system

Abstract

Provide a system. 【Solution means】 Means for collecting various information and performing preprocessing, Means for extracting features based on this preprocessed information and training a learning model, Means for predicting and evaluating store opening candidate locations using the trained learning model, Means for presenting the evaluation results and providing information to users, Means for improving the model based on opinions from users, Means for allowing users to evaluate multiple store opening candidate locations in real time using a mobile communication terminal, Means for visualizing information in the form of maps and graphs to make it comparable, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the case of a new store opening of a store, site selection is an important factor that greatly affects its success. However, especially when opening a store in a local city, there is a lack of region-specific data, making it difficult to select an appropriate site. Therefore, there is a need to construct a system that can objectively and effectively make a judgment in the selection of a store location.

Means for Solving the Problems

[0005] This invention provides means for collecting and preprocessing diverse data. It also provides means for extracting features from the collected data, training a machine learning model, and using this model to predict and evaluate potential store locations, thereby enabling effective location selection. Furthermore, the evaluation results are presented to the user, and means for improving the model based on user feedback are included, allowing for continuous improvement of accuracy.

[0006] "Diverse data" refers to all data collected from various sources, such as demographics, traffic volume, property information, competitor information, and local lifestyle data.

[0007] "Preprocessing" refers to the process of preparing collected data to make it easier to analyze, including imputing missing values, deleting inaccurate data, and standardizing data formats.

[0008] "Features" refer to individual data points that machine learning models need to understand data and make predictions, and they represent the characteristics of the data that greatly influence prediction accuracy.

[0009] A "machine learning model" refers to an algorithm or mathematical structure that learns from data and makes predictions or classifications for a specific task.

[0010] "Training" refers to the process of adjusting the parameters of a machine learning model using collected data to improve its performance.

[0011] "Conducting an evaluation" refers to the process of using machine learning models to analyze data on potential store locations and determine the commercial suitability and potential of those locations.

[0012] "Simulation" refers to the process of applying hypothetical conditions to virtually verify the feasibility of store locations and strategies, and visualizing predictable results.

[0013] An "interface" refers to a means for users to view and manipulate system results, and includes screens and control panels that support information visualization and simulation execution.

[0014] "Feedback" refers to the provision of information by users that contributes to improving the accuracy of systems and models by providing actual results and user experiences.

[0015] "Including an algorithm" means that a specific calculation or processing procedure is clearly defined, and a program or formula that executes that procedure is incorporated. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention specifically demonstrates the implementation of a system that optimizes new store opening strategies by utilizing diverse data. The system provides optimal store opening candidates by collecting, preprocessing, analyzing, predicting, evaluating, and presenting data.

[0038] First, the server collects a wide variety of data from public databases, APIs, sensor data, and other sources. This data covers regional demographics, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends.

[0039] Next, the collected data is preprocessed on the server, where missing values ​​are imputed, the format is standardized, and inaccurate data is removed. This process transforms the data into a format suitable for analysis.

[0040] Next, the server extracts features from the pre-processed data and trains a machine learning model. This model is designed to predict the optimal location for opening a store and learns key trends from the collected data. Data from past successes and failures are also used in the training to improve prediction accuracy.

[0041] Once potential locations are identified, the server performs an evaluation and presents the candidate sites in the form of scores and rankings. The evaluation results are derived from commercial suitability and competitive landscape, and the potential of each candidate site is shown in detail.

[0042] The evaluation results are sent to the device and visualized in a user-friendly format. Displayed in map and graph formats, detailed location-specific data and differences based on scenarios are clearly shown, allowing users to interactively compare potential locations.

[0043] For example, if a particular area experiences heavy nighttime traffic, that data might be considered favorable for opening a store in a specific industry, and the area could be evaluated as a potential location for businesses that operate at night.

[0044] The system further receives feedback from users and improves its model based on actual store opening results. This process enables the continuous recommendation of highly accurate store opening locations. Users can contribute to the system's evolution by providing feedback on post-opening performance data to the server.

[0045] In this way, the present invention realizes the construction of a system that enables the formulation of effective store opening strategies in various regions.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server collects a wide variety of data, including population data, traffic data, property information, and competitor information, from public databases and APIs. This data forms the basis for the system to determine the optimal store location.

[0049] Step 2:

[0050] The server preprocesses the collected data, including filling in missing data and standardizing data formats. This process also removes outliers and, if necessary, scales specific data.

[0051] Step 3:

[0052] The server extracts features from pre-processed data and trains a machine learning model. This allows it to learn patterns and trends in the data and build a foundation for predicting suitable locations for new stores.

[0053] Step 4:

[0054] The server uses a trained model to predict potential store locations. For each potential location, it evaluates its commercial suitability, taking into account traffic volume, competition, and pedestrian flow predictions.

[0055] Step 5:

[0056] The server scores and ranks the predicted candidate locations and formats the results in a user-friendly format. Evaluation criteria include factors such as potential for opening a store and predicted profit margins.

[0057] Step 6:

[0058] The terminal receives evaluation results sent from the server and visualizes them through the user interface. Information is provided to the user in map and dashboard formats, making it easy to compare potential locations.

[0059] Step 7:

[0060] Users can perform simulations based on the information provided and try out different store opening scenarios. For example, they can virtually observe changes in foot traffic under specific conditions to improve the accuracy of their decision-making.

[0061] Step 8:

[0062] Users provide feedback to the server with performance data after actually opening a store. Based on this information, the server adjusts the algorithm to improve the accuracy of the model and enhance the quality of future store opening predictions.

[0063] (Example 1)

[0064] 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."

[0065] In modern society, selecting the location for a new store is a crucial factor in determining its success, requiring accurate analysis based on a large amount of data. However, systems for efficiently collecting and analyzing vast amounts of data and presenting highly accurate potential store locations are not yet fully developed, resulting in insufficient measures against investment risks and increasing market competition. Against this backdrop, there is a need for methods that enable strategic store openings that take into account regional characteristics and the commercial environment.

[0066] 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.

[0067] In this invention, the server includes means for automatically collecting diverse data and preprocessing it in a standardized format, means for extracting features based on the preprocessed data and training a predictive model, and means for analyzing and evaluating candidate regions using the trained predictive model while considering multiple past cases. This enables users to effectively visualize candidate regions and formulate better store opening strategies.

[0068] "Diverse data" is a general term for information of multiple characteristics collected from different types of sources, including demographics, traffic information, property information, and commercial competition conditions.

[0069] A "standardized format" refers to a data format that converts different forms of data into a unified format to facilitate comparison and analysis.

[0070] "Features" refer to specific aspects or attributes of data used to train machine learning models, and are important factors for improving prediction accuracy.

[0071] A "predictive model" is an algorithm or mathematical framework used to predict potential store locations for new data, based on collected and pre-processed data and features.

[0072] "Visual presentation" refers to representing data and information in a visual format, such as maps and graphs, so that users can intuitively understand it.

[0073] "Predictive accuracy" is an indicator that shows how accurately a predictive model can predict actual results, and it is an important factor in evaluating the usefulness of a model.

[0074] "Feedback" refers to information that the system uses to improve its statistical model, based on post-opening performance data and evaluations provided by users.

[0075] An "algorithm" is a set of step-by-step procedures or calculation methods for solving a specific problem, and it forms the basis for data analysis and decision-making in a system.

[0076] This invention relates to a system for optimizing the opening strategy of new stores. The system mainly includes servers, terminals, and user interactions.

[0077] The server automatically collects diverse data by utilizing public databases, APIs, sensor networks, and other resources. The hardware used includes data collection servers and cloud services, while the software includes data integration tools and ETL (Extract, Transform, Load) tools. This data includes local demographic information, traffic patterns, commercial activity, and competitive information.

[0078] The collected data is preprocessed on the server. Data cleansing is performed using Python's pandas library and big data processing tools such as Apache Spark. From the preprocessed data, features for machine learning are extracted. The scikit-learn library is used for this process, and the predictive models are trained using TENSORFLOW® or PyTorch.

[0079] The server uses a trained model to perform regional analysis and predict potential store locations. The prediction results are evaluated through a scoring algorithm to select the optimal location.

[0080] The evaluation results are sent to the terminal and visualized in a way that users can intuitively understand. The terminal uses GIS (Geographic Information System) software and data visualization tools to display candidate locations as maps and infographics. This allows users to easily compare and select candidate locations.

[0081] For example, if the collected data indicates that a particular area has high traffic volume, especially at night, the system will identify it as a potential location for businesses suitable for nighttime operations. Based on such predictions, users can then make decisions about opening a store.

[0082] Users contribute to improving the system's model by returning actual performance data and customer feedback after opening a store to the server. This feedback allows the server to continuously update its machine learning model and improve prediction accuracy.

[0083] A concrete example of a prompt message is, "Considering local demographics and nighttime traffic volume, predict the best location for a restaurant," which users can use to query the generative AI model for potential locations.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server collects diverse data from public databases, APIs, and sensor networks. This includes demographic, traffic, and commercial environment data. The input is raw data from these data sources, and the output is the collected, unprocessed dataset. In this step, data collection scripts are run periodically to systematically accumulate up-to-date information.

[0087] Step 2:

[0088] The server preprocesses the collected data. Data cleansing includes imputing missing values, checking for format consistency, and removing inaccurate data. The input is the raw data obtained in step 1, and the output is a clean, preprocessed dataset. Specifically, the Python pandas library is used to unify information from different data sources and format it for analysis.

[0089] Step 3:

[0090] The server extracts features from pre-processed data and trains a machine learning model. Key elements such as pedestrian flow trends and store competition are incorporated into the feature extraction. The input is the clean data obtained in step 2, and the output is the trained generative AI model. Features are generated using the scikit-learn library, and the machine learning model is constructed using TensorFlow.

[0091] Step 4:

[0092] The server uses a trained model to predict and evaluate potential store locations. The input is the AI ​​model obtained in step 3 and additional evaluation data, and the output is a scored list of candidate locations. A proprietary scoring algorithm is applied to evaluate the model, quantifying the commercial potential of each candidate location.

[0093] Step 5:

[0094] The server formats the evaluation results for visualization and sends them to the terminal. The input is the candidate site list obtained in step 4, and the output is the visualized evaluation data. Prepare to plot the results on a map using a data visualization library.

[0095] Step 6:

[0096] The terminal displays the received evaluation results to the user. The input is the visualization data sent in step 5, and the output is an interface that the user can view. Using GIS software, points are displayed on a map, and the data is provided in an interactive format.

[0097] Step 7:

[0098] Users provide feedback to the server with actual store opening results data. The input is the performance after opening, and the output is accumulated data that contributes to improving the model. Based on this feedback, the server updates the model and improves the accuracy of recommending potential store locations.

[0099] (Application Example 1)

[0100] 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."

[0101] In existing store opening strategies, even when information on multiple potential locations is gathered, it is difficult to integrate and evaluate it to make appropriate decisions. Furthermore, the lack of systems capable of real-time evaluation makes it difficult to formulate store opening strategies that are suitable for the rapidly changing market environment. Therefore, there is a need for a new system that can practically and efficiently evaluate potential locations and select the optimal location.

[0102] 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.

[0103] In this invention, the server includes means for collecting and preprocessing diverse information; means for extracting features based on this preprocessed information and training a learning model; means for predicting and evaluating potential store locations using the trained learning model; means for enabling users to evaluate multiple potential store locations in real time using a mobile communication terminal; and means for visualizing and comparing information in map and graph formats. This enables users to select the optimal store location based on multifaceted information in real time.

[0104] "Diverse information" refers to various types of data, such as demographic trends, traffic volume, property information, the presence of competing stores, and pedestrian flow trends.

[0105] "Preprocessing" is the process of converting collected information into a format suitable for analysis by imputing missing values, standardizing the format, and removing inaccurate data.

[0106] "Features" are important indicators or properties that are extracted for use in training machine learning models.

[0107] A "learning model" is an algorithm that learns patterns from collected data and uses them to make predictions and evaluations about the future.

[0108] A "trained learning model" is a predictive algorithm that improves its accuracy based on various data, using past successes and failures.

[0109] A "potential location for opening a store" refers to a geographical location that is being assessed for optimal suitability when developing a new business.

[0110] "Real-time" refers to the immediate acquisition, processing, and provision of information and results.

[0111] "Mobile communication terminals" refer to portable electronic devices with communication capabilities, such as smartphones and tablets.

[0112] "Visualization" refers to displaying data and analysis results in a format that is easy for users to understand, such as maps or graphs.

[0113] The system implementing this invention is designed to collect diverse information and use it to evaluate the optimal location for a new store. The server collects diverse information such as population dynamics, traffic volume, property information, the presence of competing stores, and pedestrian flow trends through public databases and APIs, and then performs preprocessing. This preprocessing includes cleaning and standardizing the format of the data using Python.

[0114] Features are extracted from the collected information, and a learning model is trained using Scikit-Learn. This model learns patterns from past successes and failures, and can predict future potential store locations. The trained learning model enables real-time evaluation and is presented on a mobile communication terminal.

[0115] The terminals take the form of smartphones or tablets and visualize evaluation results received from the server in map and graph format. This allows users to visually understand the information and select the optimal store location.

[0116] As a concrete example, a user who wants to open a new cafe uses the app to obtain information on potential locations on their smartphone. Based on the collected information, data such as nighttime traffic volume and the competitive situation in the surrounding area are displayed. Based on this information, the user can make a decision and choose the most suitable location.

[0117] An example of a prompt message is: "To evaluate potential locations for a new cafe, please collect information on surrounding population, traffic volume, and competitors to suggest the optimal location." This system can continuously optimize its store opening strategy by further improving the model based on user feedback.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server collects diverse information through public databases and APIs. Input information includes demographic data, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends. This data is retrieved using the Python Requests library, and its integrity is checked. The output is a collection of raw data.

[0121] Step 2:

[0122] The server preprocesses the collected data. This process involves cleaning the data by imputing missing values, removing inaccurate data, and standardizing the format. Pandas is used at this stage to output the processed, clean data.

[0123] Step 3:

[0124] The server extracts features from preprocessed data and trains a machine learning model. It uses Scikit-Learn to fit patterns to the data and build the model. The input is preprocessed data, and the output is the trained machine learning model.

[0125] Step 4:

[0126] The server uses a trained learning model to predict and evaluate potential store locations from new data. Specifically, it applies newly input data on potential locations to the model and quantifies the suitability of those locations. The output is a dataset containing evaluation scores.

[0127] Step 5:

[0128] The terminal visualizes the evaluation results received from the server in map and graph format. The input is data containing evaluation scores, which is converted into a visual format using Matplotlib or Folium. The output is maps and graphs displayed in the user interface.

[0129] Step 6:

[0130] Users view evaluation results via their devices and select the optimal location for a new store. This interaction prompts them to provide opinions and send feedback to the server, following the prompt: "To evaluate potential locations for a new cafe, please gather information on surrounding population, traffic volume, and competitors to propose the best location." Input is the evaluation results in maps and graphs, while output is the selected optimal location and the feedback provided.

[0131] 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.

[0132] This invention combines an emotion engine with a system for optimizing store opening strategies. This system recognizes user emotions and provides interaction and feedback according to their emotional state, thereby supporting more effective store opening decisions.

[0133] This system first collects a wide variety of data on a server. This data includes demographics, traffic volume, pedestrian flow, property information, and competitor information. The collected data is preprocessed on the server and formatted into an appropriate format.

[0134] Next, the server extracts features based on the pre-processed data and trains a machine learning model. This model is used to predict and evaluate potential locations for new store openings. The evaluation results are scored, and locations with high commercial suitability are selected.

[0135] Furthermore, the system's main feature, the emotion engine, recognizes the user's emotions through the device. Emotion recognition is performed using technology that detects the user's emotional state from facial expressions and voice using a camera and microphone. The detected emotion data is analyzed on a server and becomes basic data for understanding how the user is reacting to information.

[0136] The device uses the results of the emotion engine's analysis to adjust the information presented to the user and the way they interact in real time. For example, if the user shows frustration, it simplifies the information presentation or provides additional supplementary information to support decision-making. This feedback loop constantly optimizes the user experience.

[0137] For example, if a user is not satisfied with the information presented regarding potential store locations, the device will suggest alternative locations based on data from its emotion engine. It can also provide additional information about locations the user has shown interest in.

[0138] Finally, once user feedback is received, the server readjusts the model parameters based on that feedback to improve the system's prediction accuracy. Through this cyclical process, the system continuously evolves, enabling it to provide users with more accurate and personalized store recommendations.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects a wide variety of data from government agencies and private data providers, including demographics, traffic volume, property information, competitive information, and people-to-people data. This data is retrieved through API calls and database queries.

[0142] Step 2:

[0143] The server preprocesses the collected raw data, including imputing missing data, removing outliers, and standardizing data formats. This process includes data cleaning and normalization, preparing the data for analysis.

[0144] Step 3:

[0145] The server extracts features from pre-processed data and trains a machine learning model. This model has the ability to predict potential store locations in a specific region and learns regional trends and patterns.

[0146] Step 4:

[0147] The server uses a trained model to predict potential locations and scores each location. The prediction takes into account factors such as traffic volume, commercial area size, and competitive landscape.

[0148] Step 5:

[0149] The terminal receives evaluation results from the server and visualizes them through a user interface. Commercially promising potential store locations are presented to the user in map and graph format.

[0150] Step 6:

[0151] When users make decisions based on the displayed candidate location information, their emotional state is recognized through facial expressions and voice detected by the emotion engine.

[0152] Step 7:

[0153] The device dynamically adjusts the information it presents and the way it interacts based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will support decision-making by simplifying explanations or providing more detailed data.

[0154] Step 8:

[0155] Users make decisions regarding potential store locations and provide the results and feedback. This feedback is sent to the server as new data.

[0156] Step 9:

[0157] The server uses user feedback to readjust its machine learning models and improve future prediction accuracy. This ensures continuous system improvement.

[0158] (Example 2)

[0159] 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".

[0160] Traditional store opening strategies face the challenge of selecting appropriate locations that fully consider regional characteristics and competitive information. Furthermore, the lack of mechanisms to effectively reflect user sentiment and feedback prevents efficient and effective optimization of store opening strategies.

[0161] 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.

[0162] In this invention, the server includes means for collecting and preprocessing a wide variety of information, means for extracting features based on this preprocessed information and training a machine learning algorithm, and means for acquiring the user's emotional state using emotion recognition technology and adjusting the information provided based on that state. This makes it possible to select the optimal store location considering regional characteristics and competitive information, and further enables the optimization of strategies that reflect user emotions and feedback.

[0163] "Diverse information" refers to a general term for data with various attributes related to store openings, such as demographics, traffic volume, pedestrian flow, property information, and competitor information.

[0164] "Preprocessing" is the process of preparing collected raw data into a format suitable for machine learning models by performing actions such as imputing missing values, removing noise, and normalizing.

[0165] "Feature extraction" is the process of extracting important information from data and generating metrics that models use for learning and prediction.

[0166] A "machine learning algorithm" is a computational method that uses data to learn patterns and perform predictions and classifications.

[0167] "Emotion recognition technology" is a technology that uses cameras and microphones to detect a user's emotional state from their facial expressions and voice.

[0168] An "interface" is a structure that provides a means for a user to interact with a system and input or output information.

[0169] "Algorithm improvement" is the process of adjusting model parameters based on user feedback to improve prediction accuracy and output quality.

[0170] This invention provides a system that predicts optimal store locations in a specific area and optimizes strategies by incorporating user feedback. The system operates through the collaboration of a server, terminals, and users.

[0171] The server is equipped with high-performance computing equipment and network connectivity. The server collects a wide variety of information, including demographic data, traffic data, pedestrian flow analysis data, property information, and competitor store information. To preprocess this data, data shaping, cleaning, and normalization are performed using programming languages ​​such as Python and dedicated libraries.

[0172] The server extracts features from preprocessed data and trains models using machine learning algorithms. It uses open-source software libraries such as Scikit-learn and TensorFlow to build random forests and neural networks. This allows for the prediction and evaluation of potential store locations, taking commercial suitability into account.

[0173] The device provides a user interface and reads the user's emotions from their facial expressions and voice through emotion recognition technology. It acquires emotion data using OpenCV and speech analysis libraries via its camera and microphone. This emotion data is sent to a server and used to adjust the data delivery method according to the user's emotions.

[0174] The system improves the accuracy of its model based on feedback provided by users interacting with the interface and providing comments on the suggested store locations. Users can evaluate potential locations through a simple and intuitive GUI.

[0175] As a concrete example, if a user requests information about potential store locations in a specific area, they might input a prompt to the generating AI model such as: "Please suggest recommended locations for new store openings, taking into account demographics, traffic volume, and the impact of competing stores." Based on this input, the system will present the most suitable candidate locations based on relevant information.

[0176] This makes it possible to select potential store locations that take regional characteristics into account, and to reflect user sentiment and feedback in the strategy in real time.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The server collects a wide variety of information related to regional characteristics. Inputs include demographic data, traffic volume, pedestrian flow, property information, and competitor store information. The server uses Python's pandas library to format this data, performing tasks such as imputing missing values ​​and removing noise. The output is pre-processed data in a format suitable for machine learning models.

[0180] Step 2:

[0181] The server extracts important features based on preprocessed data. The input is the data formatted in step 1. The server uses Scikit-learn to extract features such as population density and traffic patterns from each data point. The output is the feature set used to train the model.

[0182] Step 3:

[0183] The server trains a machine learning model using the extracted features. The input is the set of features extracted in step 2. The server uses TensorFlow to build a neural network and learn the features. The output is the trained model for predicting potential new store locations.

[0184] Step 4:

[0185] The device uses its camera and microphone to recognize the user's emotions. Input consists of the user's facial expressions and voice. The device uses OpenCV and a voice analysis library to infer emotions and sends this data to the server in real time. The output is the user's emotion data.

[0186] Step 5:

[0187] The server analyzes the user's emotional data and adjusts the information provided. The input is the emotional data sent from the terminal in step 4. Based on the user's emotions, the server modifies the information delivery method, for example, by simplifying the presentation to support decision-making. The output is the adjusted information presentation.

[0188] Step 6:

[0189] Users evaluate information and provide feedback through their devices. Input includes evaluations of candidate location information. User feedback is formatted and sent to the server. Output is feedback data for model improvement.

[0190] Step 7:

[0191] The server improves the model's accuracy based on user feedback data. The input consists of the feedback data obtained in step 6 and the trained model. The server retrains the model and adjusts its parameters. The output is the improved predictive model. This process enables the model to provide more accurate and personalized suggestions.

[0192] (Application Example 2)

[0193] 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".

[0194] When selecting potential store locations, it is necessary to consider various factors such as demographics and traffic volume. However, traditional methods fail to adequately consider customer emotions and intuitive reactions, making it difficult to formulate efficient store opening strategies. Furthermore, the sheer volume and complexity of information can cause stress for customers, preventing them from making optimal decisions.

[0195] 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.

[0196] In this invention, the server includes a device for acquiring and pre-processing a wide variety of information, a device for extracting characteristics based on this pre-processed information and training a machine learning model, and a device for recognizing the user's emotional state and adjusting the information presentation method based on feedback. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0197] "Information" refers to a variety of data necessary for the operation and evaluation of the system, such as demographics, traffic volume, and regional characteristics.

[0198] "Preprocessing" refers to data processing that formats acquired information into a state that can be analyzed and converts it into a format suitable for subsequent processing.

[0199] "Characteristics" refer to the features and indicators of data extracted as criteria for evaluating potential store locations.

[0200] A "machine learning model" is a program structure that uses a large amount of data to train algorithms and make specific patterns or predictions.

[0201] A "potential store location area" refers to a region or location that is being considered for opening a new store.

[0202] "Evaluation" is the process of determining the commercial suitability and potential success of a potential store location.

[0203] "Display" refers to the act of a system presenting evaluation results or information to a user.

[0204] A "user" is an individual or organization that operates the system and uses information to formulate store opening strategies.

[0205] "Emotional state" refers to some of the psychological reactions, such as joy, anger, and surprise, that users exhibit in response to the system.

[0206] "Feedback" refers to information based on opinions and reactions from users to the system, which is useful for improving and adjusting the system.

[0207] The system implementing this invention consists of a server that acquires and processes information, and a terminal that recognizes the user's emotional state and adjusts the way information is presented. The server collects diverse information such as demographics, traffic volume, and regional characteristics, and performs preprocessing. It extracts characteristics from the preprocessed data and creates a foundation for training a machine learning model. In this process, it is desirable to use machine learning frameworks such as TensorFlow or PyTorch.

[0208] A trained machine learning model predicts and evaluates potential store locations and outputs the results. The device uses its camera and microphone to recognize the user's emotional state in real time. Libraries such as DeepFace are used for emotion recognition, analyzing emotions from the user's facial expressions and voice.

[0209] The device optimizes the information presented to the user based on recognized emotional data. For example, if the user indicates stress, it provides support by simplifying the information or suggesting alternatives. This process enables flexible information delivery to the user by adjusting interactions according to emotions.

[0210] User feedback is sent to the server, helping to readjust the parameters of the machine learning model. This cyclical feedback loop allows the system to continuously learn and improve its accuracy.

[0211] As a concrete example, consider a scenario where a user considering opening a new store checks information about a specific region on their device. If the user shows interest, the device displays further details on the screen. Conversely, if the user looks confused, the device provides a more concise overview instead.

[0212] An example of a prompt is: "Please explain in detail how to optimize information on potential store locations using emotion recognition. This includes examples of interaction using user facial expression data and candidate locations that consider regional characteristics." Based on this example, the generative AI model will learn specific methods to support optimization that combines emotion analysis and store location strategies.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The server retrieves diverse information such as demographics, traffic volume, and regional characteristics from the web and databases. Its input is raw data obtained from external sources, which is then retrieved in various formats and formatted into a unified format. The output is an analyzable dataset.

[0216] Step 2:

[0217] The server extracts characteristics from preprocessed data and trains a machine learning model. The input is a preprocessed dataset from which geographical characteristics and commercial indicator features are extracted. Using these extracted characteristics, software such as TensorFlow and PyTorch is employed to build and train a machine learning model. The output is the trained model used for prediction.

[0218] Step 3:

[0219] The server uses a trained machine learning model to predict and evaluate potential store locations. The input consists of various data points about a specific region, which are then fed into the model to calculate a commercial suitability score. The output is an evaluation result showing the commercial suitability of each area.

[0220] Step 4:

[0221] The device uses its camera and microphone to recognize the user's emotional state in real time. Inputs include the user's facial expressions and voice, which are then analyzed using the DeepFace library. The output is the user's emotional state (e.g., happiness, anger, surprise, etc.).

[0222] Step 5:

[0223] The device optimizes how information is presented based on the sentiment analysis results. Inputs include the sentiment analysis results and evaluation results from the server, and the device adjusts the information presented to the user based on these. For example, if the user is confused, the information is simplified. The output is the adjusted information display.

[0224] Step 6:

[0225] Users provide feedback on the information provided. The input is the user's reaction to the evaluated potential store locations, which is sent to the system as feedback. The output is feedback data used to improve the system.

[0226] Step 7:

[0227] The server updates the parameters of the machine learning model based on user feedback. By receiving feedback data as input and using it to fine-tune the model, prediction accuracy improves. The output is the updated model.

[0228] 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.

[0229] Data generation model 58 is a type of 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.

[0230] 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.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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).

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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".

[0244] This invention specifically demonstrates the implementation of a system that optimizes new store opening strategies by utilizing diverse data. The system provides optimal store opening candidates by collecting, preprocessing, analyzing, predicting, evaluating, and presenting data.

[0245] First, the server collects a wide variety of data from public databases, APIs, sensor data, and other sources. This data covers regional demographics, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends.

[0246] Next, the collected data is preprocessed on the server, where missing values ​​are imputed, the format is standardized, and inaccurate data is removed. This process transforms the data into a format suitable for analysis.

[0247] Next, the server extracts features from the pre-processed data and trains a machine learning model. This model is designed to predict the optimal location for opening a store and learns key trends from the collected data. Data from past successes and failures are also used in the training to improve prediction accuracy.

[0248] Once potential locations are identified, the server performs an evaluation and presents the candidate sites in the form of scores and rankings. The evaluation results are derived from commercial suitability and competitive landscape, and the potential of each candidate site is shown in detail.

[0249] The evaluation results are sent to the device and visualized in a user-friendly format. Displayed in map and graph formats, detailed location-specific data and differences based on scenarios are clearly shown, allowing users to interactively compare potential locations.

[0250] For example, if a particular area experiences heavy nighttime traffic, that data might be considered favorable for opening a store in a specific industry, and the area could be evaluated as a potential location for businesses that operate at night.

[0251] The system further receives feedback from users and improves its model based on actual store opening results. This process enables the continuous recommendation of highly accurate store opening locations. Users can contribute to the system's evolution by providing feedback on post-opening performance data to the server.

[0252] In this way, the present invention realizes the construction of a system that enables the formulation of effective store opening strategies in various regions.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The server collects a wide variety of data, including population data, traffic data, property information, and competitor information, from public databases and APIs. This data forms the basis for the system to determine the optimal store location.

[0256] Step 2:

[0257] The server preprocesses the collected data, including filling in missing data and standardizing data formats. This process also removes outliers and, if necessary, scales specific data.

[0258] Step 3:

[0259] The server extracts features from pre-processed data and trains a machine learning model. This allows it to learn patterns and trends in the data and build a foundation for predicting suitable locations for new stores.

[0260] Step 4:

[0261] The server uses a trained model to predict potential store locations. For each potential location, it evaluates its commercial suitability, taking into account traffic volume, competition, and pedestrian flow predictions.

[0262] Step 5:

[0263] The server scores and ranks the predicted candidate locations and formats the results in a user-friendly format. Evaluation criteria include factors such as potential for opening a store and predicted profit margins.

[0264] Step 6:

[0265] The terminal receives evaluation results sent from the server and visualizes them through the user interface. Information is provided to the user in map and dashboard formats, making it easy to compare potential locations.

[0266] Step 7:

[0267] Users can perform simulations based on the information provided and try out different store opening scenarios. For example, they can virtually observe changes in foot traffic under specific conditions to improve the accuracy of their decision-making.

[0268] Step 8:

[0269] Users provide feedback to the server with performance data after actually opening a store. Based on this information, the server adjusts the algorithm to improve the accuracy of the model and enhance the quality of future store opening predictions.

[0270] (Example 1)

[0271] 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."

[0272] In modern society, selecting the location for a new store is a crucial factor in determining its success, requiring accurate analysis based on a large amount of data. However, systems for efficiently collecting and analyzing vast amounts of data and presenting highly accurate potential store locations are not yet fully developed, resulting in insufficient measures against investment risks and increasing market competition. Against this backdrop, there is a need for methods that enable strategic store openings that take into account regional characteristics and the commercial environment.

[0273] 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.

[0274] In this invention, the server includes means for automatically collecting diverse data and preprocessing it in a standardized format, means for extracting features based on the preprocessed data and training a predictive model, and means for analyzing and evaluating candidate regions using the trained predictive model while considering multiple past cases. This enables users to effectively visualize candidate regions and formulate better store opening strategies.

[0275] "Diverse data" is a general term for information of multiple characteristics collected from different types of sources, including demographics, traffic information, property information, and commercial competition conditions.

[0276] A "standardized format" refers to a data format that converts different forms of data into a unified format to facilitate comparison and analysis.

[0277] "Features" refer to specific aspects or attributes of data used to train machine learning models, and are important factors for improving prediction accuracy.

[0278] A "predictive model" is an algorithm or mathematical framework used to predict potential store locations for new data, based on collected and pre-processed data and features.

[0279] "Visual presentation" refers to representing data and information in a visual format, such as maps and graphs, so that users can intuitively understand it.

[0280] "Predictive accuracy" is an indicator that shows how accurately a predictive model can predict actual results, and it is an important factor in evaluating the usefulness of a model.

[0281] "Feedback" refers to information that the system uses to improve its statistical model, based on post-opening performance data and evaluations provided by users.

[0282] An "algorithm" is a set of step-by-step procedures or calculation methods for solving a specific problem, and it forms the basis for data analysis and decision-making in a system.

[0283] This invention relates to a system for optimizing the opening strategy of new stores. The system mainly includes servers, terminals, and user interactions.

[0284] The server automatically collects various data by leveraging public databases, APIs, sensor networks, etc. The hardware used includes data collection servers and cloud services, and the software includes data integration tools and ETL (Extract, Transform, Load) tools. These data include regional demographic information, traffic patterns, commercial activities, competitive information, etc.

[0285] The collected data is preprocessed on the server. For data cleansing, big data processing tools such as the pandas library in Python and Apache Spark are used. Feature quantities for machine learning are extracted from the preprocessed data. The scikit-learn library is used in this process, and the prediction model is trained using TensorFlow or PyTorch.

[0286] The server uses the trained model to conduct regional analysis and predict store opening candidate locations. The prediction results are evaluated through a scoring algorithm, and the optimal candidate locations are selected.

[0287] The evaluation results are sent to the terminal and visualized so that users can intuitively understand them. On the terminal, GIS (Geographic Information System) software and data visualization tools are used to display candidate locations as maps or infographics. This allows users to easily compare and select candidate locations.

[0288] For example, if the collected data indicates that there is particularly high traffic at night in a certain area, the system will list it as a store opening candidate for industries suitable for night operations. Based on such predictions, users can make decisions about opening stores.

[0289] Users contribute to the improvement of the system's model by returning the actual business performance data and customer feedback after the store opens to the server. With this feedback, the server continuously updates the machine learning model to improve the prediction accuracy.

[0290] A concrete example of a prompt message is, "Considering local demographics and nighttime traffic volume, predict the best location for a restaurant," which users can use to query the generative AI model for potential locations.

[0291] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0292] Step 1:

[0293] The server collects diverse data from public databases, APIs, and sensor networks. This includes demographic, traffic, and commercial environment data. The input is raw data from these data sources, and the output is the collected, unprocessed dataset. In this step, data collection scripts are run periodically to systematically accumulate up-to-date information.

[0294] Step 2:

[0295] The server preprocesses the collected data. Data cleansing includes imputing missing values, checking for format consistency, and removing inaccurate data. The input is the raw data obtained in step 1, and the output is a clean, preprocessed dataset. Specifically, the Python pandas library is used to unify information from different data sources and format it for analysis.

[0296] Step 3:

[0297] The server extracts features from pre-processed data and trains a machine learning model. Key elements such as pedestrian flow trends and store competition are incorporated into the feature extraction. The input is the clean data obtained in step 2, and the output is the trained generative AI model. Features are generated using the scikit-learn library, and the machine learning model is constructed using TensorFlow.

[0298] Step 4:

[0299] The server predicts and evaluates store opening candidate locations using a trained model. The input is the AI model obtained in step 3 and additional evaluation data, and the output is a scored list of candidate locations. For model evaluation, an independent scoring algorithm is applied to quantify the commercial potential of each candidate location.

[0300] Step 5:

[0301] The server formats the evaluation results for visualization and sends them to the terminal. The input is the candidate location list obtained in step 4, and the output is the visualized evaluation data. Using a data visualization library, preparations are made to plot the results on a map.

[0302] Step 6:

[0303] The terminal presents the received evaluation results to the user. The input is the visualization data sent in step 5, and the output is an interface that the user can view. Using GIS software, points are displayed on the map and the data is provided in a form that can be interactively manipulated.

[0304] Step 7:

[0305] The user provides feedback on the actual store opening result data to the server. The input is the actual performance after store opening, and the output is the accumulated data that contributes to model improvement. Based on this feedback, the server updates the model to improve the accuracy of recommended store opening candidate locations.

[0306] (Application Example 1)

[0307] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0308] In existing store opening strategies, even when information on multiple potential locations is gathered, it is difficult to integrate and evaluate it to make appropriate decisions. Furthermore, the lack of systems capable of real-time evaluation makes it difficult to formulate store opening strategies that are suitable for the rapidly changing market environment. Therefore, there is a need for a new system that can practically and efficiently evaluate potential locations and select the optimal location.

[0309] 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.

[0310] In this invention, the server includes means for collecting and preprocessing diverse information; means for extracting features based on this preprocessed information and training a learning model; means for predicting and evaluating potential store locations using the trained learning model; means for enabling users to evaluate multiple potential store locations in real time using a mobile communication terminal; and means for visualizing and comparing information in map and graph formats. This enables users to select the optimal store location based on multifaceted information in real time.

[0311] "Diverse information" refers to various types of data, such as demographic trends, traffic volume, property information, the presence of competing stores, and pedestrian flow trends.

[0312] "Preprocessing" is the process of converting collected information into a format suitable for analysis by imputing missing values, standardizing the format, and removing inaccurate data.

[0313] "Features" are important indicators or properties that are extracted for use in training machine learning models.

[0314] A "learning model" is an algorithm that learns patterns from collected data and uses them to make predictions and evaluations about the future.

[0315] A "trained learning model" is a predictive algorithm that improves its accuracy based on various data, using past successes and failures.

[0316] A "potential location for opening a store" refers to a geographical location that is being assessed for optimal suitability when developing a new business.

[0317] "Real-time" refers to the immediate acquisition, processing, and provision of information and results.

[0318] "Mobile communication terminals" refer to portable electronic devices with communication capabilities, such as smartphones and tablets.

[0319] "Visualization" refers to displaying data and analysis results in a format that is easy for users to understand, such as maps or graphs.

[0320] The system implementing this invention is designed to collect diverse information and use it to evaluate the optimal location for a new store. The server collects diverse information such as population dynamics, traffic volume, property information, the presence of competing stores, and pedestrian flow trends through public databases and APIs, and then performs preprocessing. This preprocessing includes cleaning and standardizing the format of the data using Python.

[0321] Features are extracted from the collected information, and a learning model is trained using Scikit-Learn. This model learns patterns from past successes and failures, and can predict future potential store locations. The trained learning model enables real-time evaluation and is presented on a mobile communication terminal.

[0322] The terminals take the form of smartphones or tablets and visualize evaluation results received from the server in map and graph format. This allows users to visually understand the information and select the optimal store location.

[0323] As a concrete example, a user who wants to open a new cafe uses the app to obtain information on potential locations on their smartphone. Based on the collected information, data such as nighttime traffic volume and the competitive situation in the surrounding area are displayed. Based on this information, the user can make a decision and choose the most suitable location.

[0324] An example of a prompt message is: "To evaluate potential locations for a new cafe, please collect information on surrounding population, traffic volume, and competitors to suggest the optimal location." This system can continuously optimize its store opening strategy by further improving the model based on user feedback.

[0325] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0326] Step 1:

[0327] The server collects diverse information through public databases and APIs. Input information includes demographic data, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends. This data is retrieved using the Python Requests library, and its integrity is checked. The output is a collection of raw data.

[0328] Step 2:

[0329] The server preprocesses the collected data. This process involves cleaning the data by imputing missing values, removing inaccurate data, and standardizing the format. Pandas is used at this stage to output the processed, clean data.

[0330] Step 3:

[0331] The server extracts features from preprocessed data and trains a machine learning model. It uses Scikit-Learn to fit patterns to the data and build the model. The input is preprocessed data, and the output is the trained machine learning model.

[0332] Step 4:

[0333] The server uses a trained learning model to predict and evaluate potential store locations from new data. Specifically, it applies newly input data on potential locations to the model and quantifies the suitability of those locations. The output is a dataset containing evaluation scores.

[0334] Step 5:

[0335] The terminal visualizes the evaluation results received from the server in map and graph format. The input is data containing evaluation scores, which is converted into a visual format using Matplotlib or Folium. The output is maps and graphs displayed in the user interface.

[0336] Step 6:

[0337] Users view evaluation results via their devices and select the optimal location for a new store. This interaction prompts them to provide opinions and send feedback to the server, following the prompt: "To evaluate potential locations for a new cafe, please gather information on surrounding population, traffic volume, and competitors to propose the best location." Input is the evaluation results in maps and graphs, while output is the selected optimal location and the feedback provided.

[0338] 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.

[0339] This invention combines an emotion engine with a system for optimizing store opening strategies. This system recognizes user emotions and provides interaction and feedback according to their emotional state, thereby supporting more effective store opening decisions.

[0340] This system first collects a wide variety of data on a server. This data includes demographics, traffic volume, pedestrian flow, property information, and competitor information. The collected data is preprocessed on the server and formatted into an appropriate format.

[0341] Next, the server extracts features based on the pre-processed data and trains a machine learning model. This model is used to predict and evaluate potential locations for new store openings. The evaluation results are scored, and locations with high commercial suitability are selected.

[0342] Furthermore, the system's main feature, the emotion engine, recognizes the user's emotions through the device. Emotion recognition is performed using technology that detects the user's emotional state from facial expressions and voice using a camera and microphone. The detected emotion data is analyzed on a server and becomes basic data for understanding how the user is reacting to information.

[0343] The device uses the results of the emotion engine's analysis to adjust the information presented to the user and the way they interact in real time. For example, if the user shows frustration, it simplifies the information presentation or provides additional supplementary information to support decision-making. This feedback loop constantly optimizes the user experience.

[0344] For example, if a user is not satisfied with the information presented regarding potential store locations, the device will suggest alternative locations based on data from its emotion engine. It can also provide additional information about locations the user has shown interest in.

[0345] Finally, once user feedback is received, the server readjusts the model parameters based on that feedback to improve the system's prediction accuracy. Through this cyclical process, the system continuously evolves, enabling it to provide users with more accurate and personalized store recommendations.

[0346] The following describes the processing flow.

[0347] Step 1:

[0348] The server collects a wide variety of data from government agencies and private data providers, including demographics, traffic volume, property information, competitive information, and people-to-people data. This data is retrieved through API calls and database queries.

[0349] Step 2:

[0350] The server preprocesses the collected raw data, including imputing missing data, removing outliers, and standardizing data formats. This process includes data cleaning and normalization, preparing the data for analysis.

[0351] Step 3:

[0352] The server extracts features from pre-processed data and trains a machine learning model. This model has the ability to predict potential store locations in a specific region and learns regional trends and patterns.

[0353] Step 4:

[0354] The server uses a trained model to predict potential locations and scores each location. The prediction takes into account factors such as traffic volume, commercial area size, and competitive landscape.

[0355] Step 5:

[0356] The terminal receives evaluation results from the server and visualizes them through a user interface. Commercially promising potential store locations are presented to the user in map and graph format.

[0357] Step 6:

[0358] When users make decisions based on the displayed candidate location information, their emotional state is recognized through facial expressions and voice detected by the emotion engine.

[0359] Step 7:

[0360] The device dynamically adjusts the information it presents and the way it interacts based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will support decision-making by simplifying explanations or providing more detailed data.

[0361] Step 8:

[0362] Users make decisions regarding potential store locations and provide the results and feedback. This feedback is sent to the server as new data.

[0363] Step 9:

[0364] The server uses user feedback to readjust its machine learning models and improve future prediction accuracy. This ensures continuous system improvement.

[0365] (Example 2)

[0366] 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".

[0367] Traditional store opening strategies face the challenge of selecting appropriate locations that fully consider regional characteristics and competitive information. Furthermore, the lack of mechanisms to effectively reflect user sentiment and feedback prevents efficient and effective optimization of store opening strategies.

[0368] 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.

[0369] In this invention, the server includes means for collecting and preprocessing a wide variety of information, means for extracting features based on this preprocessed information and training a machine learning algorithm, and means for acquiring the user's emotional state using emotion recognition technology and adjusting the information provided based on that state. This makes it possible to select the optimal store location considering regional characteristics and competitive information, and further enables the optimization of strategies that reflect user emotions and feedback.

[0370] "Diverse information" refers to a general term for data with various attributes related to store openings, such as demographics, traffic volume, pedestrian flow, property information, and competitor information.

[0371] "Preprocessing" is the process of preparing collected raw data into a format suitable for machine learning models by performing actions such as imputing missing values, removing noise, and normalizing.

[0372] "Feature extraction" is the process of extracting important information from data and generating metrics that models use for learning and prediction.

[0373] A "machine learning algorithm" is a computational method that uses data to learn patterns and perform predictions and classifications.

[0374] "Emotion recognition technology" is a technology that uses cameras and microphones to detect a user's emotional state from their facial expressions and voice.

[0375] An "interface" is a structure that provides a means for a user to interact with a system and input or output information.

[0376] "Algorithm improvement" is the process of adjusting model parameters based on user feedback to improve prediction accuracy and output quality.

[0377] This invention provides a system that predicts optimal store locations in a specific area and optimizes strategies by incorporating user feedback. The system operates through the collaboration of a server, terminals, and users.

[0378] The server is equipped with high-performance computing equipment and network connectivity. The server collects a wide variety of information, including demographic data, traffic data, pedestrian flow analysis data, property information, and competitor store information. To preprocess this data, data shaping, cleaning, and normalization are performed using programming languages ​​such as Python and dedicated libraries.

[0379] The server extracts features from preprocessed data and trains models using machine learning algorithms. It uses open-source software libraries such as Scikit-learn and TensorFlow to build random forests and neural networks. This allows for the prediction and evaluation of potential store locations, taking commercial suitability into account.

[0380] The device provides a user interface and reads the user's emotions from their facial expressions and voice through emotion recognition technology. It acquires emotion data using OpenCV and speech analysis libraries via its camera and microphone. This emotion data is sent to a server and used to adjust the data delivery method according to the user's emotions.

[0381] The system improves the accuracy of its model based on feedback provided by users interacting with the interface and providing comments on the suggested store locations. Users can evaluate potential locations through a simple and intuitive GUI.

[0382] As a concrete example, if a user requests information about potential store locations in a specific area, they might input a prompt to the generating AI model such as: "Please suggest recommended locations for new store openings, taking into account demographics, traffic volume, and the impact of competing stores." Based on this input, the system will present the most suitable candidate locations based on relevant information.

[0383] This makes it possible to select potential store locations that take regional characteristics into account, and to reflect user sentiment and feedback in the strategy in real time.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The server collects a wide variety of information related to regional characteristics. Inputs include demographic data, traffic volume, pedestrian flow, property information, and competitor store information. The server uses Python's pandas library to format this data, performing tasks such as imputing missing values ​​and removing noise. The output is pre-processed data in a format suitable for machine learning models.

[0387] Step 2:

[0388] The server extracts important features based on preprocessed data. The input is the data formatted in step 1. The server uses Scikit-learn to extract features such as population density and traffic patterns from each data point. The output is the feature set used to train the model.

[0389] Step 3:

[0390] The server trains a machine learning model using the extracted features. The input is the set of features extracted in step 2. The server uses TensorFlow to build a neural network and learn the features. The output is the trained model for predicting potential new store locations.

[0391] Step 4:

[0392] The device uses its camera and microphone to recognize the user's emotions. Input consists of the user's facial expressions and voice. The device uses OpenCV and a voice analysis library to infer emotions and sends this data to the server in real time. The output is the user's emotion data.

[0393] Step 5:

[0394] The server analyzes the user's emotional data and adjusts the information provided. The input is the emotional data sent from the terminal in step 4. Based on the user's emotions, the server modifies the information delivery method, for example, by simplifying the presentation to support decision-making. The output is the adjusted information presentation.

[0395] Step 6:

[0396] Users evaluate information and provide feedback through their devices. Input includes evaluations of candidate location information. User feedback is formatted and sent to the server. Output is feedback data for model improvement.

[0397] Step 7:

[0398] The server improves the model's accuracy based on user feedback data. The input consists of the feedback data obtained in step 6 and the trained model. The server retrains the model and adjusts its parameters. The output is the improved predictive model. This process enables the model to provide more accurate and personalized suggestions.

[0399] (Application Example 2)

[0400] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0401] When selecting potential store locations, it is necessary to consider various factors such as demographics and traffic volume. However, traditional methods fail to adequately consider customer emotions and intuitive reactions, making it difficult to formulate efficient store opening strategies. Furthermore, the sheer volume and complexity of information can cause stress for customers, preventing them from making optimal decisions.

[0402] 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.

[0403] In this invention, the server includes a device for acquiring and pre-processing a wide variety of information, a device for extracting characteristics based on this pre-processed information and training a machine learning model, and a device for recognizing the user's emotional state and adjusting the information presentation method based on feedback. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0404] "Information" refers to a variety of data necessary for the operation and evaluation of the system, such as demographics, traffic volume, and regional characteristics.

[0405] "Preprocessing" refers to data processing that formats acquired information into a state that can be analyzed and converts it into a format suitable for subsequent processing.

[0406] "Characteristics" refer to the features and indicators of data extracted as criteria for evaluating potential store locations.

[0407] A "machine learning model" is a program structure that uses a large amount of data to train algorithms and make specific patterns or predictions.

[0408] A "potential store location area" refers to a region or location that is being considered for opening a new store.

[0409] "Evaluation" is the process of determining the commercial suitability and potential success of a potential store location.

[0410] "Display" refers to the act of a system presenting evaluation results or information to a user.

[0411] A "user" is an individual or organization that operates the system and uses information to formulate store opening strategies.

[0412] "Emotional state" refers to some of the psychological reactions, such as joy, anger, and surprise, that users exhibit in response to the system.

[0413] "Feedback" refers to information based on opinions and reactions from users to the system, which is useful for improving and adjusting the system.

[0414] The system implementing this invention consists of a server that acquires and processes information, and a terminal that recognizes the user's emotional state and adjusts the way information is presented. The server collects diverse information such as demographics, traffic volume, and regional characteristics, and performs preprocessing. It extracts characteristics from the preprocessed data and creates a foundation for training a machine learning model. In this process, it is desirable to use machine learning frameworks such as TensorFlow or PyTorch.

[0415] A trained machine learning model predicts and evaluates potential store locations and outputs the results. The device uses its camera and microphone to recognize the user's emotional state in real time. Libraries such as DeepFace are used for emotion recognition, analyzing emotions from the user's facial expressions and voice.

[0416] The device optimizes the information presented to the user based on recognized emotional data. For example, if the user indicates stress, it provides support by simplifying the information or suggesting alternatives. This process enables flexible information delivery to the user by adjusting interactions according to emotions.

[0417] User feedback is sent to the server, helping to readjust the parameters of the machine learning model. This cyclical feedback loop allows the system to continuously learn and improve its accuracy.

[0418] As a concrete example, consider a scenario where a user considering opening a new store checks information about a specific region on their device. If the user shows interest, the device displays further details on the screen. Conversely, if the user looks confused, the device provides a more concise overview instead.

[0419] An example of a prompt is: "Please explain in detail how to optimize information on potential store locations using emotion recognition. This includes examples of interaction using user facial expression data and candidate locations that consider regional characteristics." Based on this example, the generative AI model will learn specific methods to support optimization that combines emotion analysis and store location strategies.

[0420] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0421] Step 1:

[0422] The server retrieves diverse information such as demographics, traffic volume, and regional characteristics from the web and databases. Its input is raw data obtained from external sources, which is then retrieved in various formats and formatted into a unified format. The output is an analyzable dataset.

[0423] Step 2:

[0424] The server extracts characteristics from preprocessed data and trains a machine learning model. The input is a preprocessed dataset from which geographical characteristics and commercial indicator features are extracted. Using these extracted characteristics, software such as TensorFlow and PyTorch is employed to build and train a machine learning model. The output is the trained model used for prediction.

[0425] Step 3:

[0426] The server uses a trained machine learning model to predict and evaluate potential store locations. The input consists of various data points about a specific region, which are then fed into the model to calculate a commercial suitability score. The output is an evaluation result showing the commercial suitability of each area.

[0427] Step 4:

[0428] The device uses its camera and microphone to recognize the user's emotional state in real time. Inputs include the user's facial expressions and voice, which are then analyzed using the DeepFace library. The output is the user's emotional state (e.g., happiness, anger, surprise, etc.).

[0429] Step 5:

[0430] The device optimizes how information is presented based on the sentiment analysis results. Inputs include the sentiment analysis results and evaluation results from the server, and the device adjusts the information presented to the user based on these. For example, if the user is confused, the information is simplified. The output is the adjusted information display.

[0431] Step 6:

[0432] Users provide feedback on the information provided. The input is the user's reaction to the evaluated potential store locations, which is sent to the system as feedback. The output is feedback data used to improve the system.

[0433] Step 7:

[0434] The server updates the parameters of the machine learning model based on user feedback. By receiving feedback data as input and using it to fine-tune the model, prediction accuracy improves. The output is the updated model.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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".

[0451] This invention specifically demonstrates the implementation of a system that optimizes new store opening strategies by utilizing diverse data. The system provides optimal store opening candidates by collecting, preprocessing, analyzing, predicting, evaluating, and presenting data.

[0452] First, the server collects a wide variety of data from public databases, APIs, sensor data, and other sources. This data covers regional demographics, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends.

[0453] Next, the collected data is preprocessed on the server, where missing values ​​are imputed, the format is standardized, and inaccurate data is removed. This process transforms the data into a format suitable for analysis.

[0454] Next, the server extracts features from the pre-processed data and trains a machine learning model. This model is designed to predict the optimal location for opening a store and learns key trends from the collected data. Data from past successes and failures are also used in the training to improve prediction accuracy.

[0455] Once potential locations are identified, the server performs an evaluation and presents the candidate sites in the form of scores and rankings. The evaluation results are derived from commercial suitability and competitive landscape, and the potential of each candidate site is shown in detail.

[0456] The evaluation results are sent to the device and visualized in a user-friendly format. Displayed in map and graph formats, detailed location-specific data and differences based on scenarios are clearly shown, allowing users to interactively compare potential locations.

[0457] For example, if a particular area experiences heavy nighttime traffic, that data might be considered favorable for opening a store in a specific industry, and the area could be evaluated as a potential location for businesses that operate at night.

[0458] The system further receives feedback from users and improves its model based on actual store opening results. This process enables the continuous recommendation of highly accurate store opening locations. Users can contribute to the system's evolution by providing feedback on post-opening performance data to the server.

[0459] In this way, the present invention realizes the construction of a system that enables the formulation of effective store opening strategies in various regions.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] The server collects a wide variety of data, including population data, traffic data, property information, and competitor information, from public databases and APIs. This data forms the basis for the system to determine the optimal store location.

[0463] Step 2:

[0464] The server preprocesses the collected data, including filling in missing data and standardizing data formats. This process also removes outliers and, if necessary, scales specific data.

[0465] Step 3:

[0466] The server extracts features from pre-processed data and trains a machine learning model. This allows it to learn patterns and trends in the data and build a foundation for predicting suitable locations for new stores.

[0467] Step 4:

[0468] The server uses a trained model to predict potential store locations. For each potential location, it evaluates its commercial suitability, taking into account traffic volume, competition, and pedestrian flow predictions.

[0469] Step 5:

[0470] The server scores and ranks the predicted candidate locations and formats the results in a user-friendly format. Evaluation criteria include factors such as potential for opening a store and predicted profit margins.

[0471] Step 6:

[0472] The terminal receives evaluation results sent from the server and visualizes them through the user interface. Information is provided to the user in map and dashboard formats, making it easy to compare potential locations.

[0473] Step 7:

[0474] Users can perform simulations based on the information provided and try out different store opening scenarios. For example, they can virtually observe changes in foot traffic under specific conditions to improve the accuracy of their decision-making.

[0475] Step 8:

[0476] Users provide feedback to the server with performance data after actually opening a store. Based on this information, the server adjusts the algorithm to improve the accuracy of the model and enhance the quality of future store opening predictions.

[0477] (Example 1)

[0478] 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."

[0479] In modern society, selecting the location for a new store is a crucial factor in determining its success, requiring accurate analysis based on a large amount of data. However, systems for efficiently collecting and analyzing vast amounts of data and presenting highly accurate potential store locations are not yet fully developed, resulting in insufficient measures against investment risks and increasing market competition. Against this backdrop, there is a need for methods that enable strategic store openings that take into account regional characteristics and the commercial environment.

[0480] 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.

[0481] In this invention, the server includes means for automatically collecting diverse data and preprocessing it in a standardized format, means for extracting features based on the preprocessed data and training a predictive model, and means for analyzing and evaluating candidate regions using the trained predictive model while considering multiple past cases. This enables users to effectively visualize candidate regions and formulate better store opening strategies.

[0482] "Diverse data" is a general term for information of multiple characteristics collected from different types of sources, including demographics, traffic information, property information, and commercial competition conditions.

[0483] A "standardized format" refers to a data format that converts different forms of data into a unified format to facilitate comparison and analysis.

[0484] "Features" refer to specific aspects or attributes of data used to train machine learning models, and are important factors for improving prediction accuracy.

[0485] A "predictive model" is an algorithm or mathematical framework used to predict potential store locations for new data, based on collected and pre-processed data and features.

[0486] "Visual presentation" refers to representing data and information in a visual format, such as maps and graphs, so that users can intuitively understand it.

[0487] "Predictive accuracy" is an indicator that shows how accurately a predictive model can predict actual results, and it is an important factor in evaluating the usefulness of a model.

[0488] "Feedback" refers to information that the system uses to improve its statistical model, based on post-opening performance data and evaluations provided by users.

[0489] An "algorithm" is a set of step-by-step procedures or calculation methods for solving a specific problem, and it forms the basis for data analysis and decision-making in a system.

[0490] This invention relates to a system for optimizing the opening strategy of new stores. The system mainly includes servers, terminals, and user interactions.

[0491] The server automatically collects diverse data by utilizing public databases, APIs, sensor networks, and other resources. The hardware used includes data collection servers and cloud services, while the software includes data integration tools and ETL (Extract, Transform, Load) tools. This data includes local demographic information, traffic patterns, commercial activity, and competitive information.

[0492] The collected data is preprocessed on the server. Data cleansing is performed using Python's pandas library and big data processing tools such as Apache Spark. From the preprocessed data, features for machine learning are extracted. The scikit-learn library is used for this process, and the prediction model is trained using TensorFlow or PyTorch.

[0493] The server uses a trained model to perform regional analysis and predict potential store locations. The prediction results are evaluated through a scoring algorithm to select the optimal location.

[0494] The evaluation results are sent to the terminal and visualized in a way that users can intuitively understand. The terminal uses GIS (Geographic Information System) software and data visualization tools to display candidate locations as maps and infographics. This allows users to easily compare and select candidate locations.

[0495] For example, if the collected data indicates that a particular area has high traffic volume, especially at night, the system will identify it as a potential location for businesses suitable for nighttime operations. Based on such predictions, users can then make decisions about opening a store.

[0496] Users contribute to improving the system's model by returning actual performance data and customer feedback after opening a store to the server. This feedback allows the server to continuously update its machine learning model and improve prediction accuracy.

[0497] A concrete example of a prompt message is, "Considering local demographics and nighttime traffic volume, predict the best location for a restaurant," which users can use to query the generative AI model for potential locations.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The server collects diverse data from public databases, APIs, and sensor networks. This includes demographic, traffic, and commercial environment data. The input is raw data from these data sources, and the output is the collected, unprocessed dataset. In this step, data collection scripts are run periodically to systematically accumulate up-to-date information.

[0501] Step 2:

[0502] The server preprocesses the collected data. Data cleansing includes imputing missing values, checking for format consistency, and removing inaccurate data. The input is the raw data obtained in step 1, and the output is a clean, preprocessed dataset. Specifically, the Python pandas library is used to unify information from different data sources and format it for analysis.

[0503] Step 3:

[0504] The server extracts features from pre-processed data and trains a machine learning model. Key elements such as pedestrian flow trends and store competition are incorporated into the feature extraction. The input is the clean data obtained in step 2, and the output is the trained generative AI model. Features are generated using the scikit-learn library, and the machine learning model is constructed using TensorFlow.

[0505] Step 4:

[0506] The server uses a trained model to predict and evaluate potential store locations. The input is the AI ​​model obtained in step 3 and additional evaluation data, and the output is a scored list of candidate locations. A proprietary scoring algorithm is applied to evaluate the model, quantifying the commercial potential of each candidate location.

[0507] Step 5:

[0508] The server formats the evaluation results for visualization and sends them to the terminal. The input is the candidate site list obtained in step 4, and the output is the visualized evaluation data. Prepare to plot the results on a map using a data visualization library.

[0509] Step 6:

[0510] The terminal displays the received evaluation results to the user. The input is the visualization data sent in step 5, and the output is an interface that the user can view. Using GIS software, points are displayed on a map, and the data is provided in an interactive format.

[0511] Step 7:

[0512] Users provide feedback to the server with actual store opening results data. The input is the performance after opening, and the output is accumulated data that contributes to improving the model. Based on this feedback, the server updates the model and improves the accuracy of recommending potential store locations.

[0513] (Application Example 1)

[0514] 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."

[0515] In existing store opening strategies, even when information on multiple potential locations is gathered, it is difficult to integrate and evaluate it to make appropriate decisions. Furthermore, the lack of systems capable of real-time evaluation makes it difficult to formulate store opening strategies that are suitable for the rapidly changing market environment. Therefore, there is a need for a new system that can practically and efficiently evaluate potential locations and select the optimal location.

[0516] 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.

[0517] In this invention, the server includes means for collecting and preprocessing diverse information; means for extracting features based on this preprocessed information and training a learning model; means for predicting and evaluating potential store locations using the trained learning model; means for enabling users to evaluate multiple potential store locations in real time using a mobile communication terminal; and means for visualizing and comparing information in map and graph formats. This enables users to select the optimal store location based on multifaceted information in real time.

[0518] "Diverse information" refers to various types of data, such as demographic trends, traffic volume, property information, the presence of competing stores, and pedestrian flow trends.

[0519] "Preprocessing" is the process of converting collected information into a format suitable for analysis by imputing missing values, standardizing the format, and removing inaccurate data.

[0520] "Features" are important indicators or properties that are extracted for use in training machine learning models.

[0521] A "learning model" is an algorithm that learns patterns from collected data and uses them to make predictions and evaluations about the future.

[0522] A "trained learning model" is a predictive algorithm that improves its accuracy based on various data, using past successes and failures.

[0523] A "potential location for opening a store" refers to a geographical location that is being assessed for optimal suitability when developing a new business.

[0524] "Real-time" refers to the immediate acquisition, processing, and provision of information and results.

[0525] "Mobile communication terminals" refer to portable electronic devices with communication capabilities, such as smartphones and tablets.

[0526] "Visualization" refers to displaying data and analysis results in a format that is easy for users to understand, such as maps or graphs.

[0527] The system implementing this invention is designed to collect diverse information and use it to evaluate the optimal location for a new store. The server collects diverse information such as population dynamics, traffic volume, property information, the presence of competing stores, and pedestrian flow trends through public databases and APIs, and then performs preprocessing. This preprocessing includes cleaning and standardizing the format of the data using Python.

[0528] Features are extracted from the collected information, and a learning model is trained using Scikit-Learn. This model learns patterns from past successes and failures, and can predict future potential store locations. The trained learning model enables real-time evaluation and is presented on a mobile communication terminal.

[0529] The terminals take the form of smartphones or tablets and visualize evaluation results received from the server in map and graph format. This allows users to visually understand the information and select the optimal store location.

[0530] As a concrete example, a user who wants to open a new cafe uses the app to obtain information on potential locations on their smartphone. Based on the collected information, data such as nighttime traffic volume and the competitive situation in the surrounding area are displayed. Based on this information, the user can make a decision and choose the most suitable location.

[0531] An example of a prompt message is: "To evaluate potential locations for a new cafe, please collect information on surrounding population, traffic volume, and competitors to suggest the optimal location." This system can continuously optimize its store opening strategy by further improving the model based on user feedback.

[0532] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0533] Step 1:

[0534] The server collects diverse information through public databases and APIs. Input information includes demographic data, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends. This data is retrieved using the Python Requests library, and its integrity is checked. The output is a collection of raw data.

[0535] Step 2:

[0536] The server preprocesses the collected data. This process involves cleaning the data by imputing missing values, removing inaccurate data, and standardizing the format. Pandas is used at this stage to output the processed, clean data.

[0537] Step 3:

[0538] The server extracts features from preprocessed data and trains a machine learning model. It uses Scikit-Learn to fit patterns to the data and build the model. The input is preprocessed data, and the output is the trained machine learning model.

[0539] Step 4:

[0540] The server uses a trained learning model to predict and evaluate potential store locations from new data. Specifically, it applies newly input data on potential locations to the model and quantifies the suitability of those locations. The output is a dataset containing evaluation scores.

[0541] Step 5:

[0542] The terminal visualizes the evaluation results received from the server in map and graph format. The input is data containing evaluation scores, which is converted into a visual format using Matplotlib or Folium. The output is maps and graphs displayed in the user interface.

[0543] Step 6:

[0544] Users view evaluation results via their devices and select the optimal location for a new store. This interaction prompts them to provide opinions and send feedback to the server, following the prompt: "To evaluate potential locations for a new cafe, please gather information on surrounding population, traffic volume, and competitors to propose the best location." Input is the evaluation results in maps and graphs, while output is the selected optimal location and the feedback provided.

[0545] 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.

[0546] This invention combines an emotion engine with a system for optimizing store opening strategies. This system recognizes user emotions and provides interaction and feedback according to their emotional state, thereby supporting more effective store opening decisions.

[0547] This system first collects a wide variety of data on a server. This data includes demographics, traffic volume, pedestrian flow, property information, and competitor information. The collected data is preprocessed on the server and formatted into an appropriate format.

[0548] Next, the server extracts features based on the pre-processed data and trains a machine learning model. This model is used to predict and evaluate potential locations for new store openings. The evaluation results are scored, and locations with high commercial suitability are selected.

[0549] Furthermore, the system's main feature, the emotion engine, recognizes the user's emotions through the device. Emotion recognition is performed using technology that detects the user's emotional state from facial expressions and voice using a camera and microphone. The detected emotion data is analyzed on a server and becomes basic data for understanding how the user is reacting to information.

[0550] The device uses the results of the emotion engine's analysis to adjust the information presented to the user and the way they interact in real time. For example, if the user shows frustration, it simplifies the information presentation or provides additional supplementary information to support decision-making. This feedback loop constantly optimizes the user experience.

[0551] For example, if a user is not satisfied with the information presented regarding potential store locations, the device will suggest alternative locations based on data from its emotion engine. It can also provide additional information about locations the user has shown interest in.

[0552] Finally, once user feedback is received, the server readjusts the model parameters based on that feedback to improve the system's prediction accuracy. Through this cyclical process, the system continuously evolves, enabling it to provide users with more accurate and personalized store recommendations.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] The server collects a wide variety of data from government agencies and private data providers, including demographics, traffic volume, property information, competitive information, and people-to-people data. This data is retrieved through API calls and database queries.

[0556] Step 2:

[0557] The server preprocesses the collected raw data, including imputing missing data, removing outliers, and standardizing data formats. This process includes data cleaning and normalization, preparing the data for analysis.

[0558] Step 3:

[0559] The server extracts features from pre-processed data and trains a machine learning model. This model has the ability to predict potential store locations in a specific region and learns regional trends and patterns.

[0560] Step 4:

[0561] The server uses a trained model to predict potential locations and scores each location. The prediction takes into account factors such as traffic volume, commercial area size, and competitive landscape.

[0562] Step 5:

[0563] The terminal receives evaluation results from the server and visualizes them through a user interface. Commercially promising potential store locations are presented to the user in map and graph format.

[0564] Step 6:

[0565] When users make decisions based on the displayed candidate location information, their emotional state is recognized through facial expressions and voice detected by the emotion engine.

[0566] Step 7:

[0567] The device dynamically adjusts the information it presents and the way it interacts based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will support decision-making by simplifying explanations or providing more detailed data.

[0568] Step 8:

[0569] Users make decisions regarding potential store locations and provide the results and feedback. This feedback is sent to the server as new data.

[0570] Step 9:

[0571] The server uses user feedback to readjust its machine learning models and improve future prediction accuracy. This ensures continuous system improvement.

[0572] (Example 2)

[0573] 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."

[0574] Traditional store opening strategies face the challenge of selecting appropriate locations that fully consider regional characteristics and competitive information. Furthermore, the lack of mechanisms to effectively reflect user sentiment and feedback prevents efficient and effective optimization of store opening strategies.

[0575] 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.

[0576] In this invention, the server includes means for collecting and preprocessing a wide variety of information, means for extracting features based on this preprocessed information and training a machine learning algorithm, and means for acquiring the user's emotional state using emotion recognition technology and adjusting the information provided based on that state. This makes it possible to select the optimal store location considering regional characteristics and competitive information, and further enables the optimization of strategies that reflect user emotions and feedback.

[0577] "Diverse information" refers to a general term for data with various attributes related to store openings, such as demographics, traffic volume, pedestrian flow, property information, and competitor information.

[0578] "Preprocessing" is the process of preparing collected raw data into a format suitable for machine learning models by performing actions such as imputing missing values, removing noise, and normalizing.

[0579] "Feature extraction" is the process of extracting important information from data and generating metrics that models use for learning and prediction.

[0580] A "machine learning algorithm" is a computational method that uses data to learn patterns and perform predictions and classifications.

[0581] "Emotion recognition technology" is a technology that uses cameras and microphones to detect a user's emotional state from their facial expressions and voice.

[0582] An "interface" is a structure that provides a means for a user to interact with a system and input or output information.

[0583] "Algorithm improvement" is the process of adjusting model parameters based on user feedback to improve prediction accuracy and output quality.

[0584] This invention provides a system that predicts optimal store locations in a specific area and optimizes strategies by incorporating user feedback. The system operates through the collaboration of a server, terminals, and users.

[0585] The server is equipped with high-performance computing equipment and network connectivity. The server collects a wide variety of information, including demographic data, traffic data, pedestrian flow analysis data, property information, and competitor store information. To preprocess this data, data shaping, cleaning, and normalization are performed using programming languages ​​such as Python and dedicated libraries.

[0586] The server extracts features from preprocessed data and trains models using machine learning algorithms. It uses open-source software libraries such as Scikit-learn and TensorFlow to build random forests and neural networks. This allows for the prediction and evaluation of potential store locations, taking commercial suitability into account.

[0587] The device provides a user interface and reads the user's emotions from their facial expressions and voice through emotion recognition technology. It acquires emotion data using OpenCV and speech analysis libraries via its camera and microphone. This emotion data is sent to a server and used to adjust the data delivery method according to the user's emotions.

[0588] The system improves the accuracy of its model based on feedback provided by users interacting with the interface and providing comments on the suggested store locations. Users can evaluate potential locations through a simple and intuitive GUI.

[0589] As a concrete example, if a user requests information about potential store locations in a specific area, they might input a prompt to the generating AI model such as: "Please suggest recommended locations for new store openings, taking into account demographics, traffic volume, and the impact of competing stores." Based on this input, the system will present the most suitable candidate locations based on relevant information.

[0590] This makes it possible to select potential store locations that take regional characteristics into account, and to reflect user sentiment and feedback in the strategy in real time.

[0591] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0592] Step 1:

[0593] The server collects a wide variety of information related to regional characteristics. Inputs include demographic data, traffic volume, pedestrian flow, property information, and competitor store information. The server uses Python's pandas library to format this data, performing tasks such as imputing missing values ​​and removing noise. The output is pre-processed data in a format suitable for machine learning models.

[0594] Step 2:

[0595] The server extracts important features based on preprocessed data. The input is the data formatted in step 1. The server uses Scikit-learn to extract features such as population density and traffic patterns from each data point. The output is the feature set used to train the model.

[0596] Step 3:

[0597] The server trains a machine learning model using the extracted features. The input is the set of features extracted in step 2. The server uses TensorFlow to build a neural network and learn the features. The output is the trained model for predicting potential new store locations.

[0598] Step 4:

[0599] The device uses its camera and microphone to recognize the user's emotions. Input consists of the user's facial expressions and voice. The device uses OpenCV and a voice analysis library to infer emotions and sends this data to the server in real time. The output is the user's emotion data.

[0600] Step 5:

[0601] The server analyzes the user's emotional data and adjusts the information provided. The input is the emotional data sent from the terminal in step 4. Based on the user's emotions, the server modifies the information delivery method, for example, by simplifying the presentation to support decision-making. The output is the adjusted information presentation.

[0602] Step 6:

[0603] Users evaluate information and provide feedback through their devices. Input includes evaluations of candidate location information. User feedback is formatted and sent to the server. Output is feedback data for model improvement.

[0604] Step 7:

[0605] The server improves the model's accuracy based on user feedback data. The input consists of the feedback data obtained in step 6 and the trained model. The server retrains the model and adjusts its parameters. The output is the improved predictive model. This process enables the model to provide more accurate and personalized suggestions.

[0606] (Application Example 2)

[0607] 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."

[0608] When selecting potential store locations, it is necessary to consider various factors such as demographics and traffic volume. However, traditional methods fail to adequately consider customer emotions and intuitive reactions, making it difficult to formulate efficient store opening strategies. Furthermore, the sheer volume and complexity of information can cause stress for customers, preventing them from making optimal decisions.

[0609] 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.

[0610] In this invention, the server includes a device for acquiring and pre-processing a wide variety of information, a device for extracting characteristics based on this pre-processed information and training a machine learning model, and a device for recognizing the user's emotional state and adjusting the information presentation method based on feedback. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0611] "Information" refers to a variety of data necessary for the operation and evaluation of the system, such as demographics, traffic volume, and regional characteristics.

[0612] "Preprocessing" refers to data processing that formats acquired information into a state that can be analyzed and converts it into a format suitable for subsequent processing.

[0613] "Characteristics" refer to the features and indicators of data extracted as criteria for evaluating potential store locations.

[0614] A "machine learning model" is a program structure that uses a large amount of data to train algorithms and make specific patterns or predictions.

[0615] A "potential store location area" refers to a region or location that is being considered for opening a new store.

[0616] "Evaluation" is the process of determining the commercial suitability and potential success of a potential store location.

[0617] "Display" refers to the act of a system presenting evaluation results or information to a user.

[0618] A "user" is an individual or organization that operates the system and uses information to formulate store opening strategies.

[0619] "Emotional state" refers to some of the psychological reactions, such as joy, anger, and surprise, that users exhibit in response to the system.

[0620] "Feedback" refers to information based on opinions and reactions from users to the system, which is useful for improving and adjusting the system.

[0621] The system implementing this invention consists of a server that acquires and processes information, and a terminal that recognizes the user's emotional state and adjusts the way information is presented. The server collects diverse information such as demographics, traffic volume, and regional characteristics, and performs preprocessing. It extracts characteristics from the preprocessed data and creates a foundation for training a machine learning model. In this process, it is desirable to use machine learning frameworks such as TensorFlow or PyTorch.

[0622] A trained machine learning model predicts and evaluates potential store locations and outputs the results. The device uses its camera and microphone to recognize the user's emotional state in real time. Libraries such as DeepFace are used for emotion recognition, analyzing emotions from the user's facial expressions and voice.

[0623] The device optimizes the information presented to the user based on recognized emotional data. For example, if the user indicates stress, it provides support by simplifying the information or suggesting alternatives. This process enables flexible information delivery to the user by adjusting interactions according to emotions.

[0624] User feedback is sent to the server, helping to readjust the parameters of the machine learning model. This cyclical feedback loop allows the system to continuously learn and improve its accuracy.

[0625] As a concrete example, consider a scenario where a user considering opening a new store checks information about a specific region on their device. If the user shows interest, the device displays further details on the screen. Conversely, if the user looks confused, the device provides a more concise overview instead.

[0626] An example of a prompt is: "Please explain in detail how to optimize information on potential store locations using emotion recognition. This includes examples of interaction using user facial expression data and candidate locations that consider regional characteristics." Based on this example, the generative AI model will learn specific methods to support optimization that combines emotion analysis and store location strategies.

[0627] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0628] Step 1:

[0629] The server retrieves diverse information such as demographics, traffic volume, and regional characteristics from the web and databases. Its input is raw data obtained from external sources, which is then retrieved in various formats and formatted into a unified format. The output is an analyzable dataset.

[0630] Step 2:

[0631] The server extracts characteristics from preprocessed data and trains a machine learning model. The input is a preprocessed dataset from which geographical characteristics and commercial indicator features are extracted. Using these extracted characteristics, software such as TensorFlow and PyTorch is employed to build and train a machine learning model. The output is the trained model used for prediction.

[0632] Step 3:

[0633] The server uses a trained machine learning model to predict and evaluate potential store locations. The input consists of various data points about a specific region, which are then fed into the model to calculate a commercial suitability score. The output is an evaluation result showing the commercial suitability of each area.

[0634] Step 4:

[0635] The device uses its camera and microphone to recognize the user's emotional state in real time. Inputs include the user's facial expressions and voice, which are then analyzed using the DeepFace library. The output is the user's emotional state (e.g., happiness, anger, surprise, etc.).

[0636] Step 5:

[0637] The device optimizes how information is presented based on the sentiment analysis results. Inputs include the sentiment analysis results and evaluation results from the server, and the device adjusts the information presented to the user based on these. For example, if the user is confused, the information is simplified. The output is the adjusted information display.

[0638] Step 6:

[0639] Users provide feedback on the information provided. The input is the user's reaction to the evaluated potential store locations, which is sent to the system as feedback. The output is feedback data used to improve the system.

[0640] Step 7:

[0641] The server updates the parameters of the machine learning model based on user feedback. By receiving feedback data as input and using it to fine-tune the model, prediction accuracy improves. The output is the updated model.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] [Fourth Embodiment]

[0646] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0647] 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.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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".

[0659] This invention specifically demonstrates the implementation of a system that optimizes new store opening strategies by utilizing diverse data. The system provides optimal store opening candidates by collecting, preprocessing, analyzing, predicting, evaluating, and presenting data.

[0660] First, the server collects a wide variety of data from public databases, APIs, sensor data, and other sources. This data covers regional demographics, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends.

[0661] Next, the collected data is preprocessed on the server, where missing values ​​are imputed, the format is standardized, and inaccurate data is removed. This process transforms the data into a format suitable for analysis.

[0662] Next, the server extracts features from the pre-processed data and trains a machine learning model. This model is designed to predict the optimal location for opening a store and learns key trends from the collected data. Data from past successes and failures are also used in the training to improve prediction accuracy.

[0663] Once potential locations are identified, the server performs an evaluation and presents the candidate sites in the form of scores and rankings. The evaluation results are derived from commercial suitability and competitive landscape, and the potential of each candidate site is shown in detail.

[0664] The evaluation results are sent to the device and visualized in a user-friendly format. Displayed in map and graph formats, detailed location-specific data and differences based on scenarios are clearly shown, allowing users to interactively compare potential locations.

[0665] For example, if a particular area experiences heavy nighttime traffic, that data might be considered favorable for opening a store in a specific industry, and the area could be evaluated as a potential location for businesses that operate at night.

[0666] The system further receives feedback from users and improves its model based on actual store opening results. This process enables the continuous recommendation of highly accurate store opening locations. Users can contribute to the system's evolution by providing feedback on post-opening performance data to the server.

[0667] In this way, the present invention realizes the construction of a system that enables the formulation of effective store opening strategies in various regions.

[0668] The following describes the processing flow.

[0669] Step 1:

[0670] The server collects a wide variety of data, including population data, traffic data, property information, and competitor information, from public databases and APIs. This data forms the basis for the system to determine the optimal store location.

[0671] Step 2:

[0672] The server preprocesses the collected data, including filling in missing data and standardizing data formats. This process also removes outliers and, if necessary, scales specific data.

[0673] Step 3:

[0674] The server extracts features from pre-processed data and trains a machine learning model. This allows it to learn patterns and trends in the data and build a foundation for predicting suitable locations for new stores.

[0675] Step 4:

[0676] The server uses a trained model to predict potential store locations. For each potential location, it evaluates its commercial suitability, taking into account traffic volume, competition, and pedestrian flow predictions.

[0677] Step 5:

[0678] The server scores and ranks the predicted candidate locations and formats the results in a user-friendly format. Evaluation criteria include factors such as potential for opening a store and predicted profit margins.

[0679] Step 6:

[0680] The terminal receives evaluation results sent from the server and visualizes them through the user interface. Information is provided to the user in map and dashboard formats, making it easy to compare potential locations.

[0681] Step 7:

[0682] Users can perform simulations based on the information provided and try out different store opening scenarios. For example, they can virtually observe changes in foot traffic under specific conditions to improve the accuracy of their decision-making.

[0683] Step 8:

[0684] Users provide feedback to the server with performance data after actually opening a store. Based on this information, the server adjusts the algorithm to improve the accuracy of the model and enhance the quality of future store opening predictions.

[0685] (Example 1)

[0686] 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".

[0687] In modern society, selecting the location for a new store is a crucial factor in determining its success, requiring accurate analysis based on a large amount of data. However, systems for efficiently collecting and analyzing vast amounts of data and presenting highly accurate potential store locations are not yet fully developed, resulting in insufficient measures against investment risks and increasing market competition. Against this backdrop, there is a need for methods that enable strategic store openings that take into account regional characteristics and the commercial environment.

[0688] 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.

[0689] In this invention, the server includes means for automatically collecting diverse data and preprocessing it in a standardized format, means for extracting features based on the preprocessed data and training a predictive model, and means for analyzing and evaluating candidate regions using the trained predictive model while considering multiple past cases. This enables users to effectively visualize candidate regions and formulate better store opening strategies.

[0690] "Diverse data" is a general term for information of multiple characteristics collected from different types of sources, including demographics, traffic information, property information, and commercial competition conditions.

[0691] A "standardized format" refers to a data format that converts different forms of data into a unified format to facilitate comparison and analysis.

[0692] "Features" refer to specific aspects or attributes of data used to train machine learning models, and are important factors for improving prediction accuracy.

[0693] A "predictive model" is an algorithm or mathematical framework used to predict potential store locations for new data, based on collected and pre-processed data and features.

[0694] "Visual presentation" refers to representing data and information in a visual format, such as maps and graphs, so that users can intuitively understand it.

[0695] "Predictive accuracy" is an indicator that shows how accurately a predictive model can predict actual results, and it is an important factor in evaluating the usefulness of a model.

[0696] "Feedback" refers to information that the system uses to improve its statistical model, based on post-opening performance data and evaluations provided by users.

[0697] An "algorithm" is a set of step-by-step procedures or calculation methods for solving a specific problem, and it forms the basis for data analysis and decision-making in a system.

[0698] This invention relates to a system for optimizing the opening strategy of new stores. The system mainly includes servers, terminals, and user interactions.

[0699] The server automatically collects diverse data by utilizing public databases, APIs, sensor networks, and other resources. The hardware used includes data collection servers and cloud services, while the software includes data integration tools and ETL (Extract, Transform, Load) tools. This data includes local demographic information, traffic patterns, commercial activity, and competitive information.

[0700] The collected data is preprocessed on the server. Data cleansing is performed using Python's pandas library and big data processing tools such as Apache Spark. From the preprocessed data, features for machine learning are extracted. The scikit-learn library is used for this process, and the prediction model is trained using TensorFlow or PyTorch.

[0701] The server uses a trained model to perform regional analysis and predict potential store locations. The prediction results are evaluated through a scoring algorithm to select the optimal location.

[0702] The evaluation results are sent to the terminal and visualized in a way that users can intuitively understand. The terminal uses GIS (Geographic Information System) software and data visualization tools to display candidate locations as maps and infographics. This allows users to easily compare and select candidate locations.

[0703] For example, if the collected data indicates that a particular area has high traffic volume, especially at night, the system will identify it as a potential location for businesses suitable for nighttime operations. Based on such predictions, users can then make decisions about opening a store.

[0704] Users contribute to improving the system's model by returning actual performance data and customer feedback after opening a store to the server. This feedback allows the server to continuously update its machine learning model and improve prediction accuracy.

[0705] A concrete example of a prompt message is, "Considering local demographics and nighttime traffic volume, predict the best location for a restaurant," which users can use to query the generative AI model for potential locations.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] The server collects diverse data from public databases, APIs, and sensor networks. This includes demographic, traffic, and commercial environment data. The input is raw data from these data sources, and the output is the collected, unprocessed dataset. In this step, data collection scripts are run periodically to systematically accumulate up-to-date information.

[0709] Step 2:

[0710] The server preprocesses the collected data. Data cleansing includes imputing missing values, checking for format consistency, and removing inaccurate data. The input is the raw data obtained in step 1, and the output is a clean, preprocessed dataset. Specifically, the Python pandas library is used to unify information from different data sources and format it for analysis.

[0711] Step 3:

[0712] The server extracts features from pre-processed data and trains a machine learning model. Key elements such as pedestrian flow trends and store competition are incorporated into the feature extraction. The input is the clean data obtained in step 2, and the output is the trained generative AI model. Features are generated using the scikit-learn library, and the machine learning model is constructed using TensorFlow.

[0713] Step 4:

[0714] The server uses a trained model to predict and evaluate potential store locations. The input is the AI ​​model obtained in step 3 and additional evaluation data, and the output is a scored list of candidate locations. A proprietary scoring algorithm is applied to evaluate the model, quantifying the commercial potential of each candidate location.

[0715] Step 5:

[0716] The server formats the evaluation results for visualization and sends them to the terminal. The input is the candidate site list obtained in step 4, and the output is the visualized evaluation data. Prepare to plot the results on a map using a data visualization library.

[0717] Step 6:

[0718] The terminal displays the received evaluation results to the user. The input is the visualization data sent in step 5, and the output is an interface that the user can view. Using GIS software, points are displayed on a map, and the data is provided in an interactive format.

[0719] Step 7:

[0720] Users provide feedback to the server with actual store opening results data. The input is the performance after opening, and the output is accumulated data that contributes to improving the model. Based on this feedback, the server updates the model and improves the accuracy of recommending potential store locations.

[0721] (Application Example 1)

[0722] 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".

[0723] In existing store opening strategies, even when information on multiple potential locations is gathered, it is difficult to integrate and evaluate it to make appropriate decisions. Furthermore, the lack of systems capable of real-time evaluation makes it difficult to formulate store opening strategies that are suitable for the rapidly changing market environment. Therefore, there is a need for a new system that can practically and efficiently evaluate potential locations and select the optimal location.

[0724] 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.

[0725] In this invention, the server includes means for collecting and preprocessing diverse information; means for extracting features based on this preprocessed information and training a learning model; means for predicting and evaluating potential store locations using the trained learning model; means for enabling users to evaluate multiple potential store locations in real time using a mobile communication terminal; and means for visualizing and comparing information in map and graph formats. This enables users to select the optimal store location based on multifaceted information in real time.

[0726] "Diverse information" refers to various types of data, such as demographic trends, traffic volume, property information, the presence of competing stores, and pedestrian flow trends.

[0727] "Preprocessing" is the process of converting collected information into a format suitable for analysis by imputing missing values, standardizing the format, and removing inaccurate data.

[0728] "Features" are important indicators or properties that are extracted for use in training machine learning models.

[0729] A "learning model" is an algorithm that learns patterns from collected data and uses them to make predictions and evaluations about the future.

[0730] A "trained learning model" is a predictive algorithm that improves its accuracy based on various data, using past successes and failures.

[0731] A "potential location for opening a store" refers to a geographical location that is being assessed for optimal suitability when developing a new business.

[0732] "Real-time" refers to the immediate acquisition, processing, and provision of information and results.

[0733] "Mobile communication terminals" refer to portable electronic devices with communication capabilities, such as smartphones and tablets.

[0734] "Visualization" refers to displaying data and analysis results in a format that is easy for users to understand, such as maps or graphs.

[0735] The system implementing this invention is designed to collect diverse information and use it to evaluate the optimal location for a new store. The server collects diverse information such as population dynamics, traffic volume, property information, the presence of competing stores, and pedestrian flow trends through public databases and APIs, and then performs preprocessing. This preprocessing includes cleaning and standardizing the format of the data using Python.

[0736] Features are extracted from the collected information, and a learning model is trained using Scikit-Learn. This model learns patterns from past successes and failures, and can predict future potential store locations. The trained learning model enables real-time evaluation and is presented on a mobile communication terminal.

[0737] The terminals take the form of smartphones or tablets and visualize evaluation results received from the server in map and graph format. This allows users to visually understand the information and select the optimal store location.

[0738] As a concrete example, a user who wants to open a new cafe uses the app to obtain information on potential locations on their smartphone. Based on the collected information, data such as nighttime traffic volume and the competitive situation in the surrounding area are displayed. Based on this information, the user can make a decision and choose the most suitable location.

[0739] An example of a prompt message is: "To evaluate potential locations for a new cafe, please collect information on surrounding population, traffic volume, and competitors to suggest the optimal location." This system can continuously optimize its store opening strategy by further improving the model based on user feedback.

[0740] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0741] Step 1:

[0742] The server collects diverse information through public databases and APIs. Input information includes demographic data, traffic volume, property information, the presence of competing businesses, and pedestrian flow trends. This data is retrieved using the Python Requests library, and its integrity is checked. The output is a collection of raw data.

[0743] Step 2:

[0744] The server preprocesses the collected data. This process involves cleaning the data by imputing missing values, removing inaccurate data, and standardizing the format. Pandas is used at this stage to output the processed, clean data.

[0745] Step 3:

[0746] The server extracts features from preprocessed data and trains a machine learning model. It uses Scikit-Learn to fit patterns to the data and build the model. The input is preprocessed data, and the output is the trained machine learning model.

[0747] Step 4:

[0748] The server uses a trained learning model to predict and evaluate potential store locations from new data. Specifically, it applies newly input data on potential locations to the model and quantifies the suitability of those locations. The output is a dataset containing evaluation scores.

[0749] Step 5:

[0750] The terminal visualizes the evaluation results received from the server in map and graph format. The input is data containing evaluation scores, which is converted into a visual format using Matplotlib or Folium. The output is maps and graphs displayed in the user interface.

[0751] Step 6:

[0752] Users view evaluation results via their devices and select the optimal location for a new store. This interaction prompts them to provide opinions and send feedback to the server, following the prompt: "To evaluate potential locations for a new cafe, please gather information on surrounding population, traffic volume, and competitors to propose the best location." Input is the evaluation results in maps and graphs, while output is the selected optimal location and the feedback provided.

[0753] 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.

[0754] This invention combines an emotion engine with a system for optimizing store opening strategies. This system recognizes user emotions and provides interaction and feedback according to their emotional state, thereby supporting more effective store opening decisions.

[0755] This system first collects a wide variety of data on a server. This data includes demographics, traffic volume, pedestrian flow, property information, and competitor information. The collected data is preprocessed on the server and formatted into an appropriate format.

[0756] Next, the server extracts features based on the pre-processed data and trains a machine learning model. This model is used to predict and evaluate potential locations for new store openings. The evaluation results are scored, and locations with high commercial suitability are selected.

[0757] Furthermore, the system's main feature, the emotion engine, recognizes the user's emotions through the device. Emotion recognition is performed using technology that detects the user's emotional state from facial expressions and voice using a camera and microphone. The detected emotion data is analyzed on a server and becomes basic data for understanding how the user is reacting to information.

[0758] The device uses the results of the emotion engine's analysis to adjust the information presented to the user and the way they interact in real time. For example, if the user shows frustration, it simplifies the information presentation or provides additional supplementary information to support decision-making. This feedback loop constantly optimizes the user experience.

[0759] For example, if a user is not satisfied with the information presented regarding potential store locations, the device will suggest alternative locations based on data from its emotion engine. It can also provide additional information about locations the user has shown interest in.

[0760] Finally, once user feedback is received, the server readjusts the model parameters based on that feedback to improve the system's prediction accuracy. Through this cyclical process, the system continuously evolves, enabling it to provide users with more accurate and personalized store recommendations.

[0761] The following describes the processing flow.

[0762] Step 1:

[0763] The server collects a wide variety of data from government agencies and private data providers, including demographics, traffic volume, property information, competitive information, and people-to-people data. This data is retrieved through API calls and database queries.

[0764] Step 2:

[0765] The server preprocesses the collected raw data, including imputing missing data, removing outliers, and standardizing data formats. This process includes data cleaning and normalization, preparing the data for analysis.

[0766] Step 3:

[0767] The server extracts features from pre-processed data and trains a machine learning model. This model has the ability to predict potential store locations in a specific region and learns regional trends and patterns.

[0768] Step 4:

[0769] The server uses a trained model to predict potential locations and scores each location. The prediction takes into account factors such as traffic volume, commercial area size, and competitive landscape.

[0770] Step 5:

[0771] The terminal receives evaluation results from the server and visualizes them through a user interface. Commercially promising potential store locations are presented to the user in map and graph format.

[0772] Step 6:

[0773] When users make decisions based on the displayed candidate location information, their emotional state is recognized through facial expressions and voice detected by the emotion engine.

[0774] Step 7:

[0775] The device dynamically adjusts the information it presents and the way it interacts based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will support decision-making by simplifying explanations or providing more detailed data.

[0776] Step 8:

[0777] Users make decisions regarding potential store locations and provide the results and feedback. This feedback is sent to the server as new data.

[0778] Step 9:

[0779] The server uses user feedback to readjust its machine learning models and improve future prediction accuracy. This ensures continuous system improvement.

[0780] (Example 2)

[0781] 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".

[0782] Traditional store opening strategies face the challenge of selecting appropriate locations that fully consider regional characteristics and competitive information. Furthermore, the lack of mechanisms to effectively reflect user sentiment and feedback prevents efficient and effective optimization of store opening strategies.

[0783] 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.

[0784] In this invention, the server includes means for collecting and preprocessing a wide variety of information, means for extracting features based on this preprocessed information and training a machine learning algorithm, and means for acquiring the user's emotional state using emotion recognition technology and adjusting the information provided based on that state. This makes it possible to select the optimal store location considering regional characteristics and competitive information, and further enables the optimization of strategies that reflect user emotions and feedback.

[0785] "Diverse information" refers to a general term for data with various attributes related to store openings, such as demographics, traffic volume, pedestrian flow, property information, and competitor information.

[0786] "Preprocessing" is the process of preparing collected raw data into a format suitable for machine learning models by performing actions such as imputing missing values, removing noise, and normalizing.

[0787] "Feature extraction" is the process of extracting important information from data and generating metrics that models use for learning and prediction.

[0788] A "machine learning algorithm" is a computational method that uses data to learn patterns and perform predictions and classifications.

[0789] "Emotion recognition technology" is a technology that uses cameras and microphones to detect a user's emotional state from their facial expressions and voice.

[0790] An "interface" is a structure that provides a means for a user to interact with a system and input or output information.

[0791] "Algorithm improvement" is the process of adjusting model parameters based on user feedback to improve prediction accuracy and output quality.

[0792] This invention provides a system that predicts optimal store locations in a specific area and optimizes strategies by incorporating user feedback. The system operates through the collaboration of a server, terminals, and users.

[0793] The server is equipped with high-performance computing equipment and network connectivity. The server collects a wide variety of information, including demographic data, traffic data, pedestrian flow analysis data, property information, and competitor store information. To preprocess this data, data shaping, cleaning, and normalization are performed using programming languages ​​such as Python and dedicated libraries.

[0794] The server extracts features from preprocessed data and trains models using machine learning algorithms. It uses open-source software libraries such as Scikit-learn and TensorFlow to build random forests and neural networks. This allows for the prediction and evaluation of potential store locations, taking commercial suitability into account.

[0795] The device provides a user interface and reads the user's emotions from their facial expressions and voice through emotion recognition technology. It acquires emotion data using OpenCV and speech analysis libraries via its camera and microphone. This emotion data is sent to a server and used to adjust the data delivery method according to the user's emotions.

[0796] The system improves the accuracy of its model based on feedback provided by users interacting with the interface and providing comments on the suggested store locations. Users can evaluate potential locations through a simple and intuitive GUI.

[0797] As a concrete example, if a user requests information about potential store locations in a specific area, they might input a prompt to the generating AI model such as: "Please suggest recommended locations for new store openings, taking into account demographics, traffic volume, and the impact of competing stores." Based on this input, the system will present the most suitable candidate locations based on relevant information.

[0798] This makes it possible to select potential store locations that take regional characteristics into account, and to reflect user sentiment and feedback in the strategy in real time.

[0799] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0800] Step 1:

[0801] The server collects a wide variety of information related to regional characteristics. Inputs include demographic data, traffic volume, pedestrian flow, property information, and competitor store information. The server uses Python's pandas library to format this data, performing tasks such as imputing missing values ​​and removing noise. The output is pre-processed data in a format suitable for machine learning models.

[0802] Step 2:

[0803] The server extracts important features based on preprocessed data. The input is the data formatted in step 1. The server uses Scikit-learn to extract features such as population density and traffic patterns from each data point. The output is the feature set used to train the model.

[0804] Step 3:

[0805] The server trains a machine learning model using the extracted features. The input is the set of features extracted in step 2. The server uses TensorFlow to build a neural network and learn the features. The output is the trained model for predicting potential new store locations.

[0806] Step 4:

[0807] The device uses its camera and microphone to recognize the user's emotions. Input consists of the user's facial expressions and voice. The device uses OpenCV and a voice analysis library to infer emotions and sends this data to the server in real time. The output is the user's emotion data.

[0808] Step 5:

[0809] The server analyzes the user's emotional data and adjusts the information provided. The input is the emotional data sent from the terminal in step 4. Based on the user's emotions, the server modifies the information delivery method, for example, by simplifying the presentation to support decision-making. The output is the adjusted information presentation.

[0810] Step 6:

[0811] Users evaluate information and provide feedback through their devices. Input includes evaluations of candidate location information. User feedback is formatted and sent to the server. Output is feedback data for model improvement.

[0812] Step 7:

[0813] The server improves the model's accuracy based on user feedback data. The input consists of the feedback data obtained in step 6 and the trained model. The server retrains the model and adjusts its parameters. The output is the improved predictive model. This process enables the model to provide more accurate and personalized suggestions.

[0814] (Application Example 2)

[0815] 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".

[0816] When selecting potential store locations, it is necessary to consider various factors such as demographics and traffic volume. However, traditional methods fail to adequately consider customer emotions and intuitive reactions, making it difficult to formulate efficient store opening strategies. Furthermore, the sheer volume and complexity of information can cause stress for customers, preventing them from making optimal decisions.

[0817] 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.

[0818] In this invention, the server includes a device for acquiring and pre-processing a wide variety of information, a device for extracting characteristics based on this pre-processed information and training a machine learning model, and a device for recognizing the user's emotional state and adjusting the information presentation method based on feedback. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0819] "Information" refers to a variety of data necessary for the operation and evaluation of the system, such as demographics, traffic volume, and regional characteristics.

[0820] "Preprocessing" refers to data processing that formats acquired information into a state that can be analyzed and converts it into a format suitable for subsequent processing.

[0821] "Characteristics" refer to the features and indicators of data extracted as criteria for evaluating potential store locations.

[0822] A "machine learning model" is a program structure that uses a large amount of data to train algorithms and make specific patterns or predictions.

[0823] A "potential store location area" refers to a region or location that is being considered for opening a new store.

[0824] "Evaluation" is the process of determining the commercial suitability and potential success of a potential store location.

[0825] "Display" refers to the act of a system presenting evaluation results or information to a user.

[0826] A "user" is an individual or organization that operates the system and uses information to formulate store opening strategies.

[0827] "Emotional state" refers to some of the psychological reactions, such as joy, anger, and surprise, that users exhibit in response to the system.

[0828] "Feedback" refers to information based on opinions and reactions from users to the system, which is useful for improving and adjusting the system.

[0829] The system implementing this invention consists of a server that acquires and processes information, and a terminal that recognizes the user's emotional state and adjusts the way information is presented. The server collects diverse information such as demographics, traffic volume, and regional characteristics, and performs preprocessing. It extracts characteristics from the preprocessed data and creates a foundation for training a machine learning model. In this process, it is desirable to use machine learning frameworks such as TensorFlow or PyTorch.

[0830] A trained machine learning model predicts and evaluates potential store locations and outputs the results. The device uses its camera and microphone to recognize the user's emotional state in real time. Libraries such as DeepFace are used for emotion recognition, analyzing emotions from the user's facial expressions and voice.

[0831] The device optimizes the information presented to the user based on recognized emotional data. For example, if the user indicates stress, it provides support by simplifying the information or suggesting alternatives. This process enables flexible information delivery to the user by adjusting interactions according to emotions.

[0832] User feedback is sent to the server, helping to readjust the parameters of the machine learning model. This cyclical feedback loop allows the system to continuously learn and improve its accuracy.

[0833] As a concrete example, consider a scenario where a user considering opening a new store checks information about a specific region on their device. If the user shows interest, the device displays further details on the screen. Conversely, if the user looks confused, the device provides a more concise overview instead.

[0834] An example of a prompt is: "Please explain in detail how to optimize information on potential store locations using emotion recognition. This includes examples of interaction using user facial expression data and candidate locations that consider regional characteristics." Based on this example, the generative AI model will learn specific methods to support optimization that combines emotion analysis and store location strategies.

[0835] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0836] Step 1:

[0837] The server retrieves diverse information such as demographics, traffic volume, and regional characteristics from the web and databases. Its input is raw data obtained from external sources, which is then retrieved in various formats and formatted into a unified format. The output is an analyzable dataset.

[0838] Step 2:

[0839] The server extracts characteristics from preprocessed data and trains a machine learning model. The input is a preprocessed dataset from which geographical characteristics and commercial indicator features are extracted. Using these extracted characteristics, software such as TensorFlow and PyTorch is employed to build and train a machine learning model. The output is the trained model used for prediction.

[0840] Step 3:

[0841] The server uses a trained machine learning model to predict and evaluate potential store locations. The input consists of various data points about a specific region, which are then fed into the model to calculate a commercial suitability score. The output is an evaluation result showing the commercial suitability of each area.

[0842] Step 4:

[0843] The device uses its camera and microphone to recognize the user's emotional state in real time. Inputs include the user's facial expressions and voice, which are then analyzed using the DeepFace library. The output is the user's emotional state (e.g., happiness, anger, surprise, etc.).

[0844] Step 5:

[0845] The device optimizes how information is presented based on the sentiment analysis results. Inputs include the sentiment analysis results and evaluation results from the server, and the device adjusts the information presented to the user based on these. For example, if the user is confused, the information is simplified. The output is the adjusted information display.

[0846] Step 6:

[0847] Users provide feedback on the information provided. The input is the user's reaction to the evaluated potential store locations, which is sent to the system as feedback. The output is feedback data used to improve the system.

[0848] Step 7:

[0849] The server updates the parameters of the machine learning model based on user feedback. By receiving feedback data as input and using it to fine-tune the model, prediction accuracy improves. The output is the updated model.

[0850] 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.

[0851] 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.

[0852] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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."

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] The following is further disclosed regarding the embodiments described above.

[0872] (Claim 1)

[0873] A means of collecting and pre-processing a wide variety of data,

[0874] Based on this preprocessed data, a means is used to extract features and train a machine learning model.

[0875] A method for predicting and evaluating potential store locations using a trained machine learning model,

[0876] A means of presenting evaluation results and providing information to users,

[0877] A means of improving the model based on user feedback,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, comprising an interface that allows a user to perform a simulation.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising an algorithm that optimizes potential store locations by taking into account regional characteristics based on collected data.

[0883] "Example 1"

[0884] (Claim 1)

[0885] A means for automatically collecting diverse data and preprocessing it in a standardized format,

[0886] A means for extracting features based on preprocessed data and training a predictive model,

[0887] A method for analyzing and evaluating candidate regions using a trained predictive model while considering multiple past cases,

[0888] A means of visually presenting evaluated candidate locations and providing information in a way that allows users to intuitively understand geographical information,

[0889] A means to update the predictive model based on user feedback and improve recommendation accuracy,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, comprising an interface that allows the user to compare multiple candidate locations and perform simulations under different scenarios.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising an algorithm that optimizes candidate areas by taking into account regional demographics, traffic trends, and commercial environment based on collected data.

[0895] "Application Example 1"

[0896] (Claim 1)

[0897] A means for collecting and pre-processing diverse information,

[0898] A means of extracting features based on this preprocessed information and training a learning model,

[0899] A method for predicting and evaluating potential store locations using a trained learning model,

[0900] A means of presenting evaluation results and providing information to users,

[0901] A means of improving the model based on user feedback,

[0902] A means for users to evaluate multiple potential store locations in real time using their mobile communication devices,

[0903] Means of visualizing and comparing information in map and graph formats,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, comprising an interface that allows a user to perform actions based on evaluation results.

[0907] (Claim 3)

[0908] The system according to claim 1, comprising means for optimizing potential store locations by taking into account regional characteristics based on collected information.

[0909] "Example 2 of combining an emotion engine"

[0910] (Claim 1)

[0911] A means of collecting and pre-processing a wide variety of information,

[0912] Based on this preprocessed information, features are extracted and a machine learning algorithm is trained.

[0913] A means of predicting and evaluating potential locations using a trained machine learning algorithm,

[0914] A means of acquiring a user's emotional state using emotion recognition technology and adjusting the information provided based on that state,

[0915] A means of providing information to users and obtaining feedback through an interface based on evaluation and the user's emotional state,

[0916] A means of improving the algorithm based on user feedback,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, comprising an interface that allows a user to perform a simulation.

[0920] (Claim 3)

[0921] The system according to claim 1, comprising an algorithm that optimizes location candidates by taking into account regional characteristics based on collected information.

[0922] "Application example 2 when combining with an emotional engine"

[0923] (Claim 1)

[0924] A device that acquires and preprocesses a wide variety of information,

[0925] Based on this pre-processed information, a device is used to extract characteristics and train a machine learning model.

[0926] A device that uses a trained machine learning model to predict and evaluate potential store locations,

[0927] A device that displays evaluation results and provides information to users,

[0928] A device that recognizes the user's emotional state and adjusts the way information is presented based on feedback,

[0929] A device that improves the model based on user feedback,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, which includes an interface that allows a user to perform a simulation and provides further detailed or simplified information.

[0933] (Claim 3)

[0934] The system according to claim 1, comprising an algorithm that optimizes potential store locations by taking into account regional characteristics based on collected information. [Explanation of Symbols]

[0935] 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 for collecting and pre-processing diverse information, A means of extracting features based on this preprocessed information and training a learning model, A method for predicting and evaluating potential store locations using a trained learning model, A means of presenting evaluation results and providing information to users, A means of improving the model based on user feedback, A means for users to evaluate multiple potential store locations in real time using their mobile communication devices, Means of visualizing and comparing information in map and graph formats, A system that includes this.

2. The system according to claim 1, comprising an interface that allows a user to perform actions based on evaluation results.

3. The system according to claim 1, comprising means for optimizing potential store locations by taking into account regional characteristics based on collected information.

Images