system

Abstract

We provide the system. [Solution] Data collection methods for collecting customer data, Analytical tools for analyzing customer trends and preferences based on collected data, A proposal method that suggests the optimal store location based on the analysis results, A means of updating proposals to improve their accuracy using actual sales data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the food truck business, it is difficult to select an effective store location and difficult to appeal to the target audience. Therefore, there is a problem that there is a risk of a decrease in sales due to a mistake in selecting a store location.

Means for Solving the Problems

[0005] The present invention provides a system including a data collection means for collecting customer data, an analysis means for analyzing customer trends and preferences based on the collected data, a proposal means for proposing an optimal store area based on the analysis results, and an update means for improving the accuracy of the proposal using actual sales data, thereby making it possible to identify an effective store location for a food truck.

[0006] "Customer data" refers to information related to individual customers, such as the age, gender, and purchase history of food truck users, and is used to formulate store opening strategies.

[0007] "Data collection means" refers to methods or devices for collecting customer data, local pedestrian flow data, weather data, etc.

[0008] "Analysis means" refers to methods or devices used to analyze customer trends and preferences using collected data, and to utilize this information in store opening strategies.

[0009] "Suggestion method" refers to a method or device for recommending the optimal store location based on the analysis results.

[0010] "Update method" refers to a method or device that uses actual sales data to improve the accuracy of suggestions and enhance the effectiveness of the system. [Brief explanation of the drawing]

[0011] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0012] 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.

[0013] First, the language used in the following description will be explained.

[0014] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the tagged RAM (Random Access Memory) is a memory where information is temporarily stored and is used as a work memory by a processor.

[0016] In the following embodiments, the tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0017] In the following embodiments, the tagged communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0019] [First Embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] As shown in FIG. 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is a system for optimizing the location of food truck operators. This system functions as a comprehensive platform for collecting and analyzing customer data and proposing optimal locations for operation.

[0033] In implementing the system, the server first collects various data related to the store's location, such as local pedestrian traffic data, customer attribute data, weather information, and event information. This data is collected in real time or periodically via APIs or external databases.

[0034] Next, the server uses machine learning algorithms to analyze the collected data. Specifically, it analyzes customer age groups and purchasing preferences, and uses past sales data to evaluate the potential sales in a particular area. This makes it possible to visualize customer trends and predict the effectiveness of opening a new store.

[0035] Based on the analysis, the server suggests optimal store locations to the user. This suggestion takes into account the weekly weather forecast and local event schedules for each area, providing more specific suggestions for potential store locations and time slots.

[0036] After opening a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to update the system's algorithms and serve as a reference for future suggestions. This gradually improves the system's accuracy, enabling more effective suggestions.

[0037] For example, when setting up a stall at a weekend event in a certain area, the server predicts the characteristics of the people attending the event and suggests the optimal time slot and area where increased sales are expected. It also incorporates predictions such as the attendance rate on cloudy days, enabling more planned stall operations.

[0038] This system, equipped with these features, will be an important tool for supporting the store opening strategies of food truck operators and increasing profitability.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server retrieves local pedestrian traffic data, customer attribute data, and weather data from external data sources. This data includes real-time information on people's movements, age groups, gender, and forecast weather.

[0042] Step 2:

[0043] The server preprocesses the acquired data. Specifically, it cleans the data, removes duplicates, and fills in any incomplete data. This process improves the accuracy of subsequent analysis.

[0044] Step 3:

[0045] The server applies machine learning algorithms using pre-processed data. It clusters customer characteristics and purchase patterns to perform sales forecasts for store locations.

[0046] Step 4:

[0047] The server identifies the optimal store location based on the analysis results and generates a report for the user. This report includes recommended store locations, projected sales, and recommended operating hours.

[0048] Step 5:

[0049] Users refer to reports from the server to develop store opening plans. This enables effective store openings and maximizes sales.

[0050] Step 6:

[0051] After opening a store, users send actual sales data and customer feedback from their devices to the server. This allows for an evaluation of the store's performance.

[0052] Step 7:

[0053] The server updates its analysis algorithm based on the actual sales data that has been transmitted. This improves the accuracy of future recommendations and increases the overall value of the system.

[0054] (Example 1)

[0055] 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."

[0056] Mobile vendors are required to optimize their locations and times to maximize sales. However, traditional methods have presented challenges in developing store locations, such as difficulty in forecasting demand based on local foot traffic, event information, and customer attributes, and in creating complex store locations. Furthermore, it has been difficult to develop long-term store locations by integrating weather information and customer feedback.

[0057] 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.

[0058] In this invention, the server includes information acquisition means for collecting pedestrian flow data, customer attribute data, weather information, and event information; analysis means for performing customer behavioral characteristics and demand forecasting based on the collected information; and location suggestion means for suggesting the most effective store locations based on the analysis results. This enables mobile vendors to efficiently formulate data-driven store locations, maximizing sales and improving customer satisfaction.

[0059] "Information acquisition methods" refer to technical techniques for collecting information related to mobile sales operations, such as pedestrian traffic, customer attributes, weather, and events.

[0060] "Analysis means" refers to technologies that perform the process of predicting and evaluating customer behavioral characteristics and market demand based on collected information.

[0061] "Location suggestion method" refers to the process of identifying and suggesting the optimal store location by utilizing analyzed data.

[0062] "Improvement measures" refer to techniques or methods aimed at improving the accuracy of future proposals by using sales information and customer feedback that has actually been collected.

[0063] A "machine learning model" is a data analysis technique that uses algorithms to learn patterns from data and perform future predictions and classifications.

[0064] The embodiment of the present invention relates to an information processing system for optimizing the store location strategy of mobile vendors. Specifically, a server plays the primary role in collecting and processing pedestrian flow data, customer attribute data, weather information, and event information to propose appropriate store locations.

[0065] The server uses location APIs to collect local pedestrian traffic data, and customer attribute data is obtained through marketing databases and customer relationship management software. Weather information is acquired in real time via a weather data API, and event information is received from a local event calendar API. All of the data obtained in this way is aggregated on the server.

[0066] Next, the server uses machine learning models written in programming languages ​​such as Python or R to analyze the data. These models utilize clustering and classification algorithms to predict customer behavioral characteristics and potential market demand from the collected data. This makes it possible to forecast sales in specific areas, while also considering past sales data.

[0067] Users receive suggestions from the server for the optimal store location and time slot. These suggestions take into account factors such as the weekly weather forecast and local event schedules, providing specific and actionable content. By following the server's suggestions, users can make more efficient business decisions.

[0068] After setting up a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to make future store opening suggestions, and the server updates its machine learning model for further accuracy. This continuously improves the effectiveness of the suggestions provided.

[0069] As a concrete example, consider setting up a stall at a local festival held on the weekend. The server predicts the attributes of the people attending the event and suggests the areas and times when the most visitors are expected. It also constructs scenarios that take into account the impact of rain on visitor numbers, enabling appropriate preparation.

[0070] An example of a prompt for the generated AI model would be: "Based on local events scheduled for next month, please indicate the optimal area and time for setting up a food truck. I would especially appreciate suggestions that reflect purchasing trends and weather data." This allows users to conduct concrete and planned store operations based on multifaceted analysis results.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server uses an information acquisition API to obtain pedestrian flow data. In this process, the latitude and longitude information of the target area is passed to the API as input, and the corresponding pedestrian flow data is received as output. This data includes the number of pedestrians and movement trends in the area during a specific time period. The server stores this data in a database and performs preprocessing for use in the next analysis step.

[0074] Step 2:

[0075] The server accesses the marketing database to collect customer attribute data. It uses customer IDs and region codes as inputs and retrieves attribute information such as age group, gender, and purchase history as output. This information is used for customer profiling and integrated into the database to identify specific purchase patterns. The server converts this data into the format required for analysis and stores it.

[0076] Step 3:

[0077] The server obtains weather information through a weather data API. The server takes a regional code and the desired forecast period as input, and receives detailed weather forecast data such as temperature, precipitation, and wind speed as output. This information is particularly important because weather conditions significantly impact store opening plans. The server standardizes the data format to make the acquired weather data available for use within the analysis system.

[0078] Step 4:

[0079] The server retrieves local event information. It requires the local area name and access information to the event calendar as input. The server outputs information such as the date, time, location, and scale of the event. This information is integrated and analyzed with other data because it influences pedestrian flow predictions and customer purchasing behavior.

[0080] Step 5:

[0081] The server runs a machine learning algorithm using the collected data. The input includes pedestrian flow data, customer attributes, weather information, and event information obtained in the previous step. The algorithm analyzes this data to predict the potential impact of opening a store. The output provides suggestions for the optimal store location and time slot. The server generates these suggestions and provides them to the user.

[0082] Step 6:

[0083] The user receives suggestions from the server. These suggestions include specific locations and times where sales are predicted to be maximized. This allows the user to make data-driven decisions.

[0084] Step 7:

[0085] Users input sales data and customer feedback after opening a store via a terminal and send it to the server. Input includes sales figures and customer opinions, and this feedback data is stored on the server as output. The server analyzes this data and uses it to improve algorithms for more accurate future recommendations. This allows the entire system to continuously evolve.

[0086] (Application Example 1)

[0087] 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."

[0088] This invention aims to solve the problem that mobile vendors are unable to efficiently select their sales areas and optimize their business strategies. In particular, it addresses the difficulty of identifying the optimal location and time for setting up a store in real time, especially in urban areas where customer trends and preferences change rapidly.

[0089] 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.

[0090] In this invention, the server includes data collection means for collecting customer information, analysis means for analyzing customer trends and preferences based on the collected information, and proposal means for suggesting the optimal sales area based on the analysis results. This enables mobile vendors to utilize trend information and event information from smart networks to select the optimal sales area in real time.

[0091] "Customer information" refers to personal information and consumption history collected by mobile vendors to identify customer attributes and behavioral patterns.

[0092] "Data collection means" refers to a system component that has hardware or software functions for efficiently collecting customer information and related data from external sources.

[0093] "Analysis means" refers to a system component that uses collected data to analyze customer trends and purchasing tendencies, and derives useful information based on that analysis.

[0094] The "proposal means" refers to the system component that has the function of proposing the optimal sales area and time to mobile vendors based on the data analysis results from the analysis means.

[0095] A "smart network" is an advanced technological infrastructure for providing, collecting, and distributing information in real time via the internet and other networks.

[0096] "Trend information" refers to a collection of data showing the movement, interests, and concerns of customers and the population within a specific region or community, and is used to predict visitor behavior.

[0097] "Event information" refers to data related to schedules and gatherings of people associated with events and activities held in the local area, and is information that influences consumer attraction.

[0098] "Elemental information" refers to data that indicates environmental and market conditions and factors that contribute to sales promotion. This information is useful for understanding phenomena and trends and for developing sales strategies.

[0099] The system for implementing this invention consists of a server equipped with functions for collecting, analyzing, and proposing data, and terminals for receiving and transmitting information. The server collects customer information, trend information, event information, and elemental information from external sources via a network. This utilizes data collection libraries and APIs, such as weather APIs and local event databases.

[0100] The server analyzes the collected data using machine learning algorithms (e.g., RandomForestRegressor). This analysis reveals customer trends and purchasing preferences. The analysis results serve as a basis for suggesting optimal operating areas and times for mobile vendors. Based on the analysis results, the server generates suggestions in real time and notifies the terminal.

[0101] Users receive this information via their devices and conduct sales activities based on the suggestions presented. This system allows users to utilize trend information and environmental factors in real time to efficiently select store locations and times. Furthermore, the system continuously improves the accuracy of suggestions by updating the algorithm on the server side based on actual sales data.

[0102] For example, if an event is scheduled for a weekend in a certain area, the server analyzes pedestrian traffic data related to that event and suggests the optimal location and time for a store to set up shop within that area to the user. In this way, users can develop strategies to efficiently maximize sales.

[0103] Examples of prompts for generative AI models:

[0104] "Please suggest the best time and location for a booth at a local event this weekend. Please take into account past sales data and the profiles of event attendees."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The server collects customer information, trend information, event information, and elemental information from external sources via the network. It uses information obtained from APIs or databases as input. As output, this information is stored as organized datasets. Access to each information source is automated through regular scheduling.

[0108] Step 2:

[0109] The server inputs the collected data into a machine learning algorithm to analyze customer purchasing preferences and behavioral patterns. The input is the organized dataset obtained in Step 1. The output is a modeled result regarding customer trends and potential demand. This analysis uses machine learning libraries, and data processing is performed within the server.

[0110] Step 3:

[0111] The server uses the analysis results to generate optimal sales area and time suggestions and sends them to the user's terminal. The input is the modeled result obtained in step 2. As output, specific store opening suggestion information is generated and notified to the user's terminal. To generate the suggestions, a generative AI model is used to calculate the optimal solution that satisfies various conditions.

[0112] Step 4:

[0113] The user uses a terminal to review the store opening proposal information received from the server. The input is the proposal information sent to the terminal in step 3. As output, a decision is made based on the proposed sales strategy. By executing the specific instructions obtained from this information in the field, the user can efficiently carry out sales activities.

[0114] Step 5:

[0115] Users send actual sales data after business hours as feedback from their terminal to the server. The input is sales information obtained during the day's sales activities. The output is customer feedback data stored on the server. This process is used for updating the data to improve the accuracy of future proposals.

[0116] Step 6:

[0117] The server retrains its machine learning algorithm using feedback data to improve the accuracy of its suggestions. The input is the customer feedback data obtained in step 5. The output is the newly improved model. This allows the server to make more accurate store opening suggestions in the future.

[0118] 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.

[0119] This invention is a system for food truck operators to optimize their store locations and propose effective store locations while also considering user sentiment. This system provides more comprehensive support for store locations by including data collection means, analysis means, proposal means, update means, and sentiment engine.

[0120] In implementing the system, the server first collects local pedestrian flow data, customer attribute data, weather data, and event information. This data is usually obtained through external databases or APIs, but it can also be entered directly by users.

[0121] Next, the server uses an emotion engine to extract and analyze user emotion data from sources such as social media and online reviews. This makes it possible to understand the emotions customers feel towards specific events or products. This emotion data is then analyzed in combination with sales data and foot traffic data.

[0122] The server uses machine learning algorithms to analyze customer trends and potential demand based on this data. In particular, it places emphasis on the impact of customer emotions on sales and customer acquisition, and makes sales forecasts that take emotional data into account.

[0123] Based on the analysis results, the server suggests optimal store locations to the user. It prioritizes suggesting areas and events that evoke positive customer sentiment, providing guidance for formulating specific store opening strategies.

[0124] After opening a store, users send actual sales data, customer feedback, and newly collected sentiment data from their devices to the server. This information is used to update the algorithm of the suggestion method and improve its accuracy for the next time.

[0125] As a concrete example, when setting up a booth at a specific music festival, the server investigates the past emotional data of event attendees. If the analysis reveals that festival attendees have a positive feeling towards a particular food truck, the system will prioritize suggesting that food truck to participate. In this way, strategic booth placement utilizing emotional data becomes possible, and an increase in sales can be expected.

[0126] In this way, the present invention utilizes an emotion engine to provide a comprehensive support system for realizing an effective store opening strategy for food truck businesses.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server collects local pedestrian traffic data, customer attribute data, weather data, and event information from external data sources. This collection process involves retrieving data via APIs and storing it in a database in real time.

[0130] Step 2:

[0131] The server uses an emotion engine to analyze text data from social media and review sites. Applying natural language processing techniques, it extracts emotions from keywords and phrases and classifies them into emotional categories such as positive, negative, and neutral.

[0132] Step 3:

[0133] The server integrates the sentiment data collected in the previous step with sales data and pedestrian flow data for each region, and preprocesses all the data. It performs data normalization and removes outliers to prepare the data for analysis.

[0134] Step 4:

[0135] The server applies machine learning algorithms to calculate customer behavior and the impact of emotions. In doing so, it considers the correlation between past emotional data and sales to build sales forecasting models for each area.

[0136] Step 5:

[0137] The server suggests optimal store locations based on the analysis results. This suggestion includes strategies such as opening stores in areas where emotions are positive and on days with favorable weather forecasts. The suggestions are then generated as a report that users can refer to.

[0138] Step 6:

[0139] Users review the generated reports and develop store opening plans. By considering the suggested areas and time slots and formulating an optimal store opening schedule, they aim to attract customers effectively.

[0140] Step 7:

[0141] After opening a store, users send actual sales data, feedback from new customers, and, if possible, sentiment data from their devices to the server. This provides a new dataset for evaluating the effectiveness of opening a store.

[0142] Step 8:

[0143] The server analyzes newly submitted data and updates its machine learning models and sentiment engine. This update process improves the accuracy of future store location suggestions, enabling more precise and strategic store openings.

[0144] (Example 2)

[0145] 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".

[0146] Traditional store development strategies are primarily based on sales data and basic customer trends, making it difficult to implement strategies that consider customer emotions and latent desires. Furthermore, they lack the ability to dynamically consider local events and weather conditions, resulting in a lack of adaptability in the short term. This invention solves these problems and provides a system that enables food truck businesses and other mobile vendors to implement more effective and emotion-based store development strategies.

[0147] 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.

[0148] In this invention, the server includes data collection means for collecting human behavior data, individual characteristic data, weather data, and event information; sentiment analysis means for extracting sentiment data from social media and online reviews and analyzing the emotions customers have towards specific events or products; and analysis means for analyzing customer trends and potential desires based on the collected data, taking into account the impact of sentiment data on sales. This enables the proposal of effective store locations that take customer emotions into consideration and the construction of a dynamic feedback loop to improve the accuracy of the proposals.

[0149] "Human behavior data" refers to data that shows people's movement and activity patterns, and is used to understand crowds and pedestrian traffic at specific locations and times.

[0150] "Individual characteristic data" refers to individual customer information such as age, gender, and purchase history, and is used to analyze what attributes a particular user has and what products and services they are interested in.

[0151] "Weather data" refers to data that shows weather conditions in a specific region or time, such as temperature, precipitation, and wind speed, and is used as information to take environmental factors into consideration in store opening strategies.

[0152] "Event information" refers to information about local events and special occasions, and is a factor used to analyze the ability to attract people at a specific time and place.

[0153] "Data collection means" refers to technical methods and mechanisms for gathering necessary information through external data provision means, and is used for collecting foundational information within a system.

[0154] "Sentiment analysis tools" are technologies used to evaluate the emotional aspects of texts and statements collected through social media and reviews, quantifying and analyzing how customers feel about specific products or events.

[0155] "Analysis methods" refer to techniques that use collected data to understand customer trends and potential desires, and in particular to quantify and analyze the impact of emotional data on sales.

[0156] The "store location suggestion method" is a system for presenting optimal business locations and strategies based on analysis results, and it identifies and recommends areas preferred by customers by taking emotional data into consideration.

[0157] "Update methods" refer to processes and technical mechanisms for improving the accuracy of system suggestions by incorporating user feedback and sales data.

[0158] This invention is designed to provide a system that enables food truck operators to efficiently identify locations and conduct strategic operations that take customer sentiment into consideration. The system is primarily server-based and includes data collection, sentiment analysis, data analysis, location recommendations, and update procedures.

[0159] The server first collects data on human behavior, individual characteristics, weather, and events. This utilizes public APIs and data providers for data collection. For example, the server might use the OpenWeatherMap API to obtain weather data and human movement information through another appropriate data provider.

[0160] Sentiment analysis is performed on a server. This is achieved by analyzing posts from social media and online reviews. For example, the server uses the Twitter API to obtain the necessary text data and uses a dedicated sentiment analysis engine to extract positive and negative emotions as data.

[0161] Next, the server performs data analysis. It feeds the collected data into a machine learning library such as scikit-learn to analyze customer behavior. In particular, it clarifies the impact of sentiment data on sales and customer acquisition, and optimizes sales forecasts.

[0162] The server makes suggestions for store locations based on the analysis results. This system also provides an interface on the user's device to visualize the suggestions. It is also possible to use the Google® Maps API to visually display preferred areas.

[0163] After opening a store, users send actual sales data and customer feedback to the server via their devices. This information is incorporated into the server's update process to improve the accuracy of suggestions.

[0164] As a concrete example, if a user is considering setting up a stall at a music festival, it is conceivable that the prompt "Suggest a food truck that should be set up based on sentiment data from past attendees of the music festival" would be input to the generative AI model.

[0165] This system allows food truck operators to gather local data in real time and develop efficient store opening strategies that take sentiment into account.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The server collects local human behavior data, individual characteristic data, weather data, and event information. Inputs include data provided by public APIs and data providers. For example, the server might use the OpenWeatherMap API to obtain weather data and another appropriate provider to obtain human flow data. The output includes an informational set that integrates this data.

[0169] Step 2:

[0170] The server collects textual data from social media and online reviews to perform sentiment analysis. Input includes content from posts obtained through sources such as the Twitter API and ReviewTrackers. The server uses a sentiment analysis engine to extract positive or negative emotions through natural language processing and outputs the results as numerical data.

[0171] Step 3:

[0172] The server analyzes customer trends based on the collected dataset. Inputs include previously acquired pedestrian flow data, feature data, weather data, event information, and sentiment data. The server uses machine learning libraries such as scikit-learn to analyze the dataset and extract customer motivation and sales forecast data. This allows it to output analysis results showing the impact of sentiment data on sales and customer acquisition.

[0173] Step 4:

[0174] The server considers the analysis results and suggests optimal store locations to the user. Inputs include sales forecasts and positive sentiment data derived from the analysis. Based on this, the server uses the Google Maps API to visually present specific store locations and generates a suggestion report as output.

[0175] Step 5:

[0176] After opening a store, users send actual sales data and customer feedback to the server via their device. Inputs include actual sales data and customer survey results. The server uses this data in its update process, accumulates data to improve the accuracy of the algorithm, and outputs an updated predictive model to be reflected in future suggestions.

[0177] (Application Example 2)

[0178] 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".

[0179] There is a growing need to develop effective store opening strategies based on changes in customer behavior and customer sentiment. However, conventional methods make it difficult to quickly and appropriately utilize real-time urban pedestrian flow information and event information in store opening strategies. To solve this problem, the present invention aims to provide a system that enables the proposal of smart store opening strategies that respond to dynamically changing environments.

[0180] 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.

[0181] In this invention, the server includes means for collecting customer-related information, means for analyzing customer behavior patterns and preferences based on the collected information, means for recommending the optimal store location based on the analysis results, means for improving the recommendation using actual sales information based on the optimized store location, and means for acquiring urban pedestrian flow information and event information in real time and having a function for optimizing the store location. This makes it possible to provide a rapid and highly accurate store location strategy in response to dynamic environmental changes.

[0182] "Means of collecting customer-related information" refers to systems for acquiring customer behavior patterns, preferences, location information, emotional data, and so on.

[0183] "Means of analyzing customer behavior patterns and preferences based on collected information" refers to algorithms and software that analyze collected data to understand the products, services, and behavioral characteristics that customers prefer.

[0184] "A method for recommending the optimal store location" refers to a system that, based on analysis results, selects and proposes the most suitable store location based on customer needs and current circumstances.

[0185] "Means of improving suggestions using actual sales information based on optimized store locations" refers to a function that analyzes actual sales data and updates the system to make future store location suggestions more accurate.

[0186] "A means of acquiring real-time information on urban pedestrian traffic and events, and having the functionality to optimize store locations" refers to a system that acquires real-time information on people's movement patterns and events in cities, and selects the optimal location for a store.

[0187] This invention is a system that optimizes store opening strategies using information technology, and is designed to respond to the dynamically changing needs and emotions of customers in urban environments. This system consists of a server, terminals, and users, each playing a specific role.

[0188] The server collects customer-related information from both physical and online environments. This collected data includes location information, weather data, event information, and sentiment data obtained from social media. This data is typically retrieved using the Google Places API or the OpenWeatherMap API.

[0189] The server uses Python to analyze information and employs machine learning algorithms such as TENSORFLOW® or PyTorch to analyze customer behavior patterns and preferences. Based on the results of this analysis, it recommends the optimal store location. It also uses the Google Cloud NLP API to analyze sentiment data and makes sales forecasts that take into account the impact of customer sentiment on sales.

[0190] Users check suggested store locations via their smartphones and report actual sales data from their devices to the server. This feedback information is used to improve future store location suggestions.

[0191] As a concrete example, at one music festival, a server analyzes attendees' online posts in real time and extracts positive reactions to specific food trucks. Based on this information, it recommends that users support the food truck's participation in the festival.

[0192] An example of a prompt for a generative AI model is: "Analyze visitor posts at a music festival, identify in real time the types of food trucks and products they favor, and propose a vendor strategy based on that." This prompt allows the AI ​​to quickly provide the information the user requests and support the development of optimal strategies in real time.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The server collects customer-related information via external APIs. This input includes location data, weather data, event information, and social media sentiment data. It uses the Google Places API to obtain pedestrian flow data at the current location and collects weather data through the OpenWeatherMap API. By collecting this data, the system prepares the basic information for suitable times and locations for opening a store.

[0196] Step 2:

[0197] The server performs data analysis using Python based on the collected data. First, it analyzes customer behavior patterns and preferences using machine learning algorithms such as TensorFlow or PyTorch. In this process, the input data is transformed into a model and regional sales forecasts are generated. The output forecast results are used to evaluate the priority of store locations.

[0198] Step 3:

[0199] The server uses the Google Cloud NLP API to analyze sentiment data from collected social media posts. The input includes posts in string format, and text analysis calculates their sentiment scores. This output helps understand customer sentiment towards specific products or events, and, combined with sales forecasts, aids in strategic decision-making.

[0200] Step 4:

[0201] Based on the analysis results, the server uses a generated AI model to suggest the optimal store location to the user. In this process, the AI ​​uses the generated prompt text, taking the analysis data as input, to generate a store location strategy. The suggested store location is then notified to the user's terminal.

[0202] Step 5:

[0203] Users receive proposals via their smartphones and conduct actual sales activities. After sales, users report actual sales data and customer feedback from their devices to the server. This input information is crucial for improving the accuracy of store opening strategies.

[0204] Step 6:

[0205] The server updates its suggestion algorithm based on user feedback. By inputting actual sales data and retraining the machine learning model, the next store opening suggestions become more accurate. The retrained model achieves higher predictive performance in future strategic planning.

[0206] 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.

[0207] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention is a system for optimizing the location of food truck operators. This system functions as a comprehensive platform for collecting and analyzing customer data and proposing optimal locations for operation.

[0223] In implementing the system, the server first collects various data related to the store's location, such as local pedestrian traffic data, customer attribute data, weather information, and event information. This data is collected in real time or periodically via APIs or external databases.

[0224] Next, the server uses machine learning algorithms to analyze the collected data. Specifically, it analyzes customer age groups and purchasing preferences, and uses past sales data to evaluate the potential sales in a particular area. This makes it possible to visualize customer trends and predict the effectiveness of opening a new store.

[0225] Based on the analysis, the server suggests optimal store locations to the user. This suggestion takes into account the weekly weather forecast and local event schedules for each area, providing more specific suggestions for potential store locations and time slots.

[0226] After opening a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to update the system's algorithms and serve as a reference for future suggestions. This gradually improves the system's accuracy, enabling more effective suggestions.

[0227] For example, when setting up a stall at a weekend event in a certain area, the server predicts the characteristics of the people attending the event and suggests the optimal time slot and area where increased sales are expected. It also incorporates predictions such as the attendance rate on cloudy days, enabling more planned stall operations.

[0228] This system, equipped with these features, will be an important tool for supporting the store opening strategies of food truck operators and increasing profitability.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The server retrieves local pedestrian traffic data, customer attribute data, and weather data from external data sources. This data includes real-time information on people's movements, age groups, gender, and forecast weather.

[0232] Step 2:

[0233] The server preprocesses the acquired data. Specifically, it cleans the data, removes duplicates, and fills in any incomplete data. This process improves the accuracy of subsequent analysis.

[0234] Step 3:

[0235] The server applies machine learning algorithms using pre-processed data. It clusters customer characteristics and purchase patterns to perform sales forecasts for store locations.

[0236] Step 4:

[0237] The server identifies the optimal store location based on the analysis results and generates a report for the user. This report includes recommended store locations, projected sales, and recommended operating hours.

[0238] Step 5:

[0239] Users refer to reports from the server to develop store opening plans. This enables effective store openings and maximizes sales.

[0240] Step 6:

[0241] After opening a store, users send actual sales data and customer feedback from their devices to the server. This allows for an evaluation of the store's performance.

[0242] Step 7:

[0243] The server updates its analysis algorithm based on the actual sales data that has been transmitted. This improves the accuracy of future recommendations and increases the overall value of the system.

[0244] (Example 1)

[0245] 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."

[0246] Mobile vendors are required to optimize their locations and times to maximize sales. However, traditional methods have presented challenges in developing store locations, such as difficulty in forecasting demand based on local foot traffic, event information, and customer attributes, and in creating complex store locations. Furthermore, it has been difficult to develop long-term store locations by integrating weather information and customer feedback.

[0247] 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.

[0248] In this invention, the server includes information acquisition means for collecting pedestrian flow data, customer attribute data, weather information, and event information; analysis means for performing customer behavioral characteristics and demand forecasting based on the collected information; and location suggestion means for suggesting the most effective store locations based on the analysis results. This enables mobile vendors to efficiently formulate data-driven store locations, maximizing sales and improving customer satisfaction.

[0249] "Information acquisition methods" refer to technical techniques for collecting information related to mobile sales operations, such as pedestrian traffic, customer attributes, weather, and events.

[0250] "Analysis means" refers to technologies that perform the process of predicting and evaluating customer behavioral characteristics and market demand based on collected information.

[0251] "Location suggestion method" refers to the process of identifying and suggesting the optimal store location by utilizing analyzed data.

[0252] "Improvement measures" refer to techniques or methods aimed at improving the accuracy of future proposals by using sales information and customer feedback that has actually been collected.

[0253] A "machine learning model" is a data analysis technique that uses algorithms to learn patterns from data and perform future predictions and classifications.

[0254] The embodiment of the present invention relates to an information processing system for optimizing the store location strategy of mobile vendors. Specifically, a server plays the primary role in collecting and processing pedestrian flow data, customer attribute data, weather information, and event information to propose appropriate store locations.

[0255] The server uses location APIs to collect local pedestrian traffic data, and customer attribute data is obtained through marketing databases and customer relationship management software. Weather information is acquired in real time via a weather data API, and event information is received from a local event calendar API. All of the data obtained in this way is aggregated on the server.

[0256] Next, the server uses machine learning models written in programming languages ​​such as Python or R to analyze the data. These models utilize clustering and classification algorithms to predict customer behavioral characteristics and potential market demand from the collected data. This makes it possible to forecast sales in specific areas, while also considering past sales data.

[0257] Users receive suggestions from the server for the optimal store location and time slot. These suggestions take into account factors such as the weekly weather forecast and local event schedules, providing specific and actionable content. By following the server's suggestions, users can make more efficient business decisions.

[0258] After setting up a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to make future store opening suggestions, and the server updates its machine learning model for further accuracy. This continuously improves the effectiveness of the suggestions provided.

[0259] As a concrete example, consider setting up a stall at a local festival held on the weekend. The server predicts the attributes of the people attending the event and suggests the areas and times when the most visitors are expected. It also constructs scenarios that take into account the impact of rain on visitor numbers, enabling appropriate preparation.

[0260] An example of a prompt for the generated AI model would be: "Based on local events scheduled for next month, please indicate the optimal area and time for setting up a food truck. I would especially appreciate suggestions that reflect purchasing trends and weather data." This allows users to conduct concrete and planned store operations based on multifaceted analysis results.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The server uses an information acquisition API to obtain pedestrian flow data. In this process, the latitude and longitude information of the target area is passed to the API as input, and the corresponding pedestrian flow data is received as output. This data includes the number of pedestrians and movement trends in the area during a specific time period. The server stores this data in a database and performs preprocessing for use in the next analysis step.

[0264] Step 2:

[0265] The server accesses the marketing database to collect customer attribute data. It uses customer IDs and region codes as inputs and retrieves attribute information such as age group, gender, and purchase history as output. This information is used for customer profiling and integrated into the database to identify specific purchase patterns. The server converts this data into the format required for analysis and stores it.

[0266] Step 3:

[0267] The server obtains weather information through a weather data API. The server takes a regional code and the desired forecast period as input, and receives detailed weather forecast data such as temperature, precipitation, and wind speed as output. This information is particularly important because weather conditions significantly impact store opening plans. The server standardizes the data format to make the acquired weather data available for use within the analysis system.

[0268] Step 4:

[0269] The server retrieves local event information. It requires the local area name and access information to the event calendar as input. The server outputs information such as the date, time, location, and scale of the event. This information is integrated and analyzed with other data because it influences pedestrian flow predictions and customer purchasing behavior.

[0270] Step 5:

[0271] The server runs a machine learning algorithm using the collected data. The input includes pedestrian flow data, customer attributes, weather information, and event information obtained in the previous step. The algorithm analyzes this data to predict the potential impact of opening a store. The output provides suggestions for the optimal store location and time slot. The server generates these suggestions and provides them to the user.

[0272] Step 6:

[0273] The user receives suggestions from the server. These suggestions include specific locations and times where sales are predicted to be maximized. This allows the user to make data-driven decisions.

[0274] Step 7:

[0275] Users input sales data and customer feedback after opening a store via a terminal and send it to the server. Input includes sales figures and customer opinions, and this feedback data is stored on the server as output. The server analyzes this data and uses it to improve algorithms for more accurate future recommendations. This allows the entire system to continuously evolve.

[0276] (Application Example 1)

[0277] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] This invention aims to solve the problem that mobile vendors are unable to efficiently select their sales areas and optimize their business strategies. In particular, it addresses the difficulty of identifying the optimal location and time for setting up a store in real time, especially in urban areas where customer trends and preferences change rapidly.

[0279] 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.

[0280] In this invention, the server includes data collection means for collecting customer information, analysis means for analyzing customer trends and preferences based on the collected information, and proposal means for suggesting the optimal sales area based on the analysis results. This enables mobile vendors to utilize trend information and event information from smart networks to select the optimal sales area in real time.

[0281] "Customer information" refers to personal information and consumption history collected by mobile vendors to identify customer attributes and behavioral patterns.

[0282] "Data collection means" refers to a system component that has hardware or software functions for efficiently collecting customer information and related data from external sources.

[0283] The "analysis means" is a system part that has the function of analyzing customer trends and purchasing tendencies using the collected data and deriving useful information based on it.

[0284] The "proposal means" is a system part equipped with the function of proposing an optimal business area and time to mobile vendors based on the data analysis results by the analysis means.

[0285] The "smart network" is an advanced technical infrastructure for providing information in real time via the Internet or other networks and collecting and distributing information.

[0286] The "trend information" is a collection of data indicating the movement, interests, and concerns of customers and the population within a specific region or community, and is data used to predict the behavior of visitors.

[0287] The "event information" refers to data related to the schedules and gatherings of people related to events and activities held in the region, and is information that affects the customer attraction of consumers.

[0288] The "element information" refers to data indicating the environmental, market conditions, and factors that contribute to sales promotion. This information is useful for understanding phenomena and trends and formulating business strategies.

[0289] The system for implementing this invention consists of a server equipped with the functions of collecting, analyzing, and proposing data, and a terminal for receiving and transmitting information. The server collects customer information, trend information, event information, and element information from external sources through the network. This involves utilizing data collection libraries and APIs and using weather APIs, regional event databases, etc.

[0290] The server analyzes the collected data using machine learning algorithms (e.g., RandomForestRegressor). This analysis reveals customer trends and purchasing preferences. The analysis results serve as a basis for suggesting optimal operating areas and times for mobile vendors. Based on the analysis results, the server generates suggestions in real time and notifies the terminal.

[0291] Users receive this information via their devices and conduct sales activities based on the suggestions presented. This system allows users to utilize trend information and environmental factors in real time to efficiently select store locations and times. Furthermore, the system continuously improves the accuracy of suggestions by updating the algorithm on the server side based on actual sales data.

[0292] For example, if an event is scheduled for a weekend in a certain area, the server analyzes pedestrian traffic data related to that event and suggests the optimal location and time for a store to set up shop within that area to the user. In this way, users can develop strategies to efficiently maximize sales.

[0293] Examples of prompts for generative AI models:

[0294] "Please suggest the best time and location for a booth at a local event this weekend. Please take into account past sales data and the profiles of event attendees."

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The server collects customer information, trend information, event information, and elemental information from external sources via the network. It uses information obtained from APIs or databases as input. As output, this information is stored as organized datasets. Access to each information source is automated through regular scheduling.

[0298] Step 2:

[0299] The server inputs the collected data into a machine learning algorithm to analyze customer purchasing preferences and behavioral patterns. The input is the organized dataset obtained in Step 1. The output is a modeled result regarding customer trends and potential demand. This analysis uses machine learning libraries, and data processing is performed within the server.

[0300] Step 3:

[0301] The server uses the analysis results to generate optimal sales area and time suggestions and sends them to the user's terminal. The input is the modeled result obtained in step 2. As output, specific store opening suggestion information is generated and notified to the user's terminal. To generate the suggestions, a generative AI model is used to calculate the optimal solution that satisfies various conditions.

[0302] Step 4:

[0303] The user uses a terminal to review the store opening proposal information received from the server. The input is the proposal information sent to the terminal in step 3. As output, a decision is made based on the proposed sales strategy. By executing the specific instructions obtained from this information in the field, the user can efficiently carry out sales activities.

[0304] Step 5:

[0305] Users send actual sales data after business hours as feedback from their terminal to the server. The input is sales information obtained during the day's sales activities. The output is customer feedback data stored on the server. This process is used for updating the data to improve the accuracy of future proposals.

[0306] Step 6:

[0307] The server retrains the machine learning algorithm using the feedback data to improve the accuracy of the proposal. The input is the customer feedback data obtained in step 5. The output is a newly improved model. As a result, the server can make more accurate store opening proposals for subsequent times.

[0308] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0309] The present invention is a system for a food truck operator to optimize a store opening area and propose an effective store opening strategy considering the user's emotion. This system includes data collection means, analysis means, proposal means, update means, and an emotion engine, thereby providing more comprehensive store opening support.

[0310] In the implementation of the system, first, the server collects pedestrian flow data, customer attribute data, weather data, and event information of the region. These data are usually obtained through an external database or API, but may also be directly input by the user.

[0311] Next, the server uses the emotion engine to extract and analyze the user's emotion data from social media, online reviews, etc. As a result, it becomes possible to grasp the emotion that the customer has towards a specific event or product. This emotion data is analyzed in combination with sales data and pedestrian flow data.

[0312] The server uses a machine learning algorithm to analyze customer trends and potential demands based on these data. In particular, importance is attached to the influence of the customer's emotion on sales and customer acquisition, and sales prediction considering emotion data is performed.

[0313] Based on the analysis results, the server suggests optimal store locations to the user. It prioritizes suggesting areas and events that evoke positive customer sentiment, providing guidance for formulating specific store opening strategies.

[0314] After opening a store, users send actual sales data, customer feedback, and newly collected sentiment data from their devices to the server. This information is used to update the algorithm of the suggestion method and improve its accuracy for the next time.

[0315] As a concrete example, when setting up a booth at a specific music festival, the server investigates the past emotional data of event attendees. If the analysis reveals that festival attendees have a positive feeling towards a particular food truck, the system will prioritize suggesting that food truck to participate. In this way, strategic booth placement utilizing emotional data becomes possible, and an increase in sales can be expected.

[0316] In this way, the present invention utilizes an emotion engine to provide a comprehensive support system for realizing an effective store opening strategy for food truck businesses.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The server collects local pedestrian traffic data, customer attribute data, weather data, and event information from external data sources. This collection process involves retrieving data via APIs and storing it in a database in real time.

[0320] Step 2:

[0321] The server uses an emotion engine to analyze text data from social media and review sites. Applying natural language processing techniques, it extracts emotions from keywords and phrases and classifies them into emotional categories such as positive, negative, and neutral.

[0322] Step 3:

[0323] The server integrates the sentiment data collected in the previous step with sales data and pedestrian flow data for each region, and preprocesses all the data. It performs data normalization and removes outliers to prepare the data for analysis.

[0324] Step 4:

[0325] The server applies machine learning algorithms to calculate customer behavior and the impact of emotions. In doing so, it considers the correlation between past emotional data and sales to build sales forecasting models for each area.

[0326] Step 5:

[0327] The server suggests optimal store locations based on the analysis results. This suggestion includes strategies such as opening stores in areas where emotions are positive and on days with favorable weather forecasts. The suggestions are then generated as a report that users can refer to.

[0328] Step 6:

[0329] Users review the generated reports and develop store opening plans. By considering the suggested areas and time slots and formulating an optimal store opening schedule, they aim to attract customers effectively.

[0330] Step 7:

[0331] After opening a store, users send actual sales data, feedback from new customers, and, if possible, sentiment data from their devices to the server. This provides a new dataset for evaluating the effectiveness of opening a store.

[0332] Step 8:

[0333] The server analyzes newly submitted data and updates its machine learning models and sentiment engine. This update process improves the accuracy of future store location suggestions, enabling more precise and strategic store openings.

[0334] (Example 2)

[0335] 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".

[0336] Traditional store development strategies are primarily based on sales data and basic customer trends, making it difficult to implement strategies that consider customer emotions and latent desires. Furthermore, they lack the ability to dynamically consider local events and weather conditions, resulting in a lack of adaptability in the short term. This invention solves these problems and provides a system that enables food truck businesses and other mobile vendors to implement more effective and emotion-based store development strategies.

[0337] 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.

[0338] In this invention, the server includes data collection means for collecting human behavior data, individual characteristic data, weather data, and event information; sentiment analysis means for extracting sentiment data from social media and online reviews and analyzing the emotions customers have towards specific events or products; and analysis means for analyzing customer trends and potential desires based on the collected data, taking into account the impact of sentiment data on sales. This enables the proposal of effective store locations that take customer emotions into consideration and the construction of a dynamic feedback loop to improve the accuracy of the proposals.

[0339] "Human behavior data" refers to data that shows people's movement and activity patterns, and is used to understand crowds and pedestrian traffic at specific locations and times.

[0340] "Individual characteristic data" refers to individual customer information such as age, gender, and purchase history, and is used to analyze what attributes a particular user has and what products and services they are interested in.

[0341] "Weather data" refers to data that shows weather conditions in a specific region or time, such as temperature, precipitation, and wind speed, and is used as information to take environmental factors into consideration in store opening strategies.

[0342] "Event information" refers to information about local events and special occasions, and is a factor used to analyze the ability to attract people at a specific time and place.

[0343] "Data collection means" refers to technical methods and mechanisms for gathering necessary information through external data provision means, and is used for collecting foundational information within a system.

[0344] "Sentiment analysis tools" are technologies used to evaluate the emotional aspects of texts and statements collected through social media and reviews, quantifying and analyzing how customers feel about specific products or events.

[0345] "Analysis methods" refer to techniques that use collected data to understand customer trends and potential desires, and in particular to quantify and analyze the impact of emotional data on sales.

[0346] The "store location suggestion method" is a system for presenting optimal business locations and strategies based on analysis results, and it identifies and recommends areas preferred by customers by taking emotional data into consideration.

[0347] "Update methods" refer to processes and technical mechanisms for improving the accuracy of system suggestions by incorporating user feedback and sales data.

[0348] This invention is designed to provide a system that enables food truck operators to efficiently identify locations and conduct strategic operations that take customer sentiment into consideration. The system is primarily server-based and includes data collection, sentiment analysis, data analysis, location recommendations, and update procedures.

[0349] The server first collects data on human behavior, individual characteristics, weather, and events. This utilizes public APIs and data providers for data collection. For example, the server might use the OpenWeatherMap API to obtain weather data and human movement information through another appropriate data provider.

[0350] Sentiment analysis is performed on a server. This is achieved by analyzing posts from social media and online reviews. For example, the server uses the Twitter API to obtain the necessary text data and uses a dedicated sentiment analysis engine to extract positive and negative emotions as data.

[0351] Next, the server performs data analysis. It feeds the collected data into a machine learning library such as scikit-learn to analyze customer behavior. In particular, it clarifies the impact of sentiment data on sales and customer acquisition, and optimizes sales forecasts.

[0352] The server makes suggestions for store locations based on the analysis results. This system also provides an interface on the user's device to visualize the suggestions. It is also possible to use the Google Maps API to visually display preferred areas.

[0353] After opening a store, users send actual sales data and customer feedback to the server via their devices. This information is incorporated into the server's update process to improve the accuracy of suggestions.

[0354] As a concrete example, if a user is considering setting up a stall at a music festival, it is conceivable that the prompt "Suggest a food truck that should be set up based on sentiment data from past attendees of the music festival" would be input to the generative AI model.

[0355] This system allows food truck operators to gather local data in real time and develop efficient store opening strategies that take sentiment into account.

[0356] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0357] Step 1:

[0358] The server collects local human behavior data, individual characteristic data, weather data, and event information. Inputs include data provided by public APIs and data providers. For example, the server might use the OpenWeatherMap API to obtain weather data and another appropriate provider to obtain human flow data. The output includes an informational set that integrates this data.

[0359] Step 2:

[0360] The server collects textual data from social media and online reviews to perform sentiment analysis. Input includes content from posts obtained through sources such as the Twitter API and ReviewTrackers. The server uses a sentiment analysis engine to extract positive or negative emotions through natural language processing and outputs the results as numerical data.

[0361] Step 3:

[0362] The server analyzes customer trends based on the collected dataset. Inputs include previously acquired pedestrian flow data, feature data, weather data, event information, and sentiment data. The server uses machine learning libraries such as scikit-learn to analyze the dataset and extract customer motivation and sales forecast data. This allows it to output analysis results showing the impact of sentiment data on sales and customer acquisition.

[0363] Step 4:

[0364] The server considers the analysis results and suggests optimal store locations to the user. Inputs include sales forecasts and positive sentiment data derived from the analysis. Based on this, the server uses the Google Maps API to visually present specific store locations and generates a suggestion report as output.

[0365] Step 5:

[0366] After opening a store, users send actual sales data and customer feedback to the server via their device. Inputs include actual sales data and customer survey results. The server uses this data in its update process, accumulates data to improve the accuracy of the algorithm, and outputs an updated predictive model to be reflected in future suggestions.

[0367] (Application Example 2)

[0368] 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."

[0369] There is a growing need to develop effective store opening strategies based on changes in customer behavior and customer sentiment. However, conventional methods make it difficult to quickly and appropriately utilize real-time urban pedestrian flow information and event information in store opening strategies. To solve this problem, the present invention aims to provide a system that enables the proposal of smart store opening strategies that respond to dynamically changing environments.

[0370] 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.

[0371] In this invention, the server includes means for collecting customer-related information, means for analyzing customer behavior patterns and preferences based on the collected information, means for recommending the optimal store location based on the analysis results, means for improving the recommendation using actual sales information based on the optimized store location, and means for acquiring urban pedestrian flow information and event information in real time and having a function for optimizing the store location. This makes it possible to provide a rapid and highly accurate store location strategy in response to dynamic environmental changes.

[0372] "Means of collecting customer-related information" refers to systems for acquiring customer behavior patterns, preferences, location information, emotional data, and so on.

[0373] "Means of analyzing customer behavior patterns and preferences based on collected information" refers to algorithms and software that analyze collected data to understand the products, services, and behavioral characteristics that customers prefer.

[0374] "A method for recommending the optimal store location" refers to a system that, based on analysis results, selects and proposes the most suitable store location based on customer needs and current circumstances.

[0375] "Means of improving suggestions using actual sales information based on optimized store locations" refers to a function that analyzes actual sales data and updates the system to make future store location suggestions more accurate.

[0376] "A means of acquiring real-time information on urban pedestrian traffic and events, and having the functionality to optimize store locations" refers to a system that acquires real-time information on people's movement patterns and events in cities, and selects the optimal location for a store.

[0377] This invention is a system that optimizes store opening strategies using information technology, and is designed to respond to the dynamically changing needs and emotions of customers in urban environments. This system consists of a server, terminals, and users, each playing a specific role.

[0378] The server collects customer-related information from both physical and online environments. This collected data includes location information, weather data, event information, and sentiment data obtained from social media. This data is typically retrieved using the Google Places API or the OpenWeatherMap API.

[0379] The server uses Python to analyze information and employs TensorFlow or PyTorch machine learning algorithms to analyze customer behavior patterns and preferences. Based on the results of this analysis, it recommends the optimal store location. It also uses the Google Cloud NLP API to analyze sentiment data and makes sales forecasts that take into account the impact of customer sentiment on sales.

[0380] Users check suggested store locations via their smartphones and report actual sales data from their devices to the server. This feedback information is used to improve future store location suggestions.

[0381] As a concrete example, at one music festival, a server analyzes attendees' online posts in real time and extracts positive reactions to specific food trucks. Based on this information, it recommends that users support the food truck's participation in the festival.

[0382] An example of a prompt for a generative AI model is: "Analyze visitor posts at a music festival, identify in real time the types of food trucks and products they favor, and propose a vendor strategy based on that." This prompt allows the AI ​​to quickly provide the information the user requests and support the development of optimal strategies in real time.

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The server collects customer-related information via external APIs. This input includes location data, weather data, event information, and social media sentiment data. It uses the Google Places API to obtain pedestrian flow data at the current location and collects weather data through the OpenWeatherMap API. By collecting this data, the system prepares the basic information for suitable times and locations for opening a store.

[0386] Step 2:

[0387] The server performs data analysis using Python based on the collected data. First, it analyzes customer behavior patterns and preferences using machine learning algorithms such as TensorFlow or PyTorch. In this process, the input data is transformed into a model and regional sales forecasts are generated. The output forecast results are used to evaluate the priority of store locations.

[0388] Step 3:

[0389] The server uses the Google Cloud NLP API to analyze sentiment data from collected social media posts. The input includes posts in string format, and text analysis calculates their sentiment scores. This output helps understand customer sentiment towards specific products or events, and, combined with sales forecasts, aids in strategic decision-making.

[0390] Step 4:

[0391] Based on the analysis results, the server uses a generated AI model to suggest the optimal store location to the user. In this process, the AI ​​uses the generated prompt text, taking the analysis data as input, to generate a store location strategy. The suggested store location is then notified to the user's terminal.

[0392] Step 5:

[0393] Users receive proposals via their smartphones and conduct actual sales activities. After sales, users report actual sales data and customer feedback from their devices to the server. This input information is crucial for improving the accuracy of store opening strategies.

[0394] Step 6:

[0395] The server updates its suggestion algorithm based on user feedback. By inputting actual sales data and retraining the machine learning model, the next store opening suggestions become more accurate. The retrained model achieves higher predictive performance in future strategic planning.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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".

[0412] This invention is a system for optimizing the location of food truck operators. This system functions as a comprehensive platform for collecting and analyzing customer data and proposing optimal locations for operation.

[0413] In implementing the system, the server first collects various data related to the store's location, such as local pedestrian traffic data, customer attribute data, weather information, and event information. This data is collected in real time or periodically via APIs or external databases.

[0414] Next, the server uses machine learning algorithms to analyze the collected data. Specifically, it analyzes customer age groups and purchasing preferences, and uses past sales data to evaluate the potential sales in a particular area. This makes it possible to visualize customer trends and predict the effectiveness of opening a new store.

[0415] Based on the analysis, the server suggests optimal store locations to the user. This suggestion takes into account the weekly weather forecast and local event schedules for each area, providing more specific suggestions for potential store locations and time slots.

[0416] After opening a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to update the system's algorithms and serve as a reference for future suggestions. This gradually improves the system's accuracy, enabling more effective suggestions.

[0417] For example, when setting up a stall at a weekend event in a certain area, the server predicts the characteristics of the people attending the event and suggests the optimal time slot and area where increased sales are expected. It also incorporates predictions such as the attendance rate on cloudy days, enabling more planned stall operations.

[0418] This system, equipped with these features, will be an important tool for supporting the store opening strategies of food truck operators and increasing profitability.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The server retrieves local pedestrian traffic data, customer attribute data, and weather data from external data sources. This data includes real-time information on people's movements, age groups, gender, and forecast weather.

[0422] Step 2:

[0423] The server preprocesses the acquired data. Specifically, it cleans the data, removes duplicates, and fills in any incomplete data. This process improves the accuracy of subsequent analysis.

[0424] Step 3:

[0425] The server applies machine learning algorithms using pre-processed data. It clusters customer characteristics and purchase patterns to perform sales forecasts for store locations.

[0426] Step 4:

[0427] The server identifies the optimal store location based on the analysis results and generates a report for the user. This report includes recommended store locations, projected sales, and recommended operating hours.

[0428] Step 5:

[0429] Users refer to reports from the server to develop store opening plans. This enables effective store openings and maximizes sales.

[0430] Step 6:

[0431] After opening a store, users send actual sales data and customer feedback from their devices to the server. This allows for an evaluation of the store's performance.

[0432] Step 7:

[0433] The server updates its analysis algorithm based on the actual sales data that has been transmitted. This improves the accuracy of future recommendations and increases the overall value of the system.

[0434] (Example 1)

[0435] 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."

[0436] Mobile vendors are required to optimize their locations and times to maximize sales. However, traditional methods have presented challenges in developing store locations, such as difficulty in forecasting demand based on local foot traffic, event information, and customer attributes, and in creating complex store locations. Furthermore, it has been difficult to develop long-term store locations by integrating weather information and customer feedback.

[0437] 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.

[0438] In this invention, the server includes information acquisition means for collecting pedestrian flow data, customer attribute data, weather information, and event information; analysis means for performing customer behavioral characteristics and demand forecasting based on the collected information; and location suggestion means for suggesting the most effective store locations based on the analysis results. This enables mobile vendors to efficiently formulate data-driven store locations, maximizing sales and improving customer satisfaction.

[0439] "Information acquisition methods" refer to technical techniques for collecting information related to mobile sales operations, such as pedestrian traffic, customer attributes, weather, and events.

[0440] "Analysis means" refers to technologies that perform the process of predicting and evaluating customer behavioral characteristics and market demand based on collected information.

[0441] "Location suggestion method" refers to the process of identifying and suggesting the optimal store location by utilizing analyzed data.

[0442] "Improvement measures" refer to techniques or methods aimed at improving the accuracy of future proposals by using sales information and customer feedback that has actually been collected.

[0443] A "machine learning model" is a data analysis technique that uses algorithms to learn patterns from data and perform future predictions and classifications.

[0444] The embodiment of the present invention relates to an information processing system for optimizing the store location strategy of mobile vendors. Specifically, a server plays the primary role in collecting and processing pedestrian flow data, customer attribute data, weather information, and event information to propose appropriate store locations.

[0445] The server uses location APIs to collect local pedestrian traffic data, and customer attribute data is obtained through marketing databases and customer relationship management software. Weather information is acquired in real time via a weather data API, and event information is received from a local event calendar API. All of the data obtained in this way is aggregated on the server.

[0446] Next, the server uses machine learning models written in programming languages ​​such as Python or R to analyze the data. These models utilize clustering and classification algorithms to predict customer behavioral characteristics and potential market demand from the collected data. This makes it possible to forecast sales in specific areas, while also considering past sales data.

[0447] Users receive suggestions from the server for the optimal store location and time slot. These suggestions take into account factors such as the weekly weather forecast and local event schedules, providing specific and actionable content. By following the server's suggestions, users can make more efficient business decisions.

[0448] After setting up a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to make future store opening suggestions, and the server updates its machine learning model for further accuracy. This continuously improves the effectiveness of the suggestions provided.

[0449] As a concrete example, consider setting up a stall at a local festival held on the weekend. The server predicts the attributes of the people attending the event and suggests the areas and times when the most visitors are expected. It also constructs scenarios that take into account the impact of rain on visitor numbers, enabling appropriate preparation.

[0450] An example of a prompt for the generated AI model would be: "Based on local events scheduled for next month, please indicate the optimal area and time for setting up a food truck. I would especially appreciate suggestions that reflect purchasing trends and weather data." This allows users to conduct concrete and planned store operations based on multifaceted analysis results.

[0451] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0452] Step 1:

[0453] The server uses an information acquisition API to obtain pedestrian flow data. In this process, the latitude and longitude information of the target area is passed to the API as input, and the corresponding pedestrian flow data is received as output. This data includes the number of pedestrians and movement trends in the area during a specific time period. The server stores this data in a database and performs preprocessing for use in the next analysis step.

[0454] Step 2:

[0455] The server accesses the marketing database to collect customer attribute data. It uses customer IDs and region codes as inputs and retrieves attribute information such as age group, gender, and purchase history as output. This information is used for customer profiling and integrated into the database to identify specific purchase patterns. The server converts this data into the format required for analysis and stores it.

[0456] Step 3:

[0457] The server obtains weather information through a weather data API. The server takes a regional code and the desired forecast period as input, and receives detailed weather forecast data such as temperature, precipitation, and wind speed as output. This information is particularly important because weather conditions significantly impact store opening plans. The server standardizes the data format to make the acquired weather data available for use within the analysis system.

[0458] Step 4:

[0459] The server retrieves local event information. It requires the local area name and access information to the event calendar as input. The server outputs information such as the date, time, location, and scale of the event. This information is integrated and analyzed with other data because it influences pedestrian flow predictions and customer purchasing behavior.

[0460] Step 5:

[0461] The server runs a machine learning algorithm using the collected data. The input includes pedestrian flow data, customer attributes, weather information, and event information obtained in the previous step. The algorithm analyzes this data to predict the potential impact of opening a store. The output provides suggestions for the optimal store location and time slot. The server generates these suggestions and provides them to the user.

[0462] Step 6:

[0463] The user receives suggestions from the server. These suggestions include specific locations and times where sales are predicted to be maximized. This allows the user to make data-driven decisions.

[0464] Step 7:

[0465] Users input sales data and customer feedback after opening a store via a terminal and send it to the server. Input includes sales figures and customer opinions, and this feedback data is stored on the server as output. The server analyzes this data and uses it to improve algorithms for more accurate future recommendations. This allows the entire system to continuously evolve.

[0466] (Application Example 1)

[0467] 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."

[0468] This invention aims to solve the problem that mobile vendors are unable to efficiently select their sales areas and optimize their business strategies. In particular, it addresses the difficulty of identifying the optimal location and time for setting up a store in real time, especially in urban areas where customer trends and preferences change rapidly.

[0469] 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.

[0470] In this invention, the server includes data collection means for collecting customer information, analysis means for analyzing customer trends and preferences based on the collected information, and proposal means for suggesting the optimal sales area based on the analysis results. This enables mobile vendors to utilize trend information and event information from smart networks to select the optimal sales area in real time.

[0471] "Customer information" refers to personal information and consumption history collected by mobile vendors to identify customer attributes and behavioral patterns.

[0472] "Data collection means" refers to a system component that has hardware or software functions for efficiently collecting customer information and related data from external sources.

[0473] "Analysis means" refers to a system component that uses collected data to analyze customer trends and purchasing tendencies, and derives useful information based on that analysis.

[0474] The "proposal means" refers to the system component that has the function of proposing the optimal sales area and time to mobile vendors based on the data analysis results from the analysis means.

[0475] A "smart network" is an advanced technological infrastructure for providing, collecting, and distributing information in real time via the internet and other networks.

[0476] "Trend information" refers to a collection of data showing the movement, interests, and concerns of customers and the population within a specific region or community, and is used to predict visitor behavior.

[0477] "Event information" refers to data related to schedules and gatherings of people associated with events and activities held in the local area, and is information that influences consumer attraction.

[0478] "Elemental information" refers to data that indicates environmental and market conditions and factors that contribute to sales promotion. This information is useful for understanding phenomena and trends and for developing sales strategies.

[0479] The system for implementing this invention consists of a server equipped with functions for collecting, analyzing, and proposing data, and terminals for receiving and transmitting information. The server collects customer information, trend information, event information, and elemental information from external sources via a network. This utilizes data collection libraries and APIs, such as weather APIs and local event databases.

[0480] The server analyzes the collected data using machine learning algorithms (e.g., RandomForestRegressor). This analysis reveals customer trends and purchasing preferences. The analysis results serve as a basis for suggesting optimal operating areas and times for mobile vendors. Based on the analysis results, the server generates suggestions in real time and notifies the terminal.

[0481] Users receive this information via their devices and conduct sales activities based on the suggestions presented. This system allows users to utilize trend information and environmental factors in real time to efficiently select store locations and times. Furthermore, the system continuously improves the accuracy of suggestions by updating the algorithm on the server side based on actual sales data.

[0482] For example, if an event is scheduled for a weekend in a certain area, the server analyzes pedestrian traffic data related to that event and suggests the optimal location and time for a store to set up shop within that area to the user. In this way, users can develop strategies to efficiently maximize sales.

[0483] Examples of prompts for generative AI models:

[0484] "Please suggest the best time and location for a booth at a local event this weekend. Please take into account past sales data and the profiles of event attendees."

[0485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0486] Step 1:

[0487] The server collects customer information, trend information, event information, and elemental information from external sources via the network. It uses information obtained from APIs or databases as input. As output, this information is stored as organized datasets. Access to each information source is automated through regular scheduling.

[0488] Step 2:

[0489] The server inputs the collected data into a machine learning algorithm to analyze customer purchasing preferences and behavioral patterns. The input is the organized dataset obtained in Step 1. The output is a modeled result regarding customer trends and potential demand. This analysis uses machine learning libraries, and data processing is performed within the server.

[0490] Step 3:

[0491] The server uses the analysis results to generate optimal sales area and time suggestions and sends them to the user's terminal. The input is the modeled result obtained in step 2. As output, specific store opening suggestion information is generated and notified to the user's terminal. To generate the suggestions, a generative AI model is used to calculate the optimal solution that satisfies various conditions.

[0492] Step 4:

[0493] The user uses a terminal to review the store opening proposal information received from the server. The input is the proposal information sent to the terminal in step 3. As output, a decision is made based on the proposed sales strategy. By executing the specific instructions obtained from this information in the field, the user can efficiently carry out sales activities.

[0494] Step 5:

[0495] Users send actual sales data after business hours as feedback from their terminal to the server. The input is sales information obtained during the day's sales activities. The output is customer feedback data stored on the server. This process is used for updating the data to improve the accuracy of future proposals.

[0496] Step 6:

[0497] The server retrains its machine learning algorithm using feedback data to improve the accuracy of its suggestions. The input is the customer feedback data obtained in step 5. The output is the newly improved model. This allows the server to make more accurate store opening suggestions in the future.

[0498] 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.

[0499] This invention is a system for food truck operators to optimize their store locations and propose effective store locations while also considering user sentiment. This system provides more comprehensive support for store locations by including data collection means, analysis means, proposal means, update means, and sentiment engine.

[0500] In implementing the system, the server first collects local pedestrian flow data, customer attribute data, weather data, and event information. This data is usually obtained through external databases or APIs, but it can also be entered directly by users.

[0501] Next, the server uses an emotion engine to extract and analyze user emotion data from sources such as social media and online reviews. This makes it possible to understand the emotions customers feel towards specific events or products. This emotion data is then analyzed in combination with sales data and foot traffic data.

[0502] The server uses machine learning algorithms to analyze customer trends and potential demand based on this data. In particular, it places emphasis on the impact of customer emotions on sales and customer acquisition, and makes sales forecasts that take emotional data into account.

[0503] Based on the analysis results, the server suggests optimal store locations to the user. It prioritizes suggesting areas and events that evoke positive customer sentiment, providing guidance for formulating specific store opening strategies.

[0504] After opening a store, users send actual sales data, customer feedback, and newly collected sentiment data from their devices to the server. This information is used to update the algorithm of the suggestion method and improve its accuracy for the next time.

[0505] As a concrete example, when setting up a booth at a specific music festival, the server investigates the past emotional data of event attendees. If the analysis reveals that festival attendees have a positive feeling towards a particular food truck, the system will prioritize suggesting that food truck to participate. In this way, strategic booth placement utilizing emotional data becomes possible, and an increase in sales can be expected.

[0506] In this way, the present invention utilizes an emotion engine to provide a comprehensive support system for realizing an effective store opening strategy for food truck businesses.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The server collects local pedestrian traffic data, customer attribute data, weather data, and event information from external data sources. This collection process involves retrieving data via APIs and storing it in a database in real time.

[0510] Step 2:

[0511] The server uses an emotion engine to analyze text data from social media and review sites. Applying natural language processing techniques, it extracts emotions from keywords and phrases and classifies them into emotional categories such as positive, negative, and neutral.

[0512] Step 3:

[0513] The server integrates the sentiment data collected in the previous step with sales data and pedestrian flow data for each region, and preprocesses all the data. It performs data normalization and removes outliers to prepare the data for analysis.

[0514] Step 4:

[0515] The server applies machine learning algorithms to calculate customer behavior and the impact of emotions. In doing so, it considers the correlation between past emotional data and sales to build sales forecasting models for each area.

[0516] Step 5:

[0517] The server suggests optimal store locations based on the analysis results. This suggestion includes strategies such as opening stores in areas where emotions are positive and on days with favorable weather forecasts. The suggestions are then generated as a report that users can refer to.

[0518] Step 6:

[0519] Users review the generated reports and develop store opening plans. By considering the suggested areas and time slots and formulating an optimal store opening schedule, they aim to attract customers effectively.

[0520] Step 7:

[0521] After opening a store, users send actual sales data, feedback from new customers, and, if possible, sentiment data from their devices to the server. This provides a new dataset for evaluating the effectiveness of opening a store.

[0522] Step 8:

[0523] The server analyzes newly submitted data and updates its machine learning models and sentiment engine. This update process improves the accuracy of future store location suggestions, enabling more precise and strategic store openings.

[0524] (Example 2)

[0525] 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."

[0526] Traditional store development strategies are primarily based on sales data and basic customer trends, making it difficult to implement strategies that consider customer emotions and latent desires. Furthermore, they lack the ability to dynamically consider local events and weather conditions, resulting in a lack of adaptability in the short term. This invention solves these problems and provides a system that enables food truck businesses and other mobile vendors to implement more effective and emotion-based store development strategies.

[0527] 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.

[0528] In this invention, the server includes data collection means for collecting human behavior data, individual characteristic data, weather data, and event information; sentiment analysis means for extracting sentiment data from social media and online reviews and analyzing the emotions customers have towards specific events or products; and analysis means for analyzing customer trends and potential desires based on the collected data, taking into account the impact of sentiment data on sales. This enables the proposal of effective store locations that take customer emotions into consideration and the construction of a dynamic feedback loop to improve the accuracy of the proposals.

[0529] "Human behavior data" refers to data that shows people's movement and activity patterns, and is used to understand crowds and pedestrian traffic at specific locations and times.

[0530] "Individual characteristic data" refers to individual customer information such as age, gender, and purchase history, and is used to analyze what attributes a particular user has and what products and services they are interested in.

[0531] "Weather data" refers to data that shows weather conditions in a specific region or time, such as temperature, precipitation, and wind speed, and is used as information to take environmental factors into consideration in store opening strategies.

[0532] "Event information" refers to information about local events and special occasions, and is a factor used to analyze the ability to attract people at a specific time and place.

[0533] "Data collection means" refers to technical methods and mechanisms for gathering necessary information through external data provision means, and is used for collecting foundational information within a system.

[0534] "Sentiment analysis tools" are technologies used to evaluate the emotional aspects of texts and statements collected through social media and reviews, quantifying and analyzing how customers feel about specific products or events.

[0535] "Analysis methods" refer to techniques that use collected data to understand customer trends and potential desires, and in particular to quantify and analyze the impact of emotional data on sales.

[0536] The "store location suggestion method" is a system for presenting optimal business locations and strategies based on analysis results, and it identifies and recommends areas preferred by customers by taking emotional data into consideration.

[0537] "Update methods" refer to processes and technical mechanisms for improving the accuracy of system suggestions by incorporating user feedback and sales data.

[0538] This invention is designed to provide a system that enables food truck operators to efficiently identify locations and conduct strategic operations that take customer sentiment into consideration. The system is primarily server-based and includes data collection, sentiment analysis, data analysis, location recommendations, and update procedures.

[0539] The server first collects data on human behavior, individual characteristics, weather, and events. This utilizes public APIs and data providers for data collection. For example, the server might use the OpenWeatherMap API to obtain weather data and human movement information through another appropriate data provider.

[0540] Sentiment analysis is performed on a server. This is achieved by analyzing posts from social media and online reviews. For example, the server uses the Twitter API to obtain the necessary text data and uses a dedicated sentiment analysis engine to extract positive and negative emotions as data.

[0541] Next, the server performs data analysis. It feeds the collected data into a machine learning library such as scikit-learn to analyze customer behavior. In particular, it clarifies the impact of sentiment data on sales and customer acquisition, and optimizes sales forecasts.

[0542] The server makes suggestions for store locations based on the analysis results. This system also provides an interface on the user's device to visualize the suggestions. It is also possible to use the Google Maps API to visually display preferred areas.

[0543] After opening a store, users send actual sales data and customer feedback to the server via their devices. This information is incorporated into the server's update process to improve the accuracy of suggestions.

[0544] As a concrete example, if a user is considering setting up a stall at a music festival, it is conceivable that the prompt "Suggest a food truck that should be set up based on sentiment data from past attendees of the music festival" would be input to the generative AI model.

[0545] This system allows food truck operators to gather local data in real time and develop efficient store opening strategies that take sentiment into account.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The server collects local human behavior data, individual characteristic data, weather data, and event information. Inputs include data provided by public APIs and data providers. For example, the server might use the OpenWeatherMap API to obtain weather data and another appropriate provider to obtain human flow data. The output includes an informational set that integrates this data.

[0549] Step 2:

[0550] The server collects textual data from social media and online reviews to perform sentiment analysis. Input includes content from posts obtained through sources such as the Twitter API and ReviewTrackers. The server uses a sentiment analysis engine to extract positive or negative emotions through natural language processing and outputs the results as numerical data.

[0551] Step 3:

[0552] The server analyzes customer trends based on the collected dataset. Inputs include previously acquired pedestrian flow data, feature data, weather data, event information, and sentiment data. The server uses machine learning libraries such as scikit-learn to analyze the dataset and extract customer motivation and sales forecast data. This allows it to output analysis results showing the impact of sentiment data on sales and customer acquisition.

[0553] Step 4:

[0554] The server considers the analysis results and suggests optimal store locations to the user. Inputs include sales forecasts and positive sentiment data derived from the analysis. Based on this, the server uses the Google Maps API to visually present specific store locations and generates a suggestion report as output.

[0555] Step 5:

[0556] After opening a store, users send actual sales data and customer feedback to the server via their device. Inputs include actual sales data and customer survey results. The server uses this data in its update process, accumulates data to improve the accuracy of the algorithm, and outputs an updated predictive model to be reflected in future suggestions.

[0557] (Application Example 2)

[0558] 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."

[0559] There is a growing need to develop effective store opening strategies based on changes in customer behavior and customer sentiment. However, conventional methods make it difficult to quickly and appropriately utilize real-time urban pedestrian flow information and event information in store opening strategies. To solve this problem, the present invention aims to provide a system that enables the proposal of smart store opening strategies that respond to dynamically changing environments.

[0560] 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.

[0561] In this invention, the server includes means for collecting customer-related information, means for analyzing customer behavior patterns and preferences based on the collected information, means for recommending the optimal store location based on the analysis results, means for improving the recommendation using actual sales information based on the optimized store location, and means for acquiring urban pedestrian flow information and event information in real time and having a function for optimizing the store location. This makes it possible to provide a rapid and highly accurate store location strategy in response to dynamic environmental changes.

[0562] "Means of collecting customer-related information" refers to systems for acquiring customer behavior patterns, preferences, location information, emotional data, and so on.

[0563] "Means of analyzing customer behavior patterns and preferences based on collected information" refers to algorithms and software that analyze collected data to understand the products, services, and behavioral characteristics that customers prefer.

[0564] "A method for recommending the optimal store location" refers to a system that, based on analysis results, selects and proposes the most suitable store location based on customer needs and current circumstances.

[0565] "Means of improving suggestions using actual sales information based on optimized store locations" refers to a function that analyzes actual sales data and updates the system to make future store location suggestions more accurate.

[0566] "A means of acquiring real-time information on urban pedestrian traffic and events, and having the functionality to optimize store locations" refers to a system that acquires real-time information on people's movement patterns and events in cities, and selects the optimal location for a store.

[0567] This invention is a system that optimizes store opening strategies using information technology, and is designed to respond to the dynamically changing needs and emotions of customers in urban environments. This system consists of a server, terminals, and users, each playing a specific role.

[0568] The server collects customer-related information from both physical and online environments. This collected data includes location information, weather data, event information, and sentiment data obtained from social media. This data is typically retrieved using the Google Places API or the OpenWeatherMap API.

[0569] The server uses Python to analyze information and employs TensorFlow or PyTorch machine learning algorithms to analyze customer behavior patterns and preferences. Based on the results of this analysis, it recommends the optimal store location. It also uses the Google Cloud NLP API to analyze sentiment data and makes sales forecasts that take into account the impact of customer sentiment on sales.

[0570] Users check suggested store locations via their smartphones and report actual sales data from their devices to the server. This feedback information is used to improve future store location suggestions.

[0571] As a concrete example, at one music festival, a server analyzes attendees' online posts in real time and extracts positive reactions to specific food trucks. Based on this information, it recommends that users support the food truck's participation in the festival.

[0572] An example of a prompt for a generative AI model is: "Analyze visitor posts at a music festival, identify in real time the types of food trucks and products they favor, and propose a vendor strategy based on that." This prompt allows the AI ​​to quickly provide the information the user requests and support the development of optimal strategies in real time.

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The server collects customer-related information via external APIs. This input includes location data, weather data, event information, and social media sentiment data. It uses the Google Places API to obtain pedestrian flow data at the current location and collects weather data through the OpenWeatherMap API. By collecting this data, the system prepares the basic information for suitable times and locations for opening a store.

[0576] Step 2:

[0577] The server performs data analysis using Python based on the collected data. First, it analyzes customer behavior patterns and preferences using machine learning algorithms such as TensorFlow or PyTorch. In this process, the input data is transformed into a model and regional sales forecasts are generated. The output forecast results are used to evaluate the priority of store locations.

[0578] Step 3:

[0579] The server uses the Google Cloud NLP API to analyze sentiment data from collected social media posts. The input includes posts in string format, and text analysis calculates their sentiment scores. This output helps understand customer sentiment towards specific products or events, and, combined with sales forecasts, aids in strategic decision-making.

[0580] Step 4:

[0581] Based on the analysis results, the server uses a generated AI model to suggest the optimal store location to the user. In this process, the AI ​​uses the generated prompt text, taking the analysis data as input, to generate a store location strategy. The suggested store location is then notified to the user's terminal.

[0582] Step 5:

[0583] Users receive proposals via their smartphones and conduct actual sales activities. After sales, users report actual sales data and customer feedback from their devices to the server. This input information is crucial for improving the accuracy of store opening strategies.

[0584] Step 6:

[0585] The server updates its suggestion algorithm based on user feedback. By inputting actual sales data and retraining the machine learning model, the next store opening suggestions become more accurate. The retrained model achieves higher predictive performance in future strategic planning.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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".

[0603] This invention is a system for optimizing the location of food truck operators. This system functions as a comprehensive platform for collecting and analyzing customer data and proposing optimal locations for operation.

[0604] In implementing the system, the server first collects various data related to the store's location, such as local pedestrian traffic data, customer attribute data, weather information, and event information. This data is collected in real time or periodically via APIs or external databases.

[0605] Next, the server uses machine learning algorithms to analyze the collected data. Specifically, it analyzes customer age groups and purchasing preferences, and uses past sales data to evaluate the potential sales in a particular area. This makes it possible to visualize customer trends and predict the effectiveness of opening a new store.

[0606] Based on the analysis, the server suggests optimal store locations to the user. This suggestion takes into account the weekly weather forecast and local event schedules for each area, providing more specific suggestions for potential store locations and time slots.

[0607] After opening a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to update the system's algorithms and serve as a reference for future suggestions. This gradually improves the system's accuracy, enabling more effective suggestions.

[0608] For example, when setting up a stall at a weekend event in a certain area, the server predicts the characteristics of the people attending the event and suggests the optimal time slot and area where increased sales are expected. It also incorporates predictions such as the attendance rate on cloudy days, enabling more planned stall operations.

[0609] This system, equipped with these features, will be an important tool for supporting the store opening strategies of food truck operators and increasing profitability.

[0610] The following describes the processing flow.

[0611] Step 1:

[0612] The server retrieves local pedestrian traffic data, customer attribute data, and weather data from external data sources. This data includes real-time information on people's movements, age groups, gender, and forecast weather.

[0613] Step 2:

[0614] The server preprocesses the acquired data. Specifically, it cleans the data, removes duplicates, and fills in any incomplete data. This process improves the accuracy of subsequent analysis.

[0615] Step 3:

[0616] The server applies machine learning algorithms using pre-processed data. It clusters customer characteristics and purchase patterns to perform sales forecasts for store locations.

[0617] Step 4:

[0618] The server identifies the optimal store location based on the analysis results and generates a report for the user. This report includes recommended store locations, projected sales, and recommended operating hours.

[0619] Step 5:

[0620] Users refer to reports from the server to develop store opening plans. This enables effective store openings and maximizes sales.

[0621] Step 6:

[0622] After opening a store, users send actual sales data and customer feedback from their devices to the server. This allows for an evaluation of the store's performance.

[0623] Step 7:

[0624] The server updates its analysis algorithm based on the actual sales data that has been transmitted. This improves the accuracy of future recommendations and increases the overall value of the system.

[0625] (Example 1)

[0626] 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".

[0627] Mobile vendors are required to optimize their locations and times to maximize sales. However, traditional methods have presented challenges in developing store locations, such as difficulty in forecasting demand based on local foot traffic, event information, and customer attributes, and in creating complex store locations. Furthermore, it has been difficult to develop long-term store locations by integrating weather information and customer feedback.

[0628] 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.

[0629] In this invention, the server includes information acquisition means for collecting pedestrian flow data, customer attribute data, weather information, and event information; analysis means for performing customer behavioral characteristics and demand forecasting based on the collected information; and location suggestion means for suggesting the most effective store locations based on the analysis results. This enables mobile vendors to efficiently formulate data-driven store locations, maximizing sales and improving customer satisfaction.

[0630] "Information acquisition methods" refer to technical techniques for collecting information related to mobile sales operations, such as pedestrian traffic, customer attributes, weather, and events.

[0631] "Analysis means" refers to technologies that perform the process of predicting and evaluating customer behavioral characteristics and market demand based on collected information.

[0632] "Location suggestion method" refers to the process of identifying and suggesting the optimal store location by utilizing analyzed data.

[0633] "Improvement measures" refer to techniques or methods aimed at improving the accuracy of future proposals by using sales information and customer feedback that has actually been collected.

[0634] A "machine learning model" is a data analysis technique that uses algorithms to learn patterns from data and perform future predictions and classifications.

[0635] The embodiment of the present invention relates to an information processing system for optimizing the store location strategy of mobile vendors. Specifically, a server plays the primary role in collecting and processing pedestrian flow data, customer attribute data, weather information, and event information to propose appropriate store locations.

[0636] The server uses location APIs to collect local pedestrian traffic data, and customer attribute data is obtained through marketing databases and customer relationship management software. Weather information is acquired in real time via a weather data API, and event information is received from a local event calendar API. All of the data obtained in this way is aggregated on the server.

[0637] Next, the server uses machine learning models written in programming languages ​​such as Python or R to analyze the data. These models utilize clustering and classification algorithms to predict customer behavioral characteristics and potential market demand from the collected data. This makes it possible to forecast sales in specific areas, while also considering past sales data.

[0638] Users receive suggestions from the server for the optimal store location and time slot. These suggestions take into account factors such as the weekly weather forecast and local event schedules, providing specific and actionable content. By following the server's suggestions, users can make more efficient business decisions.

[0639] After setting up a store, users use their devices to send actual sales data and customer feedback to the server. This data is used to make future store opening suggestions, and the server updates its machine learning model for further accuracy. This continuously improves the effectiveness of the suggestions provided.

[0640] As a concrete example, consider setting up a stall at a local festival held on the weekend. The server predicts the attributes of the people attending the event and suggests the areas and times when the most visitors are expected. It also constructs scenarios that take into account the impact of rain on visitor numbers, enabling appropriate preparation.

[0641] An example of a prompt for the generated AI model would be: "Based on local events scheduled for next month, please indicate the optimal area and time for setting up a food truck. I would especially appreciate suggestions that reflect purchasing trends and weather data." This allows users to conduct concrete and planned store operations based on multifaceted analysis results.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] The server uses an information acquisition API to obtain pedestrian flow data. In this process, the latitude and longitude information of the target area is passed to the API as input, and the corresponding pedestrian flow data is received as output. This data includes the number of pedestrians and movement trends in the area during a specific time period. The server stores this data in a database and performs preprocessing for use in the next analysis step.

[0645] Step 2:

[0646] The server accesses the marketing database to collect customer attribute data. It uses customer IDs and region codes as inputs and retrieves attribute information such as age group, gender, and purchase history as output. This information is used for customer profiling and integrated into the database to identify specific purchase patterns. The server converts this data into the format required for analysis and stores it.

[0647] Step 3:

[0648] The server obtains weather information through a weather data API. The server takes a regional code and the desired forecast period as input, and receives detailed weather forecast data such as temperature, precipitation, and wind speed as output. This information is particularly important because weather conditions significantly impact store opening plans. The server standardizes the data format to make the acquired weather data available for use within the analysis system.

[0649] Step 4:

[0650] The server retrieves local event information. It requires the local area name and access information to the event calendar as input. The server outputs information such as the date, time, location, and scale of the event. This information is integrated and analyzed with other data because it influences pedestrian flow predictions and customer purchasing behavior.

[0651] Step 5:

[0652] The server runs a machine learning algorithm using the collected data. The input includes pedestrian flow data, customer attributes, weather information, and event information obtained in the previous step. The algorithm analyzes this data to predict the potential impact of opening a store. The output provides suggestions for the optimal store location and time slot. The server generates these suggestions and provides them to the user.

[0653] Step 6:

[0654] The user receives suggestions from the server. These suggestions include specific locations and times where sales are predicted to be maximized. This allows the user to make data-driven decisions.

[0655] Step 7:

[0656] Users input sales data and customer feedback after opening a store via a terminal and send it to the server. Input includes sales figures and customer opinions, and this feedback data is stored on the server as output. The server analyzes this data and uses it to improve algorithms for more accurate future recommendations. This allows the entire system to continuously evolve.

[0657] (Application Example 1)

[0658] 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".

[0659] This invention aims to solve the problem that mobile vendors are unable to efficiently select their sales areas and optimize their business strategies. In particular, it addresses the difficulty of identifying the optimal location and time for setting up a store in real time, especially in urban areas where customer trends and preferences change rapidly.

[0660] 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.

[0661] In this invention, the server includes data collection means for collecting customer information, analysis means for analyzing customer trends and preferences based on the collected information, and proposal means for suggesting the optimal sales area based on the analysis results. This enables mobile vendors to utilize trend information and event information from smart networks to select the optimal sales area in real time.

[0662] "Customer information" refers to personal information and consumption history collected by mobile vendors to identify customer attributes and behavioral patterns.

[0663] "Data collection means" refers to a system component that has hardware or software functions for efficiently collecting customer information and related data from external sources.

[0664] "Analysis means" refers to a system component that uses collected data to analyze customer trends and purchasing tendencies, and derives useful information based on that analysis.

[0665] The "proposal means" refers to the system component that has the function of proposing the optimal sales area and time to mobile vendors based on the data analysis results from the analysis means.

[0666] A "smart network" is an advanced technological infrastructure for providing, collecting, and distributing information in real time via the internet and other networks.

[0667] "Trend information" refers to a collection of data showing the movement, interests, and concerns of customers and the population within a specific region or community, and is used to predict visitor behavior.

[0668] "Event information" refers to data related to schedules and gatherings of people associated with events and activities held in the local area, and is information that influences consumer attraction.

[0669] "Elemental information" refers to data that indicates environmental and market conditions and factors that contribute to sales promotion. This information is useful for understanding phenomena and trends and for developing sales strategies.

[0670] The system for implementing this invention consists of a server equipped with functions for collecting, analyzing, and proposing data, and terminals for receiving and transmitting information. The server collects customer information, trend information, event information, and elemental information from external sources via a network. This utilizes data collection libraries and APIs, such as weather APIs and local event databases.

[0671] The server analyzes the collected data using machine learning algorithms (e.g., RandomForestRegressor). This analysis reveals customer trends and purchasing preferences. The analysis results serve as a basis for suggesting optimal operating areas and times for mobile vendors. Based on the analysis results, the server generates suggestions in real time and notifies the terminal.

[0672] Users receive this information via their devices and conduct sales activities based on the suggestions presented. This system allows users to utilize trend information and environmental factors in real time to efficiently select store locations and times. Furthermore, the system continuously improves the accuracy of suggestions by updating the algorithm on the server side based on actual sales data.

[0673] For example, if an event is scheduled for a weekend in a certain area, the server analyzes pedestrian traffic data related to that event and suggests the optimal location and time for a store to set up shop within that area to the user. In this way, users can develop strategies to efficiently maximize sales.

[0674] Examples of prompts for generative AI models:

[0675] "Please suggest the best time and location for a booth at a local event this weekend. Please take into account past sales data and the profiles of event attendees."

[0676] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0677] Step 1:

[0678] The server collects customer information, trend information, event information, and elemental information from external sources via the network. It uses information obtained from APIs or databases as input. As output, this information is stored as organized datasets. Access to each information source is automated through regular scheduling.

[0679] Step 2:

[0680] The server inputs the collected data into a machine learning algorithm to analyze customer purchasing preferences and behavioral patterns. The input is the organized dataset obtained in Step 1. The output is a modeled result regarding customer trends and potential demand. This analysis uses machine learning libraries, and data processing is performed within the server.

[0681] Step 3:

[0682] The server uses the analysis results to generate optimal sales area and time suggestions and sends them to the user's terminal. The input is the modeled result obtained in step 2. As output, specific store opening suggestion information is generated and notified to the user's terminal. To generate the suggestions, a generative AI model is used to calculate the optimal solution that satisfies various conditions.

[0683] Step 4:

[0684] The user uses a terminal to review the store opening proposal information received from the server. The input is the proposal information sent to the terminal in step 3. As output, a decision is made based on the proposed sales strategy. By executing the specific instructions obtained from this information in the field, the user can efficiently carry out sales activities.

[0685] Step 5:

[0686] Users send actual sales data after business hours as feedback from their terminal to the server. The input is sales information obtained during the day's sales activities. The output is customer feedback data stored on the server. This process is used for updating the data to improve the accuracy of future proposals.

[0687] Step 6:

[0688] The server retrains its machine learning algorithm using feedback data to improve the accuracy of its suggestions. The input is the customer feedback data obtained in step 5. The output is the newly improved model. This allows the server to make more accurate store opening suggestions in the future.

[0689] 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.

[0690] This invention is a system for food truck operators to optimize their store locations and propose effective store locations while also considering user sentiment. This system provides more comprehensive support for store locations by including data collection means, analysis means, proposal means, update means, and sentiment engine.

[0691] In implementing the system, the server first collects local pedestrian flow data, customer attribute data, weather data, and event information. This data is usually obtained through external databases or APIs, but it can also be entered directly by users.

[0692] Next, the server uses an emotion engine to extract and analyze user emotion data from sources such as social media and online reviews. This makes it possible to understand the emotions customers feel towards specific events or products. This emotion data is then analyzed in combination with sales data and foot traffic data.

[0693] The server uses machine learning algorithms to analyze customer trends and potential demand based on this data. In particular, it places emphasis on the impact of customer emotions on sales and customer acquisition, and makes sales forecasts that take emotional data into account.

[0694] Based on the analysis results, the server suggests optimal store locations to the user. It prioritizes suggesting areas and events that evoke positive customer sentiment, providing guidance for formulating specific store opening strategies.

[0695] After opening a store, users send actual sales data, customer feedback, and newly collected sentiment data from their devices to the server. This information is used to update the algorithm of the suggestion method and improve its accuracy for the next time.

[0696] As a concrete example, when setting up a booth at a specific music festival, the server investigates the past emotional data of event attendees. If the analysis reveals that festival attendees have a positive feeling towards a particular food truck, the system will prioritize suggesting that food truck to participate. In this way, strategic booth placement utilizing emotional data becomes possible, and an increase in sales can be expected.

[0697] In this way, the present invention utilizes an emotion engine to provide a comprehensive support system for realizing an effective store opening strategy for food truck businesses.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The server collects local pedestrian traffic data, customer attribute data, weather data, and event information from external data sources. This collection process involves retrieving data via APIs and storing it in a database in real time.

[0701] Step 2:

[0702] The server uses an emotion engine to analyze text data from social media and review sites. Applying natural language processing techniques, it extracts emotions from keywords and phrases and classifies them into emotional categories such as positive, negative, and neutral.

[0703] Step 3:

[0704] The server integrates the sentiment data collected in the previous step with sales data and pedestrian flow data for each region, and preprocesses all the data. It performs data normalization and removes outliers to prepare the data for analysis.

[0705] Step 4:

[0706] The server applies machine learning algorithms to calculate customer behavior and the impact of emotions. In doing so, it considers the correlation between past emotional data and sales to build sales forecasting models for each area.

[0707] Step 5:

[0708] The server suggests optimal store locations based on the analysis results. This suggestion includes strategies such as opening stores in areas where emotions are positive and on days with favorable weather forecasts. The suggestions are then generated as a report that users can refer to.

[0709] Step 6:

[0710] Users review the generated reports and develop store opening plans. By considering the suggested areas and time slots and formulating an optimal store opening schedule, they aim to attract customers effectively.

[0711] Step 7:

[0712] After opening a store, users send actual sales data, feedback from new customers, and, if possible, sentiment data from their devices to the server. This provides a new dataset for evaluating the effectiveness of opening a store.

[0713] Step 8:

[0714] The server analyzes newly submitted data and updates its machine learning models and sentiment engine. This update process improves the accuracy of future store location suggestions, enabling more precise and strategic store openings.

[0715] (Example 2)

[0716] 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".

[0717] Traditional store development strategies are primarily based on sales data and basic customer trends, making it difficult to implement strategies that consider customer emotions and latent desires. Furthermore, they lack the ability to dynamically consider local events and weather conditions, resulting in a lack of adaptability in the short term. This invention solves these problems and provides a system that enables food truck businesses and other mobile vendors to implement more effective and emotion-based store development strategies.

[0718] 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.

[0719] In this invention, the server includes data collection means for collecting human behavior data, individual characteristic data, weather data, and event information; sentiment analysis means for extracting sentiment data from social media and online reviews and analyzing the emotions customers have towards specific events or products; and analysis means for analyzing customer trends and potential desires based on the collected data, taking into account the impact of sentiment data on sales. This enables the proposal of effective store locations that take customer emotions into consideration and the construction of a dynamic feedback loop to improve the accuracy of the proposals.

[0720] "Human behavior data" refers to data that shows people's movement and activity patterns, and is used to understand crowds and pedestrian traffic at specific locations and times.

[0721] "Individual characteristic data" refers to individual customer information such as age, gender, and purchase history, and is used to analyze what attributes a particular user has and what products and services they are interested in.

[0722] "Weather data" refers to data that shows weather conditions in a specific region or time, such as temperature, precipitation, and wind speed, and is used as information to take environmental factors into consideration in store opening strategies.

[0723] "Event information" refers to information about local events and special occasions, and is a factor used to analyze the ability to attract people at a specific time and place.

[0724] "Data collection means" refers to technical methods and mechanisms for gathering necessary information through external data provision means, and is used for collecting foundational information within a system.

[0725] "Sentiment analysis tools" are technologies used to evaluate the emotional aspects of texts and statements collected through social media and reviews, quantifying and analyzing how customers feel about specific products or events.

[0726] "Analysis methods" refer to techniques that use collected data to understand customer trends and potential desires, and in particular to quantify and analyze the impact of emotional data on sales.

[0727] The "store location suggestion method" is a system for presenting optimal business locations and strategies based on analysis results, and it identifies and recommends areas preferred by customers by taking emotional data into consideration.

[0728] "Update methods" refer to processes and technical mechanisms for improving the accuracy of system suggestions by incorporating user feedback and sales data.

[0729] This invention is designed to provide a system that enables food truck operators to efficiently identify locations and conduct strategic operations that take customer sentiment into consideration. The system is primarily server-based and includes data collection, sentiment analysis, data analysis, location recommendations, and update procedures.

[0730] The server first collects data on human behavior, individual characteristics, weather, and events. This utilizes public APIs and data providers for data collection. For example, the server might use the OpenWeatherMap API to obtain weather data and human movement information through another appropriate data provider.

[0731] Sentiment analysis is performed on a server. This is achieved by analyzing posts from social media and online reviews. For example, the server uses the Twitter API to obtain the necessary text data and uses a dedicated sentiment analysis engine to extract positive and negative emotions as data.

[0732] Next, the server performs data analysis. It feeds the collected data into a machine learning library such as scikit-learn to analyze customer behavior. In particular, it clarifies the impact of sentiment data on sales and customer acquisition, and optimizes sales forecasts.

[0733] The server makes suggestions for store locations based on the analysis results. This system also provides an interface on the user's device to visualize the suggestions. It is also possible to use the Google Maps API to visually display preferred areas.

[0734] After opening a store, users send actual sales data and customer feedback to the server via their devices. This information is incorporated into the server's update process to improve the accuracy of suggestions.

[0735] As a concrete example, if a user is considering setting up a stall at a music festival, it is conceivable that the prompt "Suggest a food truck that should be set up based on sentiment data from past attendees of the music festival" would be input to the generative AI model.

[0736] This system allows food truck operators to gather local data in real time and develop efficient store opening strategies that take sentiment into account.

[0737] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0738] Step 1:

[0739] The server collects local human behavior data, individual characteristic data, weather data, and event information. Inputs include data provided by public APIs and data providers. For example, the server might use the OpenWeatherMap API to obtain weather data and another appropriate provider to obtain human flow data. The output includes an informational set that integrates this data.

[0740] Step 2:

[0741] The server collects textual data from social media and online reviews to perform sentiment analysis. Input includes content from posts obtained through sources such as the Twitter API and ReviewTrackers. The server uses a sentiment analysis engine to extract positive or negative emotions through natural language processing and outputs the results as numerical data.

[0742] Step 3:

[0743] The server analyzes customer trends based on the collected dataset. Inputs include previously acquired pedestrian flow data, feature data, weather data, event information, and sentiment data. The server uses machine learning libraries such as scikit-learn to analyze the dataset and extract customer motivation and sales forecast data. This allows it to output analysis results showing the impact of sentiment data on sales and customer acquisition.

[0744] Step 4:

[0745] The server considers the analysis results and suggests optimal store locations to the user. Inputs include sales forecasts and positive sentiment data derived from the analysis. Based on this, the server uses the Google Maps API to visually present specific store locations and generates a suggestion report as output.

[0746] Step 5:

[0747] After opening a store, users send actual sales data and customer feedback to the server via their device. Inputs include actual sales data and customer survey results. The server uses this data in its update process, accumulates data to improve the accuracy of the algorithm, and outputs an updated predictive model to be reflected in future suggestions.

[0748] (Application Example 2)

[0749] 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".

[0750] There is a growing need to develop effective store opening strategies based on changes in customer behavior and customer sentiment. However, conventional methods make it difficult to quickly and appropriately utilize real-time urban pedestrian flow information and event information in store opening strategies. To solve this problem, the present invention aims to provide a system that enables the proposal of smart store opening strategies that respond to dynamically changing environments.

[0751] 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.

[0752] In this invention, the server includes means for collecting customer-related information, means for analyzing customer behavior patterns and preferences based on the collected information, means for recommending the optimal store location based on the analysis results, means for improving the recommendation using actual sales information based on the optimized store location, and means for acquiring urban pedestrian flow information and event information in real time and having a function for optimizing the store location. This makes it possible to provide a rapid and highly accurate store location strategy in response to dynamic environmental changes.

[0753] "Means of collecting customer-related information" refers to systems for acquiring customer behavior patterns, preferences, location information, emotional data, and so on.

[0754] "Means of analyzing customer behavior patterns and preferences based on collected information" refers to algorithms and software that analyze collected data to understand the products, services, and behavioral characteristics that customers prefer.

[0755] "A method for recommending the optimal store location" refers to a system that, based on analysis results, selects and proposes the most suitable store location based on customer needs and current circumstances.

[0756] "Means of improving suggestions using actual sales information based on optimized store locations" refers to a function that analyzes actual sales data and updates the system to make future store location suggestions more accurate.

[0757] "A means of acquiring real-time information on urban pedestrian traffic and events, and having the functionality to optimize store locations" refers to a system that acquires real-time information on people's movement patterns and events in cities, and selects the optimal location for a store.

[0758] This invention is a system that optimizes store opening strategies using information technology, and is designed to respond to the dynamically changing needs and emotions of customers in urban environments. This system consists of a server, terminals, and users, each playing a specific role.

[0759] The server collects customer-related information from both physical and online environments. This collected data includes location information, weather data, event information, and sentiment data obtained from social media. This data is typically retrieved using the Google Places API or the OpenWeatherMap API.

[0760] The server uses Python to analyze information and employs TensorFlow or PyTorch machine learning algorithms to analyze customer behavior patterns and preferences. Based on the results of this analysis, it recommends the optimal store location. It also uses the Google Cloud NLP API to analyze sentiment data and makes sales forecasts that take into account the impact of customer sentiment on sales.

[0761] Users check suggested store locations via their smartphones and report actual sales data from their devices to the server. This feedback information is used to improve future store location suggestions.

[0762] As a concrete example, at one music festival, a server analyzes attendees' online posts in real time and extracts positive reactions to specific food trucks. Based on this information, it recommends that users support the food truck's participation in the festival.

[0763] An example of a prompt for a generative AI model is: "Analyze visitor posts at a music festival, identify in real time the types of food trucks and products they favor, and propose a vendor strategy based on that." This prompt allows the AI ​​to quickly provide the information the user requests and support the development of optimal strategies in real time.

[0764] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0765] Step 1:

[0766] The server collects customer-related information via external APIs. This input includes location data, weather data, event information, and social media sentiment data. It uses the Google Places API to obtain pedestrian flow data at the current location and collects weather data through the OpenWeatherMap API. By collecting this data, the system prepares the basic information for suitable times and locations for opening a store.

[0767] Step 2:

[0768] The server performs data analysis using Python based on the collected data. First, it analyzes customer behavior patterns and preferences using machine learning algorithms such as TensorFlow or PyTorch. In this process, the input data is transformed into a model and regional sales forecasts are generated. The output forecast results are used to evaluate the priority of store locations.

[0769] Step 3:

[0770] The server uses the Google Cloud NLP API to analyze sentiment data from collected social media posts. The input includes posts in string format, and text analysis calculates their sentiment scores. This output helps understand customer sentiment towards specific products or events, and, combined with sales forecasts, aids in strategic decision-making.

[0771] Step 4:

[0772] Based on the analysis results, the server uses a generated AI model to suggest the optimal store location to the user. In this process, the AI ​​uses the generated prompt text, taking the analysis data as input, to generate a store location strategy. The suggested store location is then notified to the user's terminal.

[0773] Step 5:

[0774] Users receive proposals via their smartphones and conduct actual sales activities. After sales, users report actual sales data and customer feedback from their devices to the server. This input information is crucial for improving the accuracy of store opening strategies.

[0775] Step 6:

[0776] The server updates its suggestion algorithm based on user feedback. By inputting actual sales data and retraining the machine learning model, the next store opening suggestions become more accurate. The retrained model achieves higher predictive performance in future strategic planning.

[0777] 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.

[0778] 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.

[0779] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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."

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] The following is further disclosed regarding the embodiments described above.

[0799] (Claim 1)

[0800] Data collection methods for collecting customer data,

[0801] Analytical tools for analyzing customer trends and preferences based on collected data,

[0802] A proposal method that suggests the optimal store location based on the analysis results,

[0803] A means of updating proposals to improve their accuracy using actual sales data,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, wherein the data collection means collects weather data and event data.

[0807] (Claim 3)

[0808] The system according to claim 1, wherein the analytical means uses a machine learning algorithm for evaluating the potential demand in a region.

[0809] "Example 1"

[0810] (Claim 1)

[0811] Information acquisition means for collecting pedestrian flow data, customer attribute data, weather information, and event information,

[0812] An analytical tool that uses collected information to analyze customer behavior characteristics and forecast demand,

[0813] A location suggestion method that presents the most effective store location based on the analysis results,

[0814] Improvement methods to enhance the accuracy of future proposals using actual sales information and customer feedback,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, wherein the information acquisition means acquires weather information and local event information.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein the analytical means uses a machine learning model to evaluate the market potential of a region.

[0820] "Application Example 1"

[0821] (Claim 1)

[0822] Data collection methods for collecting customer information,

[0823] An analytical tool for analyzing customer trends and preferences based on collected information,

[0824] A proposal method that suggests the optimal sales area based on the analysis results,

[0825] A means of updating proposals to improve their accuracy using actual sales information,

[0826] A means to integrate trend information, event information, and elemental information provided by a smart network to suggest optimal locations and times for mobile vendors to set up shop.

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, wherein the data collection means collects weather information and event information.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein the analysis means uses a learning algorithm to evaluate the potential demand in a region and further predicts the optimal sales area based on new data.

[0832] "Example 2 of combining an emotion engine"

[0833] (Claim 1)

[0834] A data collection method for collecting human behavioral data, individual characteristic data, weather data, and event information,

[0835] A sentiment analysis tool that extracts sentiment data from social media and online reviews to analyze the emotions customers have towards specific events or products,

[0836] Based on the collected data, we analyze customer trends and potential desires, and in particular, we use analytical methods that consider the impact of emotional data on sales.

[0837] Based on the analysis results, an optimized store location suggestion method is developed that prioritizes suggesting areas and events where emotional data is trending in a favorable direction.

[0838] A means of updating to improve the accuracy of suggestions using sales data and feedback from users,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, wherein the data collection means collects weather data and event data through an external data provision means.

[0842] (Claim 3)

[0843] The system according to claim 1, wherein the analysis means uses a machine learning algorithm for making sales forecasts that take sentiment data into consideration using a specific technique.

[0844] "Application example 2 when combining with an emotional engine"

[0845] (Claim 1)

[0846] Means of collecting customer-related information,

[0847] A means of analyzing customer behavior patterns and preferences based on collected information,

[0848] A means of recommending the optimal store location based on the analysis results,

[0849] A means of improving proposals using actual sales information based on optimized store locations,

[0850] A means to acquire real-time information on pedestrian traffic and events in urban areas, and to have functions to optimize store locations,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, wherein the collection means acquires weather information and event information.

[0854] (Claim 3)

[0855] The system according to claim 1, wherein the analytical means includes an artificial intelligence algorithm for evaluating potential demand within an area. [Explanation of symbols]

[0856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Data collection methods for collecting customer data, Analytical tools for analyzing customer trends and preferences based on collected data, A proposal method that suggests the optimal store location based on the analysis results, A means of updating proposals to improve their accuracy using actual sales data, A system that includes this.

2. The system according to claim 1, wherein the data collection means collects weather data and event data.

3. The system according to claim 1, wherein the analysis means uses a machine learning algorithm for evaluating the potential demand of a region.

Images