrates it using data integration tools. Specifically, it unifies field names, converts data types, removes duplicate data, and imputes missing values. The input is the collected data, and the output is a standardized, integrated dataset.

[1210] Step 4:

[1211] The server analyzes the integrated data using data analysis tools. It employs machine learning algorithms and statistical analysis techniques to extract information such as sales trends, customer segmentation, and inventory forecasts. The input is the integrated dataset, and the output is the generated report data of the analysis results.

[1212] Step 5:

[1213] The server uses an emotion engine to analyze and recognize the user's emotions in real time from their voice and facial expressions. The input is audio or video data, and the output is the emotion recognition result. Specifically, the emotion engine performs spectral analysis of the audio waveform and facial expression analysis from the video.

[1214] Step 6:

[1215] The server uses the emotion recognition results obtained from the emotion engine as a feedback mechanism to dynamically adjust the report content. The input is the report data of the emotion recognition results and analysis results, and the output is the adjusted report that reflects the emotion feedback.

[1216] Step 7:

[1217] The server uses a report generation mechanism to create the adjusted report in a visually easy-to-understand format. This visualization includes various graphs and charts. The input is the adjusted report data, and the output is the final report document.

[1218] Step 8:

[1219] The server distributes the generated final report to the designated recipients using a report distribution method. Distribution methods include email and shared links to cloud storage. The input is the final report document, and the output is a delivery completion notification.

[1220] The above describes the specific processing steps and details of each operation for carrying out the present invention.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] 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.

[1229] 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."

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] The following is further disclosed regarding the embodiments described above.

[1243] (Claim 1)

[1244] Data collection means,

[1245] A data integration method that standardizes and integrates the collected data,

[1246] Data analysis tools that perform analysis based on integrated data,

[1247] A report generation method that generates a report using the analysis results,

[1248] A report distribution method for distributing the generated report,

[1249] A system that includes this.

[1250] (Claim 2)

[1251] The data collection method automatically acquires data from multiple external data sources via APIs.

[1252] The system according to claim 1.

[1253] (Claim 3)

[1254] Data analysis tools analyze data using machine learning algorithms and statistical analysis methods.

[1255] The system according to claim 1.

[1256] "Example 1"

[1257] (Claim 1)

[1258] Data collection means,

[1259] A data integration method that standardizes and integrates the collected data,

[1260] Data analysis tools that perform analysis based on integrated data,

[1261] A report generation method that generates a report using the analysis results,

[1262] A report distribution method for distributing the generated report,

[1263] A system that includes this.

[1264] (Claim 2)

[1265] The data collection method automatically acquires data from multiple external data sources via APIs.

[1266] The system according to claim 1.

[1267] (Claim 3)

[1268] Data analysis tools analyze data using machine learning algorithms and statistical analysis methods.

[1269] The system according to claim 1.

[1270] ---

[1271] (Revised claims)

[1272] (Claim 1)

[1273] Data collection means,

[1274] A data integration method that standardizes collected data into a common format, removes duplicate data, and imputes missing values,

[1275] Data analysis tools that diagnose integrated data and perform clustering and predictive analysis,

[1276] A report generation means that generates a report that visually displays the analysis results,

[1277] A report distribution method that automatically distributes the generated report,

[1278] A system that includes this.

[1279] (Claim 2)

[1280] The data collection method automatically retrieves data in real time from multiple external data sources specified by the user via an API and stores it in temporary storage.

[1281] The system according to claim 1.

[1282] (Claim 3)

[1283] Data analysis methods employ machine learning algorithms and statistical analysis techniques to perform clustering and predictive analysis.

[1284] The system according to claim 1.

[1285] "Application Example 1"

[1286] (Claim 1)

[1287] Data collection means,

[1288] A data integration method that standardizes and integrates the collected data,

[1289] Data analysis tools that perform analysis based on integrated data,

[1290] A presentation generation method that generates a presentation using the analysis results,

[1291] A presentation distribution method for distributing the generated presentation,

[1292] A cloud distribution method that uploads the generated presentation to the cloud,

[1293] A system that includes this.

[1294] (Claim 2)

[1295] The data collection method automatically acquires data from multiple external data sources via APIs.

[1296] The system according to claim 1.

[1297] (Claim 3)

[1298] Data analysis tools analyze data using machine learning algorithms and statistical analysis methods.

[1299] The system according to claim 1.

[1300] (Claim 4)

[1301] This includes a presentation distribution method that sends the generated presentation to a specified device or email address.

[1302] The system according to claim 1.

[1303] (Claim 5)

[1304] Includes a cloud distribution method that uploads the generated presentation to cloud storage and generates a sharing link.

[1305] The system according to claim 1.

[1306] "Example 2 of combining an emotion engine"

[1307] (Claim 1)

[1308] Data collection means,

[1309] A data integration method that standardizes and integrates the collected data,

[1310] Data analysis tools that perform analysis based on integrated data,

[1311] A report generation method that generates a report using the analysis results,

[1312] A report distribution method for distributing the generated report,

[1313] A sentiment analysis method that analyzes user emotions in real time,

[1314] A feedback provision method that provides feedback based on the results of emotion analysis,

[1315] A system that includes this.

[1316] (Claim 2)

[1317] The data acquisition method automatically acquires data from multiple external data sources through an application programming interface.

[1318] The system according to claim 1.

[1319] (Claim 3)

[1320] Data analysis tools analyze data using machine learning algorithms and statistical analysis techniques.

[1321] The system according to claim 1.

[1322] (Claim 4)

[1323] The emotion analysis means identifies emotions from the user's voice data and facial expression data.

[1324] The system according to claim 1.

[1325] (Claim 5)

[1326] The feedback provision method optimizes the content and format of the report based on the results of sentiment analysis.

[1327] The system according to claim 1.

[1328] (Claim 6)

[1329] The priority of data to be collected is dynamically changed based on the results of sentiment analysis.

[1330] The system according to claim 1.

[1331] "Application example 2 when combining with an emotional engine"

[1332] (Claim 1)

[1333] Data collection means,

[1334] A data integration method that standardizes and integrates the collected data,

[1335] Data analysis tools that perform analysis based on integrated data,

[1336] A report generation method that generates a report using the analysis results,

[1337] A report distribution method for distributing the generated report,

[1338] An emotion engine that recognizes the user's emotions,

[1339] A feedback mechanism that dynamically adjusts the content of reports based on user sentiment,

[1340] A system that includes this.

[1341] (Claim 2)

[1342] The data collection method automatically acquires data from multiple external data sources via APIs.

[1343] The system according to claim 1.

[1344] (Claim 3)

[1345] Data analysis tools analyze data using machine learning algorithms and statistical analysis methods.

[1346] The system according to claim 1.

[1347] --- [Explanation of Symbols]

[1348] 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. Data collection means, A data integration method that standardizes and integrates the collected data, Data analysis tools that perform analysis based on integrated data, A report generation method that generates a report using the analysis results, A report distribution method for distributing the generated report, A system that includes this.

2. The data collection method automatically acquires data from multiple external data sources via APIs. The system according to claim 1.

3. Data analysis tools analyze data using machine learning algorithms and statistical analysis methods. The system according to claim 1.

Images