system

Abstract

We provide the system. [Solution] Means of obtaining quarterly financial data for a specific company, Means for formatting and pre-processing acquired financial data, A method for performing competitive analysis using generative AI based on preprocessed data, A means of generating a report based on the analysis results, A means of notifying the user of the generated report, A means of collecting user feedback and incorporating it into the learning process for future generation AI, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In order for a company to maintain and improve its competitiveness, it is essential to quickly grasp the performance and market trends of competing companies and formulate appropriate business strategies based on them. However, collecting and analyzing this information requires a great deal of time and effort, which is a heavy burden for small and medium-sized enterprises and companies with limited resources. In addition, specialized knowledge is often required to ensure the accuracy and speed of analysis, which may affect business decisions. Therefore, an object of the present invention is to provide a system for simply and quickly performing competitive analysis of companies, enabling companies to efficiently improve their competitiveness.

Means for Solving the Problems

[0005] To solve the above-mentioned problems, the present invention provides the following means: a system including means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generating AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for collecting user feedback and reflecting it in the learning of the generating AI for future use. This enables companies to quickly and accurately compare the performance of a specific company with that of its competitors and efficiently obtain the information necessary for formulating management strategies.

[0006]

[0007] "Specific companies" refers to companies that the user has designated for comparative analysis.

[0008] "Quarterly financial data" refers to data that companies release on a quarterly basis, showing their financial status and performance.

[0009] "Means" refers to specific methods or systems for realizing the particular processes or functions described in this invention.

[0010] "Means of acquisition" refers to methods and systems for collecting necessary data from external data sources.

[0011] "Means for formatting and preprocessing" refers to methods and systems for converting collected data into a format that is easy to analyze, and for cleaning and standardizing the data.

[0012] "Generative AI" refers to algorithms and systems that use technologies such as machine learning and deep learning to analyze data and automatically generate solutions to specific problems.

[0013] "Methods for conducting competitive analysis" refer to methods and systems for evaluating competitiveness by comparing the performance and indicators of a specific company with its competitors.

[0014] "Means for generating a report" refers to a method or system for creating a detailed report based on the analysis results.

[0015] "Means for notifying" refers to a method or system for informing the user of the completion of the generated report.

[0016] "Means for collecting feedback" refers to a method or system for collecting evaluations and opinions from users and using them to improve the system.

Brief Description of the Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a numbered 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] 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.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. This system is implemented according to the following procedure.

[0039] First, the server collects quarterly financial data of specific companies from reliable data sources. For example, it can use APIs provided by stock exchanges. This collected data is then temporarily stored in a database on the server.

[0040] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. It also performs imputation if missing values ​​exist to maintain data quality.

[0041] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of these metrics with the competitors.

[0042] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0043] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0044] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0045] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs a comparative analysis using a generation AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on a dashboard and provides feedback on its contents. This feedback is collected by the server and used to generate future reports.

[0046] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0050] Step 2:

[0051] The server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it may use data from the previous year or industry averages to fill in the gaps.

[0052] Step 3:

[0053] The server provides input data to the generating AI based on the formatted and pre-processed data. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, and then begins an analysis to compare them.

[0054] Step 4:

[0055] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The analysis results are stored on the server as intermediate data.

[0056] Step 5:

[0057] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. These reports include specific performance comparisons and analyses of a particular company and its competitors. For example, they might state, "Company A's sales increased by 10%, while competitor B increased by 15%, and competitor C by 12%."

[0058] Step 6:

[0059] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to know that the report has been generated.

[0060] Step 7:

[0061] After receiving a notification, users access the dashboard to review the generated report. Here, they can view detailed information about the report and evaluate its contents if necessary.

[0062] Step 8:

[0063] Users provide feedback on the report's content. Specifically, a feedback form is displayed on the device for users to input their evaluation and suggestions for improvement. Users submit their opinions through this form.

[0064] Step 9:

[0065] The server collects user feedback and uses it as training data for future generation AI. The collected feedback is used to adjust the parameters of the generation AI and improve the algorithm, continuously improving the accuracy of the reports.

[0066] (Example 1)

[0067] 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."

[0068] In today's world, it is crucial to quickly and accurately understand the performance of a specific organization and conduct competitive analysis. However, traditional methods require manual data collection and analysis, which is time-consuming and labor-intensive. Furthermore, the accuracy and reproducibility of the analysis results are often not guaranteed. In addition, it is difficult to incorporate feedback, limiting the quality of the generated analysis reports. There is a need for a system that solves these problems, efficiently collects, processes, and analyzes performance data automatically, and provides reliable information.

[0069] 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.

[0070] In this invention, the server includes means for acquiring quarterly performance data of a specific organization, means for formatting and pre-processing the acquired performance data, means for performing competitive analysis using computer intelligence generated based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for collecting feedback from the user and incorporating it into the learning of the computer intelligence generated in the future. This enables automatic collection of performance data, efficient data processing, reliable competitive analysis, and the generation of high-quality reports that reflect feedback.

[0071] "Specific organization" refers to corporations, groups, or other legal entities with a specific purpose.

[0072] "Quarterly performance data" refers to data that shows the financial status and performance of an organization for each of the four periods (quarters) in which the year is divided.

[0073] A "reliable data source" refers to an organization or platform that provides data whose accuracy and reliability are guaranteed.

[0074] "Formatting and preprocessing" refers to the process of converting acquired data into an analyzable format and appropriately correcting any missing or redundant parts.

[0075] "Generated computational intelligence" refers to artificial intelligence models built using technologies such as machine learning and deep learning.

[0076] "Competitive analysis" refers to an analysis that compares the performance of a particular organization with that of other organizations to evaluate its competitiveness and market position.

[0077] "Key performance indicators" refer to important metrics used to evaluate the performance and health of a company or organization, such as sales, profits, and growth rates.

[0078] A "report" refers to a document summarizing the results of a competitive analysis, including the performance of a specific organization and a comparison with its competitors.

[0079] "Users" refers to individuals or organizations that use this system to acquire information and utilize the analysis results.

[0080] "Opinions" refer to the feedback and evaluations that users provide to the system.

[0081] This invention relates to an information processing system that automatically collects performance data from a specific organization, performs competitive analysis, and provides the results to the user. A specific example of this system is described below.

[0082] This system is primarily composed of three components: servers, terminals, and users.

[0083] First, the server is designed to collect performance data for specific organizations, which is released quarterly, from reliable data sources. This utilizes APIs provided by stock exchanges, for example. The data obtained through the API is stored in a database on the server. For example, the EDGAR API is used to retrieve quarterly financial data for a specific company.

[0084] Next, the server formats and preprocesses the acquired performance data. Specifically, it removes unnecessary fields and converts numerical data to a standardized format. It also imputes missing values ​​using the mean. This preprocessing ensures data quality.

[0085] Based on the formatted and pre-processed data, the server performs competitive analysis using a generative AI model. The generative AI model is built using programming languages ​​such as Python and extracts key metrics (sales, profits, growth rate, etc.) for a specific organization and its competitors specified by the user, and compares them. An example of a prompt is shown below.

[0086] "Obtain the latest quarterly financial data for specific company A regarding sales, profits, and growth rate, and compare it to competitors B and C."

[0087] The server generates a detailed report based on the analysis results obtained from the generated AI model. This report includes comparisons of key indicators such as sales, profits, and growth rates, and also provides comparisons with historical data. For example, it may state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0088] The generated report is notified to the user from the server. Notification methods include email and push notifications. Upon receiving this notification, the user can access their dashboard and view the detailed report.

[0089] Furthermore, users can provide feedback on the report. A feedback form is displayed on the device, allowing users to enter their opinions. The feedback is sent to the server and stored in a database. This data is then used as training data for future AI model generation.

[0090] In this way, the present invention makes it possible to automatically collect, format, and analyze performance data of a specific organization, and to provide users with reliable competitive analysis results. Furthermore, by incorporating user feedback, the generated AI model can be continuously improved.

[0091] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0092] Step 1: Data Collection

[0093] The server retrieves quarterly performance data for a specific company from a reliable data source. Specifically, it uses a stock exchange API (e.g., the EDGAR API) to collect the latest financial data. It sends a request to this API and receives the data in JSON format. The input includes a company identifier (e.g., company code) and a period (quarter). The JSON data contains information such as the company's sales, profits, and growth rate. The server stores this data in a database.

[0094] Step 2: Data Preprocessing

[0095] The server formats and preprocesses the collected performance data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. Furthermore, it imputes missing values ​​using means such as the mean. The JSON-formatted financial statements collected earlier are used as input. As a result of this data processing, a clean, preprocessed dataset is generated. The server holds this dataset in memory for use in the next step.

[0096] Step 3: Competitive Analysis

[0097] The server uses pre-processed data to input prompts into a generated AI model and performs competitive analysis. Specifically, prompts are input to an AI model built using a programming language such as Python. For example, a prompt such as "Retrieve the latest quarterly financial data regarding the sales, profits, and growth rate of company A, and compare it with competitors B and C" might be used. The AI ​​model performs the analysis based on this prompt and compares the performance of each company. As output, a comparison of the sales, profits, and growth rates of company A and its competitors is generated.

[0098] Step 4: Generate the report

[0099] The server generates a detailed report based on the analysis results of the generated AI model. Specifically, it creates reports in PDF or HTML format based on the acquired comparative data. The report includes comparative results of key indicators such as sales, profits, and growth rates. The comparative data acquired in step 3 is used as input. As output, a detailed report in a user-friendly format is generated. The server saves this report to the specified location.

[0100] Step 5: Report notification and viewing

[0101] The server notifies the user of the generated report. Specifically, it uses an SMTP server to send a report generation notification to the user's registered email address. Push notifications can also be sent. The user's contact information and the generated report are used as input. The output is a notification sent to the user's device. Upon receiving the notification, the user can access the dashboard and view the detailed report.

[0102] Step 6: Gathering and implementing feedback

[0103] Users provide feedback on the generated reports. Specifically, they enter their opinions into a feedback form displayed on their device and submit it. The feedback is sent to the server and stored in a database. The input is user feedback. The output is the feedback data stored on the server. This feedback is used as training data for future AI model generation. This improves the accuracy of the AI ​​model.

[0104] (Application Example 1)

[0105] 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."

[0106] To maintain and improve a company's competitiveness, it is necessary to quickly and efficiently compare and analyze the performance of a specific company with that of its competitors. However, traditional methods rely on manual processes for data collection, formatting, preprocessing, analysis, and report generation, which are time-consuming and labor-intensive. Furthermore, there is no efficient way to notify users of reports or collect feedback. An automated system is needed to solve these problems.

[0107] 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.

[0108] In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generative AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generative AI for subsequent uses, means for generating prompt sentences for performing analysis with the generative AI model based on the collected, formatted, and pre-processed data, and means for sending push notifications or emails when notifying the user of the generated report. This enables companies to quickly and efficiently automatically generate performance comparison analysis reports, effectively notify users of the results, and reflect the feedback in the learning of the generative AI for subsequent uses.

[0109] "Specific companies" refers to the companies selected for analysis.

[0110] "Quarterly financial data" refers to the financial information that companies report on a quarterly basis.

[0111] "Means of acquisition" refers to methods and mechanisms for collecting data from trusted data sources such as APIs.

[0112] "Means of formatting and preprocessing" refers to methods and mechanisms for removing unnecessary fields from collected data, imputing missing values, and converting data into a unified format.

[0113] "Generative AI" refers to a technology that uses artificial intelligence to analyze and predict data.

[0114] "Means of conducting competitive analysis" refers to methods and systems for comparing and analyzing the performance data of a specific company and its competitors.

[0115] "Means of generating reports" refers to methods and mechanisms for creating detailed reports to provide to users based on analysis results.

[0116] "Means of notifying users" refers to methods and mechanisms such as push notifications and emails used to inform users of generated reports.

[0117] "Means of collecting user feedback" refers to methods and mechanisms for collecting users' opinions and impressions of reports.

[0118] "Means of incorporating feedback into the learning of generative AI" refers to methods and mechanisms for improving the generative AI using collected feedback and enhancing the accuracy of subsequent analyses.

[0119] "Means for generating prompt statements" refers to methods and mechanisms for creating instruction statements for analysis by a generative AI model based on collected, formatted, and pre-processed data.

[0120] "Means of sending push notifications and emails" refers to real-time notification methods and email sending mechanisms for informing users of generated reports.

[0121] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. The following describes embodiments for carrying out this invention.

[0122] Hardware and software to be used

[0123] hardware

[0124] Servers (cloud services such as AWS and GCP)

[0125] User's smartphone

[0126] software

[0127] Data collection: Python (requests, pandas)

[0128] Data formatting and preprocessing: pandas, NumPy

[0129] Generative AI models: Tensorflow, PyTorch

[0130] Notification system: Firebase Cloud Messaging, SendGrid

[0131] Feedback collection: Firebase Realtime Database

[0132] Overall flow of the system

[0133] Data acquisition

[0134] The server uses trusted data sources such as APIs (e.g., stock exchange APIs) to collect quarterly financial data for specific companies.

[0135] Data formatting and preprocessing

[0136] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data.

[0137] Analysis by Generative AI

[0138] Based on preprocessed data, a generative AI model is used to perform competitive analysis. The generative AI model is built using Tensorflow or PyTorch, and extracts key metrics such as sales, profits, and growth rates for each company, and compares them.

[0139] An example of a prompt message to the generating AI used in this process is as follows:

[0140] Collect the latest quarterly financial data for the specified company and conduct a comparative analysis with its competitors using the following metrics: sales, profits, growth rate, etc. Based on the results, generate a detailed report and provide a prompt to notify the user.

[0141] Report generation and notification

[0142] Based on the analysis results, the server generates a detailed report. This report is then communicated to the user via Firebase Cloud Messaging or SendGrid. Push notifications and emails are sent, allowing users to confirm receipt of the report in real time.

[0143] Feedback Collection

[0144] Users can provide feedback on the reports. This feedback is collected using the Firebase Realtime Database and used as training data for future generative AI. This allows the generative AI to continuously improve and generate more accurate reports.

[0145] Specific example

[0146] For example, the system can obtain quarterly financial data for a specific company, "Company A," and its competitors, "Company B" and "Company C," and compare and analyze their respective sales, profits, and growth rates. The analysis results would then be generated as a report detailing specific information, such as "Company A's sales increased by 10% in the third quarter of 2023, while competitors B and C recorded increases of 15% and 12% respectively. The generated report would be sent to the user via push notification or email, allowing them to review it and provide feedback.

[0147] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0148] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0149] Step 1: Data Acquisition

[0150] The server collects quarterly financial data for specific companies using trusted data sources such as APIs. Specifically, it retrieves financial data from stock exchange APIs. The input is the financial data provided via the API, and the output is the retrieved raw data.

[0151] Step 2: Data preparation and preprocessing

[0152] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data. The input is the raw data obtained, and the output is the preprocessed, clean data.

[0153] Step 3: Generating prompts for the AI

[0154] The server generates prompt statements for analysis using a generative AI model, based on the formatted and pre-processed data. Specifically, it creates concrete instructions for analyzing the collected and formatted data. The input is the pre-processed data, and the output is the generated prompt statements.

[0155] Step 4: Competitive Analysis

[0156] This program performs competitive analysis based on pre-processed data using a generative AI model. The generative AI model is built using Tensorflow and PyTorch, extracting key metrics such as sales, profits, and growth rates for each company, and comparing them. The input consists of prompts and pre-processed data, while the output is the analysis results.

[0157] Step 5: Report Generation

[0158] The server generates a detailed report based on the analysis results. Specifically, it compiles key metrics of interest to the user and comparison results with competitors into a report. The input is the analysis results, and the output is the generated detailed report.

[0159] Step 6: Report Notification

[0160] The generated report is sent as a notification to the user's smartphone. Specifically, push notifications and emails are sent using Firebase Cloud Messaging or SendGrid. The input is the generated report, and the output is the notification to the user.

[0161] Step 7: Gathering Feedback

[0162] Users can provide feedback on the report. This feedback is collected using Firebase Realtime Database and used as training data for future generative AI iterations. The input is user feedback, and the output is the training data for the generative AI.

[0163] The above outlines the specific processing steps of the system that implements the application example.

[0164] 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.

[0165] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. By combining this system with an emotion engine that recognizes the user's emotions, it can provide more personalized reports.

[0166] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0167] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0168] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of the competitors based on these metrics.

[0169] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0170] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0171] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0172] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0173] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial results data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs the comparative analysis using generative AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions when providing feedback and incorporates this into the generative AI's training data. This improves future reports so that they better meet the user's expectations.

[0174] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[0175] The following describes the processing flow.

[0176] Step 1:

[0177] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers and receives the latest financial data as API responses. This data is stored in a database on the server.

[0178] Step 2:

[0179] The server formats and preprocesses the acquired financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using previous year's data or industry averages. The formatted data is then ready for use in the next processing step.

[0180] Step 3:

[0181] The server provides formatted and pre-processed data as input to the generating AI. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, as specified by the user. Based on the extracted data, it performs a comparative analysis with its competitors.

[0182] Step 4:

[0183] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The results of this analysis are temporarily stored on the server as intermediate data.

[0184] Step 5:

[0185] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. Specifically, it creates reports in PDF or HTML format that include metrics of interest to the user and comparison results for each company. These reports may include specific details such as, "Company A's sales increased by 10%, competitor B's by 15%, and competitor C's by 12%."

[0186] Step 6:

[0187] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to monitor the report generation in real time and prepare to review it.

[0188] Step 7:

[0189] After receiving a notification, users access the dashboard using their device to view the generated report. Here, they can view detailed report content and focus on specific sections.

[0190] Step 8:

[0191] Users provide feedback on the report's content. Specifically, a form for entering evaluations and suggestions for improvement will appear on their device. Users submit their opinions through this form.

[0192] Step 9:

[0193] In this step, an emotion engine is activated to recognize the user's emotions when they provide feedback. It analyzes the user's input and input method (e.g., typing speed and emphasis) to recognize positive or negative emotions.

[0194] Step 10:

[0195] The server collects user feedback and the results of the emotion engine's analysis, using this as training data for the generative AI. The collected data is used to adjust the generative AI's parameters and improve its algorithms, and this information is reflected in future report generation.

[0196] Step 11:

[0197] For subsequent report generation, the report content and format will be dynamically customized based on the analysis results of the emotion engine. Positive feedback will maintain the same report format, while negative feedback will reflect areas for improvement.

[0198] This processing flow allows companies to quickly and accurately perform comparative analysis with competitors and receive personalized reports based on user sentiment.

[0199] (Example 2)

[0200] 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".

[0201] Traditional corporate performance analysis systems often require manual comparison with competitors for specific metrics, making them inefficient and hindering the delivery of personalized reports due to their failure to consider user sentiment. Furthermore, they lack adequate mechanisms for incorporating feedback into system improvements, making subsequent reports likely to fail to meet user expectations. This has made it difficult for companies to quickly and efficiently obtain the information needed to improve their competitiveness.

[0202] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generation AI model based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for including an emotion engine that collects user feedback and analyzes that feedback, and reflects it in the learning of the generation AI model for subsequent uses. This makes it possible to automatically compare and analyze the performance of a company with that of its competitors and to quickly and efficiently provide personalized reports based on the user's emotions.

[0203] "Specific companies" refers to individual legal entities operating in a particular industry or market.

[0204] "Quarterly financial data" refers to data that shows a company's financial activities at the end of each of the four quarters in which the year is divided.

[0205] A "reliable data source" refers to an information provider that is guaranteed to provide accurate and up-to-date information.

[0206] "Formatting" refers to the process of organizing data into a format suitable for analysis and standardizing the format.

[0207] "Preprocessing" refers to the process performed to improve the quality of data prior to analysis, and specifically includes deleting unnecessary data and imputing missing values.

[0208] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically analyze data and is trained to perform a specific task.

[0209] "Competitive analysis" refers to an analysis that compares the performance of a specific company with that of its competitors to identify its strengths and weaknesses.

[0210] A "report" refers to an official document that summarizes analysis results and insights.

[0211] "Users" refer to individuals or corporations that use this system to obtain information.

[0212] "Notification" refers to a means of communication used to inform users of new information or events.

[0213] "Feedback" refers to the opinions and evaluations that users provide about the results and usability of a system.

[0214] An "emotion engine" refers to an algorithm that analyzes the emotions expressed by users during feedback and processes them as data.

[0215] Modes for carrying out the invention

[0216] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. The system can provide more personalized reports by incorporating an emotion engine that recognizes user emotions.

[0217] Data collection

[0218] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. For example, it retrieves the Q3 2023 data for company A. This data is then temporarily stored in a database on the server.

[0219] Data formatting and preprocessing

[0220] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0221] Competitive analysis

[0222] The formatted and pre-processed data is used by the generative AI model to perform competitive analysis. The server extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and uses these to perform a comparative analysis with competitors. The generative AI model is provided with prompts such as, "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in their growth rates."

[0223] Report generation

[0224] The AI ​​model generates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0225] User notifications

[0226] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0227] Feedback Collection

[0228] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI models. This allows the generation AI model to continuously improve, enabling it to produce more accurate reports.

[0229] Utilizing the Emotion Engine

[0230] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI model. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0231] Specific example

[0232] As a concrete example, consider a scenario where a user wants to perform a comparative analysis of "Company A," "Competitor B," and "Competitor C." The server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data and performs a comparative analysis using a generative AI model. The prompt used is "Compare the quarterly sales data of Company A, Company B, and Company C, and analyze the differences in growth rates." A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions during feedback and incorporates them into the training data of the generative AI model. This improves future reports to better meet user expectations.

[0233] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[0234] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0235] Step 1: Data Collection

[0236] The server retrieves quarterly financial data for a specific company from a trusted data source. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. The server sends a "GET" request to the API endpoint, receives the returned data in JSON format, and parses it. The input is the identification information of the specific company, and the output is the parsed financial data.

[0237] Step 2: Data preparation and preprocessing

[0238] The server formats and preprocesses the collected financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using historical data or industry averages. Specifically, it reads data from the database, executes formatting and preprocessing algorithms, and generates clean data. The input is parsed financial data, and the output is formatted and preprocessed data.

[0239] Step 3: Competitive Analysis

[0240] The server performs competitive analysis using a generative AI model based on the formatted and pre-processed data. It extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user. The prompt used is "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in growth rates." The server inputs the data into the generative AI model and receives the analysis results as output. The input consists of formatted and pre-processed data and the prompt, and the output is the result of the competitive analysis.

[0241] Step 4: Report Generation

[0242] The AI ​​model generates a detailed report based on the competitive analysis results. The report includes key metrics of interest to the user and comparisons with competitors. For example, it might state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B increased by 15% and competitor C by 12%." The server converts the analysis results into a text-based report and prepares it for display on the dashboard. The input is the competitive analysis results, and the output is the generated report.

[0243] Step 5: Notify the user

[0244] The server notifies the user of the generated report. It sends a message to the user via email or a push notification system stating, "A new report has been generated." Upon receiving the notification, the user can access the dashboard to view the detailed report. The input is the generated report, and the output is the notification message to the user.

[0245] Step 6: Gathering Feedback

[0246] Users provide feedback on the report's content and format through their device. A feedback form is displayed, and users enter their opinions and suggestions for improvement and submit it. The server collects this feedback. The input is the user's feedback, and the output is the feedback data.

[0247] Step 7: Emotional analysis using the emotion engine

[0248] The emotion engine analyzes the user's emotions when they provide feedback. Specifically, it uses a text analysis algorithm to classify emotions as positive or negative. For example, if the user writes, "This information was very helpful," it will be classified as a positive emotion. The input is feedback data, and the output is an emotion score.

[0249] Step 8: Updating the Generating AI

[0250] The server uses the collected feedback and sentiment data as training data for its generative AI model. This allows the generative AI model to be improved for future report generation. Specifically, the collected data is added to the training dataset, and the generative AI model is retrained. The input is the feedback and sentiment data, and the output is the updated generative AI model.

[0251] (Application Example 2)

[0252] 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".

[0253] Companies need to continuously understand market trends and competitor activities to maintain and improve their competitiveness. However, there is a lack of systems that can automatically collect and analyze vast amounts of data and then specifically propose how to utilize it in advertising strategies. Furthermore, there is a demand for personalized information that is continuously improved based on user feedback. Currently, there is no system that can integrate and efficiently provide all of these requirements, making it difficult for companies to obtain the right information quickly.

[0254] 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 means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generating AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generating AI for subsequent uses, means for analyzing the user's emotions at the time of feedback and personalizing the generated report, and means for optimizing the advertising strategy based on the report and evaluating and proposing the performance of advertising creatives and the effectiveness of campaigns. As a result, companies can automatically grasp the competitive situation and quickly build and execute effective advertising strategies.

[0255] "Specific companies" refers to one or more existing legal entities whose performance is evaluated based on financial data that is released quarterly.

[0256] "Quarterly financial data" refers to information that companies disclose on a quarterly basis, showing their financial status and including figures such as sales, profits, and growth rates.

[0257] "Data shaping and preprocessing" refers to the process of removing unnecessary fields and inaccurate data from collected quarterly financial statements and standardizing the format of numerical data.

[0258] "Generative AI" is an algorithm that uses artificial intelligence technology to perform competitive analysis based on key metrics specified by the user and generate a detailed report.

[0259] "Competitive analysis" is the process of evaluating the performance of a particular company by comparing it to other companies operating in the same market.

[0260] "Report generation" is the process of creating a document that compiles useful information for users based on analyzed competitive data.

[0261] "Notifications" refer to means of informing users of the existence of generated reports, and include email and push notifications.

[0262] "Feedback" refers to the opinions and evaluations that users provide regarding the generated reports.

[0263] "Emotional analysis" is a technology that recognizes a user's emotions during feedback and analyzes whether those emotions are positive or negative.

[0264] Personalization is the process of adjusting the information and services provided to a user to match their specific needs and expectations, based on the results of sentiment analysis.

[0265] "Advertising strategy optimization" is the process of planning and executing the most effective advertising campaigns based on analysis results and user feedback.

[0266] "Advertising creative performance" refers to evaluating how effective the elements used in an advertisement, such as images, videos, and text, actually were.

[0267] "Campaign effectiveness" is a measure used to evaluate how much an implemented advertising campaign contributed to achieving its goals.

[0268] This invention is a system for optimizing advertising strategies by comparing the performance of a specific company with that of its competitors. This system is specifically implemented as an application installed on smartphones.

[0269] First, the server retrieves quarterly financial data for a specific company from a reliable data source. Specifically, it accesses the API of a financial data provider to obtain the latest financial data. This data is then temporarily stored in a database on the server.

[0270] Next, the acquired data is formatted and preprocessed. Unnecessary fields and inaccurate data are removed, and the format of numerical data is standardized. In addition, if missing values ​​exist, they are imputed using data from the previous year or industry averages.

[0271] The formatted and pre-processed data is used for competitive analysis using generative AI. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors, and performs competitive analysis based on these metrics. Based on the analysis results, the server generates a detailed report. This report includes key metrics of interest to the user and comparisons with competitors.

[0272] The generated report is notified to the user via push notification or email on their smartphone. The user can open the application and view the detailed report on the dashboard. Here, the user can provide feedback on the report's content. The sentiment engine analyzes this feedback and recognizes the user's emotions. If the feedback is positive, additional data is added to maintain and enhance the report's content. Conversely, if negative emotions are recognized, areas for improvement in the report are clearly indicated.

[0273] Next, the generating AI uses this feedback to improve its learning for subsequent reports. This results in more accurate reports that better meet user expectations. Furthermore, as a means of optimizing advertising strategies, the system collects performance data for ad creatives and campaign effectiveness measurement data, integrating these with the results of competitive analysis. An optimized advertising strategy is then proposed to the user.

[0274] As a concrete example, let's say a specific company is "Company A," and its competitors are "Company B" and "Company C." The server retrieves the latest quarterly financial data for these companies from EDGAR and other data sources. Next, after formatting and preprocessing the data, a comparative analysis is performed by a generative AI. Based on the results of this analysis, a detailed report is generated and notified to the user. The user reviews the report on a dashboard and provides feedback. During this feedback process, an emotion engine analyzes the user's emotions and incorporates them into the generative AI's training data.

[0275] Example of a prompt:

[0276] "The user wants to compare the performance of 'Company A,' 'Company B,' and 'Company C.' Based on the latest quarterly earnings data collected, conduct a competitive analysis and generate a personalized advertising strategy report. The user's sentiment feedback is 'I am very happy with the report!' Please consider this feedback to improve the content of the next report."

[0277] The three elements of server, terminal, and user work together to efficiently perform automated analysis of corporate performance and optimize advertising strategies.

[0278] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0279] Step 1:

[0280] The server obtains the quarterly financial data of a specific company from a reliable data source. This input data is raw data obtained through an API request, and the output is the unformatted financial data stored in the database. The data is obtained via the API endpoint and saved in the server's database.

[0281] Step 2:

[0282] The server formats and preprocesses the obtained financial data. This input data is the financial data obtained from the raw database, and the output is the formatted data with unnecessary fields and inaccurate data removed and missing values filled. Specifically, redundant information is removed, and the process of filling in missing values with data from the previous year or industry average is performed.

[0283] Step 3:

[0284] The server performs competitive analysis using generative AI based on the preprocessed data. This input data is the preprocessed and formatted financial data, and the output is the competitive analysis result by the generative AI model. Specifically, key indicators such as sales, profit, and growth rate are extracted, and a comparative analysis with competing companies is performed based on these.

[0285] Step 4:

[0286] The server generates a report based on the analysis result. This input data is the competitive analysis result by the generative AI model, and the output is a detailed report. The generative AI creates a detailed report according to the specified prompt text, including key indicators that draw the user's interest and competitive comparisons.

[0287] Step 5:

[0288] The server notifies the user of the generated report. This input data is the generated detailed report, and the output is a notification to the user's smartphone. Specifically, emails or push notifications are sent to inform the user that the report is available.

[0289] Step 6:

[0290] Users view reports on a dashboard and provide feedback. The input data includes the report content and user feedback text, while the output is feedback data and the user's sentiment state. Users review the report and input their thoughts and suggestions for improvement.

[0291] Step 7:

[0292] The server collects user feedback and performs sentiment analysis. The input data is the feedback text, and the output is the user's sentiment analysis results and updated AI model training data. The sentiment engine analyzes the emotional state of the feedback and reflects this in the generative AI model.

[0293] Step 8:

[0294] The server updates the generating AI based on the sentiment analysis results and reflects them in subsequent reports. The input data consists of the sentiment analysis results and updated training data, while the output is a more personalized report in subsequent reports. The generating AI model is continuously trained to provide reports that better meet user expectations.

[0295] Step 9:

[0296] The server optimizes advertising strategies and proposes optimized advertising campaigns. The input data includes competitive analysis results and sentiment analysis results, and the output is an optimized advertising strategy report. It integrates advertising creative performance data and campaign effectiveness measurement data to suggest the best advertising strategy for the user.

[0297] 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.

[0298] 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.

[0299] 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.

[0300] [Second Embodiment]

[0301] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0302] 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.

[0303] 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).

[0304] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the microphone 238, the speaker 240, and the camera 42 are connected to the bus 52.

[0305] The microphone 238 receives instructions etc. from the user 20 by receiving the voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into voice data, and outputs it to the processor 46. The speaker 240 outputs voice according to an instruction from the processor 46.

[0306] The camera 42 is a small digital camera equipped with an optical system such as a lens, an aperture, and a shutter, and an imaging device such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and images the surroundings of the user 20 (for example, an imaging range defined by an angle of view corresponding to the field of view of a general healthy person).

[0307] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0308] FIG. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in FIG. 4, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32.

[0309] 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.

[0310] 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.

[0311] 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.

[0312] 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".

[0313] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. This system is implemented according to the following procedure.

[0314] First, the server collects quarterly financial data of specific companies from reliable data sources. For example, it can use APIs provided by stock exchanges. This collected data is then temporarily stored in a database on the server.

[0315] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. It also performs imputation if missing values ​​exist to maintain data quality.

[0316] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of these metrics with the competitors.

[0317] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0318] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0319] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0320] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs a comparative analysis using a generation AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on a dashboard and provides feedback on its contents. This feedback is collected by the server and used to generate future reports.

[0321] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0325] Step 2:

[0326] The server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it may use data from the previous year or industry averages to fill in the gaps.

[0327] Step 3:

[0328] The server provides input data to the generating AI based on the formatted and pre-processed data. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, and then begins an analysis to compare them.

[0329] Step 4:

[0330] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The analysis results are stored on the server as intermediate data.

[0331] Step 5:

[0332] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. These reports include specific performance comparisons and analyses of a particular company and its competitors. For example, they might state, "Company A's sales increased by 10%, while competitor B increased by 15%, and competitor C by 12%."

[0333] Step 6:

[0334] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to know that the report has been generated.

[0335] Step 7:

[0336] After receiving a notification, users access the dashboard to review the generated report. Here, they can view detailed information about the report and evaluate its contents if necessary.

[0337] Step 8:

[0338] Users provide feedback on the report's content. Specifically, a feedback form is displayed on the device for users to input their evaluation and suggestions for improvement. Users submit their opinions through this form.

[0339] Step 9:

[0340] The server collects user feedback and uses it as training data for future generation AI. The collected feedback is used to adjust the parameters of the generation AI and improve the algorithm, continuously improving the accuracy of the reports.

[0341] (Example 1)

[0342] 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".

[0343] In today's world, it is crucial to quickly and accurately understand the performance of a specific organization and conduct competitive analysis. However, traditional methods require manual data collection and analysis, which is time-consuming and labor-intensive. Furthermore, the accuracy and reproducibility of the analysis results are often not guaranteed. In addition, it is difficult to incorporate feedback, limiting the quality of the generated analysis reports. There is a need for a system that solves these problems, efficiently collects, processes, and analyzes performance data automatically, and provides reliable information.

[0344] 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.

[0345] In this invention, the server includes means for acquiring quarterly performance data of a specific organization, means for formatting and pre-processing the acquired performance data, means for performing competitive analysis using computer intelligence generated based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for collecting feedback from the user and incorporating it into the learning of the computer intelligence generated in the future. This enables automatic collection of performance data, efficient data processing, reliable competitive analysis, and the generation of high-quality reports that reflect feedback.

[0346] "Specific organization" refers to corporations, groups, or other legal entities with a specific purpose.

[0347] "Quarterly performance data" refers to data that shows the financial status and performance of an organization for each of the four periods (quarters) in which the year is divided.

[0348] A "reliable data source" refers to an organization or platform that provides data whose accuracy and reliability are guaranteed.

[0349] "Formatting and preprocessing" refers to the process of converting acquired data into an analyzable format and appropriately correcting any missing or redundant parts.

[0350] "Generated computational intelligence" refers to artificial intelligence models built using technologies such as machine learning and deep learning.

[0351] "Competitive analysis" refers to an analysis that compares the performance of a particular organization with that of other organizations to evaluate its competitiveness and market position.

[0352] "Key performance indicators" refer to important metrics used to evaluate the performance and health of a company or organization, such as sales, profits, and growth rates.

[0353] A "report" refers to a document summarizing the results of a competitive analysis, including the performance of a specific organization and a comparison with its competitors.

[0354] "Users" refers to individuals or organizations that use this system to acquire information and utilize the analysis results.

[0355] "Opinions" refer to the feedback and evaluations that users provide to the system.

[0356] This invention relates to an information processing system that automatically collects performance data from a specific organization, performs competitive analysis, and provides the results to the user. A specific example of this system is described below.

[0357] This system is primarily composed of three components: servers, terminals, and users.

[0358] First, the server is designed to collect performance data for specific organizations, which is released quarterly, from reliable data sources. This utilizes APIs provided by stock exchanges, for example. The data obtained through the API is stored in a database on the server. For example, the EDGAR API is used to retrieve quarterly financial data for a specific company.

[0359] Next, the server formats and preprocesses the acquired performance data. Specifically, it removes unnecessary fields and converts numerical data to a standardized format. It also imputes missing values ​​using the mean. This preprocessing ensures data quality.

[0360] Based on the formatted and pre-processed data, the server performs competitive analysis using a generative AI model. The generative AI model is built using programming languages ​​such as Python and extracts key metrics (sales, profits, growth rate, etc.) for a specific organization and its competitors specified by the user, and compares them. An example of a prompt is shown below.

[0361] "Obtain the latest quarterly financial data for specific company A regarding sales, profits, and growth rate, and compare it to competitors B and C."

[0362] The server generates a detailed report based on the analysis results obtained from the generated AI model. This report includes comparisons of key indicators such as sales, profits, and growth rates, and also provides comparisons with historical data. For example, it may state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0363] The generated report is notified to the user from the server. Notification methods include email and push notifications. Upon receiving this notification, the user can access their dashboard and view the detailed report.

[0364] Furthermore, users can provide feedback on the report. A feedback form is displayed on the device, allowing users to enter their opinions. The feedback is sent to the server and stored in a database. This data is then used as training data for future AI model generation.

[0365] In this way, the present invention makes it possible to automatically collect, format, and analyze performance data of a specific organization, and to provide users with reliable competitive analysis results. Furthermore, by incorporating user feedback, the generated AI model can be continuously improved.

[0366] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0367] Step 1: Data Collection

[0368] The server retrieves quarterly performance data for a specific company from a reliable data source. Specifically, it uses a stock exchange API (e.g., the EDGAR API) to collect the latest financial data. It sends a request to this API and receives the data in JSON format. The input includes a company identifier (e.g., company code) and a period (quarter). The JSON data contains information such as the company's sales, profits, and growth rate. The server stores this data in a database.

[0369] Step 2: Data Preprocessing

[0370] The server formats and preprocesses the collected performance data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. Furthermore, it imputes missing values ​​using means such as the mean. The JSON-formatted financial statements collected earlier are used as input. As a result of this data processing, a clean, preprocessed dataset is generated. The server holds this dataset in memory for use in the next step.

[0371] Step 3: Competitive Analysis

[0372] The server uses pre-processed data to input prompts into a generated AI model and performs competitive analysis. Specifically, prompts are input to an AI model built using a programming language such as Python. For example, a prompt such as "Retrieve the latest quarterly financial data regarding the sales, profits, and growth rate of company A, and compare it with competitors B and C" might be used. The AI ​​model performs the analysis based on this prompt and compares the performance of each company. As output, a comparison of the sales, profits, and growth rates of company A and its competitors is generated.

[0373] Step 4: Generate the report

[0374] The server generates a detailed report based on the analysis results of the generated AI model. Specifically, it creates reports in PDF or HTML format based on the acquired comparative data. The report includes comparative results of key indicators such as sales, profits, and growth rates. The comparative data acquired in step 3 is used as input. As output, a detailed report in a user-friendly format is generated. The server saves this report to the specified location.

[0375] Step 5: Report notification and viewing

[0376] The server notifies the user of the generated report. Specifically, it uses an SMTP server to send a report generation notification to the user's registered email address. Push notifications can also be sent. The user's contact information and the generated report are used as input. The output is a notification sent to the user's device. Upon receiving the notification, the user can access the dashboard and view the detailed report.

[0377] Step 6: Gathering and implementing feedback

[0378] Users provide feedback on the generated reports. Specifically, they enter their opinions into a feedback form displayed on their device and submit it. The feedback is sent to the server and stored in a database. The input is user feedback. The output is the feedback data stored on the server. This feedback is used as training data for future AI model generation. This improves the accuracy of the AI ​​model.

[0379] (Application Example 1)

[0380] 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."

[0381] To maintain and improve a company's competitiveness, it is necessary to quickly and efficiently compare and analyze the performance of a specific company with that of its competitors. However, traditional methods rely on manual processes for data collection, formatting, preprocessing, analysis, and report generation, which are time-consuming and labor-intensive. Furthermore, there is no efficient way to notify users of reports or collect feedback. An automated system is needed to solve these problems.

[0382] 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.

[0383] In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generative AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generative AI for subsequent uses, means for generating prompt sentences for performing analysis with the generative AI model based on the collected, formatted, and pre-processed data, and means for sending push notifications or emails when notifying the user of the generated report. This enables companies to quickly and efficiently automatically generate performance comparison analysis reports, effectively notify users of the results, and reflect the feedback in the learning of the generative AI for subsequent uses.

[0384] "Specific companies" refers to the companies selected for analysis.

[0385] "Quarterly financial data" refers to the financial information that companies report on a quarterly basis.

[0386] "Means of acquisition" refers to methods and mechanisms for collecting data from trusted data sources such as APIs.

[0387] "Means of formatting and preprocessing" refers to methods and mechanisms for removing unnecessary fields from collected data, imputing missing values, and converting data into a unified format.

[0388] "Generative AI" refers to a technology that uses artificial intelligence to analyze and predict data.

[0389] "Means of conducting competitive analysis" refers to methods and systems for comparing and analyzing the performance data of a specific company and its competitors.

[0390] "Means of generating reports" refers to methods and mechanisms for creating detailed reports to provide to users based on analysis results.

[0391] "Means of notifying users" refers to methods and mechanisms such as push notifications and emails used to inform users of generated reports.

[0392] "Means of collecting user feedback" refers to methods and mechanisms for collecting users' opinions and impressions of reports.

[0393] "Means of incorporating feedback into the learning of generative AI" refers to methods and mechanisms for improving the generative AI using collected feedback and enhancing the accuracy of subsequent analyses.

[0394] "Means for generating prompt statements" refers to methods and mechanisms for creating instruction statements for analysis by a generative AI model based on collected, formatted, and pre-processed data.

[0395] "Means of sending push notifications and emails" refers to real-time notification methods and email sending mechanisms for informing users of generated reports.

[0396] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. The following describes embodiments for carrying out this invention.

[0397] Hardware and software to be used

[0398] hardware

[0399] Servers (cloud services such as AWS and GCP)

[0400] User's smartphone

[0401] software

[0402] Data collection: Python (requests, pandas)

[0403] Data formatting and preprocessing: pandas, NumPy

[0404] Generative AI models: Tensorflow, PyTorch

[0405] Notification system: Firebase Cloud Messaging, SendGrid

[0406] Feedback collection: Firebase Realtime Database

[0407] Overall flow of the system

[0408] Data acquisition

[0409] The server uses trusted data sources such as APIs (e.g., stock exchange APIs) to collect quarterly financial data for specific companies.

[0410] Data formatting and preprocessing

[0411] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data.

[0412] Analysis by Generative AI

[0413] Based on preprocessed data, a generative AI model is used to perform competitive analysis. The generative AI model is built using Tensorflow or PyTorch, and extracts key metrics such as sales, profits, and growth rates for each company, and compares them.

[0414] An example of a prompt message to the generating AI used in this process is as follows:

[0415] Collect the latest quarterly financial data for the specified company and conduct a comparative analysis with its competitors using the following metrics: sales, profits, growth rate, etc. Based on the results, generate a detailed report and provide a prompt to notify the user.

[0416] Report generation and notification

[0417] Based on the analysis results, the server generates a detailed report. This report is then communicated to the user via Firebase Cloud Messaging or SendGrid. Push notifications and emails are sent, allowing users to confirm receipt of the report in real time.

[0418] Feedback Collection

[0419] Users can provide feedback on the reports. This feedback is collected using the Firebase Realtime Database and used as training data for future generative AI. This allows the generative AI to continuously improve and generate more accurate reports.

[0420] Specific example

[0421] For example, the system can obtain quarterly financial data for a specific company, "Company A," and its competitors, "Company B" and "Company C," and compare and analyze their respective sales, profits, and growth rates. The analysis results would then be generated as a report detailing specific information, such as "Company A's sales increased by 10% in the third quarter of 2023, while competitors B and C recorded increases of 15% and 12% respectively. The generated report would be sent to the user via push notification or email, allowing them to review it and provide feedback.

[0422] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0423] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0424] Step 1: Data Acquisition

[0425] The server collects quarterly financial data for specific companies using trusted data sources such as APIs. Specifically, it retrieves financial data from stock exchange APIs. The input is the financial data provided via the API, and the output is the retrieved raw data.

[0426] Step 2: Data preparation and preprocessing

[0427] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data. The input is the raw data obtained, and the output is the preprocessed, clean data.

[0428] Step 3: Generating prompts for the AI

[0429] The server generates prompt statements for analysis using a generative AI model, based on the formatted and pre-processed data. Specifically, it creates concrete instructions for analyzing the collected and formatted data. The input is the pre-processed data, and the output is the generated prompt statements.

[0430] Step 4: Competitive Analysis

[0431] This program performs competitive analysis based on pre-processed data using a generative AI model. The generative AI model is built using Tensorflow and PyTorch, extracting key metrics such as sales, profits, and growth rates for each company, and comparing them. The input consists of prompts and pre-processed data, while the output is the analysis results.

[0432] Step 5: Report Generation

[0433] The server generates a detailed report based on the analysis results. Specifically, it compiles key metrics of interest to the user and comparison results with competitors into a report. The input is the analysis results, and the output is the generated detailed report.

[0434] Step 6: Report Notification

[0435] The generated report is sent as a notification to the user's smartphone. Specifically, push notifications and emails are sent using Firebase Cloud Messaging or SendGrid. The input is the generated report, and the output is the notification to the user.

[0436] Step 7: Gathering Feedback

[0437] Users can provide feedback on the report. This feedback is collected using Firebase Realtime Database and used as training data for future generative AI iterations. The input is user feedback, and the output is the training data for the generative AI.

[0438] The above outlines the specific processing steps of the system that implements the application example.

[0439] 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.

[0440] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. By combining this system with an emotion engine that recognizes the user's emotions, it can provide more personalized reports.

[0441] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0442] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0443] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of the competitors based on these metrics.

[0444] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0445] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0446] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0447] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0448] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial results data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs the comparative analysis using generative AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions when providing feedback and incorporates this into the generative AI's training data. This improves future reports so that they better meet the user's expectations.

[0449] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers and receives the latest financial data as API responses. This data is stored in a database on the server.

[0453] Step 2:

[0454] The server formats and preprocesses the acquired financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using previous year's data or industry averages. The formatted data is then ready for use in the next processing step.

[0455] Step 3:

[0456] The server provides formatted and pre-processed data as input to the generating AI. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, as specified by the user. Based on the extracted data, it performs a comparative analysis with its competitors.

[0457] Step 4:

[0458] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The results of this analysis are temporarily stored on the server as intermediate data.

[0459] Step 5:

[0460] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. Specifically, it creates reports in PDF or HTML format that include metrics of interest to the user and comparison results for each company. These reports may include specific details such as, "Company A's sales increased by 10%, competitor B's by 15%, and competitor C's by 12%."

[0461] Step 6:

[0462] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to monitor the report generation in real time and prepare to review it.

[0463] Step 7:

[0464] After receiving a notification, users access the dashboard using their device to view the generated report. Here, they can view detailed report content and focus on specific sections.

[0465] Step 8:

[0466] Users provide feedback on the report's content. Specifically, a form for entering evaluations and suggestions for improvement will appear on their device. Users submit their opinions through this form.

[0467] Step 9:

[0468] In this step, an emotion engine is activated to recognize the user's emotions when they provide feedback. It analyzes the user's input and input method (e.g., typing speed and emphasis) to recognize positive or negative emotions.

[0469] Step 10:

[0470] The server collects user feedback and the results of the emotion engine's analysis, using this as training data for the generative AI. The collected data is used to adjust the generative AI's parameters and improve its algorithms, and this information is reflected in future report generation.

[0471] Step 11:

[0472] For subsequent report generation, the report content and format will be dynamically customized based on the analysis results of the emotion engine. Positive feedback will maintain the same report format, while negative feedback will reflect areas for improvement.

[0473] This processing flow allows companies to quickly and accurately perform comparative analysis with competitors and receive personalized reports based on user sentiment.

[0474] (Example 2)

[0475] 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".

[0476] Traditional corporate performance analysis systems often require manual comparison with competitors for specific metrics, making them inefficient and hindering the delivery of personalized reports due to their failure to consider user sentiment. Furthermore, they lack adequate mechanisms for incorporating feedback into system improvements, making subsequent reports likely to fail to meet user expectations. This has made it difficult for companies to quickly and efficiently obtain the information needed to improve their competitiveness.

[0477] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generation AI model based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for including an emotion engine that collects user feedback and analyzes that feedback, and reflects it in the learning of the generation AI model for subsequent uses. This makes it possible to automatically compare and analyze the performance of a company with that of its competitors and to quickly and efficiently provide personalized reports based on the user's emotions.

[0478] "Specific companies" refers to individual legal entities operating in a particular industry or market.

[0479] "Quarterly financial data" refers to data that shows a company's financial activities at the end of each of the four quarters in which the year is divided.

[0480] A "reliable data source" refers to an information provider that is guaranteed to provide accurate and up-to-date information.

[0481] "Formatting" refers to the process of organizing data into a format suitable for analysis and standardizing the format.

[0482] "Preprocessing" refers to the process performed to improve the quality of data prior to analysis, and specifically includes deleting unnecessary data and imputing missing values.

[0483] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically analyze data and is trained to perform a specific task.

[0484] "Competitive analysis" refers to an analysis that compares the performance of a specific company with that of its competitors to identify its strengths and weaknesses.

[0485] A "report" refers to an official document that summarizes analysis results and insights.

[0486] "Users" refer to individuals or corporations that use this system to obtain information.

[0487] "Notification" refers to a means of communication used to inform users of new information or events.

[0488] "Feedback" refers to the opinions and evaluations that users provide about the results and usability of a system.

[0489] An "emotion engine" refers to an algorithm that analyzes the emotions expressed by users during feedback and processes them as data.

[0490] Modes for carrying out the invention

[0491] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. The system can provide more personalized reports by incorporating an emotion engine that recognizes user emotions.

[0492] Data collection

[0493] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. For example, it retrieves the Q3 2023 data for company A. This data is then temporarily stored in a database on the server.

[0494] Data formatting and preprocessing

[0495] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0496] Competitive analysis

[0497] The formatted and pre-processed data is used by the generative AI model to perform competitive analysis. The server extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and uses these to perform a comparative analysis with competitors. The generative AI model is provided with prompts such as, "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in their growth rates."

[0498] Report generation

[0499] The AI ​​model generates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0500] User notifications

[0501] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0502] Feedback Collection

[0503] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI models. This allows the generation AI model to continuously improve, enabling it to produce more accurate reports.

[0504] Utilizing the Emotion Engine

[0505] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI model. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0506] Specific example

[0507] As a concrete example, consider a scenario where a user wants to perform a comparative analysis of "Company A," "Competitor B," and "Competitor C." The server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data and performs a comparative analysis using a generative AI model. The prompt used is "Compare the quarterly sales data of Company A, Company B, and Company C, and analyze the differences in growth rates." A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions during feedback and incorporates them into the training data of the generative AI model. This improves future reports to better meet user expectations.

[0508] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[0509] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0510] Step 1: Data Collection

[0511] The server retrieves quarterly financial data for a specific company from a trusted data source. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. The server sends a "GET" request to the API endpoint, receives the returned data in JSON format, and parses it. The input is the identification information of the specific company, and the output is the parsed financial data.

[0512] Step 2: Data preparation and preprocessing

[0513] The server formats and preprocesses the collected financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using historical data or industry averages. Specifically, it reads data from the database, executes formatting and preprocessing algorithms, and generates clean data. The input is parsed financial data, and the output is formatted and preprocessed data.

[0514] Step 3: Competitive Analysis

[0515] The server performs competitive analysis using a generative AI model based on the formatted and pre-processed data. It extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user. The prompt used is "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in growth rates." The server inputs the data into the generative AI model and receives the analysis results as output. The input consists of formatted and pre-processed data and the prompt, and the output is the result of the competitive analysis.

[0516] Step 4: Report Generation

[0517] The AI ​​model generates a detailed report based on the competitive analysis results. The report includes key metrics of interest to the user and comparisons with competitors. For example, it might state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B increased by 15% and competitor C by 12%." The server converts the analysis results into a text-based report and prepares it for display on the dashboard. The input is the competitive analysis results, and the output is the generated report.

[0518] Step 5: Notify the user

[0519] The server notifies the user of the generated report. It sends a message to the user via email or a push notification system stating, "A new report has been generated." Upon receiving the notification, the user can access the dashboard to view the detailed report. The input is the generated report, and the output is the notification message to the user.

[0520] Step 6: Gathering Feedback

[0521] Users provide feedback on the report's content and format through their device. A feedback form is displayed, and users enter their opinions and suggestions for improvement and submit it. The server collects this feedback. The input is the user's feedback, and the output is the feedback data.

[0522] Step 7: Emotional analysis using the emotion engine

[0523] The emotion engine analyzes the user's emotions when they provide feedback. Specifically, it uses a text analysis algorithm to classify emotions as positive or negative. For example, if the user writes, "This information was very helpful," it will be classified as a positive emotion. The input is feedback data, and the output is an emotion score.

[0524] Step 8: Updating the Generating AI

[0525] The server uses the collected feedback and sentiment data as training data for its generative AI model. This allows the generative AI model to be improved for future report generation. Specifically, the collected data is added to the training dataset, and the generative AI model is retrained. The input is the feedback and sentiment data, and the output is the updated generative AI model.

[0526] (Application Example 2)

[0527] 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."

[0528] Companies need to continuously understand market trends and competitor activities to maintain and improve their competitiveness. However, there is a lack of systems that can automatically collect and analyze vast amounts of data and then specifically propose how to utilize it in advertising strategies. Furthermore, there is a demand for personalized information that is continuously improved based on user feedback. Currently, there is no system that can integrate and efficiently provide all of these requirements, making it difficult for companies to obtain the right information quickly.

[0529] 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 means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generating AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generating AI for subsequent uses, means for analyzing the user's emotions at the time of feedback and personalizing the generated report, and means for optimizing the advertising strategy based on the report and evaluating and proposing the performance of advertising creatives and the effectiveness of campaigns. As a result, companies can automatically grasp the competitive situation and quickly build and execute effective advertising strategies.

[0530] "Specific companies" refers to one or more existing legal entities whose performance is evaluated based on financial data that is released quarterly.

[0531] "Quarterly financial data" refers to information that companies disclose on a quarterly basis, showing their financial status and including figures such as sales, profits, and growth rates.

[0532] "Data shaping and preprocessing" refers to the process of removing unnecessary fields and inaccurate data from collected quarterly financial statements and standardizing the format of numerical data.

[0533] "Generative AI" is an algorithm that uses artificial intelligence technology to perform competitive analysis based on key metrics specified by the user and generate a detailed report.

[0534] "Competitive analysis" is the process of evaluating the performance of a particular company by comparing it to other companies operating in the same market.

[0535] "Report generation" is the process of creating a document that compiles useful information for users based on analyzed competitive data.

[0536] "Notifications" refer to means of informing users of the existence of generated reports, and include email and push notifications.

[0537] "Feedback" refers to the opinions and evaluations that users provide regarding the generated reports.

[0538] "Emotional analysis" is a technology that recognizes a user's emotions during feedback and analyzes whether those emotions are positive or negative.

[0539] Personalization is the process of adjusting the information and services provided to a user to match their specific needs and expectations, based on the results of sentiment analysis.

[0540] "Advertising strategy optimization" is the process of planning and executing the most effective advertising campaigns based on analysis results and user feedback.

[0541] "Advertising creative performance" refers to evaluating how effective the elements used in an advertisement, such as images, videos, and text, actually were.

[0542] "Campaign effectiveness" is a measure used to evaluate how much an implemented advertising campaign contributed to achieving its goals.

[0543] This invention is a system for optimizing advertising strategies by comparing the performance of a specific company with that of its competitors. This system is specifically implemented as an application installed on smartphones.

[0544] First, the server retrieves quarterly financial data for a specific company from a reliable data source. Specifically, it accesses the API of a financial data provider to obtain the latest financial data. This data is then temporarily stored in a database on the server.

[0545] Next, the acquired data is formatted and preprocessed. Unnecessary fields and inaccurate data are removed, and the format of numerical data is standardized. In addition, if missing values ​​exist, they are imputed using data from the previous year or industry averages.

[0546] The formatted and pre-processed data is used for competitive analysis using generative AI. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors, and performs competitive analysis based on these metrics. Based on the analysis results, the server generates a detailed report. This report includes key metrics of interest to the user and comparisons with competitors.

[0547] The generated report is notified to the user via push notification or email on their smartphone. The user can open the application and view the detailed report on the dashboard. Here, the user can provide feedback on the report's content. The sentiment engine analyzes this feedback and recognizes the user's emotions. If the feedback is positive, additional data is added to maintain and enhance the report's content. Conversely, if negative emotions are recognized, areas for improvement in the report are clearly indicated.

[0548] Next, the generating AI uses this feedback to improve its learning for subsequent reports. This results in more accurate reports that better meet user expectations. Furthermore, as a means of optimizing advertising strategies, the system collects performance data for ad creatives and campaign effectiveness measurement data, integrating these with the results of competitive analysis. An optimized advertising strategy is then proposed to the user.

[0549] As a concrete example, let's say a specific company is "Company A," and its competitors are "Company B" and "Company C." The server retrieves the latest quarterly financial data for these companies from EDGAR and other data sources. Next, after formatting and preprocessing the data, a comparative analysis is performed by a generative AI. Based on the results of this analysis, a detailed report is generated and notified to the user. The user reviews the report on a dashboard and provides feedback. During this feedback process, an emotion engine analyzes the user's emotions and incorporates them into the generative AI's training data.

[0550] Example of a prompt:

[0551] "The user wants to compare the performance of 'Company A,' 'Company B,' and 'Company C.' Based on the latest quarterly earnings data collected, conduct a competitive analysis and generate a personalized advertising strategy report. The user's sentiment feedback is 'I am very happy with the report!' Please consider this feedback to improve the content of the next report."

[0552] The three elements of server, terminal, and user work together to efficiently perform automated analysis of corporate performance and optimize advertising strategies.

[0553] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0554] Step 1:

[0555] The server retrieves quarterly financial data for a specific company from a trusted data source. This input data is raw data retrieved via an API request, and the output is unformatted financial data stored in a database. Data is retrieved via the API endpoint and stored in the server's database.

[0556] Step 2:

[0557] The server formats and preprocesses the financial data it acquires. This input data is the financial data obtained from the raw database, and the output is formatted data with unnecessary fields and inaccurate data removed and missing values ​​imputed. Specifically, it removes redundant information and fills in missing values ​​with data from the previous year or the industry average.

[0558] Step 3:

[0559] The server performs competitive analysis using a generative AI based on pre-processed data. The input data is pre-processed and formatted financial data, and the output is the competitive analysis results from the generative AI model. Specifically, key indicators such as sales, profits, and growth rates are extracted, and a comparative analysis with competitors is performed based on these indicators.

[0560] Step 4:

[0561] The server generates a report based on the analysis results. The input data is the competitive analysis results from the generative AI model, and the output is a detailed report. The generative AI creates a detailed report according to the specified prompts, including key metrics and competitive comparisons that will interest the user.

[0562] Step 5:

[0563] The server notifies the user of the generated report. The input data is the generated detailed report, and the output is a notification to the user's smartphone. Specifically, it sends an email or push notification to inform the user that the report is available.

[0564] Step 6:

[0565] Users view reports on a dashboard and provide feedback. The input data includes the report content and user feedback text, while the output is feedback data and the user's sentiment state. Users review the report and input their thoughts and suggestions for improvement.

[0566] Step 7:

[0567] The server collects user feedback and performs sentiment analysis. The input data is the feedback text, and the output is the user's sentiment analysis results and updated AI model training data. The sentiment engine analyzes the emotional state of the feedback and reflects this in the generative AI model.

[0568] Step 8:

[0569] The server updates the generating AI based on the sentiment analysis results and reflects them in subsequent reports. The input data consists of the sentiment analysis results and updated training data, while the output is a more personalized report in subsequent reports. The generating AI model is continuously trained to provide reports that better meet user expectations.

[0570] Step 9:

[0571] The server optimizes advertising strategies and proposes optimized advertising campaigns. The input data includes competitive analysis results and sentiment analysis results, and the output is an optimized advertising strategy report. It integrates advertising creative performance data and campaign effectiveness measurement data to suggest the best advertising strategy for the user.

[0572] 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.

[0573] 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.

[0574] 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.

[0575] [Third Embodiment]

[0576] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0577] 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.

[0578] 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).

[0579] 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.

[0580] 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.

[0581] 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).

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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".

[0588] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. This system is implemented according to the following procedure.

[0589] First, the server collects quarterly financial data of specific companies from reliable data sources. For example, it can use APIs provided by stock exchanges. This collected data is then temporarily stored in a database on the server.

[0590] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. It also performs imputation if missing values ​​exist to maintain data quality.

[0591] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of these metrics with the competitors.

[0592] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0593] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0594] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0595] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs a comparative analysis using a generation AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on a dashboard and provides feedback on its contents. This feedback is collected by the server and used to generate future reports.

[0596] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0597] The following describes the processing flow.

[0598] Step 1:

[0599] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0600] Step 2:

[0601] The server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it may use data from the previous year or industry averages to fill in the gaps.

[0602] Step 3:

[0603] The server provides input data to the generating AI based on the formatted and pre-processed data. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, and then begins an analysis to compare them.

[0604] Step 4:

[0605] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The analysis results are stored on the server as intermediate data.

[0606] Step 5:

[0607] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. These reports include specific performance comparisons and analyses of a particular company and its competitors. For example, they might state, "Company A's sales increased by 10%, while competitor B increased by 15%, and competitor C by 12%."

[0608] Step 6:

[0609] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to know that the report has been generated.

[0610] Step 7:

[0611] After receiving a notification, users access the dashboard to review the generated report. Here, they can view detailed information about the report and evaluate its contents if necessary.

[0612] Step 8:

[0613] Users provide feedback on the report's content. Specifically, a feedback form is displayed on the device for users to input their evaluation and suggestions for improvement. Users submit their opinions through this form.

[0614] Step 9:

[0615] The server collects user feedback and uses it as training data for future generation AI. The collected feedback is used to adjust the parameters of the generation AI and improve the algorithm, continuously improving the accuracy of the reports.

[0616] (Example 1)

[0617] 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."

[0618] In today's world, it is crucial to quickly and accurately understand the performance of a specific organization and conduct competitive analysis. However, traditional methods require manual data collection and analysis, which is time-consuming and labor-intensive. Furthermore, the accuracy and reproducibility of the analysis results are often not guaranteed. In addition, it is difficult to incorporate feedback, limiting the quality of the generated analysis reports. There is a need for a system that solves these problems, efficiently collects, processes, and analyzes performance data automatically, and provides reliable information.

[0619] 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.

[0620] In this invention, the server includes means for acquiring quarterly performance data of a specific organization, means for formatting and pre-processing the acquired performance data, means for performing competitive analysis using computer intelligence generated based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for collecting feedback from the user and incorporating it into the learning of the computer intelligence generated in the future. This enables automatic collection of performance data, efficient data processing, reliable competitive analysis, and the generation of high-quality reports that reflect feedback.

[0621] "Specific organization" refers to corporations, groups, or other legal entities with a specific purpose.

[0622] "Quarterly performance data" refers to data that shows the financial status and performance of an organization for each of the four periods (quarters) in which the year is divided.

[0623] A "reliable data source" refers to an organization or platform that provides data whose accuracy and reliability are guaranteed.

[0624] "Formatting and preprocessing" refers to the process of converting acquired data into an analyzable format and appropriately correcting any missing or redundant parts.

[0625] "Generated computational intelligence" refers to artificial intelligence models built using technologies such as machine learning and deep learning.

[0626] "Competitive analysis" refers to an analysis that compares the performance of a particular organization with that of other organizations to evaluate its competitiveness and market position.

[0627] "Key performance indicators" refer to important metrics used to evaluate the performance and health of a company or organization, such as sales, profits, and growth rates.

[0628] A "report" refers to a document summarizing the results of a competitive analysis, including the performance of a specific organization and a comparison with its competitors.

[0629] "Users" refers to individuals or organizations that use this system to acquire information and utilize the analysis results.

[0630] "Opinions" refer to the feedback and evaluations that users provide to the system.

[0631] This invention relates to an information processing system that automatically collects performance data from a specific organization, performs competitive analysis, and provides the results to the user. A specific example of this system is described below.

[0632] This system is primarily composed of three components: servers, terminals, and users.

[0633] First, the server is designed to collect performance data for specific organizations, which is released quarterly, from reliable data sources. This utilizes APIs provided by stock exchanges, for example. The data obtained through the API is stored in a database on the server. For example, the EDGAR API is used to retrieve quarterly financial data for a specific company.

[0634] Next, the server formats and preprocesses the acquired performance data. Specifically, it removes unnecessary fields and converts numerical data to a standardized format. It also imputes missing values ​​using the mean. This preprocessing ensures data quality.

[0635] Based on the formatted and pre-processed data, the server performs competitive analysis using a generative AI model. The generative AI model is built using programming languages ​​such as Python and extracts key metrics (sales, profits, growth rate, etc.) for a specific organization and its competitors specified by the user, and compares them. An example of a prompt is shown below.

[0636] "Obtain the latest quarterly financial data for specific company A regarding sales, profits, and growth rate, and compare it to competitors B and C."

[0637] The server generates a detailed report based on the analysis results obtained from the generated AI model. This report includes comparisons of key indicators such as sales, profits, and growth rates, and also provides comparisons with historical data. For example, it may state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0638] The generated report is notified to the user from the server. Notification methods include email and push notifications. Upon receiving this notification, the user can access their dashboard and view the detailed report.

[0639] Furthermore, users can provide feedback on the report. A feedback form is displayed on the device, allowing users to enter their opinions. The feedback is sent to the server and stored in a database. This data is then used as training data for future AI model generation.

[0640] In this way, the present invention makes it possible to automatically collect, format, and analyze performance data of a specific organization, and to provide users with reliable competitive analysis results. Furthermore, by incorporating user feedback, the generated AI model can be continuously improved.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1: Data Collection

[0643] The server retrieves quarterly performance data for a specific company from a reliable data source. Specifically, it uses a stock exchange API (e.g., the EDGAR API) to collect the latest financial data. It sends a request to this API and receives the data in JSON format. The input includes a company identifier (e.g., company code) and a period (quarter). The JSON data contains information such as the company's sales, profits, and growth rate. The server stores this data in a database.

[0644] Step 2: Data Preprocessing

[0645] The server formats and preprocesses the collected performance data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. Furthermore, it imputes missing values ​​using means such as the mean. The JSON-formatted financial statements collected earlier are used as input. As a result of this data processing, a clean, preprocessed dataset is generated. The server holds this dataset in memory for use in the next step.

[0646] Step 3: Competitive Analysis

[0647] The server uses pre-processed data to input prompts into a generated AI model and performs competitive analysis. Specifically, prompts are input to an AI model built using a programming language such as Python. For example, a prompt such as "Retrieve the latest quarterly financial data regarding the sales, profits, and growth rate of company A, and compare it with competitors B and C" might be used. The AI ​​model performs the analysis based on this prompt and compares the performance of each company. As output, a comparison of the sales, profits, and growth rates of company A and its competitors is generated.

[0648] Step 4: Generate the report

[0649] The server generates a detailed report based on the analysis results of the generated AI model. Specifically, it creates reports in PDF or HTML format based on the acquired comparative data. The report includes comparative results of key indicators such as sales, profits, and growth rates. The comparative data acquired in step 3 is used as input. As output, a detailed report in a user-friendly format is generated. The server saves this report to the specified location.

[0650] Step 5: Report notification and viewing

[0651] The server notifies the user of the generated report. Specifically, it uses an SMTP server to send a report generation notification to the user's registered email address. Push notifications can also be sent. The user's contact information and the generated report are used as input. The output is a notification sent to the user's device. Upon receiving the notification, the user can access the dashboard and view the detailed report.

[0652] Step 6: Gathering and implementing feedback

[0653] Users provide feedback on the generated reports. Specifically, they enter their opinions into a feedback form displayed on their device and submit it. The feedback is sent to the server and stored in a database. The input is user feedback. The output is the feedback data stored on the server. This feedback is used as training data for future AI model generation. This improves the accuracy of the AI ​​model.

[0654] (Application Example 1)

[0655] 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."

[0656] To maintain and improve a company's competitiveness, it is necessary to quickly and efficiently compare and analyze the performance of a specific company with that of its competitors. However, traditional methods rely on manual processes for data collection, formatting, preprocessing, analysis, and report generation, which are time-consuming and labor-intensive. Furthermore, there is no efficient way to notify users of reports or collect feedback. An automated system is needed to solve these problems.

[0657] 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.

[0658] In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generative AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generative AI for subsequent uses, means for generating prompt sentences for performing analysis with the generative AI model based on the collected, formatted, and pre-processed data, and means for sending push notifications or emails when notifying the user of the generated report. This enables companies to quickly and efficiently automatically generate performance comparison analysis reports, effectively notify users of the results, and reflect the feedback in the learning of the generative AI for subsequent uses.

[0659] "Specific companies" refers to the companies selected for analysis.

[0660] "Quarterly financial data" refers to the financial information that companies report on a quarterly basis.

[0661] "Means of acquisition" refers to methods and mechanisms for collecting data from trusted data sources such as APIs.

[0662] "Means of formatting and preprocessing" refers to methods and mechanisms for removing unnecessary fields from collected data, imputing missing values, and converting data into a unified format.

[0663] "Generative AI" refers to a technology that uses artificial intelligence to analyze and predict data.

[0664] "Means of conducting competitive analysis" refers to methods and systems for comparing and analyzing the performance data of a specific company and its competitors.

[0665] "Means of generating reports" refers to methods and mechanisms for creating detailed reports to provide to users based on analysis results.

[0666] "Means of notifying users" refers to methods and mechanisms such as push notifications and emails used to inform users of generated reports.

[0667] "Means of collecting user feedback" refers to methods and mechanisms for collecting users' opinions and impressions of reports.

[0668] "Means of incorporating feedback into the learning of generative AI" refers to methods and mechanisms for improving the generative AI using collected feedback and enhancing the accuracy of subsequent analyses.

[0669] "Means for generating prompt statements" refers to methods and mechanisms for creating instruction statements for analysis by a generative AI model based on collected, formatted, and pre-processed data.

[0670] "Means of sending push notifications and emails" refers to real-time notification methods and email sending mechanisms for informing users of generated reports.

[0671] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. The following describes embodiments for carrying out this invention.

[0672] Hardware and software to be used

[0673] hardware

[0674] Servers (cloud services such as AWS and GCP)

[0675] User's smartphone

[0676] software

[0677] Data collection: Python (requests, pandas)

[0678] Data formatting and preprocessing: pandas, NumPy

[0679] Generative AI models: Tensorflow, PyTorch

[0680] Notification system: Firebase Cloud Messaging, SendGrid

[0681] Feedback collection: Firebase Realtime Database

[0682] Overall flow of the system

[0683] Data acquisition

[0684] The server uses trusted data sources such as APIs (e.g., stock exchange APIs) to collect quarterly financial data for specific companies.

[0685] Data formatting and preprocessing

[0686] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data.

[0687] Analysis by Generative AI

[0688] Based on preprocessed data, a generative AI model is used to perform competitive analysis. The generative AI model is built using Tensorflow or PyTorch, and extracts key metrics such as sales, profits, and growth rates for each company, and compares them.

[0689] An example of a prompt message to the generating AI used in this process is as follows:

[0690] Collect the latest quarterly financial data for the specified company and conduct a comparative analysis with its competitors using the following metrics: sales, profits, growth rate, etc. Based on the results, generate a detailed report and provide a prompt to notify the user.

[0691] Report generation and notification

[0692] Based on the analysis results, the server generates a detailed report. This report is then communicated to the user via Firebase Cloud Messaging or SendGrid. Push notifications and emails are sent, allowing users to confirm receipt of the report in real time.

[0693] Feedback Collection

[0694] Users can provide feedback on the reports. This feedback is collected using the Firebase Realtime Database and used as training data for future generative AI. This allows the generative AI to continuously improve and generate more accurate reports.

[0695] Specific example

[0696] For example, the system can obtain quarterly financial data for a specific company, "Company A," and its competitors, "Company B" and "Company C," and compare and analyze their respective sales, profits, and growth rates. The analysis results would then be generated as a report detailing specific information, such as "Company A's sales increased by 10% in the third quarter of 2023, while competitors B and C recorded increases of 15% and 12% respectively. The generated report would be sent to the user via push notification or email, allowing them to review it and provide feedback.

[0697] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0698] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0699] Step 1: Data Acquisition

[0700] The server collects quarterly financial data for specific companies using trusted data sources such as APIs. Specifically, it retrieves financial data from stock exchange APIs. The input is the financial data provided via the API, and the output is the retrieved raw data.

[0701] Step 2: Data preparation and preprocessing

[0702] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data. The input is the raw data obtained, and the output is the preprocessed, clean data.

[0703] Step 3: Generating prompts for the AI

[0704] The server generates prompt statements for analysis using a generative AI model, based on the formatted and pre-processed data. Specifically, it creates concrete instructions for analyzing the collected and formatted data. The input is the pre-processed data, and the output is the generated prompt statements.

[0705] Step 4: Competitive Analysis

[0706] This program performs competitive analysis based on pre-processed data using a generative AI model. The generative AI model is built using Tensorflow and PyTorch, extracting key metrics such as sales, profits, and growth rates for each company, and comparing them. The input consists of prompts and pre-processed data, while the output is the analysis results.

[0707] Step 5: Report Generation

[0708] The server generates a detailed report based on the analysis results. Specifically, it compiles key metrics of interest to the user and comparison results with competitors into a report. The input is the analysis results, and the output is the generated detailed report.

[0709] Step 6: Report Notification

[0710] The generated report is sent as a notification to the user's smartphone. Specifically, push notifications and emails are sent using Firebase Cloud Messaging or SendGrid. The input is the generated report, and the output is the notification to the user.

[0711] Step 7: Gathering Feedback

[0712] Users can provide feedback on the report. This feedback is collected using Firebase Realtime Database and used as training data for future generative AI iterations. The input is user feedback, and the output is the training data for the generative AI.

[0713] The above outlines the specific processing steps of the system that implements the application example.

[0714] 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.

[0715] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. By combining this system with an emotion engine that recognizes the user's emotions, it can provide more personalized reports.

[0716] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0717] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0718] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of the competitors based on these metrics.

[0719] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0720] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0721] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0722] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0723] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial results data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs the comparative analysis using generative AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions when providing feedback and incorporates this into the generative AI's training data. This improves future reports so that they better meet the user's expectations.

[0724] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers and receives the latest financial data as API responses. This data is stored in a database on the server.

[0728] Step 2:

[0729] The server formats and preprocesses the acquired financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using previous year's data or industry averages. The formatted data is then ready for use in the next processing step.

[0730] Step 3:

[0731] The server provides formatted and pre-processed data as input to the generating AI. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, as specified by the user. Based on the extracted data, it performs a comparative analysis with its competitors.

[0732] Step 4:

[0733] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The results of this analysis are temporarily stored on the server as intermediate data.

[0734] Step 5:

[0735] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. Specifically, it creates reports in PDF or HTML format that include metrics of interest to the user and comparison results for each company. These reports may include specific details such as, "Company A's sales increased by 10%, competitor B's by 15%, and competitor C's by 12%."

[0736] Step 6:

[0737] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to monitor the report generation in real time and prepare to review it.

[0738] Step 7:

[0739] After receiving a notification, users access the dashboard using their device to view the generated report. Here, they can view detailed report content and focus on specific sections.

[0740] Step 8:

[0741] Users provide feedback on the report's content. Specifically, a form for entering evaluations and suggestions for improvement will appear on their device. Users submit their opinions through this form.

[0742] Step 9:

[0743] In this step, an emotion engine is activated to recognize the user's emotions when they provide feedback. It analyzes the user's input and input method (e.g., typing speed and emphasis) to recognize positive or negative emotions.

[0744] Step 10:

[0745] The server collects user feedback and the results of the emotion engine's analysis, using this as training data for the generative AI. The collected data is used to adjust the generative AI's parameters and improve its algorithms, and this information is reflected in future report generation.

[0746] Step 11:

[0747] For subsequent report generation, the report content and format will be dynamically customized based on the analysis results of the emotion engine. Positive feedback will maintain the same report format, while negative feedback will reflect areas for improvement.

[0748] This processing flow allows companies to quickly and accurately perform comparative analysis with competitors and receive personalized reports based on user sentiment.

[0749] (Example 2)

[0750] 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."

[0751] Traditional corporate performance analysis systems often require manual comparison with competitors for specific metrics, making them inefficient and hindering the delivery of personalized reports due to their failure to consider user sentiment. Furthermore, they lack adequate mechanisms for incorporating feedback into system improvements, making subsequent reports likely to fail to meet user expectations. This has made it difficult for companies to quickly and efficiently obtain the information needed to improve their competitiveness.

[0752] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generation AI model based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for including an emotion engine that collects user feedback and analyzes that feedback, and reflects it in the learning of the generation AI model for subsequent uses. This makes it possible to automatically compare and analyze the performance of a company with that of its competitors and to quickly and efficiently provide personalized reports based on the user's emotions.

[0753] "Specific companies" refers to individual legal entities operating in a particular industry or market.

[0754] "Quarterly financial data" refers to data that shows a company's financial activities at the end of each of the four quarters in which the year is divided.

[0755] A "reliable data source" refers to an information provider that is guaranteed to provide accurate and up-to-date information.

[0756] "Formatting" refers to the process of organizing data into a format suitable for analysis and standardizing the format.

[0757] "Preprocessing" refers to the process performed to improve the quality of data prior to analysis, and specifically includes deleting unnecessary data and imputing missing values.

[0758] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically analyze data and is trained to perform a specific task.

[0759] "Competitive analysis" refers to an analysis that compares the performance of a specific company with that of its competitors to identify its strengths and weaknesses.

[0760] A "report" refers to an official document that summarizes analysis results and insights.

[0761] "Users" refer to individuals or corporations that use this system to obtain information.

[0762] "Notification" refers to a means of communication used to inform users of new information or events.

[0763] "Feedback" refers to the opinions and evaluations that users provide about the results and usability of a system.

[0764] An "emotion engine" refers to an algorithm that analyzes the emotions expressed by users during feedback and processes them as data.

[0765] Modes for carrying out the invention

[0766] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. The system can provide more personalized reports by incorporating an emotion engine that recognizes user emotions.

[0767] Data collection

[0768] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. For example, it retrieves the Q3 2023 data for company A. This data is then temporarily stored in a database on the server.

[0769] Data formatting and preprocessing

[0770] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0771] Competitive analysis

[0772] The formatted and pre-processed data is used by the generative AI model to perform competitive analysis. The server extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and uses these to perform a comparative analysis with competitors. The generative AI model is provided with prompts such as, "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in their growth rates."

[0773] Report generation

[0774] The AI ​​model generates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0775] User notifications

[0776] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0777] Feedback Collection

[0778] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI models. This allows the generation AI model to continuously improve, enabling it to produce more accurate reports.

[0779] Utilizing the Emotion Engine

[0780] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI model. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0781] Specific example

[0782] As a concrete example, consider a scenario where a user wants to perform a comparative analysis of "Company A," "Competitor B," and "Competitor C." The server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data and performs a comparative analysis using a generative AI model. The prompt used is "Compare the quarterly sales data of Company A, Company B, and Company C, and analyze the differences in growth rates." A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions during feedback and incorporates them into the training data of the generative AI model. This improves future reports to better meet user expectations.

[0783] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[0784] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0785] Step 1: Data Collection

[0786] The server retrieves quarterly financial data for a specific company from a trusted data source. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. The server sends a "GET" request to the API endpoint, receives the returned data in JSON format, and parses it. The input is the identification information of the specific company, and the output is the parsed financial data.

[0787] Step 2: Data preparation and preprocessing

[0788] The server formats and preprocesses the collected financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using historical data or industry averages. Specifically, it reads data from the database, executes formatting and preprocessing algorithms, and generates clean data. The input is parsed financial data, and the output is formatted and preprocessed data.

[0789] Step 3: Competitive Analysis

[0790] The server performs competitive analysis using a generative AI model based on the formatted and pre-processed data. It extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user. The prompt used is "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in growth rates." The server inputs the data into the generative AI model and receives the analysis results as output. The input consists of formatted and pre-processed data and the prompt, and the output is the result of the competitive analysis.

[0791] Step 4: Report Generation

[0792] The AI ​​model generates a detailed report based on the competitive analysis results. The report includes key metrics of interest to the user and comparisons with competitors. For example, it might state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B increased by 15% and competitor C by 12%." The server converts the analysis results into a text-based report and prepares it for display on the dashboard. The input is the competitive analysis results, and the output is the generated report.

[0793] Step 5: Notify the user

[0794] The server notifies the user of the generated report. It sends a message to the user via email or a push notification system stating, "A new report has been generated." Upon receiving the notification, the user can access the dashboard to view the detailed report. The input is the generated report, and the output is the notification message to the user.

[0795] Step 6: Gathering Feedback

[0796] Users provide feedback on the report's content and format through their device. A feedback form is displayed, and users enter their opinions and suggestions for improvement and submit it. The server collects this feedback. The input is the user's feedback, and the output is the feedback data.

[0797] Step 7: Emotional analysis using the emotion engine

[0798] The emotion engine analyzes the user's emotions when they provide feedback. Specifically, it uses a text analysis algorithm to classify emotions as positive or negative. For example, if the user writes, "This information was very helpful," it will be classified as a positive emotion. The input is feedback data, and the output is an emotion score.

[0799] Step 8: Updating the Generating AI

[0800] The server uses the collected feedback and sentiment data as training data for its generative AI model. This allows the generative AI model to be improved for future report generation. Specifically, the collected data is added to the training dataset, and the generative AI model is retrained. The input is the feedback and sentiment data, and the output is the updated generative AI model.

[0801] (Application Example 2)

[0802] 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."

[0803] Companies need to continuously understand market trends and competitor activities to maintain and improve their competitiveness. However, there is a lack of systems that can automatically collect and analyze vast amounts of data and then specifically propose how to utilize it in advertising strategies. Furthermore, there is a demand for personalized information that is continuously improved based on user feedback. Currently, there is no system that can integrate and efficiently provide all of these requirements, making it difficult for companies to obtain the right information quickly.

[0804] 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 means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generating AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generating AI for subsequent uses, means for analyzing the user's emotions at the time of feedback and personalizing the generated report, and means for optimizing the advertising strategy based on the report and evaluating and proposing the performance of advertising creatives and the effectiveness of campaigns. As a result, companies can automatically grasp the competitive situation and quickly build and execute effective advertising strategies.

[0805] "Specific companies" refers to one or more existing legal entities whose performance is evaluated based on financial data that is released quarterly.

[0806] "Quarterly financial data" refers to information that companies disclose on a quarterly basis, showing their financial status and including figures such as sales, profits, and growth rates.

[0807] "Data shaping and preprocessing" refers to the process of removing unnecessary fields and inaccurate data from collected quarterly financial statements and standardizing the format of numerical data.

[0808] "Generative AI" is an algorithm that uses artificial intelligence technology to perform competitive analysis based on key metrics specified by the user and generate a detailed report.

[0809] "Competitive analysis" is the process of evaluating the performance of a particular company by comparing it to other companies operating in the same market.

[0810] "Report generation" is the process of creating a document that compiles useful information for users based on analyzed competitive data.

[0811] "Notifications" refer to means of informing users of the existence of generated reports, and include email and push notifications.

[0812] "Feedback" refers to the opinions and evaluations that users provide regarding the generated reports.

[0813] "Emotional analysis" is a technology that recognizes a user's emotions during feedback and analyzes whether those emotions are positive or negative.

[0814] Personalization is the process of adjusting the information and services provided to a user to match their specific needs and expectations, based on the results of sentiment analysis.

[0815] "Advertising strategy optimization" is the process of planning and executing the most effective advertising campaigns based on analysis results and user feedback.

[0816] "Advertising creative performance" refers to evaluating how effective the elements used in an advertisement, such as images, videos, and text, actually were.

[0817] "Campaign effectiveness" is a measure used to evaluate how much an implemented advertising campaign contributed to achieving its goals.

[0818] This invention is a system for optimizing advertising strategies by comparing the performance of a specific company with that of its competitors. This system is specifically implemented as an application installed on smartphones.

[0819] First, the server retrieves quarterly financial data for a specific company from a reliable data source. Specifically, it accesses the API of a financial data provider to obtain the latest financial data. This data is then temporarily stored in a database on the server.

[0820] Next, the acquired data is formatted and preprocessed. Unnecessary fields and inaccurate data are removed, and the format of numerical data is standardized. In addition, if missing values ​​exist, they are imputed using data from the previous year or industry averages.

[0821] The formatted and pre-processed data is used for competitive analysis using generative AI. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors, and performs competitive analysis based on these metrics. Based on the analysis results, the server generates a detailed report. This report includes key metrics of interest to the user and comparisons with competitors.

[0822] The generated report is notified to the user via push notification or email on their smartphone. The user can open the application and view the detailed report on the dashboard. Here, the user can provide feedback on the report's content. The sentiment engine analyzes this feedback and recognizes the user's emotions. If the feedback is positive, additional data is added to maintain and enhance the report's content. Conversely, if negative emotions are recognized, areas for improvement in the report are clearly indicated.

[0823] Next, the generating AI uses this feedback to improve its learning for subsequent reports. This results in more accurate reports that better meet user expectations. Furthermore, as a means of optimizing advertising strategies, the system collects performance data for ad creatives and campaign effectiveness measurement data, integrating these with the results of competitive analysis. An optimized advertising strategy is then proposed to the user.

[0824] As a concrete example, let's say a specific company is "Company A," and its competitors are "Company B" and "Company C." The server retrieves the latest quarterly financial data for these companies from EDGAR and other data sources. Next, after formatting and preprocessing the data, a comparative analysis is performed by a generative AI. Based on the results of this analysis, a detailed report is generated and notified to the user. The user reviews the report on a dashboard and provides feedback. During this feedback process, an emotion engine analyzes the user's emotions and incorporates them into the generative AI's training data.

[0825] Example of a prompt:

[0826] "The user wants to compare the performance of 'Company A,' 'Company B,' and 'Company C.' Based on the latest quarterly earnings data collected, conduct a competitive analysis and generate a personalized advertising strategy report. The user's sentiment feedback is 'I am very happy with the report!' Please consider this feedback to improve the content of the next report."

[0827] The three elements of server, terminal, and user work together to efficiently perform automated analysis of corporate performance and optimize advertising strategies.

[0828] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0829] Step 1:

[0830] The server retrieves quarterly financial data for a specific company from a trusted data source. This input data is raw data retrieved via an API request, and the output is unformatted financial data stored in a database. Data is retrieved via the API endpoint and stored in the server's database.

[0831] Step 2:

[0832] The server formats and preprocesses the financial data it acquires. This input data is the financial data obtained from the raw database, and the output is formatted data with unnecessary fields and inaccurate data removed and missing values ​​imputed. Specifically, it removes redundant information and fills in missing values ​​with data from the previous year or the industry average.

[0833] Step 3:

[0834] The server performs competitive analysis using a generative AI based on pre-processed data. The input data is pre-processed and formatted financial data, and the output is the competitive analysis results from the generative AI model. Specifically, key indicators such as sales, profits, and growth rates are extracted, and a comparative analysis with competitors is performed based on these indicators.

[0835] Step 4:

[0836] The server generates a report based on the analysis results. The input data is the competitive analysis results from the generative AI model, and the output is a detailed report. The generative AI creates a detailed report according to the specified prompts, including key metrics and competitive comparisons that will interest the user.

[0837] Step 5:

[0838] The server notifies the user of the generated report. The input data is the generated detailed report, and the output is a notification to the user's smartphone. Specifically, it sends an email or push notification to inform the user that the report is available.

[0839] Step 6:

[0840] Users view reports on a dashboard and provide feedback. The input data includes the report content and user feedback text, while the output is feedback data and the user's sentiment state. Users review the report and input their thoughts and suggestions for improvement.

[0841] Step 7:

[0842] The server collects user feedback and performs sentiment analysis. The input data is the feedback text, and the output is the user's sentiment analysis results and updated AI model training data. The sentiment engine analyzes the emotional state of the feedback and reflects this in the generative AI model.

[0843] Step 8:

[0844] The server updates the generating AI based on the sentiment analysis results and reflects them in subsequent reports. The input data consists of the sentiment analysis results and updated training data, while the output is a more personalized report in subsequent reports. The generating AI model is continuously trained to provide reports that better meet user expectations.

[0845] Step 9:

[0846] The server optimizes advertising strategies and proposes optimized advertising campaigns. The input data includes competitive analysis results and sentiment analysis results, and the output is an optimized advertising strategy report. It integrates advertising creative performance data and campaign effectiveness measurement data to suggest the best advertising strategy for the user.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] [Fourth Embodiment]

[0851] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0852] 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.

[0853] 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).

[0854] 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.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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".

[0864] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. This system is implemented according to the following procedure.

[0865] First, the server collects quarterly financial data of specific companies from reliable data sources. For example, it can use APIs provided by stock exchanges. This collected data is then temporarily stored in a database on the server.

[0866] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. It also performs imputation if missing values ​​exist to maintain data quality.

[0867] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of these metrics with the competitors.

[0868] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0869] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0870] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0871] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs a comparative analysis using a generation AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on a dashboard and provides feedback on its contents. This feedback is collected by the server and used to generate future reports.

[0872] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0873] The following describes the processing flow.

[0874] Step 1:

[0875] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0876] Step 2:

[0877] The server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it may use data from the previous year or industry averages to fill in the gaps.

[0878] Step 3:

[0879] The server provides input data to the generating AI based on the formatted and pre-processed data. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, and then begins an analysis to compare them.

[0880] Step 4:

[0881] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The analysis results are stored on the server as intermediate data.

[0882] Step 5:

[0883] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. These reports include specific performance comparisons and analyses of a particular company and its competitors. For example, they might state, "Company A's sales increased by 10%, while competitor B increased by 15%, and competitor C by 12%."

[0884] Step 6:

[0885] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to know that the report has been generated.

[0886] Step 7:

[0887] After receiving a notification, users access the dashboard to review the generated report. Here, they can view detailed information about the report and evaluate its contents if necessary.

[0888] Step 8:

[0889] Users provide feedback on the report's content. Specifically, a feedback form is displayed on the device for users to input their evaluation and suggestions for improvement. Users submit their opinions through this form.

[0890] Step 9:

[0891] The server collects user feedback and uses it as training data for future generation AI. The collected feedback is used to adjust the parameters of the generation AI and improve the algorithm, continuously improving the accuracy of the reports.

[0892] (Example 1)

[0893] 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".

[0894] In today's world, it is crucial to quickly and accurately understand the performance of a specific organization and conduct competitive analysis. However, traditional methods require manual data collection and analysis, which is time-consuming and labor-intensive. Furthermore, the accuracy and reproducibility of the analysis results are often not guaranteed. In addition, it is difficult to incorporate feedback, limiting the quality of the generated analysis reports. There is a need for a system that solves these problems, efficiently collects, processes, and analyzes performance data automatically, and provides reliable information.

[0895] 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.

[0896] In this invention, the server includes means for acquiring quarterly performance data of a specific organization, means for formatting and pre-processing the acquired performance data, means for performing competitive analysis using computer intelligence generated based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for collecting feedback from the user and incorporating it into the learning of the computer intelligence generated in the future. This enables automatic collection of performance data, efficient data processing, reliable competitive analysis, and the generation of high-quality reports that reflect feedback.

[0897] "Specific organization" refers to corporations, groups, or other legal entities with a specific purpose.

[0898] "Quarterly performance data" refers to data that shows the financial status and performance of an organization for each of the four periods (quarters) in which the year is divided.

[0899] A "reliable data source" refers to an organization or platform that provides data whose accuracy and reliability are guaranteed.

[0900] "Formatting and preprocessing" refers to the process of converting acquired data into an analyzable format and appropriately correcting any missing or redundant parts.

[0901] "Generated computational intelligence" refers to artificial intelligence models built using technologies such as machine learning and deep learning.

[0902] "Competitive analysis" refers to an analysis that compares the performance of a particular organization with that of other organizations to evaluate its competitiveness and market position.

[0903] "Key performance indicators" refer to important metrics used to evaluate the performance and health of a company or organization, such as sales, profits, and growth rates.

[0904] A "report" refers to a document summarizing the results of a competitive analysis, including the performance of a specific organization and a comparison with its competitors.

[0905] "Users" refers to individuals or organizations that use this system to acquire information and utilize the analysis results.

[0906] "Opinions" refer to the feedback and evaluations that users provide to the system.

[0907] This invention relates to an information processing system that automatically collects performance data from a specific organization, performs competitive analysis, and provides the results to the user. A specific example of this system is described below.

[0908] This system is primarily composed of three components: servers, terminals, and users.

[0909] First, the server is designed to collect performance data for specific organizations, which is released quarterly, from reliable data sources. This utilizes APIs provided by stock exchanges, for example. The data obtained through the API is stored in a database on the server. For example, the EDGAR API is used to retrieve quarterly financial data for a specific company.

[0910] Next, the server formats and preprocesses the acquired performance data. Specifically, it removes unnecessary fields and converts numerical data to a standardized format. It also imputes missing values ​​using the mean. This preprocessing ensures data quality.

[0911] Based on the formatted and pre-processed data, the server performs competitive analysis using a generative AI model. The generative AI model is built using programming languages ​​such as Python and extracts key metrics (sales, profits, growth rate, etc.) for a specific organization and its competitors specified by the user, and compares them. An example of a prompt is shown below.

[0912] "Obtain the latest quarterly financial data for specific company A regarding sales, profits, and growth rate, and compare it to competitors B and C."

[0913] The server generates a detailed report based on the analysis results obtained from the generated AI model. This report includes comparisons of key indicators such as sales, profits, and growth rates, and also provides comparisons with historical data. For example, it may state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0914] The generated report is notified to the user from the server. Notification methods include email and push notifications. Upon receiving this notification, the user can access their dashboard and view the detailed report.

[0915] Furthermore, users can provide feedback on the report. A feedback form is displayed on the device, allowing users to enter their opinions. The feedback is sent to the server and stored in a database. This data is then used as training data for future AI model generation.

[0916] In this way, the present invention makes it possible to automatically collect, format, and analyze performance data of a specific organization, and to provide users with reliable competitive analysis results. Furthermore, by incorporating user feedback, the generated AI model can be continuously improved.

[0917] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0918] Step 1: Data Collection

[0919] The server retrieves quarterly performance data for a specific company from a reliable data source. Specifically, it uses a stock exchange API (e.g., the EDGAR API) to collect the latest financial data. It sends a request to this API and receives the data in JSON format. The input includes a company identifier (e.g., company code) and a period (quarter). The JSON data contains information such as the company's sales, profits, and growth rate. The server stores this data in a database.

[0920] Step 2: Data Preprocessing

[0921] The server formats and preprocesses the collected performance data. Specifically, it removes unnecessary fields and converts numerical data into a unified format. Furthermore, it imputes missing values ​​using means such as the mean. The JSON-formatted financial statements collected earlier are used as input. As a result of this data processing, a clean, preprocessed dataset is generated. The server holds this dataset in memory for use in the next step.

[0922] Step 3: Competitive Analysis

[0923] The server uses pre-processed data to input prompts into a generated AI model and performs competitive analysis. Specifically, prompts are input to an AI model built using a programming language such as Python. For example, a prompt such as "Retrieve the latest quarterly financial data regarding the sales, profits, and growth rate of company A, and compare it with competitors B and C" might be used. The AI ​​model performs the analysis based on this prompt and compares the performance of each company. As output, a comparison of the sales, profits, and growth rates of company A and its competitors is generated.

[0924] Step 4: Generate the report

[0925] The server generates a detailed report based on the analysis results of the generated AI model. Specifically, it creates reports in PDF or HTML format based on the acquired comparative data. The report includes comparative results of key indicators such as sales, profits, and growth rates. The comparative data acquired in step 3 is used as input. As output, a detailed report in a user-friendly format is generated. The server saves this report to the specified location.

[0926] Step 5: Report notification and viewing

[0927] The server notifies the user of the generated report. Specifically, it uses an SMTP server to send a report generation notification to the user's registered email address. Push notifications can also be sent. The user's contact information and the generated report are used as input. The output is a notification sent to the user's device. Upon receiving the notification, the user can access the dashboard and view the detailed report.

[0928] Step 6: Gathering and implementing feedback

[0929] Users provide feedback on the generated reports. Specifically, they enter their opinions into a feedback form displayed on their device and submit it. The feedback is sent to the server and stored in a database. The input is user feedback. The output is the feedback data stored on the server. This feedback is used as training data for future AI model generation. This improves the accuracy of the AI ​​model.

[0930] (Application Example 1)

[0931] 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".

[0932] To maintain and improve a company's competitiveness, it is necessary to quickly and efficiently compare and analyze the performance of a specific company with that of its competitors. However, traditional methods rely on manual processes for data collection, formatting, preprocessing, analysis, and report generation, which are time-consuming and labor-intensive. Furthermore, there is no efficient way to notify users of reports or collect feedback. An automated system is needed to solve these problems.

[0933] 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.

[0934] In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generative AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generative AI for subsequent uses, means for generating prompt sentences for performing analysis with the generative AI model based on the collected, formatted, and pre-processed data, and means for sending push notifications or emails when notifying the user of the generated report. This enables companies to quickly and efficiently automatically generate performance comparison analysis reports, effectively notify users of the results, and reflect the feedback in the learning of the generative AI for subsequent uses.

[0935] "Specific companies" refers to the companies selected for analysis.

[0936] "Quarterly financial data" refers to the financial information that companies report on a quarterly basis.

[0937] "Means of acquisition" refers to methods and mechanisms for collecting data from trusted data sources such as APIs.

[0938] "Means of formatting and preprocessing" refers to methods and mechanisms for removing unnecessary fields from collected data, imputing missing values, and converting data into a unified format.

[0939] "Generative AI" refers to a technology that uses artificial intelligence to analyze and predict data.

[0940] "Means of conducting competitive analysis" refers to methods and systems for comparing and analyzing the performance data of a specific company and its competitors.

[0941] "Means of generating reports" refers to methods and mechanisms for creating detailed reports to provide to users based on analysis results.

[0942] "Means of notifying users" refers to methods and mechanisms such as push notifications and emails used to inform users of generated reports.

[0943] "Means of collecting user feedback" refers to methods and mechanisms for collecting users' opinions and impressions of reports.

[0944] "Means of incorporating feedback into the learning of generative AI" refers to methods and mechanisms for improving the generative AI using collected feedback and enhancing the accuracy of subsequent analyses.

[0945] "Means for generating prompt statements" refers to methods and mechanisms for creating instruction statements for analysis by a generative AI model based on collected, formatted, and pre-processed data.

[0946] "Means of sending push notifications and emails" refers to real-time notification methods and email sending mechanisms for informing users of generated reports.

[0947] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, and provides users with useful information. The following describes embodiments for carrying out this invention.

[0948] Hardware and software to be used

[0949] hardware

[0950] Servers (cloud services such as AWS and GCP)

[0951] User's smartphone

[0952] software

[0953] Data collection: Python (requests, pandas)

[0954] Data formatting and preprocessing: pandas, NumPy

[0955] Generative AI models: Tensorflow, PyTorch

[0956] Notification system: Firebase Cloud Messaging, SendGrid

[0957] Feedback collection: Firebase Realtime Database

[0958] Overall flow of the system

[0959] Data acquisition

[0960] The server uses trusted data sources such as APIs (e.g., stock exchange APIs) to collect quarterly financial data for specific companies.

[0961] Data formatting and preprocessing

[0962] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data.

[0963] Analysis by Generative AI

[0964] Based on preprocessed data, a generative AI model is used to perform competitive analysis. The generative AI model is built using Tensorflow or PyTorch, and extracts key metrics such as sales, profits, and growth rates for each company, and compares them.

[0965] An example of a prompt message to the generating AI used in this process is as follows:

[0966] Collect the latest quarterly financial data for the specified company and conduct a comparative analysis with its competitors using the following metrics: sales, profits, growth rate, etc. Based on the results, generate a detailed report and provide a prompt to notify the user.

[0967] Report generation and notification

[0968] Based on the analysis results, the server generates a detailed report. This report is then communicated to the user via Firebase Cloud Messaging or SendGrid. Push notifications and emails are sent, allowing users to confirm receipt of the report in real time.

[0969] Feedback Collection

[0970] Users can provide feedback on the reports. This feedback is collected using the Firebase Realtime Database and used as training data for future generative AI. This allows the generative AI to continuously improve and generate more accurate reports.

[0971] Specific example

[0972] For example, the system can obtain quarterly financial data for a specific company, "Company A," and its competitors, "Company B" and "Company C," and compare and analyze their respective sales, profits, and growth rates. The analysis results would then be generated as a report detailing specific information, such as "Company A's sales increased by 10% in the third quarter of 2023, while competitors B and C recorded increases of 15% and 12% respectively. The generated report would be sent to the user via push notification or email, allowing them to review it and provide feedback.

[0973] In this way, companies can quickly and efficiently obtain the information they need to maintain and improve their competitiveness.

[0974] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0975] Step 1: Data Acquisition

[0976] The server collects quarterly financial data for specific companies using trusted data sources such as APIs. Specifically, it retrieves financial data from stock exchange APIs. The input is the financial data provided via the API, and the output is the retrieved raw data.

[0977] Step 2: Data preparation and preprocessing

[0978] The server removes unnecessary fields from the collected financial data, imputes missing values, and converts the data into a unified format. Specifically, it uses Python's pandas and NumPy to format and preprocess the data. The input is the raw data obtained, and the output is the preprocessed, clean data.

[0979] Step 3: Generating prompts for the AI

[0980] The server generates prompt statements for analysis using a generative AI model, based on the formatted and pre-processed data. Specifically, it creates concrete instructions for analyzing the collected and formatted data. The input is the pre-processed data, and the output is the generated prompt statements.

[0981] Step 4: Competitive Analysis

[0982] This program performs competitive analysis based on pre-processed data using a generative AI model. The generative AI model is built using Tensorflow and PyTorch, extracting key metrics such as sales, profits, and growth rates for each company, and comparing them. The input consists of prompts and pre-processed data, while the output is the analysis results.

[0983] Step 5: Report Generation

[0984] The server generates a detailed report based on the analysis results. Specifically, it compiles key metrics of interest to the user and comparison results with competitors into a report. The input is the analysis results, and the output is the generated detailed report.

[0985] Step 6: Report Notification

[0986] The generated report is sent as a notification to the user's smartphone. Specifically, push notifications and emails are sent using Firebase Cloud Messaging or SendGrid. The input is the generated report, and the output is the notification to the user.

[0987] Step 7: Gathering Feedback

[0988] Users can provide feedback on the report. This feedback is collected using Firebase Realtime Database and used as training data for future generative AI iterations. The input is user feedback, and the output is the training data for the generative AI.

[0989] The above outlines the specific processing steps of the system that implements the application example.

[0990] 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.

[0991] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. By combining this system with an emotion engine that recognizes the user's emotions, it can provide more personalized reports.

[0992] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to retrieve the latest financial data. This data is then temporarily stored in a database on the server.

[0993] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[0994] The formatted and pre-processed data is used by the generating AI to perform competitive analysis. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and performs a comparative analysis of the competitors based on these metrics.

[0995] The generating AI creates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[0996] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[0997] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI. This allows the generation AI to continuously improve and generate more accurate reports.

[0998] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[0999] As a concrete example, if a user wants to perform a comparative analysis by specifying "Company A," "Competitor B," and "Competitor C," the server first retrieves the latest quarterly financial results data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data, and then performs the comparative analysis using generative AI. A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions when providing feedback and incorporates this into the generative AI's training data. This improves future reports so that they better meet the user's expectations.

[1000] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[1001] The following describes the processing flow.

[1002] Step 1:

[1003] The server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers and receives the latest financial data as API responses. This data is stored in a database on the server.

[1004] Step 2:

[1005] The server formats and preprocesses the acquired financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using previous year's data or industry averages. The formatted data is then ready for use in the next processing step.

[1006] Step 3:

[1007] The server provides formatted and pre-processed data as input to the generating AI. The generating AI extracts key metrics such as sales, profits, and growth rates for a specific company and its competitors, as specified by the user. Based on the extracted data, it performs a comparative analysis with its competitors.

[1008] Step 4:

[1009] The generating AI compares and analyzes the performance of a specific company and its competitors based on extracted key metrics. Specifically, it calculates each company's growth rate and profit margin, and evaluates their relative performance. The results of this analysis are temporarily stored on the server as intermediate data.

[1010] Step 5:

[1011] The server generates detailed reports based on intermediate data, taking into account user preferences and past feedback. Specifically, it creates reports in PDF or HTML format that include metrics of interest to the user and comparison results for each company. These reports may include specific details such as, "Company A's sales increased by 10%, competitor B's by 15%, and competitor C's by 12%."

[1012] Step 6:

[1013] The server notifies the user when the generated report is complete. This notification is sent via email or push notification. This allows the user to monitor the report generation in real time and prepare to review it.

[1014] Step 7:

[1015] After receiving a notification, users access the dashboard using their device to view the generated report. Here, they can view detailed report content and focus on specific sections.

[1016] Step 8:

[1017] Users provide feedback on the report's content. Specifically, a form for entering evaluations and suggestions for improvement will appear on their device. Users submit their opinions through this form.

[1018] Step 9:

[1019] In this step, an emotion engine is activated to recognize the user's emotions when they provide feedback. It analyzes the user's input and input method (e.g., typing speed and emphasis) to recognize positive or negative emotions.

[1020] Step 10:

[1021] The server collects user feedback and the results of the emotion engine's analysis, using this as training data for the generative AI. The collected data is used to adjust the generative AI's parameters and improve its algorithms, and this information is reflected in future report generation.

[1022] Step 11:

[1023] For subsequent report generation, the report content and format will be dynamically customized based on the analysis results of the emotion engine. Positive feedback will maintain the same report format, while negative feedback will reflect areas for improvement.

[1024] This processing flow allows companies to quickly and accurately perform comparative analysis with competitors and receive personalized reports based on user sentiment.

[1025] (Example 2)

[1026] 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".

[1027] Traditional corporate performance analysis systems often require manual comparison with competitors for specific metrics, making them inefficient and hindering the delivery of personalized reports due to their failure to consider user sentiment. Furthermore, they lack adequate mechanisms for incorporating feedback into system improvements, making subsequent reports likely to fail to meet user expectations. This has made it difficult for companies to quickly and efficiently obtain the information needed to improve their competitiveness.

[1028] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generation AI model based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, and means for including an emotion engine that collects user feedback and analyzes that feedback, and reflects it in the learning of the generation AI model for subsequent uses. This makes it possible to automatically compare and analyze the performance of a company with that of its competitors and to quickly and efficiently provide personalized reports based on the user's emotions.

[1029] "Specific companies" refers to individual legal entities operating in a particular industry or market.

[1030] "Quarterly financial data" refers to data that shows a company's financial activities at the end of each of the four quarters in which the year is divided.

[1031] A "reliable data source" refers to an information provider that is guaranteed to provide accurate and up-to-date information.

[1032] "Formatting" refers to the process of organizing data into a format suitable for analysis and standardizing the format.

[1033] "Preprocessing" refers to the process performed to improve the quality of data prior to analysis, and specifically includes deleting unnecessary data and imputing missing values.

[1034] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically analyze data and is trained to perform a specific task.

[1035] "Competitive analysis" refers to an analysis that compares the performance of a specific company with that of its competitors to identify its strengths and weaknesses.

[1036] A "report" refers to an official document that summarizes analysis results and insights.

[1037] "Users" refer to individuals or corporations that use this system to obtain information.

[1038] "Notification" refers to a means of communication used to inform users of new information or events.

[1039] "Feedback" refers to the opinions and evaluations that users provide about the results and usability of a system.

[1040] An "emotion engine" refers to an algorithm that analyzes the emotions expressed by users during feedback and processes them as data.

[1041] Modes for carrying out the invention

[1042] This invention relates to a system that automatically compares and analyzes the performance of a specific company with that of its competitors, providing users with useful information. The system can provide more personalized reports by incorporating an emotion engine that recognizes user emotions.

[1043] Data collection

[1044] First, the server collects quarterly financial data for specific companies from reliable data sources. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. For example, it retrieves the Q3 2023 data for company A. This data is then temporarily stored in a database on the server.

[1045] Data formatting and preprocessing

[1046] Next, the server formats and preprocesses the acquired financial data. Specifically, it removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. It also performs interpolation if missing values ​​exist. For example, if sales data is missing, it will use data from the previous year or industry averages to fill in the gaps.

[1047] Competitive analysis

[1048] The formatted and pre-processed data is used by the generative AI model to perform competitive analysis. The server extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user, and uses these to perform a comparative analysis with competitors. The generative AI model is provided with prompts such as, "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in their growth rates."

[1049] Report generation

[1050] The AI ​​model generates a detailed report on the server based on the analysis results. This report includes key metrics of interest to the user and comparisons with competitors. For example, it might include specific details such as, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B recorded a 15% increase and competitor C recorded a 12% increase."

[1051] User notifications

[1052] The generated report is notified to the user from the server. Notification methods include email and push notifications. This allows the user to know that a report has been generated and to access the dashboard to view the details.

[1053] Feedback Collection

[1054] Furthermore, users can provide feedback on the generated reports. A feedback form is displayed on the device, allowing users to fill in their opinions on the report's content, format, and analysis results. The server collects this feedback and uses it as training data for future generation AI models. This allows the generation AI model to continuously improve, enabling it to produce more accurate reports.

[1055] Utilizing the Emotion Engine

[1056] Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's emotions when feedback is input and reflects the results as training data for the generating AI model. For example, if the user shows positive emotions, data is added to enhance the report's content. On the other hand, if negative emotions are recognized, adjustments are made to improve the report and address the user's dissatisfaction.

[1057] Specific example

[1058] As a concrete example, consider a scenario where a user wants to perform a comparative analysis of "Company A," "Competitor B," and "Competitor C." The server first retrieves the latest quarterly financial data for these companies from EDGAR or other data sources. Next, it formats and preprocesses the data and performs a comparative analysis using a generative AI model. The prompt used is "Compare the quarterly sales data of Company A, Company B, and Company C, and analyze the differences in growth rates." A detailed report is generated based on the analysis results and notified to the user. The user reviews the report on the dashboard and provides feedback on its contents. Furthermore, the sentiment engine analyzes the user's emotions during feedback and incorporates them into the training data of the generative AI model. This improves future reports to better meet user expectations.

[1059] In this way, companies can not only quickly and efficiently obtain the information necessary to maintain and improve their competitiveness, but also enjoy personalized reports based on user sentiment.

[1060] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1061] Step 1: Data Collection

[1062] The server retrieves quarterly financial data for a specific company from a trusted data source. Specifically, it accesses APIs from stock exchanges and financial data providers to obtain the latest financial data. The server sends a "GET" request to the API endpoint, receives the returned data in JSON format, and parses it. The input is the identification information of the specific company, and the output is the parsed financial data.

[1063] Step 2: Data preparation and preprocessing

[1064] The server formats and preprocesses the collected financial data. It removes unnecessary fields and inaccurate data, and standardizes the format of numerical data. If missing values ​​exist, it imputes them using historical data or industry averages. Specifically, it reads data from the database, executes formatting and preprocessing algorithms, and generates clean data. The input is parsed financial data, and the output is formatted and preprocessed data.

[1065] Step 3: Competitive Analysis

[1066] The server performs competitive analysis using a generative AI model based on the formatted and pre-processed data. It extracts key metrics (sales, profits, growth rate, etc.) for a specific company and its competitors specified by the user. The prompt used is "Compare the quarterly sales data of company A, company B, and company C, and analyze the differences in growth rates." The server inputs the data into the generative AI model and receives the analysis results as output. The input consists of formatted and pre-processed data and the prompt, and the output is the result of the competitive analysis.

[1067] Step 4: Report Generation

[1068] The AI ​​model generates a detailed report based on the competitive analysis results. The report includes key metrics of interest to the user and comparisons with competitors. For example, it might state, "Company A's sales increased by 10% in the third quarter of 2023, while competitor B increased by 15% and competitor C by 12%." The server converts the analysis results into a text-based report and prepares it for display on the dashboard. The input is the competitive analysis results, and the output is the generated report.

[1069] Step 5: Notify the user

[1070] The server notifies the user of the generated report. It sends a message to the user via email or a push notification system stating, "A new report has been generated." Upon receiving the notification, the user can access the dashboard to view the detailed report. The input is the generated report, and the output is the notification message to the user.

[1071] Step 6: Gathering Feedback

[1072] Users provide feedback on the report's content and format through their device. A feedback form is displayed, and users enter their opinions and suggestions for improvement and submit it. The server collects this feedback. The input is the user's feedback, and the output is the feedback data.

[1073] Step 7: Emotional analysis using the emotion engine

[1074] The emotion engine analyzes the user's emotions when they provide feedback. Specifically, it uses a text analysis algorithm to classify emotions as positive or negative. For example, if the user writes, "This information was very helpful," it will be classified as a positive emotion. The input is feedback data, and the output is an emotion score.

[1075] Step 8: Updating the Generating AI

[1076] The server uses the collected feedback and sentiment data as training data for its generative AI model. This allows the generative AI model to be improved for future report generation. Specifically, the collected data is added to the training dataset, and the generative AI model is retrained. The input is the feedback and sentiment data, and the output is the updated generative AI model.

[1077] (Application Example 2)

[1078] 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".

[1079] Companies need to continuously understand market trends and competitor activities to maintain and improve their competitiveness. However, there is a lack of systems that can automatically collect and analyze vast amounts of data and then specifically propose how to utilize it in advertising strategies. Furthermore, there is a demand for personalized information that is continuously improved based on user feedback. Currently, there is no system that can integrate and efficiently provide all of these requirements, making it difficult for companies to obtain the right information quickly.

[1080] 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 means for acquiring quarterly financial data of a specific company, means for formatting and pre-processing the acquired financial data, means for performing competitive analysis using a generating AI based on the pre-processed data, means for generating a report based on the analysis results, means for notifying the user of the generated report, means for collecting feedback from the user and reflecting it in the learning of the generating AI for subsequent uses, means for analyzing the user's emotions at the time of feedback and personalizing the generated report, and means for optimizing the advertising strategy based on the report and evaluating and proposing the performance of advertising creatives and the effectiveness of campaigns. As a result, companies can automatically grasp the competitive situation and quickly build and execute effective advertising strategies.

[1081] "Specific companies" refers to one or more existing legal entities whose performance is evaluated based on financial data that is released quarterly.

[1082] "Quarterly financial data" refers to information that companies disclose on a quarterly basis, showing their financial status and including figures such as sales, profits, and growth rates.

[1083] "Data shaping and preprocessing" refers to the process of removing unnecessary fields and inaccurate data from collected quarterly financial statements and standardizing the format of numerical data.

[1084] "Generative AI" is an algorithm that uses artificial intelligence technology to perform competitive analysis based on key metrics specified by the user and generate a detailed report.

[1085] "Competitive analysis" is the process of evaluating the performance of a particular company by comparing it to other companies operating in the same market.

[1086] "Report generation" is the process of creating a document that compiles useful information for users based on analyzed competitive data.

[1087] "Notifications" refer to means of informing users of the existence of generated reports, and include email and push notifications.

[1088] "Feedback" refers to the opinions and evaluations that users provide regarding the generated reports.

[1089] "Emotional analysis" is a technology that recognizes a user's emotions during feedback and analyzes whether those emotions are positive or negative.

[1090] Personalization is the process of adjusting the information and services provided to a user to match their specific needs and expectations, based on the results of sentiment analysis.

[1091] "Advertising strategy optimization" is the process of planning and executing the most effective advertising campaigns based on analysis results and user feedback.

[1092] "Advertising creative performance" refers to evaluating how effective the elements used in an advertisement, such as images, videos, and text, actually were.

[1093] "Campaign effectiveness" is a measure used to evaluate how much an implemented advertising campaign contributed to achieving its goals.

[1094] This invention is a system for optimizing advertising strategies by comparing the performance of a specific company with that of its competitors. This system is specifically implemented as an application installed on smartphones.

[1095] First, the server retrieves quarterly financial data for a specific company from a reliable data source. Specifically, it accesses the API of a financial data provider to obtain the latest financial data. This data is then temporarily stored in a database on the server.

[1096] Next, the acquired data is formatted and preprocessed. Unnecessary fields and inaccurate data are removed, and the format of numerical data is standardized. In addition, if missing values ​​exist, they are imputed using data from the previous year or industry averages.

[1097] The formatted and pre-processed data is used for competitive analysis using generative AI. The server extracts key metrics (e.g., sales, profits, growth rate, etc.) for a specific company and its competitors, and performs competitive analysis based on these metrics. Based on the analysis results, the server generates a detailed report. This report includes key metrics of interest to the user and comparisons with competitors.

[1098] The generated report is notified to the user via push notification or email on their smartphone. The user can open the application and view the detailed report on the dashboard. Here, the user can provide feedback on the report's content. The sentiment engine analyzes this feedback and recognizes the user's emotions. If the feedback is positive, additional data is added to maintain and enhance the report's content. Conversely, if negative emotions are recognized, areas for improvement in the report are clearly indicated.

[1099] Next, the generating AI uses this feedback to improve its learning for subsequent reports. This results in more accurate reports that better meet user expectations. Furthermore, as a means of optimizing advertising strategies, the system collects performance data for ad creatives and campaign effectiveness measurement data, integrating these with the results of competitive analysis. An optimized advertising strategy is then proposed to the user.

[1100] As a concrete example, let's say a specific company is "Company A," and its competitors are "Company B" and "Company C." The server retrieves the latest quarterly financial data for these companies from EDGAR and other data sources. Next, after formatting and preprocessing the data, a comparative analysis is performed by a generative AI. Based on the results of this analysis, a detailed report is generated and notified to the user. The user reviews the report on a dashboard and provides feedback. During this feedback process, an emotion engine analyzes the user's emotions and incorporates them into the generative AI's training data.

[1101] Example of a prompt:

[1102] "The user wants to compare the performance of 'Company A,' 'Company B,' and 'Company C.' Based on the latest quarterly earnings data collected, conduct a competitive analysis and generate a personalized advertising strategy report. The user's sentiment feedback is 'I am very happy with the report!' Please consider this feedback to improve the content of the next report."

[1103] The three elements of server, terminal, and user work together to efficiently perform automated analysis of corporate performance and optimize advertising strategies.

[1104] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1105] Step 1:

[1106] The server retrieves quarterly financial data for a specific company from a trusted data source. This input data is raw data retrieved via an API request, and the output is unformatted financial data stored in a database. Data is retrieved via the API endpoint and stored in the server's database.

[1107] Step 2:

[1108] The server formats and preprocesses the financial data it acquires. This input data is the financial data obtained from the raw database, and the output is formatted data with unnecessary fields and inaccurate data removed and missing values ​​imputed. Specifically, it removes redundant information and fills in missing values ​​with data from the previous year or the industry average.

[1109] Step 3:

[1110] The server performs competitive analysis using a generative AI based on pre-processed data. The input data is pre-processed and formatted financial data, and the output is the competitive analysis results from the generative AI model. Specifically, key indicators such as sales, profits, and growth rates are extracted, and a comparative analysis with competitors is performed based on these indicators.

[1111] Step 4:

[1112] The server generates a report based on the analysis results. The input data is the competitive analysis results from the generative AI model, and the output is a detailed report. The generative AI creates a detailed report according to the specified prompts, including key metrics and competitive comparisons that will interest the user.

[1113] Step 5:

[1114] The server notifies the user of the generated report. The input data is the generated detailed report, and the output is a notification to the user's smartphone. Specifically, it sends an email or push notification to inform the user that the report is available.

[1115] Step 6:

[1116] Users view reports on a dashboard and provide feedback. The input data includes the report content and user feedback text, while the output is feedback data and the user's sentiment state. Users review the report and input their thoughts and suggestions for improvement.

[1117] Step 7:

[1118] The server collects user feedback and performs sentiment analysis. The input data is the feedback text, and the output is the user's sentiment analysis results and updated AI model training data. The sentiment engine analyzes the emotional state of the feedback and reflects this in the generative AI model.

[1119] Step 8:

[1120] The server updates the generating AI based on the sentiment analysis results and reflects them in subsequent reports. The input data consists of the sentiment analysis results and updated training data, while the output is a more personalized report in subsequent reports. The generating AI model is continuously trained to provide reports that better meet user expectations.

[1121] Step 9:

[1122] The server optimizes advertising strategies and proposes optimized advertising campaigns. The input data includes competitive analysis results and sentiment analysis results, and the output is an optimized advertising strategy report. It integrates advertising creative performance data and campaign effectiveness measurement data to suggest the best advertising strategy for the user.

[1123] 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.

[1124] 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.

[1125] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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."

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] The following is further disclosed regarding the embodiments described above.

[1145] (Claim 1)

[1146] Means of obtaining quarterly financial data for a specific company,

[1147] Means for formatting and pre-processing acquired financial data,

[1148] A method for performing competitive analysis using generative AI based on preprocessed data,

[1149] A means of generating a report based on the analysis results,

[1150] A means of notifying the user of the generated report,

[1151] A means of collecting user feedback and incorporating it into the learning process for future generation AI,

[1152] A system that includes this.

[1153] (Claim 2)

[1154] The system according to claim 1, comprising means for periodically collecting quarterly financial data of the aforementioned specific company from a reliable data source.

[1155] (Claim 3)

[1156] The system according to claim 1, wherein the generating AI extracts key indicators such as sales, profits, and growth rates for each company and compares them.

[1157]

[1158] "Example 1"

[1159] (Claim 1)

[1160] Means of obtaining quarterly performance data for a specific organization,

[1161] Means for formatting and preprocessing acquired performance data,

[1162] A means of performing competitive analysis using computational intelligence generated based on preprocessed data,

[1163] A means of generating a report based on the analysis results,

[1164] A means of notifying users of the generated report,

[1165] A means of collecting user feedback and incorporating it into the learning process of the generated computer intelligence in the future,

[1166] An information processing system that includes this.

[1167] (Claim 2)

[1168] The information processing system according to claim 1, comprising means for periodically collecting quarterly performance data of the aforementioned specific organization from a reliable data source.

[1169] (Claim 3)

[1170] The information processing system according to claim 1, wherein the generated computer intelligence extracts key indicators such as sales, profits, and growth rates of each organization and compares them.

[1171] "Application Example 1"

[1172] (Claim 1)

[1173] Means of obtaining quarterly financial data for a specific company,

[1174] Means for formatting and pre-processing acquired financial data,

[1175] A method for performing competitive analysis using generative AI based on preprocessed data,

[1176] A means of generating a report based on the analysis results,

[1177] A means of notifying the user of the generated report,

[1178] A means of collecting user feedback and incorporating it into the learning process for future generation AI,

[1179] A means for generating prompt sentences to be analyzed by a generated AI model based on collected, formatted, and preprocessed data,

[1180] When notifying users of the generated report, methods such as push notifications and email notifications are available.

[1181] A system that includes this.

[1182] (Claim 2)

[1183] The system according to claim 1, comprising means for periodically collecting quarterly financial data of the aforementioned specific company from a reliable data source.

[1184] (Claim 3)

[1185] The system according to claim 1, wherein the generating AI extracts key indicators such as sales, profits, and growth rates for each company and compares them.

[1186] "Example 2 of combining an emotion engine"

[1187] (Claim 1)

[1188] Means of obtaining quarterly financial data for a specific company,

[1189] Means for formatting and pre-processing acquired financial data,

[1190] A means of performing competitive analysis using a generative AI model based on preprocessed data,

[1191] A means of generating a report based on the analysis results,

[1192] A means of notifying the user of the generated report,

[1193] This system includes an emotion engine that collects user feedback and analyzes it, and incorporates this feedback into the learning of subsequent generative AI models.

[1194] A system that includes this.

[1195] (Claim 2)

[1196] The system according to claim 1, comprising means for periodically collecting quarterly financial data of the aforementioned specific company from a reliable data source.

[1197] (Claim 3)

[1198] The system according to claim 1, wherein the generating AI model extracts key indicators such as sales, profits, and growth rates of each company using prompt sentences and compares them.

[1199] "Application example 2 when combining with an emotional engine"

[1200] (Claim 1)

[1201] Means of obtaining quarterly financial data for a specific company,

[1202] Means for formatting and pre-processing acquired financial data,

[1203] A method for performing competitive analysis using generative AI based on preprocessed data,

[1204] A means of generating a report based on the analysis results,

[1205] A means of notifying the user of the generated report,

[1206] A means of collecting user feedback and incorporating it into the learning process for future generation AI,

[1207] A means to analyze user emotions during feedback and personalize the generated report,

[1208] Based on this report, we will optimize our advertising strategy and provide a means to evaluate and propose the performance of advertising creatives and the effectiveness of campaigns.

[1209] A system that includes this.

[1210] (Claim 2)

[1211] The system according to claim 1, comprising means for periodically collecting quarterly financial data of the aforementioned specific company from a reliable data source.

[1212] (Claim 3)

[1213] The system according to claim 1, wherein the generating AI extracts key indicators such as sales, profits, and growth rates for each company and compares them. [Explanation of symbols]

[1214] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining quarterly financial data for a specific company, Means for formatting and pre-processing acquired financial data, A method for performing competitive analysis using generative AI based on preprocessed data, A means of generating a report based on the analysis results, A means of notifying the user of the generated report, A means of collecting user feedback and incorporating it into the learning process for future generation AI, A system that includes this.

2. The system according to claim 1, comprising means for periodically collecting quarterly financial data of the aforementioned specific company from a reliable data source.

3. The system according to claim 1, wherein the generating AI extracts key indicators such as sales, profits, and growth rates for each company and compares them.

Images