system

Abstract

We provide the system. [Solution] A means of collecting data from multiple data sources, A means for cleaning the aforementioned data and formatting it into a unified format, A means for analyzing the aforementioned data using a generative model and forecasting demand, A means of visualizing and displaying the analysis results, A means for generating recommendations regarding inventory management and production planning, 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] Predicting fluctuations in demand in enterprises is complex, and conventional methods have problems of causing excess inventory or supply shortages, resulting in increased costs and opportunity losses. Also, in conventional demand forecasting, it is difficult to comprehensively handle various data such as sales data, weather information, competitive information, and consumers' social media posts, and it is difficult to make highly accurate predictions.

Means for Solving the Problems

[0005] This invention provides a system that collects data from multiple data sources, cleans and formats it into a unified format, performs analysis using a generative model, and then performs demand forecasting. This system visually displays the analysis results and generates recommendations regarding inventory management and production planning, thereby supporting timely and optimal decision-making. In this process, it considers diverse data such as sales data, weather data, competitor information, and consumer social media posts, and utilizes time series analysis and multivariate analysis to achieve highly accurate demand forecasting.

[0006] A "data source" refers to the original source or foundation from which information is obtained, and includes sales data, weather data, competitor information, and consumer social media posts.

[0007] "Cleaning" is the process of removing errors, omissions, and unnecessary parts from collected data, making it suitable for data analysis.

[0008] A "unified format" refers to a framework or format that arranges data in different formats into a consistent form, ensuring data integrity in analysis.

[0009] A "generative model" is an algorithm or computational method built on historical data for the purpose of making predictions or performing analyses.

[0010] "Analysis results" refer to the processing results of collected and analyzed data, and are used for visualizing demand forecasts and making recommendations.

[0011] "Visualization" is a method of displaying the results of data analysis in a graphical form to make them easier to understand.

[0012] "Recommendation" refers to suggesting actions or choices that are deemed optimal based on data.

[0013] "Inventory management" refers to the processes and strategies necessary to maintain and control the inventory of goods, and is an activity aimed at maintaining an efficient supply chain.

[0014] A "production plan" is a plan for setting and implementing overall policies and specific production schedules related to the production of a product.

[0015] Time series analysis is a method of analyzing data recorded at different times, and it is an analysis that predicts the future based on past trends.

[0016] "Multivariable analysis" is a method that comprehensively analyzes data involving multiple variables and factors to clarify their relationships and influences. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]Shows an emotion map where 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 Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes 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 processor with a reference numeral (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 RAM (Random Access Memory) with a reference numeral 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] The system according to the present invention enables more accurate demand forecasting by applying other technologies and integrating and analyzing diverse data sources. The system consists of a server, a terminal, and a user interface.

[0039] Data collection and integration

[0040] The server retrieves data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts. It collects the necessary information via APIs or web scraping and stores it in a database. For example, sales data is obtained from a business management system, and weather data from a weather service.

[0041] Data preprocessing

[0042] The server cleans the collected data and formats it into a unified format, making it parseable across different data types. It handles missing and outlier values, generating a consistent dataset overall.

[0043] Analysis and demand forecasting

[0044] The server inputs pre-processed data into a generative model and performs demand forecasting based on time series analysis and multivariate analysis. The AI ​​analyzes past data patterns and predicts future demand. The results are output to a visual dashboard.

[0045] Visualization and Recommendation

[0046] The server displays the analysis results in easy-to-understand graphs and charts, presenting them to the user via a terminal. Furthermore, the system provides specific recommendations regarding inventory management and production planning, supporting the user's decision-making.

[0047] Specific example

[0048] For example, the server predicts the peak demand for a particular product next month based on past sales data. This analysis also takes into account that past weather data is associated with increased sales on weekends. As a result of the analysis, the server recommends increasing inventory during that period and notifies the user via a terminal. The user then uses this information to adjust the supply chain and optimize inventory.

[0049] In this way, the system can use diverse data to forecast demand and support accurate inventory management and production planning.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server collects sales data, weather data, competitor information, and consumer social media posts from data sources. Sales data is obtained through the business management system's API, and weather data is obtained from a weather API. Competitor information is scraped from web news, and social media posts are collected using SNS APIs.

[0053] Step 2:

[0054] The server cleans the collected data. It detects, corrects, or removes incomplete data and outliers to ensure data consistency. This prepares a dataset that is free from problems for subsequent analysis.

[0055] Step 3:

[0056] The server converts the cleaned data into a unified format. It standardizes different data formats and date formats, and formats the data into a parseable form.

[0057] Step 4:

[0058] The server feeds the formatted data into a generative model for analysis. The AI ​​model utilizes time series analysis and multivariate analysis to forecast demand in real time or at regular intervals.

[0059] Step 5:

[0060] The server generates graphs and charts based on the analysis results for display on the visualization dashboard. This allows users to intuitively understand the data.

[0061] Step 6:

[0062] The server generates recommendations for inventory management and production planning based on demand forecasts. It suggests specific inventory replenishment and adjustments to production schedules.

[0063] Step 7:

[0064] The terminal displays a dashboard, presenting analysis results and recommendations to the user. The user then makes business decisions based on the displayed information.

[0065] (Example 1)

[0066] 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."

[0067] In today's business environment, there is a demand for improved accuracy in demand forecasting, but it is difficult to make accurate forecasts in near real-time while utilizing diverse data sources. Furthermore, there is a lack of systems that present analysis results in an easy-to-understand manner and provide concrete guidance for inventory management and production planning. As a result, there is insufficient support for making appropriate decisions.

[0068] 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.

[0069] In this invention, the server includes means for acquiring information from various sources and storing it in a database, means for organizing the information and converting it into a standard format, and means for analyzing the data using artificial intelligence and performing demand forecasting. This makes it possible to centrally manage data obtained from various sources and to perform highly accurate demand forecasting using that data. Furthermore, by visualizing the analysis results and providing them to users in an easy-to-understand manner, it is possible to support quick and accurate decision-making.

[0070] "Diverse information sources" refers to a collection of data sources that include information from various categories, such as sales data, weather information, competitor information, and online consumer posts.

[0071] "Means of acquiring information and storing it in a database" refers to the process of collecting external data using APIs or web scraping techniques, organizing it, and saving it to a storage system.

[0072] "Means of organizing information and converting it to a standard format" refers to the process of cleaning and formatting acquired data to remove outliers and standardize data formats.

[0073] "Means of using artificial intelligence to analyze the aforementioned data and perform demand forecasting" refers to a process of analyzing data using machine learning and deep learning technologies to predict future demand.

[0074] "Means of visualization and output to users" refers to tools and technologies that display analyzed data results in graphics or charts, providing them in a way that is easy for users to understand.

[0075] "Means for generating recommended information regarding resource management and production planning" refers to a process that proposes appropriate inventory and production volumes to users based on demand forecast results, thereby promoting efficient resource utilization.

[0076] The system according to the present invention is an advanced technological platform for data collection, preprocessing, analysis, visualization, and generation of recommendation information. This system consists of a server, terminals, and a user interface.

[0077] The server retrieves information from various sources and stores it in a database. The hardware used is a server with high-performance network connectivity that provides the necessary processing power. Software-wise, APIs and web scraping techniques are used for data collection. For example, sales information is obtained from a business management system, and weather information is obtained from weather services via APIs.

[0078] The collected information is processed by the server and converted to a standard format. Common data handling tools are used for data preparation. For example, libraries such as Pandas and NumPy are utilized to handle missing values ​​and standardize the data.

[0079] Data analysis using artificial intelligence is a crucial element for demand forecasting. The server executes generative AI models and performs data analysis. Models such as Prophet and LSTM are used for time series analysis and multidimensional analysis. Through this analysis, future demand patterns are predicted.

[0080] The analysis results are visualized by the server and output to the user via the terminal. Tools such as Tableau and Power BI are used for visualization. This allows users to intuitively understand the analysis results and make decisions based on that information.

[0081] Furthermore, the system generates recommended resource management and production planning information based on the analysis results, supporting users' strategic decision-making. Users access the system using their terminals and utilize the information provided on the dashboard. This enables optimization of inventory management and production planning.

[0082] In this way, the server efficiently handles all data processing, while users can use the provided information to improve their work processes.

[0083] Example prompt: "Based on past sales data and weather data, predict next month's demand."

[0084] This invention significantly improves the operational efficiency of users by centrally managing data from diverse information sources and using it to perform highly accurate demand forecasting.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server collects data from diverse sources. It accepts sales information, weather information, competitor information, and online consumer posts as input. This data is retrieved using APIs and web scraping techniques and stored in a database. For example, sales information is retrieved via data requests from the business management system and stored on the server.

[0088] Step 2:

[0089] The server processes the collected data and converts it to a standard format. The input to this process is the raw, unprocessed data collected in step 1. Data cleansing tools are used to impute missing values ​​and remove outliers. The output is processed data that can be analyzed. Specifically, the server uses the Pandas library to unify and standardize the data format.

[0090] Step 3:

[0091] The server takes pre-processed data as input and performs analysis using a generated AI model. Specifically, it performs time-series analysis and multidimensional analysis to forecast demand. The output is forecast result data. At this time, the server loads a Prophet model and executes the model's calculations to predict future supply and demand relationships.

[0092] Step 4:

[0093] The server visualizes the analyzed prediction results and outputs them to the user via the terminal. The input is the prediction results obtained in step 3. The server uses Tableau or Power BI to visualize the results in graph and chart format. The visualized data is provided to the user on the terminal and displayed in an easy-to-understand format.

[0094] Step 5:

[0095] Users review recommendations presented through their devices and make decisions regarding resource management and production planning. Analysis results and recommendations are provided as input. Based on this data, users optimize inventory and adjust production schedules. Specifically, users utilize the information displayed on the dashboard to determine concrete actions to adjust their business strategies.

[0096] Through this entire process, the system supports supply and demand forecasting based on diverse data and improves operational efficiency.

[0097] (Application Example 1)

[0098] 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."

[0099] Improving the accuracy of demand forecasting and optimizing inventory management remain major challenges in modern logistics centers. In particular, there is a growing need to integrate data from multiple sources to make timely decisions regarding inventory replenishment and production planning. However, due to the diversity of data and the complexity of analytical methods, effective approaches are currently lacking.

[0100] 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.

[0101] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, and means for analyzing the information using a generative model and making demand forecasts. This makes it possible to provide more accurate demand forecasts and appropriate recommendations in inventory management and production planning at logistics centers.

[0102] "Information sources" refer to sources and media that provide diverse data, specifically including sales data, weather information, competitor information, and consumer social media posts.

[0103] "Information cleaning" is the process of removing noise and missing values ​​from collected raw data and processing it into a state suitable for analysis.

[0104] A "unified format" is a data format that standardizes data from different formats and specifications, and formats it into a consistent form.

[0105] A "generative model" is an artificial intelligence algorithm or mathematical model used to learn past data patterns and perform future demand forecasting and analysis.

[0106] "Visualization" is the act of visually representing data using graphs and charts in order to display analysis results in an easy-to-understand manner.

[0107] A "user interface" refers to the means of interaction, including screens and input methods, that a user uses to interact with a computer system.

[0108] "Recommendation" refers to advice or suggestions based on analysis results that recommend specific actions or support decision-making.

[0109] The system implementing this invention first involves a server collecting information from multiple sources. Specifically, it obtains sales data, weather information, competitor information, consumer social media posts, etc., using APIs and web scraping techniques. The information is stored in a database, data cleaning is performed using software such as Pandas, and the data is formatted into a unified format.

[0110] Next, the server inputs the formatted information into a generative model and performs demand forecasting using time series analysis and multidimensional analysis techniques. This process utilizes machine learning libraries such as Scikit-learn and TENSORFLOW®. The analysis results are visualized using Matplotlib and Plotly and presented to the user through a user interface.

[0111] Users can view the visualized analysis results through their devices and optimize inventory management and production planning based on them. The system further supports user decision-making by generating appropriate recommendations based on the analysis results.

[0112] For example, if the server predicts increased demand for a particular product next month, it will display a recommendation to increase inventory in preparation for that period. This allows users to adjust their supply chain and optimize their inventory.

[0113] An example of a prompt message is, "Please forecast demand based on next week's weather and past sales data." By inputting this prompt into the AI ​​model, more accurate forecast results can be obtained.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects information from multiple sources. Specifically, it obtains sales data and weather information via APIs, and uses web scraping techniques to collect competitor information and consumer social media posts. The input is raw data obtained from external sources, and the output is an unprocessed dataset.

[0117] Step 2:

[0118] The server cleans the collected data and formats it into a unified format. Pandas is used to handle missing values ​​and outliers, ensuring consistent data structure. The input is a raw dataset, and the output is data formatted for analysis.

[0119] Step 3:

[0120] The server generates formatted data, which is then input into an AI model for time series analysis and multidimensional analysis. Using Scikit-learn and TensorFlow, the model learns past data patterns and predicts future demand. The input is formatted data, and the output is predicted demand data.

[0121] Step 4:

[0122] The server visualizes the analysis results and creates easy-to-understand graphs and charts. It uses Matplotlib and Plotly to visually represent the data and provide it to the user. The input is predicted demand data, and the output is graphs and charts of the visualized data.

[0123] Step 5:

[0124] Users view analysis results via a terminal and receive recommendations for inventory management and production planning based on those results. They make decisions and adjust the supply chain based on the data displayed on the terminal. The input is the visualized data and recommendations displayed on the terminal, and the output is the user's decision.

[0125] 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.

[0126] This invention provides an integrated system for companies to perform more accurate demand forecasting and optimize inventory management and production planning. In addition to conventional data analysis methods, this system incorporates an emotion engine that analyzes consumer sentiment, thereby achieving comprehensive demand forecasting that takes consumer feelings into account.

[0127] Data collection and cleaning

[0128] The server collects data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts, using standard APIs and scraping techniques. The collected data undergoes a cleaning process to remove outliers, is supplemented as needed, and converted into a unified format.

[0129] emotion recognition

[0130] The server utilizes an emotion engine to analyze consumer social media posts. It recognizes the emotions contained in the posts and identifies consumer likes and dissatisfactions. For example, if a particular product's reputation is rising on social media, this information can be used for demand forecasting to predict how much positive emotion will impact sales.

[0131] Demand forecasting and analysis

[0132] The server inputs the cleaned data and sentiment analysis results into a generative model to perform demand forecasting through time series analysis and multivariate analysis. By taking into account the impact of sentiment fluctuations, more realistic results can be obtained. These analysis results are updated in real time.

[0133] Visualization and Recommendation

[0134] The analysis results are displayed on a dashboard by the server. Information is conveyed visually using graphs and charts, making it easy for users to understand. Furthermore, the server uses this data to provide each user with the most relevant recommendations. For example, it might suggest inventory replenishment or promotional activities to address specific sentiment trends.

[0135] Specific example

[0136] The server analyzes weather data and consumer social media posts, and if it detects positive social media sentiment for popular products on rainy days, in conjunction with a forecast of rain on the next week's sale day, it predicts increased demand for those products. Recommendations for restocking are immediately displayed on the device, allowing users to adjust appropriate orders and promotional strategies.

[0137] Thus, the system of the present invention utilizes an emotion engine to incorporate consumer emotions into demand forecasting and provides a highly effective recommendation function, thereby supporting corporate management decisions.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server collects data from sales data, weather data, competitor information, and consumer social media posts. APIs and scraping techniques are used for each data source, and the data is updated regularly as needed.

[0141] Step 2:

[0142] The server cleans the data it has collected. It improves data reliability by detecting incomplete data and anomalous data points and correcting or removing them.

[0143] Step 3:

[0144] The server converts the cleaned data into a unified format. This step unifies different data formats and date formats, making the data parseable.

[0145] Step 4:

[0146] The server uses an emotion engine to analyze social media posts and recognize consumer emotions. Text analysis is used to classify and quantify emotions as positive, negative, neutral, etc.

[0147] Step 5:

[0148] The server inputs cleaned data, including sentiment data, into the generative model. The model, which combines time series analysis and multivariate analysis, performs demand forecasting and generates results.

[0149] Step 6:

[0150] The server visualizes the demand forecast results and displays them on the terminal as a dashboard. Graphs and charts are used to visually represent the analysis results and an overview of the supply and demand forecast.

[0151] Step 7:

[0152] The server generates recommendations for inventory management and production planning based on prediction results. It creates recommendations that take sentiment data into account and suggests specific actions to the user regarding particular products or promotional initiatives.

[0153] Step 8:

[0154] The terminal displays a dashboard and recommendations from the server to the user. The user makes business decisions based on the displayed information and adjusts inventory and production plans as needed.

[0155] (Example 2)

[0156] 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".

[0157] Traditional demand forecasting systems struggle to accurately predict the demand for goods and services, and they fail to take into account changes in consumer sentiment. As a result, incorrect decisions can be made in inventory management and production planning, leading to problems such as excess inventory, stockouts, and lost sales opportunities.

[0158] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0159] In this invention, the server includes means for acquiring information from multiple information sources, means for detecting and removing anomalies in the information, imputing missing values, and converting it into a unified format, and means for analyzing consumer sentiment using natural language processing and integrating the results of the sentiment analysis with the information. This enables more accurate demand forecasting that takes consumer sentiment into account.

[0160] "Information sources" refer to external data sources that the system uses to collect data, such as sales data, weather information, competitor information, and consumer social network posts.

[0161] An "outlier" refers to a value within a dataset that lacks regularity and falls outside the normal range, potentially impairing the accuracy of data analysis.

[0162] "Missing values" refer to parts of a dataset where data that should be present is missing, and these need to be imputed to improve the accuracy of statistical processing.

[0163] "Sentiment analysis" is the process of identifying positive, negative, or neutral emotions from text expressed by consumers using natural language processing technology.

[0164] A "generative AI model" is a predictive model that utilizes artificial intelligence technology to analyze and simulate collected data.

[0165] Time series analysis is a statistical method that analyzes changes in data over time and uses past trends to predict the future.

[0166] "Multivariable analysis" is a statistical method that simultaneously analyzes the relationships between multiple variables and evaluates their impact on the problem being addressed.

[0167] "Recommendation" refers to supporting decision-making by providing specific action suggestions and improvement measures to users based on analysis results.

[0168] In a form for carrying out the invention, this system is formed by the server, terminal, and user each fulfilling their respective roles. First, the server retrieves data from multiple sources. This process utilizes common APIs and web scraping techniques. Using these methods, the server stores sales information, weather information, competitor information, and consumer posts from social networks into a database.

[0169] Next, the server performs data cleansing. It detects and removes outliers and imputes missing values ​​using appropriate statistical methods. At this stage, the collected data is converted into a standardized format and becomes ready for analysis.

[0170] The server then uses a sentiment analysis engine to extract sentiment information from social media text. Specifically, it leverages natural language processing techniques to identify the positive, negative, and neutral sentiments expressed by consumers. This result becomes a crucial variable input into a demand forecasting model.

[0171] The generative AI model predicts future demand using advanced algorithms, including time series analysis and multivariate analysis. This may involve the use of data analysis platforms such as Python and R. The resulting predictions are visualized in a dashboard format and displayed on the user's device. This visualized information allows users to make concrete decisions regarding inventory management and manufacturing planning.

[0172] For example, suppose the server analyzes data and predicts rain for the following week, while simultaneously detecting positive social media sentiment regarding products popular on rainy days. In this case, the system anticipates increased demand and recommends replenishing inventory to the user. Based on this, the user can quickly adjust their promotional strategy. Another example of a prompt given to the generating AI model is a specific instruction such as, "Please forecast demand based on weather and consumer sentiment that will affect next week's sale day." In this way, the system supports accurate, data-driven business decisions.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server retrieves data from multiple sources, specifically sales information, weather information, competitor information, and consumer posts from social networks. This involves using API calls and scraping techniques to collect data according to a regular schedule. Input consists of raw data from each source, while output is information storage in a unified data format.

[0176] Step 2:

[0177] The server performs a cleansing process on the collected data. Specifically, it removes outliers from the data using an anomaly detection algorithm and imputes missing values ​​using appropriate statistical methods. The input is the acquired raw data, and the output is a cleaned, analyzable dataset. This data is converted to a standard format and passed on to the next step.

[0178] Step 3:

[0179] The server analyzes social media posts using a sentiment analysis engine. Specifically, it uses natural language processing techniques to identify positive, negative, and neutral sentiments contained in the text data. The input is cleaned social network data, and the output is a dataset containing sentiment scores and trends. This result provides important input information for demand forecasting.

[0180] Step 4:

[0181] The server inputs cleaned data and sentiment analysis results into a generative AI model to perform demand forecasting. The generative AI model uses time series analysis and multivariate analysis to execute an algorithm that predicts future demand. The input is an integrated dataset, and the output is the demand forecast result. This result provides foundational information to guide decision-making necessary for business operations.

[0182] Step 5:

[0183] The server visualizes the demand forecast results and displays them on the terminal in a dashboard format. This uses graphs and charts, designed to allow users to intuitively understand the information. The input is demand forecast data, and the output is visualized information. Based on this information, users can take specific actions to optimize inventory management and production planning.

[0184] Step 6:

[0185] The server generates and presents recommendations regarding inventory management and manufacturing plans based on the analysis results. Specifically, it suggests inventory replenishment in response to predicted demand increases and promotional activities based on specific sentiment trends. The input consists of demand forecast data and consumer sentiment analysis results, while the output is specific recommendations. By implementing these recommendations, users can make more effective business decisions.

[0186] (Application Example 2)

[0187] 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".

[0188] In today's market, there is a need for highly accurate demand forecasting that can respond to consumer emotions and sudden changes in trends. However, conventional demand forecasting systems cannot fully utilize emotional information, making it difficult to respond flexibly and quickly in inventory management and production planning. To solve this problem, it is necessary to build a new system that incorporates consumer emotions into demand forecasting.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, means for analyzing the information using a generative model and forecasting demand, means for identifying consumer sentiment using a sentiment analysis engine, means for visualizing and displaying the analysis results, and means for generating recommendations regarding inventory management and production planning. This enables dynamic and highly accurate demand forecasting that takes consumer sentiment into account, as well as the optimization of responsive inventory management and production planning.

[0191] "Information sources" refer to the starting point for acquiring data, such as sales data, weather information, competitor information, and consumer social media posts.

[0192] "Cleaning" is the process of removing outliers from acquired information, filling in missing parts, and preparing it in a format suitable for analysis.

[0193] A "generative model" is an algorithm used to analyze data and make predictions using time series analysis and multivariate analysis.

[0194] A "sentiment analysis engine" is a technology that reads emotions from text data such as consumers' social media posts and quantifies those emotions.

[0195] "Demand forecasting" is the process of predicting future fluctuations in demand and estimating future demand for a product.

[0196] "Inventory management" is the process of maintaining inventory levels with maximum efficiency and replenishing or adjusting stocks as needed.

[0197] "Production planning" is a management task that optimizes production volume and schedule in accordance with future demand forecasts.

[0198] "Recommendation" is the process of suggesting the optimal course of action, such as replenishing inventory or implementing promotional activities, based on analyzed data.

[0199] The system implementing this invention is primarily composed of a program running on a server. The server first collects data from multiple information sources, such as sales information, weather information, competitor information, and consumer social media posts. Various APIs and scraping techniques are used to access the information sources. After data collection, a data cleansing process is performed to remove outliers, fill in missing parts, and format the data into a unified format. This makes the data suitable for analysis.

[0200] Next, the server uses a generative model to analyze the cleaned data and generate demand forecasts. During this process, the server utilizes a sentiment analysis engine to analyze the text of consumers' social media posts, identifying and quantifying positive or negative emotions. This incorporates sentiment data into the demand forecast, improving its accuracy and making it more realistic.

[0201] The analysis results are displayed on the administrator's terminal via a visualization tool. Graphs and charts are used for visualization, presenting the results in a format easily understandable to the user. Furthermore, the server generates and presents optimal recommendations for inventory management and production planning based on the analysis results. For example, if an increase in demand for a specific product based on consumer sentiment is predicted, this information is immediately communicated to the administrator, prompting rapid inventory replenishment and adjustments to promotional strategies.

[0202] For example, if the weather forecast predicts rain during the rainy season and positive sentiment towards a specific product increases on social media, the system will generate a demand forecast stating that "the product is likely to sell well" and recommend replenishing the product's inventory. An example of a prompt message would be: "The weather forecast for next week is rain, and positive sentiment towards a specific product is increasing on social media. Please provide a demand forecast and inventory replenishment advice based on these conditions."

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server uses APIs and scraping techniques to collect data from sources such as sales information, weather information, competitor information, and consumer social media posts. Input requires authentication credentials to access each source, and output generates raw data in various formats. This prepares the server to obtain data on a variety of factors influencing consumer demand.

[0206] Step 2:

[0207] The server performs a data cleaning process to remove outliers and fill in missing data from the raw data. The input is the collected raw data, and the output is cleaned data formatted into a unified format. This creates a clean dataset suitable for analysis.

[0208] Step 3:

[0209] The server uses a generated AI model to analyze cleaned data and generate demand forecasts. Time-series data and multiple variable data are provided as input, and the output is numerical data representing the predicted demand. In particular, a sentiment analysis engine is used to identify the sentiment of consumer posts, and this information is incorporated into the demand forecast.

[0210] Step 4:

[0211] The server visualizes the analysis results based on the generated demand forecast and displays them as graphs and charts on the administrator's terminal. Forecast data is provided as input, and the output is a visually easy-to-understand visualization graphic. The administrator uses this to check inventory and production plans.

[0212] Step 5:

[0213] The server utilizes the analysis results to generate and present specific recommendations for inventory management and production planning to the user. Inputs include visualized forecast data and the user's current inventory status, while output provides recommendations indicating the optimal course of action. Based on these recommendations, the user considers product replenishment and promotional plans.

[0214] Step 6:

[0215] Users follow the provided recommendations to appropriately adjust inventory replenishment and promotional activities. Inputs include recommendations provided by the server and current market conditions, while output is strategic decision-making. This enables dynamic inventory and production management based on consumer sentiment.

[0216] 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.

[0217] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] The system according to the present invention enables more accurate demand forecasting by applying other technologies and integrating and analyzing diverse data sources. The system consists of a server, a terminal, and a user interface.

[0233] Data collection and integration

[0234] The server retrieves data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts. It collects the necessary information via APIs or web scraping and stores it in a database. For example, sales data is obtained from a business management system, and weather data from a weather service.

[0235] Data preprocessing

[0236] The server cleans the collected data and formats it into a unified format, making it parseable across different data types. It handles missing and outlier values, generating a consistent dataset overall.

[0237] Analysis and demand forecasting

[0238] The server inputs pre-processed data into a generative model and performs demand forecasting based on time series analysis and multivariate analysis. The AI ​​analyzes past data patterns and predicts future demand. The results are output to a visual dashboard.

[0239] Visualization and Recommendation

[0240] The server displays the analysis results in easy-to-understand graphs and charts, presenting them to the user via a terminal. Furthermore, the system provides specific recommendations regarding inventory management and production planning, supporting the user's decision-making.

[0241] Specific example

[0242] For example, the server predicts the peak demand for a particular product next month based on past sales data. This analysis also takes into account that past weather data is associated with increased sales on weekends. As a result of the analysis, the server recommends increasing inventory during that period and notifies the user via a terminal. The user then uses this information to adjust the supply chain and optimize inventory.

[0243] In this way, the system can use diverse data to forecast demand and support accurate inventory management and production planning.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The server collects sales data, weather data, competitor information, and consumer social media posts from data sources. Sales data is obtained through the business management system's API, and weather data is obtained from a weather API. Competitor information is scraped from web news, and social media posts are collected using SNS APIs.

[0247] Step 2:

[0248] The server cleans the collected data. It detects, corrects, or removes incomplete data and outliers to ensure data consistency. This prepares a dataset that is free from problems for subsequent analysis.

[0249] Step 3:

[0250] The server converts the cleaned data into a unified format. It standardizes different data formats and date formats, and formats the data into a parseable form.

[0251] Step 4:

[0252] The server feeds the formatted data into a generative model for analysis. The AI ​​model utilizes time series analysis and multivariate analysis to forecast demand in real time or at regular intervals.

[0253] Step 5:

[0254] The server generates graphs and charts based on the analysis results for display on the visualization dashboard. This allows users to intuitively understand the data.

[0255] Step 6:

[0256] The server generates recommendations for inventory management and production planning based on demand forecasts. It suggests specific inventory replenishment and adjustments to production schedules.

[0257] Step 7:

[0258] The terminal displays a dashboard, presenting analysis results and recommendations to the user. The user then makes business decisions based on the displayed information.

[0259] (Example 1)

[0260] 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."

[0261] In today's business environment, there is a demand for improved accuracy in demand forecasting, but it is difficult to make accurate forecasts in near real-time while utilizing diverse data sources. Furthermore, there is a lack of systems that present analysis results in an easy-to-understand manner and provide concrete guidance for inventory management and production planning. As a result, there is insufficient support for making appropriate decisions.

[0262] 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.

[0263] In this invention, the server includes means for acquiring information from various sources and storing it in a database, means for organizing the information and converting it into a standard format, and means for analyzing the data using artificial intelligence and performing demand forecasting. This makes it possible to centrally manage data obtained from various sources and to perform highly accurate demand forecasting using that data. Furthermore, by visualizing the analysis results and providing them to users in an easy-to-understand manner, it is possible to support quick and accurate decision-making.

[0264] "Diverse information sources" refers to a collection of data sources that include information from various categories, such as sales data, weather information, competitor information, and online consumer posts.

[0265] "Means of acquiring information and storing it in a database" refers to the process of collecting external data using APIs or web scraping techniques, organizing it, and saving it to a storage system.

[0266] "Means of organizing information and converting it to a standard format" refers to the process of cleaning and formatting acquired data to remove outliers and standardize data formats.

[0267] "Means of using artificial intelligence to analyze the aforementioned data and perform demand forecasting" refers to a process of analyzing data using machine learning and deep learning technologies to predict future demand.

[0268] "Means of visualization and output to users" refers to tools and technologies that display analyzed data results in graphics or charts, providing them in a way that is easy for users to understand.

[0269] "Means for generating recommended information regarding resource management and production planning" refers to a process that proposes appropriate inventory and production volumes to users based on demand forecast results, thereby promoting efficient resource utilization.

[0270] The system according to the present invention is an advanced technological platform for data collection, preprocessing, analysis, visualization, and generation of recommendation information. This system consists of a server, terminals, and a user interface.

[0271] The server retrieves information from various sources and stores it in a database. The hardware used is a server with high-performance network connectivity that provides the necessary processing power. Software-wise, APIs and web scraping techniques are used for data collection. For example, sales information is obtained from a business management system, and weather information is obtained from weather services via APIs.

[0272] The collected information is processed by the server and converted to a standard format. Common data handling tools are used for data preparation. For example, libraries such as Pandas and NumPy are utilized to handle missing values ​​and standardize the data.

[0273] Data analysis using artificial intelligence is a crucial element for demand forecasting. The server executes generative AI models and performs data analysis. Models such as Prophet and LSTM are used for time series analysis and multidimensional analysis. Through this analysis, future demand patterns are predicted.

[0274] The analysis results are visualized by the server and output to the user via the terminal. Tools such as Tableau and Power BI are used for visualization. This allows users to intuitively understand the analysis results and make decisions based on that information.

[0275] Furthermore, the system generates recommended resource management and production planning information based on the analysis results, supporting users' strategic decision-making. Users access the system using their terminals and utilize the information provided on the dashboard. This enables optimization of inventory management and production planning.

[0276] In this way, the server efficiently handles all data processing, while users can use the provided information to improve their work processes.

[0277] Example prompt: "Based on past sales data and weather data, predict next month's demand."

[0278] This invention centrally manages data from various information sources and uses it to perform highly accurate demand forecasting, thereby greatly improving the business efficiency of users.

[0279] The flow of the specific process in Example 1 will be described using FIG. 11.

[0280] Step 1:

[0281] The server collects data from various information sources. As inputs, it receives sales information, weather information, competitor information, and consumers' online posts. These data are acquired using API or web scraping technology and stored in a database. For example, the sales information is obtained through a data request from an enterprise management system and saved on the server.

[0282] Step 2:

[0283] The server cleans and converts the collected data into a standard format. The input for this process is the raw, uncleaned data collected in Step 1. A data cleansing tool is used to complete missing values and remove outliers. As output, analyzable, cleaned data is obtained. Specifically, the server uses the Pandas library to unify the data format and perform standardization.

[0284] Step 3:

[0285] The server uses the cleaned data as input and performs analysis using a generative AI model. As specific operations, time series analysis and multi-dimensional analysis are carried out to perform demand forecasting. As output, prediction result data is obtained. At this time, the server loads the Prophet model and executes the model's calculations to predict the future supply-demand relationship.

[0286] Step 4:

[0287] The server visualizes the analyzed prediction results and outputs them to the user via the terminal. The input is the prediction results obtained in step 3. The server uses Tableau or Power BI to visualize the results in graph and chart format. The visualized data is provided to the user on the terminal and displayed in an easy-to-understand format.

[0288] Step 5:

[0289] Users review recommendations presented through their devices and make decisions regarding resource management and production planning. Analysis results and recommendations are provided as input. Based on this data, users optimize inventory and adjust production schedules. Specifically, users utilize the information displayed on the dashboard to determine concrete actions to adjust their business strategies.

[0290] Through this entire process, the system supports supply and demand forecasting based on diverse data and improves operational efficiency.

[0291] (Application Example 1)

[0292] 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."

[0293] Improving the accuracy of demand forecasting and optimizing inventory management remain major challenges in modern logistics centers. In particular, there is a growing need to integrate data from multiple sources to make timely decisions regarding inventory replenishment and production planning. However, due to the diversity of data and the complexity of analytical methods, effective approaches are currently lacking.

[0294] 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.

[0295] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, and means for analyzing the information using a generative model and making demand forecasts. This makes it possible to provide more accurate demand forecasts and appropriate recommendations in inventory management and production planning at logistics centers.

[0296] "Information sources" refer to sources and media that provide diverse data, specifically including sales data, weather information, competitor information, and consumer social media posts.

[0297] "Information cleaning" is the process of removing noise and missing values ​​from collected raw data and processing it into a state suitable for analysis.

[0298] A "unified format" is a data format that standardizes data from different formats and specifications, and formats it into a consistent form.

[0299] A "generative model" is an artificial intelligence algorithm or mathematical model used to learn past data patterns and perform future demand forecasting and analysis.

[0300] "Visualization" is the act of visually representing data using graphs and charts in order to display analysis results in an easy-to-understand manner.

[0301] A "user interface" refers to the means of interaction, including screens and input methods, that a user uses to interact with a computer system.

[0302] "Recommendation" refers to advice or suggestions based on analysis results that recommend specific actions or support decision-making.

[0303] The system for implementing this invention first has the server collect information from multiple information sources. Specifically, it obtains sales data, weather information, competitive information, consumers' social media posts, etc. using APIs and web scraping technologies. The information is stored in a database, and data cleaning is performed using software such as Pandas and formatted into a unified format.

[0304] Next, the server inputs the formatted information into a generation model and performs demand forecasting using time series analysis and multi-dimensional analysis methods. Machine learning libraries such as Scikit-learn and TensorFlow are utilized in this process. The analysis results are visualized using Matplotlib and Plotly and presented to the user through the user interface.

[0305] The user can view the visualized analysis results through the terminal and optimize inventory management and production plans based on them. The system further generates appropriate recommendations based on the analysis results to assist the user in decision-making.

[0306] As a specific example, when the server predicts that the demand for a specific product will increase next month, it displays a recommendation to increase the inventory in preparation for that period. Thereby, the user can adjust the supply chain and optimize the inventory.

[0307] Examples of prompt texts include "Please perform demand forecasting based on next week's weather and past sales data." By inputting this prompt into the generative AI model, more accurate prediction results can be obtained.

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The server collects information from multiple sources. Specifically, it obtains sales data and weather information via APIs, and uses web scraping techniques to collect competitor information and consumer social media posts. The input is raw data obtained from external sources, and the output is an unprocessed dataset.

[0311] Step 2:

[0312] The server cleans the collected data and formats it into a unified format. Pandas is used to handle missing values ​​and outliers, ensuring consistent data structure. The input is a raw dataset, and the output is data formatted for analysis.

[0313] Step 3:

[0314] The server generates formatted data, which is then input into an AI model for time series analysis and multidimensional analysis. Using Scikit-learn and TensorFlow, the model learns past data patterns and predicts future demand. The input is formatted data, and the output is predicted demand data.

[0315] Step 4:

[0316] The server visualizes the analysis results and creates easy-to-understand graphs and charts. It uses Matplotlib and Plotly to visually represent the data and provide it to the user. The input is predicted demand data, and the output is graphs and charts of the visualized data.

[0317] Step 5:

[0318] Users view analysis results via a terminal and receive recommendations for inventory management and production planning based on those results. They make decisions and adjust the supply chain based on the data displayed on the terminal. The input is the visualized data and recommendations displayed on the terminal, and the output is the user's decision.

[0319] 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.

[0320] This invention provides an integrated system for companies to perform more accurate demand forecasting and optimize inventory management and production planning. In addition to conventional data analysis methods, this system incorporates an emotion engine that analyzes consumer sentiment, thereby achieving comprehensive demand forecasting that takes consumer feelings into account.

[0321] Data collection and cleaning

[0322] The server collects data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts, using standard APIs and scraping techniques. The collected data undergoes a cleaning process to remove outliers, is supplemented as needed, and converted into a unified format.

[0323] emotion recognition

[0324] The server utilizes an emotion engine to analyze consumer social media posts. It recognizes the emotions contained in the posts and identifies consumer likes and dissatisfactions. For example, if a particular product's reputation is rising on social media, this information can be used for demand forecasting to predict how much positive emotion will impact sales.

[0325] Demand forecasting and analysis

[0326] The server inputs the cleaned data and sentiment analysis results into a generative model to perform demand forecasting through time series analysis and multivariate analysis. By taking into account the impact of sentiment fluctuations, more realistic results can be obtained. These analysis results are updated in real time.

[0327] Visualization and Recommendation

[0328] The analysis results are displayed on a dashboard by the server. Information is conveyed visually using graphs and charts, making it easy for users to understand. Furthermore, the server uses this data to provide each user with the most relevant recommendations. For example, it might suggest inventory replenishment or promotional activities to address specific sentiment trends.

[0329] Specific example

[0330] The server analyzes weather data and consumer social media posts, and if it detects positive social media sentiment for popular products on rainy days, in conjunction with a forecast of rain on the next week's sale day, it predicts increased demand for those products. Recommendations for restocking are immediately displayed on the device, allowing users to adjust appropriate orders and promotional strategies.

[0331] Thus, the system of the present invention utilizes an emotion engine to incorporate consumer emotions into demand forecasting and provides a highly effective recommendation function, thereby supporting corporate management decisions.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server collects data from sales data, weather data, competitor information, and consumer social media posts. APIs and scraping techniques are used for each data source, and the data is updated regularly as needed.

[0335] Step 2:

[0336] The server cleans the data it has collected. It improves data reliability by detecting incomplete data and anomalous data points and correcting or removing them.

[0337] Step 3:

[0338] The server converts the cleaned data into a unified format. This step unifies different data formats and date formats, making the data parseable.

[0339] Step 4:

[0340] The server uses an emotion engine to analyze social media posts and recognize consumer emotions. Text analysis is used to classify and quantify emotions as positive, negative, neutral, etc.

[0341] Step 5:

[0342] The server inputs cleaned data, including sentiment data, into the generative model. The model, which combines time series analysis and multivariate analysis, performs demand forecasting and generates results.

[0343] Step 6:

[0344] The server visualizes the demand forecast results and displays them on the terminal as a dashboard. Graphs and charts are used to visually represent the analysis results and an overview of the supply and demand forecast.

[0345] Step 7:

[0346] The server generates recommendations for inventory management and production planning based on prediction results. It creates recommendations that take sentiment data into account and suggests specific actions to the user regarding particular products or promotional initiatives.

[0347] Step 8:

[0348] The terminal displays a dashboard and recommendations from the server to the user. The user makes business decisions based on the displayed information and adjusts inventory and production plans as needed.

[0349] (Example 2)

[0350] 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".

[0351] Traditional demand forecasting systems struggle to accurately predict the demand for goods and services, and they fail to take into account changes in consumer sentiment. As a result, incorrect decisions can be made in inventory management and production planning, leading to problems such as excess inventory, stockouts, and lost sales opportunities.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for acquiring information from multiple information sources, means for detecting and removing anomalies in the information, imputing missing values, and converting it into a unified format, and means for analyzing consumer sentiment using natural language processing and integrating the results of the sentiment analysis with the information. This enables more accurate demand forecasting that takes consumer sentiment into account.

[0354] "Information sources" refer to external data sources that the system uses to collect data, such as sales data, weather information, competitor information, and consumer social network posts.

[0355] An "outlier" refers to a value within a dataset that lacks regularity and falls outside the normal range, potentially impairing the accuracy of data analysis.

[0356] "Missing values" refer to parts of a dataset where data that should be present is missing, and these need to be imputed to improve the accuracy of statistical processing.

[0357] "Sentiment analysis" is the process of identifying positive, negative, or neutral emotions from text expressed by consumers using natural language processing technology.

[0358] A "generative AI model" is a predictive model that utilizes artificial intelligence technology to analyze and simulate collected data.

[0359] Time series analysis is a statistical method that analyzes changes in data over time and uses past trends to predict the future.

[0360] "Multivariable analysis" is a statistical method that simultaneously analyzes the relationships between multiple variables and evaluates their impact on the problem being addressed.

[0361] "Recommendation" refers to supporting decision-making by providing specific action suggestions and improvement measures to users based on analysis results.

[0362] In a form for carrying out the invention, this system is formed by the server, terminal, and user each fulfilling their respective roles. First, the server retrieves data from multiple sources. This process utilizes common APIs and web scraping techniques. Using these methods, the server stores sales information, weather information, competitor information, and consumer posts from social networks into a database.

[0363] Next, the server performs data cleansing. It detects and removes outliers and imputes missing values ​​using appropriate statistical methods. At this stage, the collected data is converted into a standardized format and becomes ready for analysis.

[0364] The server then uses a sentiment analysis engine to extract sentiment information from social media text. Specifically, it leverages natural language processing techniques to identify the positive, negative, and neutral sentiments expressed by consumers. This result becomes a crucial variable input into a demand forecasting model.

[0365] The generative AI model predicts future demand using advanced algorithms, including time series analysis and multivariate analysis. This may involve the use of data analysis platforms such as Python and R. The resulting predictions are visualized in a dashboard format and displayed on the user's device. This visualized information allows users to make concrete decisions regarding inventory management and manufacturing planning.

[0366] For example, suppose the server analyzes data and predicts rain for the following week, while simultaneously detecting positive social media sentiment regarding products popular on rainy days. In this case, the system anticipates increased demand and recommends replenishing inventory to the user. Based on this, the user can quickly adjust their promotional strategy. Another example of a prompt given to the generating AI model is a specific instruction such as, "Please forecast demand based on weather and consumer sentiment that will affect next week's sale day." In this way, the system supports accurate, data-driven business decisions.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The server retrieves data from multiple sources, specifically sales information, weather information, competitor information, and consumer posts from social networks. This involves using API calls and scraping techniques to collect data according to a regular schedule. Input consists of raw data from each source, while output is information storage in a unified data format.

[0370] Step 2:

[0371] The server performs a cleansing process on the collected data. Specifically, it removes outliers from the data using an anomaly detection algorithm and imputes missing values ​​using appropriate statistical methods. The input is the acquired raw data, and the output is a cleaned, analyzable dataset. This data is converted to a standard format and passed on to the next step.

[0372] Step 3:

[0373] The server analyzes social media posts using a sentiment analysis engine. Specifically, it uses natural language processing techniques to identify positive, negative, and neutral sentiments contained in the text data. The input is cleaned social network data, and the output is a dataset containing sentiment scores and trends. This result provides important input information for demand forecasting.

[0374] Step 4:

[0375] The server inputs cleaned data and sentiment analysis results into a generative AI model to perform demand forecasting. The generative AI model uses time series analysis and multivariate analysis to execute an algorithm that predicts future demand. The input is an integrated dataset, and the output is the demand forecast result. This result provides foundational information to guide decision-making necessary for business operations.

[0376] Step 5:

[0377] The server visualizes the demand forecast results and displays them on the terminal in a dashboard format. This uses graphs and charts, designed to allow users to intuitively understand the information. The input is demand forecast data, and the output is visualized information. Based on this information, users can take specific actions to optimize inventory management and production planning.

[0378] Step 6:

[0379] The server generates and presents recommendations regarding inventory management and manufacturing plans based on the analysis results. Specifically, it suggests inventory replenishment in response to predicted demand increases and promotional activities based on specific sentiment trends. The input consists of demand forecast data and consumer sentiment analysis results, while the output is specific recommendations. By implementing these recommendations, users can make more effective business decisions.

[0380] (Application Example 2)

[0381] 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 as the "terminal".

[0382] In today's market, there is a need for highly accurate demand forecasting that can respond to consumer emotions and sudden changes in trends. However, conventional demand forecasting systems cannot fully utilize emotional information, making it difficult to respond flexibly and quickly in inventory management and production planning. To solve this problem, it is necessary to build a new system that incorporates consumer emotions into demand forecasting.

[0383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0384] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, means for analyzing the information using a generative model and forecasting demand, means for identifying consumer sentiment using a sentiment analysis engine, means for visualizing and displaying the analysis results, and means for generating recommendations regarding inventory management and production planning. This enables dynamic and highly accurate demand forecasting that takes consumer sentiment into account, as well as the optimization of responsive inventory management and production planning.

[0385] "Information sources" refer to the starting point for acquiring data, such as sales data, weather information, competitor information, and consumer social media posts.

[0386] "Cleaning" is the process of removing outliers from acquired information, filling in missing parts, and preparing it in a format suitable for analysis.

[0387] A "generative model" is an algorithm used to analyze data and make predictions using time series analysis and multivariate analysis.

[0388] A "sentiment analysis engine" is a technology that reads emotions from text data such as consumers' social media posts and quantifies those emotions.

[0389] "Demand forecasting" is the process of predicting future fluctuations in demand and estimating future demand for a product.

[0390] "Inventory management" is the process of maintaining inventory levels with maximum efficiency and replenishing or adjusting stocks as needed.

[0391] "Production planning" is a management task that optimizes production volume and schedule in accordance with future demand forecasts.

[0392] "Recommendation" is the process of suggesting the optimal course of action, such as replenishing inventory or implementing promotional activities, based on analyzed data.

[0393] The system implementing this invention is primarily composed of a program running on a server. The server first collects data from multiple information sources, such as sales information, weather information, competitor information, and consumer social media posts. Various APIs and scraping techniques are used to access the information sources. After data collection, a data cleansing process is performed to remove outliers, fill in missing parts, and format the data into a unified format. This makes the data suitable for analysis.

[0394] Next, the server uses a generative model to analyze the cleaned data and generate demand forecasts. During this process, the server utilizes a sentiment analysis engine to analyze the text of consumers' social media posts, identifying and quantifying positive or negative emotions. This incorporates sentiment data into the demand forecast, improving its accuracy and making it more realistic.

[0395] The analysis results are displayed on the administrator's terminal via a visualization tool. Graphs and charts are used for visualization, presenting the results in a format easily understandable to the user. Furthermore, the server generates and presents optimal recommendations for inventory management and production planning based on the analysis results. For example, if an increase in demand for a specific product based on consumer sentiment is predicted, this information is immediately communicated to the administrator, prompting rapid inventory replenishment and adjustments to promotional strategies.

[0396] For example, if the weather forecast predicts rain during the rainy season and positive sentiment towards a specific product increases on social media, the system will generate a demand forecast stating that "the product is likely to sell well" and recommend replenishing the product's inventory. An example of a prompt message would be: "The weather forecast for next week is rain, and positive sentiment towards a specific product is increasing on social media. Please provide a demand forecast and inventory replenishment advice based on these conditions."

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] The server uses APIs and scraping techniques to collect data from sources such as sales information, weather information, competitor information, and consumer social media posts. Input requires authentication credentials to access each source, and output generates raw data in various formats. This prepares the server to obtain data on a variety of factors influencing consumer demand.

[0400] Step 2:

[0401] The server performs a data cleaning process to remove outliers and fill in missing data from the raw data. The input is the collected raw data, and the output is cleaned data formatted into a unified format. This creates a clean dataset suitable for analysis.

[0402] Step 3:

[0403] The server uses a generated AI model to analyze cleaned data and generate demand forecasts. Time-series data and multiple variable data are provided as input, and the output is numerical data representing the predicted demand. In particular, a sentiment analysis engine is used to identify the sentiment of consumer posts, and this information is incorporated into the demand forecast.

[0404] Step 4:

[0405] The server visualizes the analysis results based on the generated demand forecast and displays them as graphs and charts on the administrator's terminal. Forecast data is provided as input, and the output is a visually easy-to-understand visualization graphic. The administrator uses this to check inventory and production plans.

[0406] Step 5:

[0407] The server utilizes the analysis results to generate and present specific recommendations for inventory management and production planning to the user. Inputs include visualized forecast data and the user's current inventory status, while output provides recommendations indicating the optimal course of action. Based on these recommendations, the user considers product replenishment and promotional plans.

[0408] Step 6:

[0409] Users follow the provided recommendations to appropriately adjust inventory replenishment and promotional activities. Inputs include recommendations provided by the server and current market conditions, while output is strategic decision-making. This enables dynamic inventory and production management based on consumer sentiment.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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".

[0426] The system according to the present invention enables more accurate demand forecasting by applying other technologies and integrating and analyzing diverse data sources. The system consists of a server, a terminal, and a user interface.

[0427] Data collection and integration

[0428] The server retrieves data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts. It collects the necessary information via APIs or web scraping and stores it in a database. For example, sales data is obtained from a business management system, and weather data from a weather service.

[0429] Data preprocessing

[0430] The server cleans the collected data and formats it into a unified format, making it parseable across different data types. It handles missing and outlier values, generating a consistent dataset overall.

[0431] Analysis and demand forecasting

[0432] The server inputs pre-processed data into a generative model and performs demand forecasting based on time series analysis and multivariate analysis. The AI ​​analyzes past data patterns and predicts future demand. The results are output to a visual dashboard.

[0433] Visualization and Recommendation

[0434] The server displays the analysis results in easy-to-understand graphs and charts, presenting them to the user via a terminal. Furthermore, the system provides specific recommendations regarding inventory management and production planning, supporting the user's decision-making.

[0435] Specific example

[0436] For example, the server predicts the peak demand for a particular product next month based on past sales data. This analysis also takes into account that past weather data is associated with increased sales on weekends. As a result of the analysis, the server recommends increasing inventory during that period and notifies the user via a terminal. The user then uses this information to adjust the supply chain and optimize inventory.

[0437] In this way, the system can use diverse data to forecast demand and support accurate inventory management and production planning.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The server collects sales data, weather data, competitor information, and consumer social media posts from data sources. Sales data is obtained through the business management system's API, and weather data is obtained from a weather API. Competitor information is scraped from web news, and social media posts are collected using SNS APIs.

[0441] Step 2:

[0442] The server cleans the collected data. It detects, corrects, or removes incomplete data and outliers to ensure data consistency. This prepares a dataset that is free from problems for subsequent analysis.

[0443] Step 3:

[0444] The server converts the cleaned data into a unified format. It standardizes different data formats and date formats, and formats the data into a parseable form.

[0445] Step 4:

[0446] The server feeds the formatted data into a generative model for analysis. The AI ​​model utilizes time series analysis and multivariate analysis to forecast demand in real time or at regular intervals.

[0447] Step 5:

[0448] The server generates graphs and charts based on the analysis results for display on the visualization dashboard. This allows users to intuitively understand the data.

[0449] Step 6:

[0450] The server generates recommendations for inventory management and production planning based on demand forecasts. It suggests specific inventory replenishment and adjustments to production schedules.

[0451] Step 7:

[0452] The terminal displays a dashboard, presenting analysis results and recommendations to the user. The user then makes business decisions based on the displayed information.

[0453] (Example 1)

[0454] 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."

[0455] In today's business environment, there is a demand for improved accuracy in demand forecasting, but it is difficult to make accurate forecasts in near real-time while utilizing diverse data sources. Furthermore, there is a lack of systems that present analysis results in an easy-to-understand manner and provide concrete guidance for inventory management and production planning. As a result, there is insufficient support for making appropriate decisions.

[0456] 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.

[0457] In this invention, the server includes means for acquiring information from various sources and storing it in a database, means for organizing the information and converting it into a standard format, and means for analyzing the data using artificial intelligence and performing demand forecasting. This makes it possible to centrally manage data obtained from various sources and to perform highly accurate demand forecasting using that data. Furthermore, by visualizing the analysis results and providing them to users in an easy-to-understand manner, it is possible to support quick and accurate decision-making.

[0458] "Diverse information sources" refers to a collection of data sources that include information from various categories, such as sales data, weather information, competitor information, and online consumer posts.

[0459] "Means of acquiring information and storing it in a database" refers to the process of collecting external data using APIs or web scraping techniques, organizing it, and saving it to a storage system.

[0460] "Means of organizing information and converting it to a standard format" refers to the process of cleaning and formatting acquired data to remove outliers and standardize data formats.

[0461] "Means of using artificial intelligence to analyze the aforementioned data and perform demand forecasting" refers to a process of analyzing data using machine learning and deep learning technologies to predict future demand.

[0462] "Means of visualization and output to users" refers to tools and technologies that display analyzed data results in graphics or charts, providing them in a way that is easy for users to understand.

[0463] "Means for generating recommended information regarding resource management and production planning" refers to a process that proposes appropriate inventory and production volumes to users based on demand forecast results, thereby promoting efficient resource utilization.

[0464] The system according to the present invention is an advanced technological platform for data collection, preprocessing, analysis, visualization, and generation of recommendation information. This system consists of a server, terminals, and a user interface.

[0465] The server retrieves information from various sources and stores it in a database. The hardware used is a server with high-performance network connectivity that provides the necessary processing power. Software-wise, APIs and web scraping techniques are used for data collection. For example, sales information is obtained from a business management system, and weather information is obtained from weather services via APIs.

[0466] The collected information is processed by the server and converted to a standard format. Common data handling tools are used for data preparation. For example, libraries such as Pandas and NumPy are utilized to handle missing values ​​and standardize the data.

[0467] Data analysis using artificial intelligence is a crucial element for demand forecasting. The server executes generative AI models and performs data analysis. Models such as Prophet and LSTM are used for time series analysis and multidimensional analysis. Through this analysis, future demand patterns are predicted.

[0468] The analysis results are visualized by the server and output to the user via the terminal. Tools such as Tableau and Power BI are used for visualization. This allows users to intuitively understand the analysis results and make decisions based on that information.

[0469] Furthermore, the system generates recommended resource management and production planning information based on the analysis results, supporting users' strategic decision-making. Users access the system using their terminals and utilize the information provided on the dashboard. This enables optimization of inventory management and production planning.

[0470] In this way, the server efficiently handles all data processing, while users can use the provided information to improve their work processes.

[0471] Example prompt: "Based on past sales data and weather data, predict next month's demand."

[0472] This invention significantly improves the operational efficiency of users by centrally managing data from diverse information sources and using it to perform highly accurate demand forecasting.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The server collects data from diverse sources. It accepts sales information, weather information, competitor information, and online consumer posts as input. This data is retrieved using APIs and web scraping techniques and stored in a database. For example, sales information is retrieved via data requests from the business management system and stored on the server.

[0476] Step 2:

[0477] The server processes the collected data and converts it to a standard format. The input to this process is the raw, unprocessed data collected in step 1. Data cleansing tools are used to impute missing values ​​and remove outliers. The output is processed data that can be analyzed. Specifically, the server uses the Pandas library to unify and standardize the data format.

[0478] Step 3:

[0479] The server takes pre-processed data as input and performs analysis using a generated AI model. Specifically, it performs time-series analysis and multidimensional analysis to forecast demand. The output is forecast result data. At this time, the server loads a Prophet model and executes the model's calculations to predict future supply and demand relationships.

[0480] Step 4:

[0481] The server visualizes the analyzed prediction results and outputs them to the user via the terminal. The input is the prediction results obtained in step 3. The server uses Tableau or Power BI to visualize the results in graph and chart format. The visualized data is provided to the user on the terminal and displayed in an easy-to-understand format.

[0482] Step 5:

[0483] Users review recommendations presented through their devices and make decisions regarding resource management and production planning. Analysis results and recommendations are provided as input. Based on this data, users optimize inventory and adjust production schedules. Specifically, users utilize the information displayed on the dashboard to determine concrete actions to adjust their business strategies.

[0484] Through this entire process, the system supports supply and demand forecasting based on diverse data and improves operational efficiency.

[0485] (Application Example 1)

[0486] 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."

[0487] Improving the accuracy of demand forecasting and optimizing inventory management remain major challenges in modern logistics centers. In particular, there is a growing need to integrate data from multiple sources to make timely decisions regarding inventory replenishment and production planning. However, due to the diversity of data and the complexity of analytical methods, effective approaches are currently lacking.

[0488] 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.

[0489] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, and means for analyzing the information using a generative model and making demand forecasts. This makes it possible to provide more accurate demand forecasts and appropriate recommendations in inventory management and production planning at logistics centers.

[0490] "Information sources" refer to sources and media that provide diverse data, specifically including sales data, weather information, competitor information, and consumer social media posts.

[0491] "Information cleaning" is the process of removing noise and missing values ​​from collected raw data and processing it into a state suitable for analysis.

[0492] A "unified format" is a data format that standardizes data from different formats and specifications, and formats it into a consistent form.

[0493] A "generative model" is an artificial intelligence algorithm or mathematical model used to learn past data patterns and perform future demand forecasting and analysis.

[0494] "Visualization" is the act of visually representing data using graphs and charts in order to display analysis results in an easy-to-understand manner.

[0495] A "user interface" refers to the means of interaction, including screens and input methods, that a user uses to interact with a computer system.

[0496] "Recommendation" refers to advice or suggestions based on analysis results that recommend specific actions or support decision-making.

[0497] The system implementing this invention first involves a server collecting information from multiple sources. Specifically, it obtains sales data, weather information, competitor information, consumer social media posts, etc., using APIs and web scraping techniques. The information is stored in a database, data cleaning is performed using software such as Pandas, and the data is formatted into a unified format.

[0498] Next, the server inputs the formatted information into a generative model and performs demand forecasting using time series analysis and multidimensional analysis techniques. This process utilizes machine learning libraries such as Scikit-learn and TensorFlow. The analysis results are visualized using Matplotlib and Plotly and presented to the user through a user interface.

[0499] Users can view the visualized analysis results through their devices and optimize inventory management and production planning based on them. The system further supports user decision-making by generating appropriate recommendations based on the analysis results.

[0500] For example, if the server predicts increased demand for a particular product next month, it will display a recommendation to increase inventory in preparation for that period. This allows users to adjust their supply chain and optimize their inventory.

[0501] An example of a prompt message is, "Please forecast demand based on next week's weather and past sales data." By inputting this prompt into the AI ​​model, more accurate forecast results can be obtained.

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] The server collects information from multiple sources. Specifically, it obtains sales data and weather information via APIs, and uses web scraping techniques to collect competitor information and consumer social media posts. The input is raw data obtained from external sources, and the output is an unprocessed dataset.

[0505] Step 2:

[0506] The server cleans the collected data and formats it into a unified format. Pandas is used to handle missing values ​​and outliers, ensuring consistent data structure. The input is a raw dataset, and the output is data formatted for analysis.

[0507] Step 3:

[0508] The server generates formatted data, which is then input into an AI model for time series analysis and multidimensional analysis. Using Scikit-learn and TensorFlow, the model learns past data patterns and predicts future demand. The input is formatted data, and the output is predicted demand data.

[0509] Step 4:

[0510] The server visualizes the analysis results and creates easy-to-understand graphs and charts. It uses Matplotlib and Plotly to visually represent the data and provide it to the user. The input is predicted demand data, and the output is graphs and charts of the visualized data.

[0511] Step 5:

[0512] Users view analysis results via a terminal and receive recommendations for inventory management and production planning based on those results. They make decisions and adjust the supply chain based on the data displayed on the terminal. The input is the visualized data and recommendations displayed on the terminal, and the output is the user's decision.

[0513] 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.

[0514] This invention provides an integrated system for companies to perform more accurate demand forecasting and optimize inventory management and production planning. In addition to conventional data analysis methods, this system incorporates an emotion engine that analyzes consumer sentiment, thereby achieving comprehensive demand forecasting that takes consumer feelings into account.

[0515] Data collection and cleaning

[0516] The server collects data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts, using standard APIs and scraping techniques. The collected data undergoes a cleaning process to remove outliers, is supplemented as needed, and converted into a unified format.

[0517] emotion recognition

[0518] The server utilizes an emotion engine to analyze consumer social media posts. It recognizes the emotions contained in the posts and identifies consumer likes and dissatisfactions. For example, if a particular product's reputation is rising on social media, this information can be used for demand forecasting to predict how much positive emotion will impact sales.

[0519] Demand forecasting and analysis

[0520] The server inputs the cleaned data and sentiment analysis results into a generative model to perform demand forecasting through time series analysis and multivariate analysis. By taking into account the impact of sentiment fluctuations, more realistic results can be obtained. These analysis results are updated in real time.

[0521] Visualization and Recommendation

[0522] The analysis results are displayed on a dashboard by the server. Information is conveyed visually using graphs and charts, making it easy for users to understand. Furthermore, the server uses this data to provide each user with the most relevant recommendations. For example, it might suggest inventory replenishment or promotional activities to address specific sentiment trends.

[0523] Specific example

[0524] The server analyzes weather data and consumer social media posts, and if it detects positive social media sentiment for popular products on rainy days, in conjunction with a forecast of rain on the next week's sale day, it predicts increased demand for those products. Recommendations for restocking are immediately displayed on the device, allowing users to adjust appropriate orders and promotional strategies.

[0525] Thus, the system of the present invention utilizes an emotion engine to incorporate consumer emotions into demand forecasting and provides a highly effective recommendation function, thereby supporting corporate management decisions.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The server collects data from sales data, weather data, competitor information, and consumer social media posts. APIs and scraping techniques are used for each data source, and the data is updated regularly as needed.

[0529] Step 2:

[0530] The server cleans the data it has collected. It improves data reliability by detecting incomplete data and anomalous data points and correcting or removing them.

[0531] Step 3:

[0532] The server converts the cleaned data into a unified format. This step unifies different data formats and date formats, making the data parseable.

[0533] Step 4:

[0534] The server uses an emotion engine to analyze social media posts and recognize consumer emotions. Text analysis is used to classify and quantify emotions as positive, negative, neutral, etc.

[0535] Step 5:

[0536] The server inputs cleaned data, including sentiment data, into the generative model. The model, which combines time series analysis and multivariate analysis, performs demand forecasting and generates results.

[0537] Step 6:

[0538] The server visualizes the demand forecast results and displays them on the terminal as a dashboard. Graphs and charts are used to visually represent the analysis results and an overview of the supply and demand forecast.

[0539] Step 7:

[0540] The server generates recommendations for inventory management and production planning based on prediction results. It creates recommendations that take sentiment data into account and suggests specific actions to the user regarding particular products or promotional initiatives.

[0541] Step 8:

[0542] The terminal displays a dashboard and recommendations from the server to the user. The user makes business decisions based on the displayed information and adjusts inventory and production plans as needed.

[0543] (Example 2)

[0544] 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."

[0545] Traditional demand forecasting systems struggle to accurately predict the demand for goods and services, and they fail to take into account changes in consumer sentiment. As a result, incorrect decisions can be made in inventory management and production planning, leading to problems such as excess inventory, stockouts, and lost sales opportunities.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0547] In this invention, the server includes means for acquiring information from multiple information sources, means for detecting and removing anomalies in the information, imputing missing values, and converting it into a unified format, and means for analyzing consumer sentiment using natural language processing and integrating the results of the sentiment analysis with the information. This enables more accurate demand forecasting that takes consumer sentiment into account.

[0548] "Information sources" refer to external data sources that the system uses to collect data, such as sales data, weather information, competitor information, and consumer social network posts.

[0549] An "outlier" refers to a value within a dataset that lacks regularity and falls outside the normal range, potentially impairing the accuracy of data analysis.

[0550] "Missing values" refer to parts of a dataset where data that should be present is missing, and these need to be imputed to improve the accuracy of statistical processing.

[0551] "Sentiment analysis" is the process of identifying positive, negative, or neutral emotions from text expressed by consumers using natural language processing technology.

[0552] A "generative AI model" is a predictive model that utilizes artificial intelligence technology to analyze and simulate collected data.

[0553] Time series analysis is a statistical method that analyzes changes in data over time and uses past trends to predict the future.

[0554] "Multivariable analysis" is a statistical method that simultaneously analyzes the relationships between multiple variables and evaluates their impact on the problem being addressed.

[0555] "Recommendation" refers to supporting decision-making by providing specific action suggestions and improvement measures to users based on analysis results.

[0556] In a form for carrying out the invention, this system is formed by the server, terminal, and user each fulfilling their respective roles. First, the server retrieves data from multiple sources. This process utilizes common APIs and web scraping techniques. Using these methods, the server stores sales information, weather information, competitor information, and consumer posts from social networks into a database.

[0557] Next, the server performs data cleansing. It detects and removes outliers and imputes missing values ​​using appropriate statistical methods. At this stage, the collected data is converted into a standardized format and becomes ready for analysis.

[0558] The server then uses a sentiment analysis engine to extract sentiment information from social media text. Specifically, it leverages natural language processing techniques to identify the positive, negative, and neutral sentiments expressed by consumers. This result becomes a crucial variable input into a demand forecasting model.

[0559] The generative AI model predicts future demand using advanced algorithms, including time series analysis and multivariate analysis. This may involve the use of data analysis platforms such as Python and R. The resulting predictions are visualized in a dashboard format and displayed on the user's device. This visualized information allows users to make concrete decisions regarding inventory management and manufacturing planning.

[0560] For example, suppose the server analyzes data and predicts rain for the following week, while simultaneously detecting positive social media sentiment regarding products popular on rainy days. In this case, the system anticipates increased demand and recommends replenishing inventory to the user. Based on this, the user can quickly adjust their promotional strategy. Another example of a prompt given to the generating AI model is a specific instruction such as, "Please forecast demand based on weather and consumer sentiment that will affect next week's sale day." In this way, the system supports accurate, data-driven business decisions.

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] The server retrieves data from multiple sources, specifically sales information, weather information, competitor information, and consumer posts from social networks. This involves using API calls and scraping techniques to collect data according to a regular schedule. Input consists of raw data from each source, while output is information storage in a unified data format.

[0564] Step 2:

[0565] The server performs a cleansing process on the collected data. Specifically, it removes outliers from the data using an anomaly detection algorithm and imputes missing values ​​using appropriate statistical methods. The input is the acquired raw data, and the output is a cleaned, analyzable dataset. This data is converted to a standard format and passed on to the next step.

[0566] Step 3:

[0567] The server analyzes social media posts using a sentiment analysis engine. Specifically, it uses natural language processing techniques to identify positive, negative, and neutral sentiments contained in the text data. The input is cleaned social network data, and the output is a dataset containing sentiment scores and trends. This result provides important input information for demand forecasting.

[0568] Step 4:

[0569] The server inputs cleaned data and sentiment analysis results into a generative AI model to perform demand forecasting. The generative AI model uses time series analysis and multivariate analysis to execute an algorithm that predicts future demand. The input is an integrated dataset, and the output is the demand forecast result. This result provides foundational information to guide decision-making necessary for business operations.

[0570] Step 5:

[0571] The server visualizes the demand forecast results and displays them on the terminal in a dashboard format. This uses graphs and charts, designed to allow users to intuitively understand the information. The input is demand forecast data, and the output is visualized information. Based on this information, users can take specific actions to optimize inventory management and production planning.

[0572] Step 6:

[0573] The server generates and presents recommendations regarding inventory management and manufacturing plans based on the analysis results. Specifically, it suggests inventory replenishment in response to predicted demand increases and promotional activities based on specific sentiment trends. The input consists of demand forecast data and consumer sentiment analysis results, while the output is specific recommendations. By implementing these recommendations, users can make more effective business decisions.

[0574] (Application Example 2)

[0575] 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."

[0576] In today's market, there is a need for highly accurate demand forecasting that can respond to consumer emotions and sudden changes in trends. However, conventional demand forecasting systems cannot fully utilize emotional information, making it difficult to respond flexibly and quickly in inventory management and production planning. To solve this problem, it is necessary to build a new system that incorporates consumer emotions into demand forecasting.

[0577] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0578] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, means for analyzing the information using a generative model and forecasting demand, means for identifying consumer sentiment using a sentiment analysis engine, means for visualizing and displaying the analysis results, and means for generating recommendations regarding inventory management and production planning. This enables dynamic and highly accurate demand forecasting that takes consumer sentiment into account, as well as the optimization of responsive inventory management and production planning.

[0579] "Information sources" refer to the starting point for acquiring data, such as sales data, weather information, competitor information, and consumer social media posts.

[0580] "Cleaning" is the process of removing outliers from acquired information, filling in missing parts, and preparing it in a format suitable for analysis.

[0581] A "generative model" is an algorithm used to analyze data and make predictions using time series analysis and multivariate analysis.

[0582] A "sentiment analysis engine" is a technology that reads emotions from text data such as consumers' social media posts and quantifies those emotions.

[0583] "Demand forecasting" is the process of predicting future fluctuations in demand and estimating future demand for a product.

[0584] "Inventory management" is the process of maintaining inventory levels with maximum efficiency and replenishing or adjusting stocks as needed.

[0585] "Production planning" is a management task that optimizes production volume and schedule in accordance with future demand forecasts.

[0586] "Recommendation" is the process of suggesting the optimal course of action, such as replenishing inventory or implementing promotional activities, based on analyzed data.

[0587] The system implementing this invention is primarily composed of a program running on a server. The server first collects data from multiple information sources, such as sales information, weather information, competitor information, and consumer social media posts. Various APIs and scraping techniques are used to access the information sources. After data collection, a data cleansing process is performed to remove outliers, fill in missing parts, and format the data into a unified format. This makes the data suitable for analysis.

[0588] Next, the server uses a generative model to analyze the cleaned data and generate demand forecasts. During this process, the server utilizes a sentiment analysis engine to analyze the text of consumers' social media posts, identifying and quantifying positive or negative emotions. This incorporates sentiment data into the demand forecast, improving its accuracy and making it more realistic.

[0589] The analysis results are displayed on the administrator's terminal via a visualization tool. Graphs and charts are used for visualization, presenting the results in a format easily understandable to the user. Furthermore, the server generates and presents optimal recommendations for inventory management and production planning based on the analysis results. For example, if an increase in demand for a specific product based on consumer sentiment is predicted, this information is immediately communicated to the administrator, prompting rapid inventory replenishment and adjustments to promotional strategies.

[0590] For example, if the weather forecast predicts rain during the rainy season and positive sentiment towards a specific product increases on social media, the system will generate a demand forecast stating that "the product is likely to sell well" and recommend replenishing the product's inventory. An example of a prompt message would be: "The weather forecast for next week is rain, and positive sentiment towards a specific product is increasing on social media. Please provide a demand forecast and inventory replenishment advice based on these conditions."

[0591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0592] Step 1:

[0593] The server uses APIs and scraping techniques to collect data from sources such as sales information, weather information, competitor information, and consumer social media posts. Input requires authentication credentials to access each source, and output generates raw data in various formats. This prepares the server to obtain data on a variety of factors influencing consumer demand.

[0594] Step 2:

[0595] The server performs a data cleaning process to remove outliers and fill in missing data from the raw data. The input is the collected raw data, and the output is cleaned data formatted into a unified format. This creates a clean dataset suitable for analysis.

[0596] Step 3:

[0597] The server uses a generated AI model to analyze cleaned data and generate demand forecasts. Time-series data and multiple variable data are provided as input, and the output is numerical data representing the predicted demand. In particular, a sentiment analysis engine is used to identify the sentiment of consumer posts, and this information is incorporated into the demand forecast.

[0598] Step 4:

[0599] The server visualizes the analysis results based on the generated demand forecast and displays them as graphs and charts on the administrator's terminal. Forecast data is provided as input, and the output is a visually easy-to-understand visualization graphic. The administrator uses this to check inventory and production plans.

[0600] Step 5:

[0601] The server utilizes the analysis results to generate and present specific recommendations for inventory management and production planning to the user. Inputs include visualized forecast data and the user's current inventory status, while output provides recommendations indicating the optimal course of action. Based on these recommendations, the user considers product replenishment and promotional plans.

[0602] Step 6:

[0603] Users follow the provided recommendations to appropriately adjust inventory replenishment and promotional activities. Inputs include recommendations provided by the server and current market conditions, while output is strategic decision-making. This enables dynamic inventory and production management based on consumer sentiment.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] 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.

[0610] 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).

[0611] 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.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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".

[0621] The system according to the present invention enables more accurate demand forecasting by applying other technologies and integrating and analyzing diverse data sources. The system consists of a server, a terminal, and a user interface.

[0622] Data collection and integration

[0623] The server retrieves data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts. It collects the necessary information via APIs or web scraping and stores it in a database. For example, sales data is obtained from a business management system, and weather data from a weather service.

[0624] Data preprocessing

[0625] The server cleans the collected data and formats it into a unified format, making it parseable across different data types. It handles missing and outlier values, generating a consistent dataset overall.

[0626] Analysis and demand forecasting

[0627] The server inputs pre-processed data into a generative model and performs demand forecasting based on time series analysis and multivariate analysis. The AI ​​analyzes past data patterns and predicts future demand. The results are output to a visual dashboard.

[0628] Visualization and Recommendation

[0629] The server displays the analysis results in easy-to-understand graphs and charts, presenting them to the user via a terminal. Furthermore, the system provides specific recommendations regarding inventory management and production planning, supporting the user's decision-making.

[0630] Specific example

[0631] For example, the server predicts the peak demand for a particular product next month based on past sales data. This analysis also takes into account that past weather data is associated with increased sales on weekends. As a result of the analysis, the server recommends increasing inventory during that period and notifies the user via a terminal. The user then uses this information to adjust the supply chain and optimize inventory.

[0632] In this way, the system can use diverse data to forecast demand and support accurate inventory management and production planning.

[0633] The following describes the processing flow.

[0634] Step 1:

[0635] The server collects sales data, weather data, competitor information, and consumer social media posts from data sources. Sales data is obtained through the business management system's API, and weather data is obtained from a weather API. Competitor information is scraped from web news, and social media posts are collected using SNS APIs.

[0636] Step 2:

[0637] The server cleans the collected data. It detects, corrects, or removes incomplete data and outliers to ensure data consistency. This prepares a dataset that is free from problems for subsequent analysis.

[0638] Step 3:

[0639] The server converts the cleaned data into a unified format. It standardizes different data formats and date formats, and formats the data into a parseable form.

[0640] Step 4:

[0641] The server feeds the formatted data into a generative model for analysis. The AI ​​model utilizes time series analysis and multivariate analysis to forecast demand in real time or at regular intervals.

[0642] Step 5:

[0643] The server generates graphs and charts based on the analysis results for display on the visualization dashboard. This allows users to intuitively understand the data.

[0644] Step 6:

[0645] The server generates recommendations for inventory management and production planning based on demand forecasts. It suggests specific inventory replenishment and adjustments to production schedules.

[0646] Step 7:

[0647] The terminal displays a dashboard, presenting analysis results and recommendations to the user. The user then makes business decisions based on the displayed information.

[0648] (Example 1)

[0649] 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".

[0650] In today's business environment, there is a demand for improved accuracy in demand forecasting, but it is difficult to make accurate forecasts in near real-time while utilizing diverse data sources. Furthermore, there is a lack of systems that present analysis results in an easy-to-understand manner and provide concrete guidance for inventory management and production planning. As a result, there is insufficient support for making appropriate decisions.

[0651] 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.

[0652] In this invention, the server includes means for acquiring information from various sources and storing it in a database, means for organizing the information and converting it into a standard format, and means for analyzing the data using artificial intelligence and performing demand forecasting. This makes it possible to centrally manage data obtained from various sources and to perform highly accurate demand forecasting using that data. Furthermore, by visualizing the analysis results and providing them to users in an easy-to-understand manner, it is possible to support quick and accurate decision-making.

[0653] "Diverse information sources" refers to a collection of data sources that include information from various categories, such as sales data, weather information, competitor information, and online consumer posts.

[0654] "Means of acquiring information and storing it in a database" refers to the process of collecting external data using APIs or web scraping techniques, organizing it, and saving it to a storage system.

[0655] "Means of organizing information and converting it to a standard format" refers to the process of cleaning and formatting acquired data to remove outliers and standardize data formats.

[0656] "Means of using artificial intelligence to analyze the aforementioned data and perform demand forecasting" refers to a process of analyzing data using machine learning and deep learning technologies to predict future demand.

[0657] "Means of visualization and output to users" refers to tools and technologies that display analyzed data results in graphics or charts, providing them in a way that is easy for users to understand.

[0658] "Means for generating recommended information regarding resource management and production planning" refers to a process that proposes appropriate inventory and production volumes to users based on demand forecast results, thereby promoting efficient resource utilization.

[0659] The system according to the present invention is an advanced technological platform for data collection, preprocessing, analysis, visualization, and generation of recommendation information. This system consists of a server, terminals, and a user interface.

[0660] The server retrieves information from various sources and stores it in a database. The hardware used is a server with high-performance network connectivity that provides the necessary processing power. Software-wise, APIs and web scraping techniques are used for data collection. For example, sales information is obtained from a business management system, and weather information is obtained from weather services via APIs.

[0661] The collected information is processed by the server and converted to a standard format. Common data handling tools are used for data preparation. For example, libraries such as Pandas and NumPy are utilized to handle missing values ​​and standardize the data.

[0662] Data analysis using artificial intelligence is a crucial element for demand forecasting. The server executes generative AI models and performs data analysis. Models such as Prophet and LSTM are used for time series analysis and multidimensional analysis. Through this analysis, future demand patterns are predicted.

[0663] The analysis results are visualized by the server and output to the user via the terminal. Tools such as Tableau and Power BI are used for visualization. This allows users to intuitively understand the analysis results and make decisions based on that information.

[0664] Furthermore, the system generates recommended resource management and production planning information based on the analysis results, supporting users' strategic decision-making. Users access the system using their terminals and utilize the information provided on the dashboard. This enables optimization of inventory management and production planning.

[0665] In this way, the server efficiently handles all data processing, while users can use the provided information to improve their work processes.

[0666] Example prompt: "Based on past sales data and weather data, predict next month's demand."

[0667] This invention significantly improves the operational efficiency of users by centrally managing data from diverse information sources and using it to perform highly accurate demand forecasting.

[0668] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0669] Step 1:

[0670] The server collects data from diverse sources. It accepts sales information, weather information, competitor information, and online consumer posts as input. This data is retrieved using APIs and web scraping techniques and stored in a database. For example, sales information is retrieved via data requests from the business management system and stored on the server.

[0671] Step 2:

[0672] The server processes the collected data and converts it to a standard format. The input to this process is the raw, unprocessed data collected in step 1. Data cleansing tools are used to impute missing values ​​and remove outliers. The output is processed data that can be analyzed. Specifically, the server uses the Pandas library to unify and standardize the data format.

[0673] Step 3:

[0674] The server takes pre-processed data as input and performs analysis using a generated AI model. Specifically, it performs time-series analysis and multidimensional analysis to forecast demand. The output is forecast result data. At this time, the server loads a Prophet model and executes the model's calculations to predict future supply and demand relationships.

[0675] Step 4:

[0676] The server visualizes the analyzed prediction results and outputs them to the user via the terminal. The input is the prediction results obtained in step 3. The server uses Tableau or Power BI to visualize the results in graph and chart format. The visualized data is provided to the user on the terminal and displayed in an easy-to-understand format.

[0677] Step 5:

[0678] Users review recommendations presented through their devices and make decisions regarding resource management and production planning. Analysis results and recommendations are provided as input. Based on this data, users optimize inventory and adjust production schedules. Specifically, users utilize the information displayed on the dashboard to determine concrete actions to adjust their business strategies.

[0679] Through this entire process, the system supports supply and demand forecasting based on diverse data and improves operational efficiency.

[0680] (Application Example 1)

[0681] 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".

[0682] Improving the accuracy of demand forecasting and optimizing inventory management remain major challenges in modern logistics centers. In particular, there is a growing need to integrate data from multiple sources to make timely decisions regarding inventory replenishment and production planning. However, due to the diversity of data and the complexity of analytical methods, effective approaches are currently lacking.

[0683] 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.

[0684] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, and means for analyzing the information using a generative model and making demand forecasts. This makes it possible to provide more accurate demand forecasts and appropriate recommendations in inventory management and production planning at logistics centers.

[0685] "Information sources" refer to sources and media that provide diverse data, specifically including sales data, weather information, competitor information, and consumer social media posts.

[0686] "Information cleaning" is the process of removing noise and missing values ​​from collected raw data and processing it into a state suitable for analysis.

[0687] A "unified format" is a data format that standardizes data from different formats and specifications, and formats it into a consistent form.

[0688] A "generative model" is an artificial intelligence algorithm or mathematical model used to learn past data patterns and perform future demand forecasting and analysis.

[0689] "Visualization" is the act of visually representing data using graphs and charts in order to display analysis results in an easy-to-understand manner.

[0690] A "user interface" refers to the means of interaction, including screens and input methods, that a user uses to interact with a computer system.

[0691] "Recommendation" refers to advice or suggestions based on analysis results that recommend specific actions or support decision-making.

[0692] The system implementing this invention first involves a server collecting information from multiple sources. Specifically, it obtains sales data, weather information, competitor information, consumer social media posts, etc., using APIs and web scraping techniques. The information is stored in a database, data cleaning is performed using software such as Pandas, and the data is formatted into a unified format.

[0693] Next, the server inputs the formatted information into a generative model and performs demand forecasting using time series analysis and multidimensional analysis techniques. This process utilizes machine learning libraries such as Scikit-learn and TensorFlow. The analysis results are visualized using Matplotlib and Plotly and presented to the user through a user interface.

[0694] Users can view the visualized analysis results through their devices and optimize inventory management and production planning based on them. The system further supports user decision-making by generating appropriate recommendations based on the analysis results.

[0695] For example, if the server predicts increased demand for a particular product next month, it will display a recommendation to increase inventory in preparation for that period. This allows users to adjust their supply chain and optimize their inventory.

[0696] An example of a prompt message is, "Please forecast demand based on next week's weather and past sales data." By inputting this prompt into the AI ​​model, more accurate forecast results can be obtained.

[0697] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0698] Step 1:

[0699] The server collects information from multiple sources. Specifically, it obtains sales data and weather information via APIs, and uses web scraping techniques to collect competitor information and consumer social media posts. The input is raw data obtained from external sources, and the output is an unprocessed dataset.

[0700] Step 2:

[0701] The server cleans the collected data and formats it into a unified format. Pandas is used to handle missing values ​​and outliers, ensuring consistent data structure. The input is a raw dataset, and the output is data formatted for analysis.

[0702] Step 3:

[0703] The server generates formatted data, which is then input into an AI model for time series analysis and multidimensional analysis. Using Scikit-learn and TensorFlow, the model learns past data patterns and predicts future demand. The input is formatted data, and the output is predicted demand data.

[0704] Step 4:

[0705] The server visualizes the analysis results and creates easy-to-understand graphs and charts. It uses Matplotlib and Plotly to visually represent the data and provide it to the user. The input is predicted demand data, and the output is graphs and charts of the visualized data.

[0706] Step 5:

[0707] Users view analysis results via a terminal and receive recommendations for inventory management and production planning based on those results. They make decisions and adjust the supply chain based on the data displayed on the terminal. The input is the visualized data and recommendations displayed on the terminal, and the output is the user's decision.

[0708] 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.

[0709] This invention provides an integrated system for companies to perform more accurate demand forecasting and optimize inventory management and production planning. In addition to conventional data analysis methods, this system incorporates an emotion engine that analyzes consumer sentiment, thereby achieving comprehensive demand forecasting that takes consumer feelings into account.

[0710] Data collection and cleaning

[0711] The server collects data from diverse data sources, including sales data, weather data, competitor information, and consumer social media posts, using standard APIs and scraping techniques. The collected data undergoes a cleaning process to remove outliers, is supplemented as needed, and converted into a unified format.

[0712] emotion recognition

[0713] The server utilizes an emotion engine to analyze consumer social media posts. It recognizes the emotions contained in the posts and identifies consumer likes and dissatisfactions. For example, if a particular product's reputation is rising on social media, this information can be used for demand forecasting to predict how much positive emotion will impact sales.

[0714] Demand forecasting and analysis

[0715] The server inputs the cleaned data and sentiment analysis results into a generative model to perform demand forecasting through time series analysis and multivariate analysis. By taking into account the impact of sentiment fluctuations, more realistic results can be obtained. These analysis results are updated in real time.

[0716] Visualization and Recommendation

[0717] The analysis results are displayed on a dashboard by the server. Information is conveyed visually using graphs and charts, making it easy for users to understand. Furthermore, the server uses this data to provide each user with the most relevant recommendations. For example, it might suggest inventory replenishment or promotional activities to address specific sentiment trends.

[0718] Specific example

[0719] The server analyzes weather data and consumer social media posts, and if it detects positive social media sentiment for popular products on rainy days, in conjunction with a forecast of rain on the next week's sale day, it predicts increased demand for those products. Recommendations for restocking are immediately displayed on the device, allowing users to adjust appropriate orders and promotional strategies.

[0720] Thus, the system of the present invention utilizes an emotion engine to incorporate consumer emotions into demand forecasting and provides a highly effective recommendation function, thereby supporting corporate management decisions.

[0721] The following describes the processing flow.

[0722] Step 1:

[0723] The server collects data from sales data, weather data, competitor information, and consumer social media posts. APIs and scraping techniques are used for each data source, and the data is updated regularly as needed.

[0724] Step 2:

[0725] The server cleans the data it has collected. It improves data reliability by detecting incomplete data and anomalous data points and correcting or removing them.

[0726] Step 3:

[0727] The server converts the cleaned data into a unified format. This step unifies different data formats and date formats, making the data parseable.

[0728] Step 4:

[0729] The server uses an emotion engine to analyze social media posts and recognize consumer emotions. Text analysis is used to classify and quantify emotions as positive, negative, neutral, etc.

[0730] Step 5:

[0731] The server inputs cleaned data, including sentiment data, into the generative model. The model, which combines time series analysis and multivariate analysis, performs demand forecasting and generates results.

[0732] Step 6:

[0733] The server visualizes the demand forecast results and displays them on the terminal as a dashboard. Graphs and charts are used to visually represent the analysis results and an overview of the supply and demand forecast.

[0734] Step 7:

[0735] The server generates recommendations for inventory management and production planning based on prediction results. It creates recommendations that take sentiment data into account and suggests specific actions to the user regarding particular products or promotional initiatives.

[0736] Step 8:

[0737] The terminal displays a dashboard and recommendations from the server to the user. The user makes business decisions based on the displayed information and adjusts inventory and production plans as needed.

[0738] (Example 2)

[0739] 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".

[0740] Traditional demand forecasting systems struggle to accurately predict the demand for goods and services, and they fail to take into account changes in consumer sentiment. As a result, incorrect decisions can be made in inventory management and production planning, leading to problems such as excess inventory, stockouts, and lost sales opportunities.

[0741] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0742] In this invention, the server includes means for acquiring information from multiple information sources, means for detecting and removing anomalies in the information, imputing missing values, and converting it into a unified format, and means for analyzing consumer sentiment using natural language processing and integrating the results of the sentiment analysis with the information. This enables more accurate demand forecasting that takes consumer sentiment into account.

[0743] "Information sources" refer to external data sources that the system uses to collect data, such as sales data, weather information, competitor information, and consumer social network posts.

[0744] An "outlier" refers to a value within a dataset that lacks regularity and falls outside the normal range, potentially impairing the accuracy of data analysis.

[0745] "Missing values" refer to parts of a dataset where data that should be present is missing, and these need to be imputed to improve the accuracy of statistical processing.

[0746] "Sentiment analysis" is the process of identifying positive, negative, or neutral emotions from text expressed by consumers using natural language processing technology.

[0747] A "generative AI model" is a predictive model that utilizes artificial intelligence technology to analyze and simulate collected data.

[0748] Time series analysis is a statistical method that analyzes changes in data over time and uses past trends to predict the future.

[0749] "Multivariable analysis" is a statistical method that simultaneously analyzes the relationships between multiple variables and evaluates their impact on the problem being addressed.

[0750] "Recommendation" refers to supporting decision-making by providing specific action suggestions and improvement measures to users based on analysis results.

[0751] In a form for carrying out the invention, this system is formed by the server, terminal, and user each fulfilling their respective roles. First, the server retrieves data from multiple sources. This process utilizes common APIs and web scraping techniques. Using these methods, the server stores sales information, weather information, competitor information, and consumer posts from social networks into a database.

[0752] Next, the server performs data cleansing. It detects and removes outliers and imputes missing values ​​using appropriate statistical methods. At this stage, the collected data is converted into a standardized format and becomes ready for analysis.

[0753] The server then uses a sentiment analysis engine to extract sentiment information from social media text. Specifically, it leverages natural language processing techniques to identify the positive, negative, and neutral sentiments expressed by consumers. This result becomes a crucial variable input into a demand forecasting model.

[0754] The generative AI model predicts future demand using advanced algorithms, including time series analysis and multivariate analysis. This may involve the use of data analysis platforms such as Python and R. The resulting predictions are visualized in a dashboard format and displayed on the user's device. This visualized information allows users to make concrete decisions regarding inventory management and manufacturing planning.

[0755] For example, suppose the server analyzes data and predicts rain for the following week, while simultaneously detecting positive social media sentiment regarding products popular on rainy days. In this case, the system anticipates increased demand and recommends replenishing inventory to the user. Based on this, the user can quickly adjust their promotional strategy. Another example of a prompt given to the generating AI model is a specific instruction such as, "Please forecast demand based on weather and consumer sentiment that will affect next week's sale day." In this way, the system supports accurate, data-driven business decisions.

[0756] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0757] Step 1:

[0758] The server retrieves data from multiple sources, specifically sales information, weather information, competitor information, and consumer posts from social networks. This involves using API calls and scraping techniques to collect data according to a regular schedule. Input consists of raw data from each source, while output is information storage in a unified data format.

[0759] Step 2:

[0760] The server performs a cleansing process on the collected data. Specifically, it removes outliers from the data using an anomaly detection algorithm and imputes missing values ​​using appropriate statistical methods. The input is the acquired raw data, and the output is a cleaned, analyzable dataset. This data is converted to a standard format and passed on to the next step.

[0761] Step 3:

[0762] The server analyzes social media posts using a sentiment analysis engine. Specifically, it uses natural language processing techniques to identify positive, negative, and neutral sentiments contained in the text data. The input is cleaned social network data, and the output is a dataset containing sentiment scores and trends. This result provides important input information for demand forecasting.

[0763] Step 4:

[0764] The server inputs cleaned data and sentiment analysis results into a generative AI model to perform demand forecasting. The generative AI model uses time series analysis and multivariate analysis to execute an algorithm that predicts future demand. The input is an integrated dataset, and the output is the demand forecast result. This result provides foundational information to guide decision-making necessary for business operations.

[0765] Step 5:

[0766] The server visualizes the demand forecast results and displays them on the terminal in a dashboard format. This uses graphs and charts, designed to allow users to intuitively understand the information. The input is demand forecast data, and the output is visualized information. Based on this information, users can take specific actions to optimize inventory management and production planning.

[0767] Step 6:

[0768] The server generates and presents recommendations regarding inventory management and manufacturing plans based on the analysis results. Specifically, it suggests inventory replenishment in response to predicted demand increases and promotional activities based on specific sentiment trends. The input consists of demand forecast data and consumer sentiment analysis results, while the output is specific recommendations. By implementing these recommendations, users can make more effective business decisions.

[0769] (Application Example 2)

[0770] 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".

[0771] In today's market, there is a need for highly accurate demand forecasting that can respond to consumer emotions and sudden changes in trends. However, conventional demand forecasting systems cannot fully utilize emotional information, making it difficult to respond flexibly and quickly in inventory management and production planning. To solve this problem, it is necessary to build a new system that incorporates consumer emotions into demand forecasting.

[0772] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0773] In this invention, the server includes means for collecting information from multiple information sources, means for cleaning the information and formatting it into a unified format, means for analyzing the information using a generative model and forecasting demand, means for identifying consumer sentiment using a sentiment analysis engine, means for visualizing and displaying the analysis results, and means for generating recommendations regarding inventory management and production planning. This enables dynamic and highly accurate demand forecasting that takes consumer sentiment into account, as well as the optimization of responsive inventory management and production planning.

[0774] "Information sources" refer to the starting point for acquiring data, such as sales data, weather information, competitor information, and consumer social media posts.

[0775] "Cleaning" is the process of removing outliers from acquired information, filling in missing parts, and preparing it in a format suitable for analysis.

[0776] A "generative model" is an algorithm used to analyze data and make predictions using time series analysis and multivariate analysis.

[0777] A "sentiment analysis engine" is a technology that reads emotions from text data such as consumers' social media posts and quantifies those emotions.

[0778] "Demand forecasting" is the process of predicting future fluctuations in demand and estimating future demand for a product.

[0779] "Inventory management" is the process of maintaining inventory levels with maximum efficiency and replenishing or adjusting stocks as needed.

[0780] "Production planning" is a management task that optimizes production volume and schedule in accordance with future demand forecasts.

[0781] "Recommendation" is the process of suggesting the optimal course of action, such as replenishing inventory or implementing promotional activities, based on analyzed data.

[0782] The system implementing this invention is primarily composed of a program running on a server. The server first collects data from multiple information sources, such as sales information, weather information, competitor information, and consumer social media posts. Various APIs and scraping techniques are used to access the information sources. After data collection, a data cleansing process is performed to remove outliers, fill in missing parts, and format the data into a unified format. This makes the data suitable for analysis.

[0783] Next, the server uses a generative model to analyze the cleaned data and generate demand forecasts. During this process, the server utilizes a sentiment analysis engine to analyze the text of consumers' social media posts, identifying and quantifying positive or negative emotions. This incorporates sentiment data into the demand forecast, improving its accuracy and making it more realistic.

[0784] The analysis results are displayed on the administrator's terminal via a visualization tool. Graphs and charts are used for visualization, presenting the results in a format easily understandable to the user. Furthermore, the server generates and presents optimal recommendations for inventory management and production planning based on the analysis results. For example, if an increase in demand for a specific product based on consumer sentiment is predicted, this information is immediately communicated to the administrator, prompting rapid inventory replenishment and adjustments to promotional strategies.

[0785] For example, if the weather forecast predicts rain during the rainy season and positive sentiment towards a specific product increases on social media, the system will generate a demand forecast stating that "the product is likely to sell well" and recommend replenishing the product's inventory. An example of a prompt message would be: "The weather forecast for next week is rain, and positive sentiment towards a specific product is increasing on social media. Please provide a demand forecast and inventory replenishment advice based on these conditions."

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The server uses APIs and scraping techniques to collect data from sources such as sales information, weather information, competitor information, and consumer social media posts. Input requires authentication credentials to access each source, and output generates raw data in various formats. This prepares the server to obtain data on a variety of factors influencing consumer demand.

[0789] Step 2:

[0790] The server performs a data cleaning process to remove outliers and fill in missing data from the raw data. The input is the collected raw data, and the output is cleaned data formatted into a unified format. This creates a clean dataset suitable for analysis.

[0791] Step 3:

[0792] The server uses a generated AI model to analyze cleaned data and generate demand forecasts. Time-series data and multiple variable data are provided as input, and the output is numerical data representing the predicted demand. In particular, a sentiment analysis engine is used to identify the sentiment of consumer posts, and this information is incorporated into the demand forecast.

[0793] Step 4:

[0794] The server visualizes the analysis results based on the generated demand forecast and displays them as graphs and charts on the administrator's terminal. Forecast data is provided as input, and the output is a visually easy-to-understand visualization graphic. The administrator uses this to check inventory and production plans.

[0795] Step 5:

[0796] The server utilizes the analysis results to generate and present specific recommendations for inventory management and production planning to the user. Inputs include visualized forecast data and the user's current inventory status, while output provides recommendations indicating the optimal course of action. Based on these recommendations, the user considers product replenishment and promotional plans.

[0797] Step 6:

[0798] Users follow the provided recommendations to appropriately adjust inventory replenishment and promotional activities. Inputs include recommendations provided by the server and current market conditions, while output is strategic decision-making. This enables dynamic inventory and production management based on consumer sentiment.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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."

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] The following is further disclosed regarding the embodiments described above.

[0821] (Claim 1)

[0822] A means of collecting data from multiple data sources,

[0823] A means for cleaning the aforementioned data and formatting it into a unified format,

[0824] A means for analyzing the aforementioned data using a generative model and forecasting demand,

[0825] A means of visualizing and displaying the analysis results,

[0826] A means for generating recommendations regarding inventory management and production planning,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, wherein the plurality of data sources include sales data, weather data, competitor information, and consumer social media posts.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein the generative model is for performing time series analysis and multivariate analysis.

[0832] "Example 1"

[0833] (Claim 1)

[0834] Means for obtaining information from diverse sources and storing it in a database,

[0835] A means for organizing the aforementioned information and converting it to a standard format,

[0836] A means for performing demand forecasting by analyzing the aforementioned data using artificial intelligence,

[0837] A means of visualizing the analysis results and outputting them to the user,

[0838] A means for generating recommended information regarding resource management and production planning,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, wherein the diverse information sources include sales information, weather information, competitor information, and consumer online postings.

[0842] (Claim 3)

[0843] The system according to claim 1, wherein the artificial intelligence is for performing time-series analysis and multidimensional analysis.

[0844] "Application Example 1"

[0845] (Claim 1)

[0846] Means of gathering information from multiple sources,

[0847] A means for cleaning the aforementioned information and formatting it into a unified format,

[0848] A means for analyzing the aforementioned information using a generative model and forecasting demand,

[0849] A means of visualizing and displaying the analysis results,

[0850] A means for generating recommendations regarding inventory management and production planning,

[0851] A means of providing a user interface that integrates the analysis results,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, wherein the plurality of information sources include sales data, weather information, competitor information, and consumer social media posts.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the generative model is for performing time series analysis and multidimensional analysis.

[0857] "Example 2 of combining an emotion engine"

[0858] (Claim 1)

[0859] Means of obtaining information from multiple sources,

[0860] Means for detecting and removing abnormal values ​​in the aforementioned information, imputing missing values, and converting to a unified format,

[0861] A means for analyzing consumer emotions using natural language processing and integrating the results of the emotion analysis into the aforementioned information,

[0862] Using generative AI models to perform comprehensive analysis and provide a means to predict future demand,

[0863] A means of visually displaying the results of the analysis and providing information in a way that is easy for users to understand,

[0864] A means of generating and presenting proposals for inventory management and manufacturing planning,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, wherein the plurality of information sources include sales information, weather information, competitor information, and posts on consumer social networks.

[0868] (Claim 3)

[0869] The system according to claim 1, wherein the generating AI model is for performing time series analysis and multivariate analysis, and reflects changes in consumer sentiment in demand forecasting.

[0870] "Application example 2 when combining with an emotional engine"

[0871] (Claim 1)

[0872] Means of gathering information from multiple sources,

[0873] A means for cleaning the aforementioned information and formatting it into a unified format,

[0874] A means for analyzing the aforementioned information using a generative model and forecasting demand,

[0875] A means of identifying consumer emotions using an emotion analysis engine,

[0876] A means of visualizing and displaying the analysis results,

[0877] A means for generating recommendations regarding inventory management and production planning,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, wherein the multiple information sources include sales information, weather information, competitor information, and consumer social media posts, and analyze consumer sentiment.

[0881] (Claim 3)

[0882] The system according to claim 1, wherein the generative model performs time series analysis and multivariate analysis and provides results that are updated in real time. [Explanation of symbols]

[0883] 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. A means of collecting data from multiple data sources, A means for cleaning the aforementioned data and formatting it into a unified format, A means for analyzing the aforementioned data using a generative model and forecasting demand, A means of visualizing and displaying the analysis results, A means for generating recommendations regarding inventory management and production planning, A system that includes this.

2. The system according to claim 1, wherein the plurality of data sources include sales data, weather data, competitor information, and consumer social media posts.

3. The system according to claim 1, wherein the generative model is for performing time series analysis and multivariate analysis.

Images