System

Abstract

A system is provided.SOLUTION: The snow condition prediction system includes a weather information acquisition means, a past snow quality data acquisition means, a means for training a machine learning model using these data, a means for predicting future snow quality based on the machine learning model, and a means for providing a prediction result to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Current weather forecasts have limitations in their ability to predict detailed snowfall and snow quality, making it difficult to accurately predict the best powder weather for skiing and snowboarding. Due to the inaccuracy of weather forecasts, skiers and snowboarders often fail to enjoy optimal snow quality at their intended destinations. The present invention aims to solve this problem by providing a system that can accurately predict the best powder weather. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a snow condition prediction system that includes a weather information acquisition means, a past snow quality data acquisition means, a means for training a machine learning model using the data, a means for predicting future snow quality based on the machine learning model, and a means for providing the prediction results to a user. The weather information acquisition means acquires weather forecast data based on a specific location, and by using a random forest classifier trained using past snow quality data, future snow quality can be predicted with high accuracy. By providing the user with the prediction results, the user can know in advance whether the weather will be suitable for powder snow at their destination, allowing them to plan an optimal skiing or snowboarding trip.

[0006] A "weather information acquisition means" is a means for acquiring weather forecast data from an external weather service based on a specific location.

[0007] The "means for acquiring past snow quality data" is a means for acquiring data on the temperature, amount of snowfall, and snow quality on past days.

[0008] "Means for training a machine learning model" refers to a means for training an algorithm that uses acquired weather information and past snow quality data to learn a target prediction value (e.g., snow quality) from one or more features.

[0009] The "means for predicting future snow conditions" is a means for predicting snow conditions from future weather information using a trained machine learning model.

[0010] The "means for providing the user with the predicted results" refers to a means for displaying or notifying the user of the predicted future snow quality.

[0011] "Snow condition prediction system" refers to the entire system including a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model, a means for predicting future snow quality, and a means for providing the prediction results to a user. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. 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), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a 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.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0026] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The present invention provides a system for accurately predicting powder weather conditions, which includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model, a means for predicting future snow quality, and a means for providing the prediction results to a user.

[0034] Get weather information

[0035] The server retrieves weather data for a specific location (e.g., a popular ski resort) from a weather API. It sends a request to the weather API and receives a JSON response containing near-future weather forecast data. This data includes information such as average daily temperatures and snowfall.

[0036] Obtaining past snow quality data

[0037] The server retrieves historical snow data, including past daily temperature, snowfall, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0038] Training an AI model

[0039] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0040] Powder weather forecast

[0041] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0042] Providing prediction results

[0043] The device will then provide the user with the forecast results, such as a list of predicted powder weather dates, so the user can plan their skiing or snowboarding trip.

[0044] Specific examples

[0045] User example: A user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining the predicted results from the server.

[0046] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict powder weather. If the forecast result is "2023-01-02," the device displays this to the user.

[0047] These steps allow users to know the best snow conditions at their destination in advance and plan their trip based on snow quality.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The server retrieves weather data for a specific location from the weather API. It sends a request to the weather API using the API key and receives a 10-day weather forecast in JSON format in response.

[0051] Step 2:

[0052] The server analyzes the weather data and extracts the average temperature and snowfall for each day, which are used as inputs for subsequent forecasting.

[0053] Step 3:

[0054] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality for that day (e.g., good, very good, poor).

[0055] Step 4:

[0056] The server separates historical snow quality data into features (temperature, snowfall) and labels (snow quality), which are then used to train a machine learning algorithm (e.g., a random forest classifier).

[0057] Step 5:

[0058] The server uses a trained machine learning model to predict future snow conditions based on weather forecast data, and adds dates that are deemed "very good" (ideal for powder) to the list.

[0059] Step 6:

[0060] The device retrieves the prediction results from the server and displays them to the user, including the dates of powder weather for the specific location.

[0061] Step 7:

[0062] Users can check the display on their device and plan their skiing or snowboarding trip based on the best powder weather conditions, ensuring they can enjoy the best conditions.

[0063] Example 1

[0064] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0065] Conventional snow condition prediction systems have struggled to effectively utilize weather forecast data and past data to accurately predict snow quality. This has made it difficult for users to plan optimal skiing or snowboarding trips, resulting in inconvenience. The present invention aims to solve these problems and provide a system that enables highly accurate prediction of powder weather.

[0066] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0067] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to a user, means for acquiring and analyzing JSON-formatted weather forecast data from a weather API, means for acquiring detailed weather information based on a specific geographic location, means for formatting past weather data as a training set, and a terminal for displaying the prediction results in response to a user request, thereby enabling a user to obtain highly accurate predictions of powder days based on detailed weather forecasts and past data.

[0068] A "means for obtaining weather information" is a function for obtaining weather forecast data for a specific geographic location from an external weather API.

[0069] "Means for obtaining past snow quality data" is a function for collecting information on past temperatures, snowfall amounts, and snow quality in a specific area.

[0070] "Means for training machine learning models" refers to a function for training models based on machine learning algorithms using collected historical weather information and snow quality data.

[0071] "Means for predicting future snow quality based on a machine learning model" is a function that uses a trained machine learning model to input future weather forecast data and predict snow quality.

[0072] The "means for providing the predicted results to the user" is a function for displaying the predicted results of powder weather on the user's device.

[0073] "Means for obtaining and analyzing weather forecast data in JSON format from a weather API" is a function for analyzing weather forecast data in JSON format obtained from an external weather API and extracting the necessary information.

[0074] The "means for obtaining detailed weather information based on a specific geographic location" is a function for obtaining detailed weather forecast data for a region based on a geographic location specified by a user.

[0075] "Means for formatting historical weather data as a training set" is a function for formatting previously collected weather information and snow quality data into a format suitable for training machine learning models.

[0076] A "terminal that displays prediction results in response to a user request" is a device that receives prediction results from a server in response to a question or request entered by a user and displays them to the user.

[0077] The present invention describes a snow condition forecasting system that accurately predicts powder weather. The system includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model using the acquired data, a means for predicting future snow quality based on the machine learning model, and a means for providing the predicted results to a user. The details are described below.

[0078] Hardware and Software

[0079] The server is the main hardware responsible for data collection, analysis, training, and prediction. The main software tools include an HTTP client for sending and receiving requests to the weather API, a parser for parsing JSON data, and a machine learning framework containing machine learning algorithms (e.g., random forest classifier). The database is used to store historical weather information, snow quality data, and trained AI models.

[0080] The terminal is a device that receives a user request, obtains prediction results from the server, and displays them to the user. Examples of this include smartphone apps and web browsers.

[0081] Users are individuals who want to know the best snow conditions (powder weather) at their ski resorts. Users access the system via their terminals and check the forecast results.

[0082] Data processing and calculation

[0083] 1. Get weather information:

[0084] The server sends a request to the weather API to retrieve near-future weather data for a specific ski resort. The retrieved data is in JSON format and includes daily average temperatures, snowfall, humidity, etc. This data is then analyzed and the necessary information is stored in a database.

[0085] 2. Obtaining historical snow quality data:

[0086] The server retrieves historical temperature, snowfall, and daily snow quality data for a particular ski resort, formats this data as a training set, and stores it in a database.

[0087] 3. Training the AI ​​model:

[0088] The server uses historical weather and snow data to train an AI model (such as a random forest classifier), which is then used to predict snow quality based on future weather conditions.

[0089] 4. Powder Weather Forecast:

[0090] The server uses a trained AI model to predict future snow conditions based on weather forecast data, identifying days when the forecast results are "very good" (powder-friendly) and generating a list of those days.

[0091] 5. Providing prediction results:

[0092] The server sends a list of predicted powder weather days to the terminal in response to a user request, and the terminal displays the list to the user.

[0093] Specific examples

[0094] User example: If a user is planning to go to a particular ski resort (e.g., Niseko), they ask through their device, "When will the best days for powder snow at Niseko be?" The server retrieves weather data from the weather API and makes a prediction using a trained AI model. If the prediction results in "2023-01-02" being a good day for powder snow, the device displays this to the user.

[0095] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then uses past weather and snow data to train an AI model, which then uses future weather data to predict powder conditions. The server adds the date for which the forecast is "very good" (e.g., 2023-01-02) to a list and sends that date to the device.

[0096] Prompt Sentence Examples

[0097] User: "When is the best time for powder snow in Niseko?"

[0098] Response from the server: "The next good powder day is 2023-01-02."

[0099] User: "Based on recent weather forecasts, what's the snow forecast for this weekend?"

[0100] This system allows users to efficiently plan their skiing or snowboarding trips, allowing them to enjoy the best possible natural conditions.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] Get weather information:

[0104] The server sends a request to a weather API to retrieve weather data for a geographic location specified by the user.

[0105] Input: A specific geographic location and forecast period

[0106] Output: Weather forecast data in JSON format (e.g., daily average temperature, snowfall, etc.)

[0107] What happens: The server sends a request to the weather API in the form "GET / weather?location=specified_location&days=10". The API response returns a JSON object containing weather data for the next 10 days. The server parses the data, extracts the necessary information (average temperature, snowfall, etc.), and stores it in a database.

[0108] Step 2:

[0109] Obtaining historical snow quality data:

[0110] The server retrieves historical weather and snow quality data for a particular ski resort from a database or external data source.

[0111] Input: Request for geographic location and specific time period

[0112] Output: Historical weather and snow data formatted for training purposes

[0113] What it does: The server sends the query "SELECT FROM historical_snow_data WHERE location="specified_location"" to retrieve data from the database. The retrieved data includes information on daily temperature, snowfall, and snow type, and is formatted as a training dataset for machine learning.

[0114] Step 3:

[0115] Training an AI model:

[0116] The server trains machine learning models using collected historical weather and snow data.

[0117] Input: Historical weather data (features) and snow quality data (labels)

[0118] Output: A trained machine learning model

[0119] Specific operation: The server trains a model using a random forest classifier using the format "train_model(past_weather_data, snow_quality_labels)". After training is complete, the model is saved using the format "model.save('snow_quality_predictor.model')".

[0120] Step 4:

[0121] Powder weather forecast:

[0122] The server uses a trained AI model to predict snow quality based on future weather forecast data.

[0123] Input: Future weather forecast data (average temperature, snowfall, etc.)

[0124] Output: Predicted future daily snow quality data

[0125] Specific operation: The server makes a prediction using future weather data in the form of "predictions = model.predict(future_weather_data)". Dates for which the prediction result is judged to be "very good" (suitable for powdery weather) are added to the list.

[0126] Step 5:

[0127] Providing prediction results:

[0128] The server provides the user with a list of predicted powder weather dates.

[0129] Input: User request (e.g., "When is the best time for powder weather in Niseko?")

[0130] Output: Prediction results (date list) displayed on the user's device

[0131] Specific operation: The server receives a user request, generates a list of predicted dates, and sends it to the terminal. The terminal displays this list to the user, providing information such as, "The next good day for powder weather is 2023-01-02."

[0132] (Application example 1)

[0133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0134] Conventional food delivery systems create delivery plans without taking into account weather or past delay data, resulting in unexpected delays and inefficient route selection. Delivery delays are particularly frequent during bad weather such as snow or rain, resulting in reduced user satisfaction.

[0135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0136] In this invention, the server includes a means for acquiring weather information, a means for acquiring past data, and a means for using this data to train a machine learning model, which makes it possible to predict future conditions and to predict and notify delivery efficiency and potential delays.

[0137] The "weather information acquisition means" is a device or program that has the function of acquiring weather data for a specified area from an external data source.

[0138] A "historical data acquisition means" is a device or program for collecting historical weather conditions and related data for a particular area.

[0139] A "means for training a machine learning model" is a device or program that applies a machine learning algorithm using collected data to build and improve a predictive model.

[0140] A "means for predicting future conditions" is a device or program that uses a trained machine learning model to predict certain future conditions (e.g., the likelihood of delivery delays).

[0141] The "means for providing the predicted result to the user" is a device or program for notifying or displaying the predicted result on the user's device.

[0142] "Means for predicting and notifying delivery efficiency and possible delays" refers to a device or program that predicts delivery efficiency and possible delays based on future weather conditions and past data, and notifies the user of the results.

[0143] A system for predicting delivery efficiency and possible delays based on different weather conditions and providing this information to users is implemented as follows.

[0144] Overall system configuration

[0145] The system consists of the following major components:

[0146] 1. How to get weather information

[0147] 2. How to obtain past data

[0148] 3. Means of training machine learning models

[0149] 4. A means of predicting future conditions

[0150] 5. Means of providing prediction results to users

[0151] Get weather information

[0152] The server retrieves weather data for a specific location (e.g., a city) using a weather API. It sends a request to the weather API and receives a response in JSON format containing future weather forecast data. This data includes information such as average daily temperatures and snowfall amounts. Possible APIs to use include the Weather API or the OpenWeatherMap API.

[0153] Obtaining historical data

[0154] The server retrieves historical weather data for a specific location and delivery delay data for that period. This data includes daily temperature, snowfall, and delivery status (e.g., delayed, normal). This forms a training dataset for learning correlations between weather conditions and delivery delays.

[0155] Training a machine learning model

[0156] The server uses historical data to train an AI model using machine learning algorithms such as random forest classifiers, learning from past weather data (features) and resulting delivery statuses (labels). This training allows the model to predict delivery delays under specific weather conditions.

[0157] Predicting conditions

[0158] The server uses a trained AI model to predict delivery efficiency and the possibility of delays based on future weather forecast data. The weather forecast data includes daily average temperatures and snowfall amounts, and these are input into the model to determine future delivery status. Days with a high probability of a "delay" are selected, and the date and reason for the delay are added to a list.

[0159] Providing prediction results

[0160] The terminal provides the user with the predicted results, for example by displaying a list of predicted possible delay dates on the user's device, allowing the user to adjust their delivery schedule based on this information.

[0161] Examples of concrete examples and prompts

[0162] As a specific example, assume that the user makes the following inquiry:

[0163] Example prompt sentence:

[0164] Please predict the weather and possible delivery delays in Tokyo next Saturday.

[0165] By feeding this prompt into the generative AI model, we can get the following output:

[0166] Example output produced:

[0167] Next Saturday (2023-10-14) in Tokyo, the average temperature is predicted to be 5°C and snowfall 2cm. Based on this, there is a high possibility of delivery delays. Please leave early and take appropriate cold weather precautions when making deliveries.

[0168] This allows users to make appropriate preparations depending on the weather and delivery conditions.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] The server retrieves weather information for the specified location.

[0172] Input: Location information

[0173] How it works: The server sends a request to a weather API (e.g., Weather API or OpenWeatherMap API) and retrieves future weather forecast data in JSON format.

[0174] Output: Weather forecast data (average temperature, snowfall, etc.)

[0175] Step 2:

[0176] The server retrieves historical weather data and delivery delay data.

[0177] Input: Location information, historical data sources

[0178] How it works: The server retrieves historical weather data and associated delivery delay information from a pre-defined database or external data sources, including daily temperature, snowfall, and delivery status (delayed, normal).

[0179] Output: Historical weather data and delivery delay data

[0180] Step 3:

[0181] The server trains the machine learning model using historical data.

[0182] Input: Historical weather data, delivery delay data

[0183] How it works: The server uses machine learning algorithms, such as a random forest classifier, to train historical weather data (features) and delivery status (labels), allowing the model to predict delivery delays under specific weather conditions.

[0184] Output: A trained machine learning model

[0185] Step 4:

[0186] The server predicts delivery efficiency and possible delays based on future weather forecast data.

[0187] Input: trained machine learning model, future weather forecast data

[0188] How it works: The server inputs future weather forecast data into the trained model to predict future delivery status (likely delays). It selects days where the predicted result is likely to be "delayed" and adds those dates and reasons to a list.

[0189] Output: Delivery delay prediction list

[0190] Step 5:

[0191] The terminal provides the prediction result to the user.

[0192] Input: Delivery delay prediction list

[0193] How it works: The device displays a list of predicted possible delay dates on the user's device, and notifies them via a smartphone app or web interface.

[0194] Output: Delay prediction notification

[0195] Step 6:

[0196] The user adjusts the delivery schedule.

[0197] Input: Delay forecast notification

[0198] How it works: The user adjusts their delivery schedule appropriately based on the forecast information provided, which may include changing delivery times or making advance preparations.

[0199] Output: Adjusted delivery schedule

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] The present invention provides a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes user emotions. The system includes a weather information acquisition means, a past snow quality data acquisition means, a machine learning model training means, a prediction means for future snow quality, a means for providing the prediction results to the user, and an emotion engine that recognizes user emotions.

[0202] Get weather information

[0203] The server retrieves weather data for a specific location from a weather API. It sends a request to the weather API using an API key and receives a 10-day weather forecast in JSON format in response. This data includes information such as average daily temperatures and snowfall amounts.

[0204] Obtaining past snow quality data

[0205] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0206] Training an AI model

[0207] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0208] Powder weather forecast

[0209] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0210] Utilizing the Emotion Engine

[0211] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[0212] Providing prediction results

[0213] When the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is in high spirits, the device will notify them of the perfect day for powdering in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data, and can suggest the best day for powdering for the user.

[0214] Specific examples

[0215] User example: Suppose a user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining a prediction result from the server. Furthermore, if the emotion engine evaluates the user's level of expectation highly, the device notifies the user, "Next weekend will be the best weather for powder snow!"

[0216] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict the best days for powder weather. If the prediction is "2023-01-02," the device will display "The best days for powder weather you're looking forward to are 2023-01-02" based on the analysis results of the emotion engine.

[0217] In this way, by predicting and notifying users of powder weather taking their emotions into consideration, we provide a system that allows users to enjoy a better experience.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] The server retrieves weather data for a specific location from a weather API, uses an API key to access the weather API, and sends a request. From the returned JSON response, the server parses the 10-day weather forecast data and extracts the average temperature and snowfall for each day.

[0221] Step 2:

[0222] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and the snow quality for that day (e.g., good, very good, poor), and then collects and analyzes it.

[0223] Step 3:

[0224] The server trains a machine learning model based on past weather and snow quality data. Specifically, it uses a random forest classifier to train the model to take temperature and snowfall features as input and output snow quality. This model can then predict snow quality under specific weather conditions.

[0225] Step 4:

[0226] The server uses a trained machine learning model to predict snow quality based on future weather forecast data. It inputs average temperature and snowfall from 10 days of weather data and determines the predicted snow quality for each day. Days predicted as "very good" (perfect for powder) are added to the list.

[0227] Step 5:

[0228] To recognize the user's emotions, the server acquires the user's emotion data using an emotion engine. The emotion engine collects data from sensors (e.g., heart rate sensors, facial recognition technology) installed on the user's device and analyzes the user's excitement and expectation.

[0229] Step 6:

[0230] The device receives the prediction results and the user's emotional data from the server. Based on this, the prediction results are displayed in a way that is optimal for the user. For example, if the user is in an excited state, the device will notify the user of the date when it will be a good day for powdering in a more positive way.

[0231] Step 7:

[0232] The user checks the display on their device and plans their skiing or snowboarding trip based on the best powder weather. Information, including the analysis results of the emotion engine, allows the user to enjoy the trip under the best conditions. Specifically, the user will receive a notification saying, "Next weekend is the best powder weather!" and adjust their travel plans to target that day.

[0233] Example 2

[0234] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0235] Conventional snow condition prediction systems can predict future snow conditions based on weather information and past snow quality data, but they cannot customize the prediction results to take the user's emotional state into account. This makes it difficult to provide optimal information to users. Furthermore, detailed data analysis and customization to improve prediction accuracy are time-consuming. The purpose of this invention is to solve these problems and provide a more accurate and user-friendly snow condition prediction system.

[0236] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0237] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to the user, means for acquiring the user's emotional state, and means for customizing the prediction results according to the user's emotional state. This enables highly accurate prediction and notification of powder weather according to the user's emotions.

[0238] "Weather information" means data about weather conditions, such as temperature, snowfall, and wind speed, at a particular location.

[0239] "Snow Quality Data" means information about past or current snow conditions at a particular location, including ratings such as good, very good, or poor.

[0240] A "machine learning model" is an algorithm that uses past data to learn certain patterns and relationships, and then uses that to predict future events or situations.

[0241] "Weather Forecast Data" means data that indicates future weather conditions at a particular location, including predicted temperature, snowfall, and wind speed.

[0242] "Prediction results" are information about future snow quality and weather conditions predicted by the machine learning model.

[0243] "User" refers to any individual or organization that uses this system to obtain weather and snow quality information.

[0244] "Emotional state" refers to a user's current mental and emotional situation or state, including emotions such as excitement, anticipation, and anxiety.

[0245] "Customization" means changing the way prediction results and information are presented according to the user's needs and situation.

[0246] This invention relates to a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes the user's emotions. This system is realized using the following hardware and software.

[0247] First, the server uses a weather API (e.g., OpenWeatherMap) to obtain weather data for a specific location. Specifically, the server uses an API key to send a request to the weather API and receives 10-day weather forecast data in JSON format in response. This data includes information such as the average daily temperature and amount of snowfall. For example, the server can obtain the required data by entering a prompt statement such as "I want to get the 10-day weather forecast for Niseko."

[0248] The server then retrieves historical snow quality data from a database that stores past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a specific location. This information is used to form a training dataset for learning correlations between weather conditions and snow quality. For example, the server can collect the required data by entering a prompt statement such as, "Get snow quality data for Niseko for the past year."

[0249] The server then uses machine learning algorithms, such as a random forest classifier, to train an AI model based on historical data. This training enables the model to predict snow conditions under specific weather conditions. For example, the server can do this by entering the prompt "Train a snow condition prediction model using historical data."

[0250] Using the trained AI model, the server predicts snow quality from future weather forecast data. Specifically, the model inputs the daily average temperature and snowfall amount from the weather forecast data to determine future snow quality. Days for which the forecast result is "very good" (powder weather) are added to a list and the date is saved. For example, the server can make this prediction by entering a prompt statement such as "Predict powder weather conditions in Niseko for the next 10 days."

[0251] Furthermore, the server uses an emotion engine to recognize the user's emotional state. The emotion engine acquires data from sensors (e.g., heart rate sensors, facial recognition technology) installed in the user's device and measures the user's level of excitement and expectation. This allows the server to analyze the user's emotions under specific conditions. For example, emotion analysis is performed by the server inputting a prompt statement such as, "Analyze the user's emotional state and evaluate the expectation level."

[0252] Finally, when the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is excited, it will notify them of the perfect day for powder snow in a more positive manner. The device analyzes past behavioral history and emotional data from the emotion engine, and can suggest the best day for powder snow for the user. For example, the device can heighten the user's expectations by notifying them, "Next weekend will be the perfect day for powder snow!"

[0253] In this way, a specific system configuration is provided for highly accurate prediction and notification of powder weather according to the user's feelings.

[0254] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0255] Step 1:

[0256] The server retrieves weather information. The input is the name of a specific location (e.g., a ski resort) and the access key provided by the weather API. The server accesses the weather API (e.g., OpenWeatherMap) and retrieves 10-day weather forecast data for the specific location. Specifically, the server generates an API request and accesses the URL using the HTTP protocol. The output is data such as the average daily temperature and snowfall amount in JSON format.

[0257] Step 2:

[0258] The server retrieves historical snow quality data. The input requires a specific location and time period (e.g., the past year). The server connects to the database and queries for snow quality data (temperature, snowfall, snow quality rating) based on the specified location and time period. Specifically, it runs an SQL query to extract the relevant data and converts it into a format that can be used within the program. The output is a dataset of the query results.

[0259] Step 3:

[0260] The server trains the AI ​​model. Historical weather data and snow quality data are required as input. The server preprocesses this data (e.g., imputing missing values ​​and normalizing data) and trains it using a machine learning algorithm (e.g., random forest classifier). Specifically, it preprocesses the data and trains the model using a machine learning library. The output is a trained AI model.

[0261] Step 4:

[0262] The server predicts the best days for powder snow. The inputs required are a trained AI model and future weather forecast data (daily temperature and snowfall). The server inputs this data into the AI ​​model to predict future snow conditions. Specifically, it works by listing the dates for which the prediction results (such as "very good," "good," or "poor") are available. The output is a list of the days predicted to be good for powder snow.

[0263] Step 5:

[0264] The server uses an emotion engine to obtain the user's emotional state. Sensor data (e.g., heart rate, facial recognition data) from the user's device is required as input. The server uses an emotion recognition algorithm to analyze the user's emotions from this sensor data. Specifically, the server collects sensor data and evaluates emotions using an algorithm. The output is the user's emotional state (e.g., excitement, anticipation, anxiety).

[0265] Step 6:

[0266] The device provides the prediction results to the user. The inputs required are a list of predicted powder days and the user's emotional state. The device generates a message based on this information and notifies the user. Specific operations include generating and notifying a message. For example, if the user is excited, the device sends a positive message such as "Next weekend will be perfect powder days!" The output is a customized notification message of the prediction results.

[0267] (Application example 2)

[0268] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0269] In modern food delivery services, methods for improving the accuracy of demand forecasts and increasing customer satisfaction are extremely important. However, systems that effectively utilize various factors such as weather, local characteristics, and past order data to predict future demand remain limited. Furthermore, there is a lack of means to recognize users' real-time emotions and provide customized notifications and services based on them. Therefore, there is a need to solve these issues and provide a more accurate and user-friendly demand forecasting system.

[0270] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0271] In this invention, the server includes a means for acquiring weather information, a means for acquiring past order data, a means for training a machine learning model using the acquired data, a means including an emotion engine for recognizing user emotions, and a means for providing the user with the prediction results. This makes it possible to integrate various data to achieve highly accurate demand forecasts and provide customized notifications and services based on the user's emotions.

[0272] The "weather information acquisition means" is a means for acquiring weather forecast data for a specific area.

[0273] The "means for obtaining past order data" is a means for obtaining order history from a past database.

[0274] A "machine learning model" is a model that uses a learning algorithm based on past data to predict future demand.

[0275] An "emotion engine" is a system for recognizing and analyzing a user's real-time emotions.

[0276] The "means for providing predicted results" is a means for notifying and providing the user with the results predicted based on the machine learning model.

[0277] The present invention provides a highly accurate system that integrates weather information, past order data, and user sentiment to predict food delivery demand and notify users. The system includes the following means:

[0278] Get weather information

[0279] The server retrieves weather information for a specific region from a weather API. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format in response. This data includes information such as average daily temperatures and precipitation amounts.

[0280] Obtaining historical order data

[0281] The server retrieves historical order data from a database, including past daily temperature, precipitation, and order counts for a particular region, forming a training data set for learning correlations between weather conditions and order counts.

[0282] Training an AI model

[0283] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting order numbers (labels). This training enables the model to predict order numbers under specific weather conditions.

[0284] Demand forecasting

[0285] The server uses a trained AI model to predict demand based on future weather forecast data. The weather forecast data, including average daily temperatures and precipitation, is input into the model to determine future order quantities. The server selects days with "high demand" and adds them to the list.

[0286] Utilizing the Emotion Engine

[0287] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[0288] Providing prediction results

[0289] The device takes the user's emotional state into account when providing predictions to the user. For example, if the user is in high spirits, it will notify them of high demand days in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data to suggest the best food delivery days for the user.

[0290] Specific use cases

[0291] User example: Suppose a user is planning to use food delivery services over the weekend. The device responds to the user's question, "What will the demand for food delivery be this weekend?" by obtaining the predicted results from the server. Furthermore, if the emotion engine evaluates the user's expectations highly, the device will notify the user, "High demand is predicted for next weekend! Please plan your order early."

[0292] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict demand. If the prediction results in a "good day for high demand," the device will display, based on the analysis results of the emotion engine, a message saying, "The high demand day you're looking forward to is next weekend."

[0293] Example prompt: A user asks, "What will the food delivery demand be in Tokyo next week?"

[0294] In this way, the system integrates a variety of data to achieve highly accurate demand forecasts and enables the provision of customized notifications and services based on user emotions.

[0295] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0296] Step 1:

[0297] The server retrieves weather information. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format as a response. This data includes average daily temperatures and precipitation amounts. The input is the region information and API key, and the output is the weather forecast data.

[0298] Step 2:

[0299] The server retrieves historical order data from a database, which includes past daily temperature, precipitation, and order counts for a particular region. The input is the region information and the output is the historical order data. The server uses SQL queries to extract the required data from the database.

[0300] Step 3:

[0301] The server uses past order data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn the correlation between past weather data and order numbers. The input is past order data and weather data, and the output is the trained AI model.

[0302] Step 4:

[0303] The server uses a trained AI model to predict demand from future weather forecast data. The weather forecast data is input into the model to predict future order numbers. The input is weather forecast data, and the output is the predicted future order numbers.

[0304] Step 5:

[0305] The server customizes the display of prediction results using an emotion engine that recognizes the user's emotions. The emotion engine measures the user's excitement and expectation by obtaining data from sensors (e.g., heart rate sensors and facial recognition technology) installed on the user's device. The input is sensor data, and the output is the user's emotional state.

[0306] Step 6:

[0307] The terminal provides the user with the prediction results. The prediction results are customized based on the user's emotional state. For example, if the user is excited, the terminal may notify the user, "High demand is predicted for the next weekend! Please plan your orders early." The inputs are the prediction results and the user's emotional state, and the output is a customized notification.

[0308] Step 7:

[0309] Users plan their food delivery orders based on notifications provided by their devices, which are timed to optimally accommodate predicted demand and user sentiment. The input is a customized notification, and the output is the user's plan of action.

[0310] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0311] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0312] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0313] [Second embodiment]

[0314] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0315] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0316] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0317] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0318] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0319] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0320] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0321] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0322] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0323] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0324] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0325] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0326] The present invention provides a system for accurately predicting powder weather conditions, which includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model, a means for predicting future snow quality, and a means for providing the prediction results to a user.

[0327] Get weather information

[0328] The server retrieves weather data for a specific location (e.g., a popular ski resort) from a weather API. It sends a request to the weather API and receives a JSON response containing near-future weather forecast data. This data includes information such as average daily temperatures and snowfall.

[0329] Obtaining past snow quality data

[0330] The server retrieves historical snow data, including past daily temperature, snowfall, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0331] Training an AI model

[0332] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0333] Powder weather forecast

[0334] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0335] Providing prediction results

[0336] The device will then provide the user with the forecast results, such as a list of predicted powder weather dates, so the user can plan their skiing or snowboarding trip.

[0337] Specific examples

[0338] User example: A user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining the predicted results from the server.

[0339] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict powder weather. If the forecast result is "2023-01-02," the device displays this to the user.

[0340] These steps allow users to know the best snow conditions at their destination in advance and plan their trip based on snow quality.

[0341] The processing flow will be explained below.

[0342] Step 1:

[0343] The server retrieves weather data for a specific location from the weather API. It sends a request to the weather API using the API key and receives a 10-day weather forecast in JSON format in response.

[0344] Step 2:

[0345] The server analyzes the weather data and extracts the average temperature and snowfall for each day, which are used as inputs for subsequent forecasting.

[0346] Step 3:

[0347] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality for that day (e.g., good, very good, poor).

[0348] Step 4:

[0349] The server separates historical snow quality data into features (temperature, snowfall) and labels (snow quality), which are then used to train a machine learning algorithm (e.g., a random forest classifier).

[0350] Step 5:

[0351] The server uses a trained machine learning model to predict future snow conditions based on weather forecast data, and adds dates that are deemed "very good" (ideal for powder) to the list.

[0352] Step 6:

[0353] The device retrieves the prediction results from the server and displays them to the user, including the dates of powder weather for the specific location.

[0354] Step 7:

[0355] Users can check the display on their device and plan their skiing or snowboarding trip based on the best powder weather conditions, ensuring they can enjoy the best conditions.

[0356] Example 1

[0357] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0358] Conventional snow condition prediction systems have struggled to effectively utilize weather forecast data and past data to accurately predict snow quality. This has made it difficult for users to plan optimal skiing or snowboarding trips, resulting in inconvenience. The present invention aims to solve these problems and provide a system that enables highly accurate prediction of powder weather.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0360] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to a user, means for acquiring and analyzing JSON-formatted weather forecast data from a weather API, means for acquiring detailed weather information based on a specific geographic location, means for formatting past weather data as a training set, and a terminal for displaying the prediction results in response to a user request, thereby enabling a user to obtain highly accurate predictions of powder days based on detailed weather forecasts and past data.

[0361] A "means for obtaining weather information" is a function for obtaining weather forecast data for a specific geographic location from an external weather API.

[0362] "Means for obtaining past snow quality data" is a function for collecting information on past temperatures, snowfall amounts, and snow quality in a specific area.

[0363] "Means for training machine learning models" refers to a function for training models based on machine learning algorithms using collected historical weather information and snow quality data.

[0364] "Means for predicting future snow quality based on a machine learning model" is a function that uses a trained machine learning model to input future weather forecast data and predict snow quality.

[0365] The "means for providing the predicted results to the user" is a function for displaying the predicted results of powder weather on the user's device.

[0366] "Means for obtaining and analyzing weather forecast data in JSON format from a weather API" is a function for analyzing weather forecast data in JSON format obtained from an external weather API and extracting the necessary information.

[0367] The "means for obtaining detailed weather information based on a specific geographic location" is a function for obtaining detailed weather forecast data for a region based on a geographic location specified by a user.

[0368] "Means for formatting historical weather data as a training set" is a function for formatting previously collected weather information and snow quality data into a format suitable for training machine learning models.

[0369] A "terminal that displays prediction results in response to a user request" is a device that receives prediction results from a server in response to a question or request entered by a user and displays them to the user.

[0370] The present invention describes a snow condition forecasting system that accurately predicts powder weather. The system includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model using the acquired data, a means for predicting future snow quality based on the machine learning model, and a means for providing the predicted results to a user. The details are described below.

[0371] Hardware and Software

[0372] The server is the main hardware responsible for data collection, analysis, training, and prediction. The main software tools include an HTTP client for sending and receiving requests to the weather API, a parser for parsing JSON data, and a machine learning framework containing machine learning algorithms (e.g., random forest classifier). The database is used to store historical weather information, snow quality data, and trained AI models.

[0373] The terminal is a device that receives a user request, obtains prediction results from the server, and displays them to the user. Examples of this include smartphone apps and web browsers.

[0374] Users are individuals who want to know the best snow conditions (powder weather) at their ski resorts. Users access the system via their terminals and check the forecast results.

[0375] Data processing and calculation

[0376] 1. Get weather information:

[0377] The server sends a request to the weather API to retrieve near-future weather data for a specific ski resort. The retrieved data is in JSON format and includes daily average temperatures, snowfall, humidity, etc. This data is then analyzed and the necessary information is stored in a database.

[0378] 2. Obtaining historical snow quality data:

[0379] The server retrieves historical temperature, snowfall, and daily snow quality data for a particular ski resort, formats this data as a training set, and stores it in a database.

[0380] 3. Training the AI ​​model:

[0381] The server uses historical weather and snow data to train an AI model (such as a random forest classifier), which is then used to predict snow quality based on future weather conditions.

[0382] 4. Powder Weather Forecast:

[0383] The server uses a trained AI model to predict future snow conditions based on weather forecast data, identifying days when the forecast results are "very good" (powder-friendly) and generating a list of those days.

[0384] 5. Providing prediction results:

[0385] The server sends a list of predicted powder weather days to the terminal in response to a user request, and the terminal displays the list to the user.

[0386] Specific examples

[0387] User example: If a user is planning to go to a particular ski resort (e.g., Niseko), they ask through their device, "When will the best days for powder snow at Niseko be?" The server retrieves weather data from the weather API and makes a prediction using a trained AI model. If the prediction results in "2023-01-02" being a good day for powder snow, the device displays this to the user.

[0388] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then uses past weather and snow data to train an AI model, which then uses future weather data to predict powder conditions. The server adds the date for which the forecast is "very good" (e.g., 2023-01-02) to a list and sends that date to the device.

[0389] Prompt Sentence Examples

[0390] User: "When is the best time for powder snow in Niseko?"

[0391] Response from the server: "The next good powder day is 2023-01-02."

[0392] User: "Based on recent weather forecasts, what's the snow forecast for this weekend?"

[0393] This system allows users to efficiently plan their skiing or snowboarding trips, allowing them to enjoy the best possible natural conditions.

[0394] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0395] Step 1:

[0396] Get weather information:

[0397] The server sends a request to a weather API to retrieve weather data for a geographic location specified by the user.

[0398] Input: A specific geographic location and forecast period

[0399] Output: Weather forecast data in JSON format (e.g., daily average temperature, snowfall, etc.)

[0400] What happens: The server sends a request to the weather API in the form "GET / weather?location=specified_location&days=10". The API response returns a JSON object containing weather data for the next 10 days. The server parses the data, extracts the necessary information (average temperature, snowfall, etc.), and stores it in a database.

[0401] Step 2:

[0402] Obtaining historical snow quality data:

[0403] The server retrieves historical weather and snow quality data for a particular ski resort from a database or external data source.

[0404] Input: Request for geographic location and specific time period

[0405] Output: Historical weather and snow data formatted for training purposes

[0406] What it does: The server sends the query "SELECT FROM historical_snow_data WHERE location="specified_location"" to retrieve data from the database. The retrieved data includes information on daily temperature, snowfall, and snow type, and is formatted as a training dataset for machine learning.

[0407] Step 3:

[0408] Training an AI model:

[0409] The server trains machine learning models using collected historical weather and snow data.

[0410] Input: Historical weather data (features) and snow quality data (labels)

[0411] Output: A trained machine learning model

[0412] Specific operation: The server trains a model using a random forest classifier using the format "train_model(past_weather_data, snow_quality_labels)". After training is complete, the model is saved using the format "model.save('snow_quality_predictor.model')".

[0413] Step 4:

[0414] Powder weather forecast:

[0415] The server uses a trained AI model to predict snow quality based on future weather forecast data.

[0416] Input: Future weather forecast data (average temperature, snowfall, etc.)

[0417] Output: Predicted future daily snow quality data

[0418] Specific operation: The server makes a prediction using future weather data in the form of "predictions = model.predict(future_weather_data)". Dates for which the prediction result is judged to be "very good" (suitable for powdery weather) are added to the list.

[0419] Step 5:

[0420] Providing prediction results:

[0421] The server provides the user with a list of predicted powder weather dates.

[0422] Input: User request (e.g., "When is the best time for powder weather in Niseko?")

[0423] Output: Prediction results (date list) displayed on the user's device

[0424] Specific operation: The server receives a user request, generates a list of predicted dates, and sends it to the terminal. The terminal displays this list to the user, providing information such as, "The next good day for powder weather is 2023-01-02."

[0425] (Application example 1)

[0426] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0427] Conventional food delivery systems create delivery plans without taking into account weather or past delay data, resulting in unexpected delays and inefficient route selection. Delivery delays are particularly frequent during bad weather such as snow or rain, resulting in reduced user satisfaction.

[0428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0429] In this invention, the server includes a means for acquiring weather information, a means for acquiring past data, and a means for using this data to train a machine learning model, which makes it possible to predict future conditions and to predict and notify delivery efficiency and potential delays.

[0430] The "weather information acquisition means" is a device or program that has the function of acquiring weather data for a specified area from an external data source.

[0431] A "historical data acquisition means" is a device or program for collecting historical weather conditions and related data for a particular area.

[0432] A "means for training a machine learning model" is a device or program that applies a machine learning algorithm using collected data to build and improve a predictive model.

[0433] A "means for predicting future conditions" is a device or program that uses a trained machine learning model to predict certain future conditions (e.g., the likelihood of delivery delays).

[0434] The "means for providing the predicted result to the user" is a device or program for notifying or displaying the predicted result on the user's device.

[0435] "Means for predicting and notifying delivery efficiency and possible delays" refers to a device or program that predicts delivery efficiency and possible delays based on future weather conditions and past data, and notifies the user of the results.

[0436] A system for predicting delivery efficiency and possible delays based on different weather conditions and providing this information to users is implemented as follows.

[0437] Overall system configuration

[0438] The system consists of the following major components:

[0439] 1. How to get weather information

[0440] 2. How to obtain past data

[0441] 3. Means of training machine learning models

[0442] 4. A means of predicting future conditions

[0443] 5. Means of providing prediction results to users

[0444] Get weather information

[0445] The server retrieves weather data for a specific location (e.g., a city) using a weather API. It sends a request to the weather API and receives a response in JSON format containing future weather forecast data. This data includes information such as average daily temperatures and snowfall amounts. Possible APIs to use include the Weather API or the OpenWeatherMap API.

[0446] Obtaining historical data

[0447] The server retrieves historical weather data for a specific location and delivery delay data for that period. This data includes daily temperature, snowfall, and delivery status (e.g., delayed, normal). This forms a training dataset for learning correlations between weather conditions and delivery delays.

[0448] Training a machine learning model

[0449] The server uses historical data to train an AI model using machine learning algorithms such as random forest classifiers, learning from past weather data (features) and resulting delivery statuses (labels). This training allows the model to predict delivery delays under specific weather conditions.

[0450] Predicting conditions

[0451] The server uses a trained AI model to predict delivery efficiency and the possibility of delays based on future weather forecast data. The weather forecast data includes daily average temperatures and snowfall amounts, and these are input into the model to determine future delivery status. Days with a high probability of a "delay" are selected, and the date and reason for the delay are added to a list.

[0452] Providing prediction results

[0453] The terminal provides the user with the predicted results, for example by displaying a list of predicted possible delay dates on the user's device, allowing the user to adjust their delivery schedule based on this information.

[0454] Examples of concrete examples and prompts

[0455] As a specific example, assume that the user makes the following inquiry:

[0456] Example prompt sentence:

[0457] Please predict the weather and possible delivery delays in Tokyo next Saturday.

[0458] By feeding this prompt into the generative AI model, we can get the following output:

[0459] Example output produced:

[0460] Next Saturday (2023-10-14) in Tokyo, the average temperature is predicted to be 5°C and snowfall 2cm. Based on this, there is a high possibility of delivery delays. Please leave early and take appropriate cold weather precautions when making deliveries.

[0461] This allows users to make appropriate preparations depending on the weather and delivery conditions.

[0462] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0463] Step 1:

[0464] The server retrieves weather information for the specified location.

[0465] Input: Location information

[0466] How it works: The server sends a request to a weather API (e.g., Weather API or OpenWeatherMap API) and retrieves future weather forecast data in JSON format.

[0467] Output: Weather forecast data (average temperature, snowfall, etc.)

[0468] Step 2:

[0469] The server retrieves historical weather data and delivery delay data.

[0470] Input: Location information, historical data sources

[0471] How it works: The server retrieves historical weather data and associated delivery delay information from a pre-defined database or external data sources, including daily temperature, snowfall, and delivery status (delayed, normal).

[0472] Output: Historical weather data and delivery delay data

[0473] Step 3:

[0474] The server trains the machine learning model using historical data.

[0475] Input: Historical weather data, delivery delay data

[0476] How it works: The server uses machine learning algorithms, such as a random forest classifier, to train historical weather data (features) and delivery status (labels), allowing the model to predict delivery delays under specific weather conditions.

[0477] Output: A trained machine learning model

[0478] Step 4:

[0479] The server predicts delivery efficiency and possible delays based on future weather forecast data.

[0480] Input: trained machine learning model, future weather forecast data

[0481] How it works: The server inputs future weather forecast data into the trained model to predict future delivery status (likely delays). It selects days where the predicted result is likely to be "delayed" and adds those dates and reasons to a list.

[0482] Output: Delivery delay prediction list

[0483] Step 5:

[0484] The terminal provides the prediction result to the user.

[0485] Input: Delivery delay prediction list

[0486] How it works: The device displays a list of predicted possible delay dates on the user's device, and notifies them via a smartphone app or web interface.

[0487] Output: Delay prediction notification

[0488] Step 6:

[0489] The user adjusts the delivery schedule.

[0490] Input: Delay forecast notification

[0491] How it works: The user adjusts their delivery schedule appropriately based on the forecast information provided, which may include changing delivery times or making advance preparations.

[0492] Output: Adjusted delivery schedule

[0493] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0494] The present invention provides a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes user emotions. The system includes a weather information acquisition means, a past snow quality data acquisition means, a machine learning model training means, a prediction means for future snow quality, a means for providing the prediction results to the user, and an emotion engine that recognizes user emotions.

[0495] Get weather information

[0496] The server retrieves weather data for a specific location from a weather API. It sends a request to the weather API using an API key and receives a 10-day weather forecast in JSON format in response. This data includes information such as average daily temperatures and snowfall amounts.

[0497] Obtaining past snow quality data

[0498] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0499] Training an AI model

[0500] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0501] Powder weather forecast

[0502] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0503] Utilizing the Emotion Engine

[0504] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[0505] Providing prediction results

[0506] When the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is in high spirits, the device will notify them of the perfect day for powdering in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data, and can suggest the best day for powdering for the user.

[0507] Specific examples

[0508] User example: Suppose a user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining a prediction result from the server. Furthermore, if the emotion engine evaluates the user's level of expectation highly, the device notifies the user, "Next weekend will be the best weather for powder snow!"

[0509] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict the best days for powder weather. If the prediction is "2023-01-02," the device will display "The best days for powder weather you're looking forward to are 2023-01-02" based on the analysis results of the emotion engine.

[0510] In this way, by predicting and notifying users of powder weather taking their emotions into consideration, we provide a system that allows users to enjoy a better experience.

[0511] The processing flow will be explained below.

[0512] Step 1:

[0513] The server retrieves weather data for a specific location from a weather API, uses an API key to access the weather API, and sends a request. From the returned JSON response, the server parses the 10-day weather forecast data and extracts the average temperature and snowfall for each day.

[0514] Step 2:

[0515] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and the snow quality for that day (e.g., good, very good, poor), and then collects and analyzes it.

[0516] Step 3:

[0517] The server trains a machine learning model based on past weather and snow quality data. Specifically, it uses a random forest classifier to train the model to take temperature and snowfall features as input and output snow quality. This model can then predict snow quality under specific weather conditions.

[0518] Step 4:

[0519] The server uses a trained machine learning model to predict snow quality based on future weather forecast data. It inputs average temperature and snowfall from 10 days of weather data and determines the predicted snow quality for each day. Days predicted as "very good" (perfect for powder) are added to the list.

[0520] Step 5:

[0521] To recognize the user's emotions, the server acquires the user's emotion data using an emotion engine. The emotion engine collects data from sensors (e.g., heart rate sensors, facial recognition technology) installed on the user's device and analyzes the user's excitement and expectation.

[0522] Step 6:

[0523] The device receives the prediction results and the user's emotional data from the server. Based on this, the prediction results are displayed in a way that is optimal for the user. For example, if the user is in an excited state, the device will notify the user of the date when it will be a good day for powdering in a more positive way.

[0524] Step 7:

[0525] The user checks the display on their device and plans their skiing or snowboarding trip based on the best powder weather. Information, including the analysis results of the emotion engine, allows the user to enjoy the trip under the best conditions. Specifically, the user will receive a notification saying, "Next weekend is the best powder weather!" and adjust their travel plans to target that day.

[0526] Example 2

[0527] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] Conventional snow condition prediction systems can predict future snow conditions based on weather information and past snow quality data, but they cannot customize the prediction results to take the user's emotional state into account. This makes it difficult to provide optimal information to users. Furthermore, detailed data analysis and customization to improve prediction accuracy are time-consuming. The purpose of this invention is to solve these problems and provide a more accurate and user-friendly snow condition prediction system.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0530] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to the user, means for acquiring the user's emotional state, and means for customizing the prediction results according to the user's emotional state. This enables highly accurate prediction and notification of powder weather according to the user's emotions.

[0531] "Weather information" means data about weather conditions, such as temperature, snowfall, and wind speed, at a particular location.

[0532] "Snow Quality Data" means information about past or current snow conditions at a particular location, including ratings such as good, very good, or poor.

[0533] A "machine learning model" is an algorithm that uses past data to learn certain patterns and relationships, and then uses that to predict future events or situations.

[0534] "Weather Forecast Data" means data that indicates future weather conditions at a particular location, including predicted temperature, snowfall, and wind speed.

[0535] "Prediction results" are information about future snow quality and weather conditions predicted by the machine learning model.

[0536] "User" refers to any individual or organization that uses this system to obtain weather and snow quality information.

[0537] "Emotional state" refers to a user's current mental and emotional situation or state, including emotions such as excitement, anticipation, and anxiety.

[0538] "Customization" means changing the way prediction results and information are presented according to the user's needs and situation.

[0539] This invention relates to a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes the user's emotions. This system is realized using the following hardware and software.

[0540] First, the server uses a weather API (e.g., OpenWeatherMap) to obtain weather data for a specific location. Specifically, the server uses an API key to send a request to the weather API and receives 10-day weather forecast data in JSON format in response. This data includes information such as the average daily temperature and amount of snowfall. For example, the server can obtain the required data by entering a prompt statement such as "I want to get the 10-day weather forecast for Niseko."

[0541] The server then retrieves historical snow quality data from a database that stores past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a specific location. This information is used to form a training dataset for learning correlations between weather conditions and snow quality. For example, the server can collect the required data by entering a prompt statement such as, "Get snow quality data for Niseko for the past year."

[0542] The server then uses machine learning algorithms, such as a random forest classifier, to train an AI model based on historical data. This training enables the model to predict snow conditions under specific weather conditions. For example, the server can do this by entering the prompt "Train a snow condition prediction model using historical data."

[0543] Using the trained AI model, the server predicts snow quality from future weather forecast data. Specifically, the model inputs the daily average temperature and snowfall amount from the weather forecast data to determine future snow quality. Days for which the forecast result is "very good" (powder weather) are added to a list and the date is saved. For example, the server can make this prediction by entering a prompt statement such as "Predict powder weather conditions in Niseko for the next 10 days."

[0544] Furthermore, the server uses an emotion engine to recognize the user's emotional state. The emotion engine acquires data from sensors (e.g., heart rate sensors, facial recognition technology) installed in the user's device and measures the user's level of excitement and expectation. This allows the server to analyze the user's emotions under specific conditions. For example, emotion analysis is performed by the server inputting a prompt statement such as, "Analyze the user's emotional state and evaluate the expectation level."

[0545] Finally, when the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is excited, it will notify them of the perfect day for powder snow in a more positive manner. The device analyzes past behavioral history and emotional data from the emotion engine, and can suggest the best day for powder snow for the user. For example, the device can heighten the user's expectations by notifying them, "Next weekend will be the perfect day for powder snow!"

[0546] In this way, a specific system configuration is provided for highly accurate prediction and notification of powder weather according to the user's feelings.

[0547] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0548] Step 1:

[0549] The server retrieves weather information. The input is the name of a specific location (e.g., a ski resort) and the access key provided by the weather API. The server accesses the weather API (e.g., OpenWeatherMap) and retrieves 10-day weather forecast data for the specific location. Specifically, the server generates an API request and accesses the URL using the HTTP protocol. The output is data such as the average daily temperature and snowfall amount in JSON format.

[0550] Step 2:

[0551] The server retrieves historical snow quality data. The input requires a specific location and time period (e.g., the past year). The server connects to the database and queries for snow quality data (temperature, snowfall, snow quality rating) based on the specified location and time period. Specifically, it runs an SQL query to extract the relevant data and converts it into a format that can be used within the program. The output is a dataset of the query results.

[0552] Step 3:

[0553] The server trains the AI ​​model. Historical weather data and snow quality data are required as input. The server preprocesses this data (e.g., imputing missing values ​​and normalizing data) and trains it using a machine learning algorithm (e.g., random forest classifier). Specifically, it preprocesses the data and trains the model using a machine learning library. The output is a trained AI model.

[0554] Step 4:

[0555] The server predicts the best days for powder snow. The inputs required are a trained AI model and future weather forecast data (daily temperature and snowfall). The server inputs this data into the AI ​​model to predict future snow conditions. Specifically, it works by listing the dates for which the prediction results (such as "very good," "good," or "poor") are available. The output is a list of the days predicted to be good for powder snow.

[0556] Step 5:

[0557] The server uses an emotion engine to obtain the user's emotional state. Sensor data (e.g., heart rate, facial recognition data) from the user's device is required as input. The server uses an emotion recognition algorithm to analyze the user's emotions from this sensor data. Specifically, the server collects sensor data and evaluates emotions using an algorithm. The output is the user's emotional state (e.g., excitement, anticipation, anxiety).

[0558] Step 6:

[0559] The device provides the prediction results to the user. The inputs required are a list of predicted powder days and the user's emotional state. The device generates a message based on this information and notifies the user. Specific operations include generating and notifying a message. For example, if the user is excited, the device sends a positive message such as "Next weekend will be perfect powder days!" The output is a customized notification message of the prediction results.

[0560] (Application example 2)

[0561] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0562] In modern food delivery services, methods for improving the accuracy of demand forecasts and increasing customer satisfaction are extremely important. However, systems that effectively utilize various factors such as weather, local characteristics, and past order data to predict future demand remain limited. Furthermore, there is a lack of means to recognize users' real-time emotions and provide customized notifications and services based on them. Therefore, there is a need to solve these issues and provide a more accurate and user-friendly demand forecasting system.

[0563] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0564] In this invention, the server includes a means for acquiring weather information, a means for acquiring past order data, a means for training a machine learning model using the acquired data, a means including an emotion engine for recognizing user emotions, and a means for providing the user with the prediction results. This makes it possible to integrate various data to achieve highly accurate demand forecasts and provide customized notifications and services based on the user's emotions.

[0565] The "weather information acquisition means" is a means for acquiring weather forecast data for a specific area.

[0566] The "means for obtaining past order data" is a means for obtaining order history from a past database.

[0567] A "machine learning model" is a model that uses a learning algorithm based on past data to predict future demand.

[0568] An "emotion engine" is a system for recognizing and analyzing a user's real-time emotions.

[0569] The "means for providing predicted results" is a means for notifying and providing the user with the results predicted based on the machine learning model.

[0570] The present invention provides a highly accurate system that integrates weather information, past order data, and user sentiment to predict food delivery demand and notify users. The system includes the following means:

[0571] Get weather information

[0572] The server retrieves weather information for a specific region from a weather API. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format in response. This data includes information such as average daily temperatures and precipitation amounts.

[0573] Obtaining historical order data

[0574] The server retrieves historical order data from a database, including past daily temperature, precipitation, and order counts for a particular region, forming a training data set for learning correlations between weather conditions and order counts.

[0575] Training an AI model

[0576] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting order numbers (labels). This training enables the model to predict order numbers under specific weather conditions.

[0577] Demand forecasting

[0578] The server uses a trained AI model to predict demand based on future weather forecast data. The weather forecast data, including average daily temperatures and precipitation, is input into the model to determine future order quantities. The server selects days with "high demand" and adds them to the list.

[0579] Utilizing the Emotion Engine

[0580] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[0581] Providing prediction results

[0582] The device takes the user's emotional state into account when providing predictions to the user. For example, if the user is in high spirits, it will notify them of high demand days in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data to suggest the best food delivery days for the user.

[0583] Specific use cases

[0584] User example: Suppose a user is planning to use food delivery services over the weekend. The device responds to the user's question, "What will the demand for food delivery be this weekend?" by obtaining the predicted results from the server. Furthermore, if the emotion engine evaluates the user's expectations highly, the device will notify the user, "High demand is predicted for next weekend! Please plan your order early."

[0585] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict demand. If the prediction results in a "good day for high demand," the device will display, based on the analysis results of the emotion engine, a message saying, "The high demand day you're looking forward to is next weekend."

[0586] Example prompt: A user asks, "What will the food delivery demand be in Tokyo next week?"

[0587] In this way, the system integrates a variety of data to achieve highly accurate demand forecasts and enables the provision of customized notifications and services based on user emotions.

[0588] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0589] Step 1:

[0590] The server retrieves weather information. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format as a response. This data includes average daily temperatures and precipitation amounts. The input is the region information and API key, and the output is the weather forecast data.

[0591] Step 2:

[0592] The server retrieves historical order data from a database, which includes past daily temperature, precipitation, and order counts for a particular region. The input is the region information and the output is the historical order data. The server uses SQL queries to extract the required data from the database.

[0593] Step 3:

[0594] The server uses past order data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn the correlation between past weather data and order numbers. The input is past order data and weather data, and the output is the trained AI model.

[0595] Step 4:

[0596] The server uses a trained AI model to predict demand from future weather forecast data. The weather forecast data is input into the model to predict future order numbers. The input is weather forecast data, and the output is the predicted future order numbers.

[0597] Step 5:

[0598] The server customizes the display of prediction results using an emotion engine that recognizes the user's emotions. The emotion engine measures the user's excitement and expectation by obtaining data from sensors (e.g., heart rate sensors and facial recognition technology) installed on the user's device. The input is sensor data, and the output is the user's emotional state.

[0599] Step 6:

[0600] The terminal provides the user with the prediction results. The prediction results are customized based on the user's emotional state. For example, if the user is excited, the terminal may notify the user, "High demand is predicted for the next weekend! Please plan your orders early." The inputs are the prediction results and the user's emotional state, and the output is a customized notification.

[0601] Step 7:

[0602] Users plan their food delivery orders based on notifications provided by their devices, which are timed to optimally accommodate predicted demand and user sentiment. The input is a customized notification, and the output is the user's plan of action.

[0603] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0604] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0605] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0606] [Third embodiment]

[0607] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0608] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0609] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0610] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0611] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0612] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0613] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0614] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0615] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0616] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0617] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0618] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0619] The present invention provides a system for accurately predicting powder weather conditions, which includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model, a means for predicting future snow quality, and a means for providing the prediction results to a user.

[0620] Get weather information

[0621] The server retrieves weather data for a specific location (e.g., a popular ski resort) from a weather API. It sends a request to the weather API and receives a JSON response containing near-future weather forecast data. This data includes information such as average daily temperatures and snowfall.

[0622] Obtaining past snow quality data

[0623] The server retrieves historical snow data, including past daily temperature, snowfall, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0624] Training an AI model

[0625] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0626] Powder weather forecast

[0627] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0628] Providing prediction results

[0629] The device will then provide the user with the forecast results, such as a list of predicted powder weather dates, so the user can plan their skiing or snowboarding trip.

[0630] Specific examples

[0631] User example: A user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining the predicted results from the server.

[0632] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict powder weather. If the forecast result is "2023-01-02," the device displays this to the user.

[0633] These steps allow users to know the best snow conditions at their destination in advance and plan their trip based on snow quality.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] The server retrieves weather data for a specific location from the weather API. It sends a request to the weather API using the API key and receives a 10-day weather forecast in JSON format in response.

[0637] Step 2:

[0638] The server analyzes the weather data and extracts the average temperature and snowfall for each day, which are used as inputs for subsequent forecasting.

[0639] Step 3:

[0640] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality for that day (e.g., good, very good, poor).

[0641] Step 4:

[0642] The server separates historical snow quality data into features (temperature, snowfall) and labels (snow quality), which are then used to train a machine learning algorithm (e.g., a random forest classifier).

[0643] Step 5:

[0644] The server uses a trained machine learning model to predict future snow conditions based on weather forecast data, and adds dates that are deemed "very good" (ideal for powder) to the list.

[0645] Step 6:

[0646] The device retrieves the prediction results from the server and displays them to the user, including the dates of powder weather for the specific location.

[0647] Step 7:

[0648] Users can check the display on their device and plan their skiing or snowboarding trip based on the best powder weather conditions, ensuring they can enjoy the best conditions.

[0649] Example 1

[0650] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0651] Conventional snow condition prediction systems have struggled to effectively utilize weather forecast data and past data to accurately predict snow quality. This has made it difficult for users to plan optimal skiing or snowboarding trips, resulting in inconvenience. The present invention aims to solve these problems and provide a system that enables highly accurate prediction of powder weather.

[0652] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0653] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to a user, means for acquiring and analyzing JSON-formatted weather forecast data from a weather API, means for acquiring detailed weather information based on a specific geographic location, means for formatting past weather data as a training set, and a terminal for displaying the prediction results in response to a user request, thereby enabling a user to obtain highly accurate predictions of powder days based on detailed weather forecasts and past data.

[0654] A "means for obtaining weather information" is a function for obtaining weather forecast data for a specific geographic location from an external weather API.

[0655] "Means for obtaining past snow quality data" is a function for collecting information on past temperatures, snowfall amounts, and snow quality in a specific area.

[0656] "Means for training machine learning models" refers to a function for training models based on machine learning algorithms using collected historical weather information and snow quality data.

[0657] "Means for predicting future snow quality based on a machine learning model" is a function that uses a trained machine learning model to input future weather forecast data and predict snow quality.

[0658] The "means for providing the predicted results to the user" is a function for displaying the predicted results of powder weather on the user's device.

[0659] "Means for obtaining and analyzing weather forecast data in JSON format from a weather API" is a function for analyzing weather forecast data in JSON format obtained from an external weather API and extracting the necessary information.

[0660] The "means for obtaining detailed weather information based on a specific geographic location" is a function for obtaining detailed weather forecast data for a region based on a geographic location specified by a user.

[0661] "Means for formatting historical weather data as a training set" is a function for formatting previously collected weather information and snow quality data into a format suitable for training machine learning models.

[0662] A "terminal that displays prediction results in response to a user request" is a device that receives prediction results from a server in response to a question or request entered by a user and displays them to the user.

[0663] The present invention describes a snow condition forecasting system that accurately predicts powder weather. The system includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model using the acquired data, a means for predicting future snow quality based on the machine learning model, and a means for providing the predicted results to a user. The details are described below.

[0664] Hardware and Software

[0665] The server is the main hardware responsible for data collection, analysis, training, and prediction. The main software tools include an HTTP client for sending and receiving requests to the weather API, a parser for parsing JSON data, and a machine learning framework containing machine learning algorithms (e.g., random forest classifier). The database is used to store historical weather information, snow quality data, and trained AI models.

[0666] The terminal is a device that receives a user request, obtains prediction results from the server, and displays them to the user. Examples of this include smartphone apps and web browsers.

[0667] Users are individuals who want to know the best snow conditions (powder weather) at their ski resorts. Users access the system via their terminals and check the forecast results.

[0668] Data processing and calculation

[0669] 1. Get weather information:

[0670] The server sends a request to the weather API to retrieve near-future weather data for a specific ski resort. The retrieved data is in JSON format and includes daily average temperatures, snowfall, humidity, etc. This data is then analyzed and the necessary information is stored in a database.

[0671] 2. Obtaining historical snow quality data:

[0672] The server retrieves historical temperature, snowfall, and daily snow quality data for a particular ski resort, formats this data as a training set, and stores it in a database.

[0673] 3. Training the AI ​​model:

[0674] The server uses historical weather and snow data to train an AI model (such as a random forest classifier), which is then used to predict snow quality based on future weather conditions.

[0675] 4. Powder Weather Forecast:

[0676] The server uses a trained AI model to predict future snow conditions based on weather forecast data, identifying days when the forecast results are "very good" (powder-friendly) and generating a list of those days.

[0677] 5. Providing prediction results:

[0678] The server sends a list of predicted powder weather days to the terminal in response to a user request, and the terminal displays the list to the user.

[0679] Specific examples

[0680] User example: If a user is planning to go to a particular ski resort (e.g., Niseko), they ask through their device, "When will the best days for powder snow at Niseko be?" The server retrieves weather data from the weather API and makes a prediction using a trained AI model. If the prediction results in "2023-01-02" being a good day for powder snow, the device displays this to the user.

[0681] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then uses past weather and snow data to train an AI model, which then uses future weather data to predict powder conditions. The server adds the date for which the forecast is "very good" (e.g., 2023-01-02) to a list and sends that date to the device.

[0682] Prompt Sentence Examples

[0683] User: "When is the best time for powder snow in Niseko?"

[0684] Response from the server: "The next good powder day is 2023-01-02."

[0685] User: "Based on recent weather forecasts, what's the snow forecast for this weekend?"

[0686] This system allows users to efficiently plan their skiing or snowboarding trips, allowing them to enjoy the best possible natural conditions.

[0687] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0688] Step 1:

[0689] Get weather information:

[0690] The server sends a request to a weather API to retrieve weather data for a geographic location specified by the user.

[0691] Input: A specific geographic location and forecast period

[0692] Output: Weather forecast data in JSON format (e.g., daily average temperature, snowfall, etc.)

[0693] What happens: The server sends a request to the weather API in the form "GET / weather?location=specified_location&days=10". The API response returns a JSON object containing weather data for the next 10 days. The server parses the data, extracts the necessary information (average temperature, snowfall, etc.), and stores it in a database.

[0694] Step 2:

[0695] Obtaining historical snow quality data:

[0696] The server retrieves historical weather and snow quality data for a particular ski resort from a database or external data source.

[0697] Input: Request for geographic location and specific time period

[0698] Output: Historical weather and snow data formatted for training purposes

[0699] What it does: The server sends the query "SELECT FROM historical_snow_data WHERE location="specified_location"" to retrieve data from the database. The retrieved data includes information on daily temperature, snowfall, and snow type, and is formatted as a training dataset for machine learning.

[0700] Step 3:

[0701] Training an AI model:

[0702] The server trains machine learning models using collected historical weather and snow data.

[0703] Input: Historical weather data (features) and snow quality data (labels)

[0704] Output: A trained machine learning model

[0705] Specific operation: The server trains a model using a random forest classifier using the format "train_model(past_weather_data, snow_quality_labels)". After training is complete, the model is saved using the format "model.save('snow_quality_predictor.model')".

[0706] Step 4:

[0707] Powder weather forecast:

[0708] The server uses a trained AI model to predict snow quality based on future weather forecast data.

[0709] Input: Future weather forecast data (average temperature, snowfall, etc.)

[0710] Output: Predicted future daily snow quality data

[0711] Specific operation: The server makes a prediction using future weather data in the form of "predictions = model.predict(future_weather_data)". Dates for which the prediction result is judged to be "very good" (suitable for powdery weather) are added to the list.

[0712] Step 5:

[0713] Providing prediction results:

[0714] The server provides the user with a list of predicted powder weather dates.

[0715] Input: User request (e.g., "When is the best time for powder weather in Niseko?")

[0716] Output: Prediction results (date list) displayed on the user's device

[0717] Specific operation: The server receives a user request, generates a list of predicted dates, and sends it to the terminal. The terminal displays this list to the user, providing information such as, "The next good day for powder weather is 2023-01-02."

[0718] (Application example 1)

[0719] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0720] Conventional food delivery systems create delivery plans without taking into account weather or past delay data, resulting in unexpected delays and inefficient route selection. Delivery delays are particularly frequent during bad weather such as snow or rain, resulting in reduced user satisfaction.

[0721] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0722] In this invention, the server includes a means for acquiring weather information, a means for acquiring past data, and a means for using this data to train a machine learning model, which makes it possible to predict future conditions and to predict and notify delivery efficiency and potential delays.

[0723] The "weather information acquisition means" is a device or program that has the function of acquiring weather data for a specified area from an external data source.

[0724] A "historical data acquisition means" is a device or program for collecting historical weather conditions and related data for a particular area.

[0725] A "means for training a machine learning model" is a device or program that applies a machine learning algorithm using collected data to build and improve a predictive model.

[0726] A "means for predicting future conditions" is a device or program that uses a trained machine learning model to predict certain future conditions (e.g., the likelihood of delivery delays).

[0727] The "means for providing the predicted result to the user" is a device or program for notifying or displaying the predicted result on the user's device.

[0728] "Means for predicting and notifying delivery efficiency and possible delays" refers to a device or program that predicts delivery efficiency and possible delays based on future weather conditions and past data, and notifies the user of the results.

[0729] A system for predicting delivery efficiency and possible delays based on different weather conditions and providing this information to users is implemented as follows.

[0730] Overall system configuration

[0731] The system consists of the following major components:

[0732] 1. How to get weather information

[0733] 2. How to obtain past data

[0734] 3. Means of training machine learning models

[0735] 4. A means of predicting future conditions

[0736] 5. Means of providing prediction results to users

[0737] Get weather information

[0738] The server retrieves weather data for a specific location (e.g., a city) using a weather API. It sends a request to the weather API and receives a response in JSON format containing future weather forecast data. This data includes information such as average daily temperatures and snowfall amounts. Possible APIs to use include the Weather API or the OpenWeatherMap API.

[0739] Obtaining historical data

[0740] The server retrieves historical weather data for a specific location and delivery delay data for that period. This data includes daily temperature, snowfall, and delivery status (e.g., delayed, normal). This forms a training dataset for learning correlations between weather conditions and delivery delays.

[0741] Training a machine learning model

[0742] The server uses historical data to train an AI model using machine learning algorithms such as random forest classifiers, learning from past weather data (features) and resulting delivery statuses (labels). This training allows the model to predict delivery delays under specific weather conditions.

[0743] Predicting conditions

[0744] The server uses a trained AI model to predict delivery efficiency and the possibility of delays based on future weather forecast data. The weather forecast data includes daily average temperatures and snowfall amounts, and these are input into the model to determine future delivery status. Days with a high probability of a "delay" are selected, and the date and reason for the delay are added to a list.

[0745] Providing prediction results

[0746] The terminal provides the user with the predicted results, for example by displaying a list of predicted possible delay dates on the user's device, allowing the user to adjust their delivery schedule based on this information.

[0747] Examples of concrete examples and prompts

[0748] As a specific example, assume that the user makes the following inquiry:

[0749] Example prompt sentence:

[0750] Please predict the weather and possible delivery delays in Tokyo next Saturday.

[0751] By feeding this prompt into the generative AI model, we can get the following output:

[0752] Example output produced:

[0753] Next Saturday (2023-10-14) in Tokyo, the average temperature is predicted to be 5°C and snowfall 2cm. Based on this, there is a high possibility of delivery delays. Please leave early and take appropriate cold weather precautions when making deliveries.

[0754] This allows users to make appropriate preparations depending on the weather and delivery conditions.

[0755] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0756] Step 1:

[0757] The server retrieves weather information for the specified location.

[0758] Input: Location information

[0759] How it works: The server sends a request to a weather API (e.g., Weather API or OpenWeatherMap API) and retrieves future weather forecast data in JSON format.

[0760] Output: Weather forecast data (average temperature, snowfall, etc.)

[0761] Step 2:

[0762] The server retrieves historical weather data and delivery delay data.

[0763] Input: Location information, historical data sources

[0764] How it works: The server retrieves historical weather data and associated delivery delay information from a pre-defined database or external data sources, including daily temperature, snowfall, and delivery status (delayed, normal).

[0765] Output: Historical weather data and delivery delay data

[0766] Step 3:

[0767] The server trains the machine learning model using historical data.

[0768] Input: Historical weather data, delivery delay data

[0769] How it works: The server uses machine learning algorithms, such as a random forest classifier, to train historical weather data (features) and delivery status (labels), allowing the model to predict delivery delays under specific weather conditions.

[0770] Output: A trained machine learning model

[0771] Step 4:

[0772] The server predicts delivery efficiency and possible delays based on future weather forecast data.

[0773] Input: trained machine learning model, future weather forecast data

[0774] How it works: The server inputs future weather forecast data into the trained model to predict future delivery status (likely delays). It selects days where the predicted result is likely to be "delayed" and adds those dates and reasons to a list.

[0775] Output: Delivery delay prediction list

[0776] Step 5:

[0777] The terminal provides the prediction result to the user.

[0778] Input: Delivery delay prediction list

[0779] How it works: The device displays a list of predicted possible delay dates on the user's device, and notifies them via a smartphone app or web interface.

[0780] Output: Delay prediction notification

[0781] Step 6:

[0782] The user adjusts the delivery schedule.

[0783] Input: Delay forecast notification

[0784] How it works: The user adjusts their delivery schedule appropriately based on the forecast information provided, which may include changing delivery times or making advance preparations.

[0785] Output: Adjusted delivery schedule

[0786] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0787] The present invention provides a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes user emotions. The system includes a weather information acquisition means, a past snow quality data acquisition means, a machine learning model training means, a prediction means for future snow quality, a means for providing the prediction results to the user, and an emotion engine that recognizes user emotions.

[0788] Get weather information

[0789] The server retrieves weather data for a specific location from a weather API. It sends a request to the weather API using an API key and receives a 10-day weather forecast in JSON format in response. This data includes information such as average daily temperatures and snowfall amounts.

[0790] Obtaining past snow quality data

[0791] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0792] Training an AI model

[0793] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0794] Powder weather forecast

[0795] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0796] Utilizing the Emotion Engine

[0797] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[0798] Providing prediction results

[0799] When the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is in high spirits, the device will notify them of the perfect day for powdering in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data, and can suggest the best day for powdering for the user.

[0800] Specific examples

[0801] User example: Suppose a user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining a prediction result from the server. Furthermore, if the emotion engine evaluates the user's level of expectation highly, the device notifies the user, "Next weekend will be the best weather for powder snow!"

[0802] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict the best days for powder weather. If the prediction is "2023-01-02," the device will display "The best days for powder weather you're looking forward to are 2023-01-02" based on the analysis results of the emotion engine.

[0803] In this way, by predicting and notifying users of powder weather taking their emotions into consideration, we provide a system that allows users to enjoy a better experience.

[0804] The processing flow will be explained below.

[0805] Step 1:

[0806] The server retrieves weather data for a specific location from a weather API, uses an API key to access the weather API, and sends a request. From the returned JSON response, the server parses the 10-day weather forecast data and extracts the average temperature and snowfall for each day.

[0807] Step 2:

[0808] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and the snow quality for that day (e.g., good, very good, poor), and then collects and analyzes it.

[0809] Step 3:

[0810] The server trains a machine learning model based on past weather and snow quality data. Specifically, it uses a random forest classifier to train the model to take temperature and snowfall features as input and output snow quality. This model can then predict snow quality under specific weather conditions.

[0811] Step 4:

[0812] The server uses a trained machine learning model to predict snow quality based on future weather forecast data. It inputs average temperature and snowfall from 10 days of weather data and determines the predicted snow quality for each day. Days predicted as "very good" (perfect for powder) are added to the list.

[0813] Step 5:

[0814] To recognize the user's emotions, the server acquires the user's emotion data using an emotion engine. The emotion engine collects data from sensors (e.g., heart rate sensors, facial recognition technology) installed on the user's device and analyzes the user's excitement and expectation.

[0815] Step 6:

[0816] The device receives the prediction results and the user's emotional data from the server. Based on this, the prediction results are displayed in a way that is optimal for the user. For example, if the user is in an excited state, the device will notify the user of the date when it will be a good day for powdering in a more positive way.

[0817] Step 7:

[0818] The user checks the display on their device and plans their skiing or snowboarding trip based on the best powder weather. Information, including the analysis results of the emotion engine, allows the user to enjoy the trip under the best conditions. Specifically, the user will receive a notification saying, "Next weekend is the best powder weather!" and adjust their travel plans to target that day.

[0819] Example 2

[0820] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0821] Conventional snow condition prediction systems can predict future snow conditions based on weather information and past snow quality data, but they cannot customize the prediction results to take the user's emotional state into account. This makes it difficult to provide optimal information to users. Furthermore, detailed data analysis and customization to improve prediction accuracy are time-consuming. The purpose of this invention is to solve these problems and provide a more accurate and user-friendly snow condition prediction system.

[0822] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0823] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to the user, means for acquiring the user's emotional state, and means for customizing the prediction results according to the user's emotional state. This enables highly accurate prediction and notification of powder weather according to the user's emotions.

[0824] "Weather information" means data about weather conditions, such as temperature, snowfall, and wind speed, at a particular location.

[0825] "Snow Quality Data" means information about past or current snow conditions at a particular location, including ratings such as good, very good, or poor.

[0826] A "machine learning model" is an algorithm that uses past data to learn certain patterns and relationships, and then uses that to predict future events or situations.

[0827] "Weather Forecast Data" means data that indicates future weather conditions at a particular location, including predicted temperature, snowfall, and wind speed.

[0828] "Prediction results" are information about future snow quality and weather conditions predicted by the machine learning model.

[0829] "User" refers to any individual or organization that uses this system to obtain weather and snow quality information.

[0830] "Emotional state" refers to a user's current mental and emotional situation or state, including emotions such as excitement, anticipation, and anxiety.

[0831] "Customization" means changing the way prediction results and information are presented according to the user's needs and situation.

[0832] This invention relates to a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes the user's emotions. This system is realized using the following hardware and software.

[0833] First, the server uses a weather API (e.g., OpenWeatherMap) to obtain weather data for a specific location. Specifically, the server uses an API key to send a request to the weather API and receives 10-day weather forecast data in JSON format in response. This data includes information such as the average daily temperature and amount of snowfall. For example, the server can obtain the required data by entering a prompt statement such as "I want to get the 10-day weather forecast for Niseko."

[0834] The server then retrieves historical snow quality data from a database that stores past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a specific location. This information is used to form a training dataset for learning correlations between weather conditions and snow quality. For example, the server can collect the required data by entering a prompt statement such as, "Get snow quality data for Niseko for the past year."

[0835] The server then uses machine learning algorithms, such as a random forest classifier, to train an AI model based on historical data. This training enables the model to predict snow conditions under specific weather conditions. For example, the server can do this by entering the prompt "Train a snow condition prediction model using historical data."

[0836] Using the trained AI model, the server predicts snow quality from future weather forecast data. Specifically, the model inputs the daily average temperature and snowfall amount from the weather forecast data to determine future snow quality. Days for which the forecast result is "very good" (powder weather) are added to a list and the date is saved. For example, the server can make this prediction by entering a prompt statement such as "Predict powder weather conditions in Niseko for the next 10 days."

[0837] Furthermore, the server uses an emotion engine to recognize the user's emotional state. The emotion engine acquires data from sensors (e.g., heart rate sensors, facial recognition technology) installed in the user's device and measures the user's level of excitement and expectation. This allows the server to analyze the user's emotions under specific conditions. For example, emotion analysis is performed by the server inputting a prompt statement such as, "Analyze the user's emotional state and evaluate the expectation level."

[0838] Finally, when the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is excited, it will notify them of the perfect day for powder snow in a more positive manner. The device analyzes past behavioral history and emotional data from the emotion engine, and can suggest the best day for powder snow for the user. For example, the device can heighten the user's expectations by notifying them, "Next weekend will be the perfect day for powder snow!"

[0839] In this way, a specific system configuration is provided for highly accurate prediction and notification of powder weather according to the user's feelings.

[0840] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0841] Step 1:

[0842] The server retrieves weather information. The input is the name of a specific location (e.g., a ski resort) and the access key provided by the weather API. The server accesses the weather API (e.g., OpenWeatherMap) and retrieves 10-day weather forecast data for the specific location. Specifically, the server generates an API request and accesses the URL using the HTTP protocol. The output is data such as the average daily temperature and snowfall amount in JSON format.

[0843] Step 2:

[0844] The server retrieves historical snow quality data. The input requires a specific location and time period (e.g., the past year). The server connects to the database and queries for snow quality data (temperature, snowfall, snow quality rating) based on the specified location and time period. Specifically, it runs an SQL query to extract the relevant data and converts it into a format that can be used within the program. The output is a dataset of the query results.

[0845] Step 3:

[0846] The server trains the AI ​​model. Historical weather data and snow quality data are required as input. The server preprocesses this data (e.g., imputing missing values ​​and normalizing data) and trains it using a machine learning algorithm (e.g., random forest classifier). Specifically, it preprocesses the data and trains the model using a machine learning library. The output is a trained AI model.

[0847] Step 4:

[0848] The server predicts the best days for powder snow. The inputs required are a trained AI model and future weather forecast data (daily temperature and snowfall). The server inputs this data into the AI ​​model to predict future snow conditions. Specifically, it works by listing the dates for which the prediction results (such as "very good," "good," or "poor") are available. The output is a list of the days predicted to be good for powder snow.

[0849] Step 5:

[0850] The server uses an emotion engine to obtain the user's emotional state. Sensor data (e.g., heart rate, facial recognition data) from the user's device is required as input. The server uses an emotion recognition algorithm to analyze the user's emotions from this sensor data. Specifically, the server collects sensor data and evaluates emotions using an algorithm. The output is the user's emotional state (e.g., excitement, anticipation, anxiety).

[0851] Step 6:

[0852] The device provides the prediction results to the user. The inputs required are a list of predicted powder days and the user's emotional state. The device generates a message based on this information and notifies the user. Specific operations include generating and notifying a message. For example, if the user is excited, the device sends a positive message such as "Next weekend will be perfect powder days!" The output is a customized notification message of the prediction results.

[0853] (Application example 2)

[0854] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0855] In modern food delivery services, methods for improving the accuracy of demand forecasts and increasing customer satisfaction are extremely important. However, systems that effectively utilize various factors such as weather, local characteristics, and past order data to predict future demand remain limited. Furthermore, there is a lack of means to recognize users' real-time emotions and provide customized notifications and services based on them. Therefore, there is a need to solve these issues and provide a more accurate and user-friendly demand forecasting system.

[0856] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0857] In this invention, the server includes a means for acquiring weather information, a means for acquiring past order data, a means for training a machine learning model using the acquired data, a means including an emotion engine for recognizing user emotions, and a means for providing the user with the prediction results. This makes it possible to integrate various data to achieve highly accurate demand forecasts and provide customized notifications and services based on the user's emotions.

[0858] The "weather information acquisition means" is a means for acquiring weather forecast data for a specific area.

[0859] The "means for obtaining past order data" is a means for obtaining order history from a past database.

[0860] A "machine learning model" is a model that uses a learning algorithm based on past data to predict future demand.

[0861] An "emotion engine" is a system for recognizing and analyzing a user's real-time emotions.

[0862] The "means for providing predicted results" is a means for notifying and providing the user with the results predicted based on the machine learning model.

[0863] The present invention provides a highly accurate system that integrates weather information, past order data, and user sentiment to predict food delivery demand and notify users. The system includes the following means:

[0864] Get weather information

[0865] The server retrieves weather information for a specific region from a weather API. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format in response. This data includes information such as average daily temperatures and precipitation amounts.

[0866] Obtaining historical order data

[0867] The server retrieves historical order data from a database, including past daily temperature, precipitation, and order counts for a particular region, forming a training data set for learning correlations between weather conditions and order counts.

[0868] Training an AI model

[0869] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting order numbers (labels). This training enables the model to predict order numbers under specific weather conditions.

[0870] Demand forecasting

[0871] The server uses a trained AI model to predict demand based on future weather forecast data. The weather forecast data, including average daily temperatures and precipitation, is input into the model to determine future order quantities. The server selects days with "high demand" and adds them to the list.

[0872] Utilizing the Emotion Engine

[0873] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[0874] Providing prediction results

[0875] The device takes the user's emotional state into account when providing predictions to the user. For example, if the user is in high spirits, it will notify them of high demand days in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data to suggest the best food delivery days for the user.

[0876] Specific use cases

[0877] User example: Suppose a user is planning to use food delivery services over the weekend. The device responds to the user's question, "What will the demand for food delivery be this weekend?" by obtaining the predicted results from the server. Furthermore, if the emotion engine evaluates the user's expectations highly, the device will notify the user, "High demand is predicted for next weekend! Please plan your order early."

[0878] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict demand. If the prediction results in a "good day for high demand," the device will display, based on the analysis results of the emotion engine, a message saying, "The high demand day you're looking forward to is next weekend."

[0879] Example prompt: A user asks, "What will the food delivery demand be in Tokyo next week?"

[0880] In this way, the system integrates a variety of data to achieve highly accurate demand forecasts and enables the provision of customized notifications and services based on user emotions.

[0881] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0882] Step 1:

[0883] The server retrieves weather information. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format as a response. This data includes average daily temperatures and precipitation amounts. The input is the region information and API key, and the output is the weather forecast data.

[0884] Step 2:

[0885] The server retrieves historical order data from a database, which includes past daily temperature, precipitation, and order counts for a particular region. The input is the region information and the output is the historical order data. The server uses SQL queries to extract the required data from the database.

[0886] Step 3:

[0887] The server uses past order data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn the correlation between past weather data and order numbers. The input is past order data and weather data, and the output is the trained AI model.

[0888] Step 4:

[0889] The server uses a trained AI model to predict demand from future weather forecast data. The weather forecast data is input into the model to predict future order numbers. The input is weather forecast data, and the output is the predicted future order numbers.

[0890] Step 5:

[0891] The server customizes the display of prediction results using an emotion engine that recognizes the user's emotions. The emotion engine measures the user's excitement and expectation by obtaining data from sensors (e.g., heart rate sensors and facial recognition technology) installed on the user's device. The input is sensor data, and the output is the user's emotional state.

[0892] Step 6:

[0893] The terminal provides the user with the prediction results. The prediction results are customized based on the user's emotional state. For example, if the user is excited, the terminal may notify the user, "High demand is predicted for the next weekend! Please plan your orders early." The inputs are the prediction results and the user's emotional state, and the output is a customized notification.

[0894] Step 7:

[0895] Users plan their food delivery orders based on notifications provided by their devices, which are timed to optimally accommodate predicted demand and user sentiment. The input is a customized notification, and the output is the user's plan of action.

[0896] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0897] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0898] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0899] [Fourth embodiment]

[0900] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0901] 7, a 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.

[0902] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0903] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0904] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0905] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0906] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0907] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0908] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0909] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0910] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0911] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0912] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0913] The present invention provides a system for accurately predicting powder weather conditions, which includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model, a means for predicting future snow quality, and a means for providing the prediction results to a user.

[0914] Get weather information

[0915] The server retrieves weather data for a specific location (e.g., a popular ski resort) from a weather API. It sends a request to the weather API and receives a JSON response containing near-future weather forecast data. This data includes information such as average daily temperatures and snowfall.

[0916] Obtaining past snow quality data

[0917] The server retrieves historical snow data, including past daily temperature, snowfall, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[0918] Training an AI model

[0919] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[0920] Powder weather forecast

[0921] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[0922] Providing prediction results

[0923] The device will then provide the user with the forecast results, such as a list of predicted powder weather dates, so the user can plan their skiing or snowboarding trip.

[0924] Specific examples

[0925] User example: A user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining the predicted results from the server.

[0926] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict powder weather. If the forecast result is "2023-01-02," the device displays this to the user.

[0927] These steps allow users to know the best snow conditions at their destination in advance and plan their trip based on snow quality.

[0928] The processing flow will be explained below.

[0929] Step 1:

[0930] The server retrieves weather data for a specific location from the weather API. It sends a request to the weather API using the API key and receives a 10-day weather forecast in JSON format in response.

[0931] Step 2:

[0932] The server analyzes the weather data and extracts the average temperature and snowfall for each day, which are used as inputs for subsequent forecasting.

[0933] Step 3:

[0934] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality for that day (e.g., good, very good, poor).

[0935] Step 4:

[0936] The server separates historical snow quality data into features (temperature, snowfall) and labels (snow quality), which are then used to train a machine learning algorithm (e.g., a random forest classifier).

[0937] Step 5:

[0938] The server uses a trained machine learning model to predict future snow conditions based on weather forecast data, and adds dates that are deemed "very good" (ideal for powder) to the list.

[0939] Step 6:

[0940] The device retrieves the prediction results from the server and displays them to the user, including the dates of powder weather for the specific location.

[0941] Step 7:

[0942] Users can check the display on their device and plan their skiing or snowboarding trip based on the best powder weather conditions, ensuring they can enjoy the best conditions.

[0943] Example 1

[0944] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0945] Conventional snow condition prediction systems have struggled to effectively utilize weather forecast data and past data to accurately predict snow quality. This has made it difficult for users to plan optimal skiing or snowboarding trips, resulting in inconvenience. The present invention aims to solve these problems and provide a system that enables highly accurate prediction of powder weather.

[0946] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0947] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to a user, means for acquiring and analyzing JSON-formatted weather forecast data from a weather API, means for acquiring detailed weather information based on a specific geographic location, means for formatting past weather data as a training set, and a terminal for displaying the prediction results in response to a user request, thereby enabling a user to obtain highly accurate predictions of powder days based on detailed weather forecasts and past data.

[0948] A "means for obtaining weather information" is a function for obtaining weather forecast data for a specific geographic location from an external weather API.

[0949] "Means for obtaining past snow quality data" is a function for collecting information on past temperatures, snowfall amounts, and snow quality in a specific area.

[0950] "Means for training machine learning models" refers to a function for training models based on machine learning algorithms using collected historical weather information and snow quality data.

[0951] "Means for predicting future snow quality based on a machine learning model" is a function that uses a trained machine learning model to input future weather forecast data and predict snow quality.

[0952] The "means for providing the predicted results to the user" is a function for displaying the predicted results of powder weather on the user's device.

[0953] "Means for obtaining and analyzing weather forecast data in JSON format from a weather API" is a function for analyzing weather forecast data in JSON format obtained from an external weather API and extracting the necessary information.

[0954] The "means for obtaining detailed weather information based on a specific geographic location" is a function for obtaining detailed weather forecast data for a region based on a geographic location specified by a user.

[0955] "Means for formatting historical weather data as a training set" is a function for formatting previously collected weather information and snow quality data into a format suitable for training machine learning models.

[0956] A "terminal that displays prediction results in response to a user request" is a device that receives prediction results from a server in response to a question or request entered by a user and displays them to the user.

[0957] The present invention describes a snow condition forecasting system that accurately predicts powder weather. The system includes a means for acquiring weather information, a means for acquiring past snow quality data, a means for training a machine learning model using the acquired data, a means for predicting future snow quality based on the machine learning model, and a means for providing the predicted results to a user. The details are described below.

[0958] Hardware and Software

[0959] The server is the main hardware responsible for data collection, analysis, training, and prediction. The main software tools include an HTTP client for sending and receiving requests to the weather API, a parser for parsing JSON data, and a machine learning framework containing machine learning algorithms (e.g., random forest classifier). The database is used to store historical weather information, snow quality data, and trained AI models.

[0960] The terminal is a device that receives a user request, obtains prediction results from the server, and displays them to the user. Examples of this include smartphone apps and web browsers.

[0961] Users are individuals who want to know the best snow conditions (powder weather) at their ski resorts. Users access the system via their terminals and check the forecast results.

[0962] Data processing and calculation

[0963] 1. Get weather information:

[0964] The server sends a request to the weather API to retrieve near-future weather data for a specific ski resort. The retrieved data is in JSON format and includes daily average temperatures, snowfall, humidity, etc. This data is then analyzed and the necessary information is stored in a database.

[0965] 2. Obtaining historical snow quality data:

[0966] The server retrieves historical temperature, snowfall, and daily snow quality data for a particular ski resort, formats this data as a training set, and stores it in a database.

[0967] 3. Training the AI ​​model:

[0968] The server uses historical weather and snow data to train an AI model (such as a random forest classifier), which is then used to predict snow quality based on future weather conditions.

[0969] 4. Powder Weather Forecast:

[0970] The server uses a trained AI model to predict future snow conditions based on weather forecast data, identifying days when the forecast results are "very good" (powder-friendly) and generating a list of those days.

[0971] 5. Providing prediction results:

[0972] The server sends a list of predicted powder weather days to the terminal in response to a user request, and the terminal displays the list to the user.

[0973] Specific examples

[0974] User example: If a user is planning to go to a particular ski resort (e.g., Niseko), they ask through their device, "When will the best days for powder snow at Niseko be?" The server retrieves weather data from the weather API and makes a prediction using a trained AI model. If the prediction results in "2023-01-02" being a good day for powder snow, the device displays this to the user.

[0975] Server processing example: The server sends a request to the weather API to retrieve weather data for the next 10 days. It then uses past weather and snow data to train an AI model, which then uses future weather data to predict powder conditions. The server adds the date for which the forecast is "very good" (e.g., 2023-01-02) to a list and sends that date to the device.

[0976] Prompt Sentence Examples

[0977] User: "When is the best time for powder snow in Niseko?"

[0978] Response from the server: "The next good powder day is 2023-01-02."

[0979] User: "Based on recent weather forecasts, what's the snow forecast for this weekend?"

[0980] This system allows users to efficiently plan their skiing or snowboarding trips, allowing them to enjoy the best possible natural conditions.

[0981] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0982] Step 1:

[0983] Get weather information:

[0984] The server sends a request to a weather API to retrieve weather data for a geographic location specified by the user.

[0985] Input: A specific geographic location and forecast period

[0986] Output: Weather forecast data in JSON format (e.g., daily average temperature, snowfall, etc.)

[0987] What happens: The server sends a request to the weather API in the form "GET / weather?location=specified_location&days=10". The API response returns a JSON object containing weather data for the next 10 days. The server parses the data, extracts the necessary information (average temperature, snowfall, etc.), and stores it in a database.

[0988] Step 2:

[0989] Obtaining historical snow quality data:

[0990] The server retrieves historical weather and snow quality data for a particular ski resort from a database or external data source.

[0991] Input: Request for geographic location and specific time period

[0992] Output: Historical weather and snow data formatted for training purposes

[0993] What it does: The server sends the query "SELECT FROM historical_snow_data WHERE location="specified_location"" to retrieve data from the database. The retrieved data includes information on daily temperature, snowfall, and snow type, and is formatted as a training dataset for machine learning.

[0994] Step 3:

[0995] Training an AI model:

[0996] The server trains machine learning models using collected historical weather and snow data.

[0997] Input: Historical weather data (features) and snow quality data (labels)

[0998] Output: A trained machine learning model

[0999] Specific operation: The server trains a model using a random forest classifier using the format "train_model(past_weather_data, snow_quality_labels)". After training is complete, the model is saved using the format "model.save('snow_quality_predictor.model')".

[1000] Step 4:

[1001] Powder weather forecast:

[1002] The server uses a trained AI model to predict snow quality based on future weather forecast data.

[1003] Input: Future weather forecast data (average temperature, snowfall, etc.)

[1004] Output: Predicted future daily snow quality data

[1005] Specific operation: The server makes a prediction using future weather data in the form of "predictions = model.predict(future_weather_data)". Dates for which the prediction result is judged to be "very good" (suitable for powdery weather) are added to the list.

[1006] Step 5:

[1007] Providing prediction results:

[1008] The server provides the user with a list of predicted powder weather dates.

[1009] Input: User request (e.g., "When is the best time for powder weather in Niseko?")

[1010] Output: Prediction results (date list) displayed on the user's device

[1011] Specific operation: The server receives a user request, generates a list of predicted dates, and sends it to the terminal. The terminal displays this list to the user, providing information such as, "The next good day for powder weather is 2023-01-02."

[1012] (Application example 1)

[1013] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1014] Conventional food delivery systems create delivery plans without taking into account weather or past delay data, resulting in unexpected delays and inefficient route selection. Delivery delays are particularly frequent during bad weather such as snow or rain, resulting in reduced user satisfaction.

[1015] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1016] In this invention, the server includes a means for acquiring weather information, a means for acquiring past data, and a means for using this data to train a machine learning model, which makes it possible to predict future conditions and to predict and notify delivery efficiency and potential delays.

[1017] The "weather information acquisition means" is a device or program that has the function of acquiring weather data for a specified area from an external data source.

[1018] A "historical data acquisition means" is a device or program for collecting historical weather conditions and related data for a particular area.

[1019] A "means for training a machine learning model" is a device or program that applies a machine learning algorithm using collected data to build and improve a predictive model.

[1020] A "means for predicting future conditions" is a device or program that uses a trained machine learning model to predict certain future conditions (e.g., the likelihood of delivery delays).

[1021] The "means for providing the predicted result to the user" is a device or program for notifying or displaying the predicted result on the user's device.

[1022] "Means for predicting and notifying delivery efficiency and possible delays" refers to a device or program that predicts delivery efficiency and possible delays based on future weather conditions and past data, and notifies the user of the results.

[1023] A system for predicting delivery efficiency and possible delays based on different weather conditions and providing this information to users is implemented as follows.

[1024] Overall system configuration

[1025] The system consists of the following major components:

[1026] 1. How to get weather information

[1027] 2. How to obtain past data

[1028] 3. Means of training machine learning models

[1029] 4. A means of predicting future conditions

[1030] 5. Means of providing prediction results to users

[1031] Get weather information

[1032] The server retrieves weather data for a specific location (e.g., a city) using a weather API. It sends a request to the weather API and receives a response in JSON format containing future weather forecast data. This data includes information such as average daily temperatures and snowfall amounts. Possible APIs to use include the Weather API or the OpenWeatherMap API.

[1033] Obtaining historical data

[1034] The server retrieves historical weather data for a specific location and delivery delay data for that period. This data includes daily temperature, snowfall, and delivery status (e.g., delayed, normal). This forms a training dataset for learning correlations between weather conditions and delivery delays.

[1035] Training a machine learning model

[1036] The server uses historical data to train an AI model using machine learning algorithms such as random forest classifiers, learning from past weather data (features) and resulting delivery statuses (labels). This training allows the model to predict delivery delays under specific weather conditions.

[1037] Predicting conditions

[1038] The server uses a trained AI model to predict delivery efficiency and the possibility of delays based on future weather forecast data. The weather forecast data includes daily average temperatures and snowfall amounts, and these are input into the model to determine future delivery status. Days with a high probability of a "delay" are selected, and the date and reason for the delay are added to a list.

[1039] Providing prediction results

[1040] The terminal provides the user with the predicted results, for example by displaying a list of predicted possible delay dates on the user's device, allowing the user to adjust their delivery schedule based on this information.

[1041] Examples of concrete examples and prompts

[1042] As a specific example, assume that the user makes the following inquiry:

[1043] Example prompt sentence:

[1044] Please predict the weather and possible delivery delays in Tokyo next Saturday.

[1045] By feeding this prompt into the generative AI model, we can get the following output:

[1046] Example output produced:

[1047] Next Saturday (2023-10-14) in Tokyo, the average temperature is predicted to be 5°C and snowfall 2cm. Based on this, there is a high possibility of delivery delays. Please leave early and take appropriate cold weather precautions when making deliveries.

[1048] This allows users to make appropriate preparations depending on the weather and delivery conditions.

[1049] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1050] Step 1:

[1051] The server retrieves weather information for the specified location.

[1052] Input: Location information

[1053] How it works: The server sends a request to a weather API (e.g., Weather API or OpenWeatherMap API) and retrieves future weather forecast data in JSON format.

[1054] Output: Weather forecast data (average temperature, snowfall, etc.)

[1055] Step 2:

[1056] The server retrieves historical weather data and delivery delay data.

[1057] Input: Location information, historical data sources

[1058] How it works: The server retrieves historical weather data and associated delivery delay information from a pre-defined database or external data sources, including daily temperature, snowfall, and delivery status (delayed, normal).

[1059] Output: Historical weather data and delivery delay data

[1060] Step 3:

[1061] The server trains the machine learning model using historical data.

[1062] Input: Historical weather data, delivery delay data

[1063] How it works: The server uses machine learning algorithms, such as a random forest classifier, to train historical weather data (features) and delivery status (labels), allowing the model to predict delivery delays under specific weather conditions.

[1064] Output: A trained machine learning model

[1065] Step 4:

[1066] The server predicts delivery efficiency and possible delays based on future weather forecast data.

[1067] Input: trained machine learning model, future weather forecast data

[1068] How it works: The server inputs future weather forecast data into the trained model to predict future delivery status (likely delays). It selects days where the predicted result is likely to be "delayed" and adds those dates and reasons to a list.

[1069] Output: Delivery delay prediction list

[1070] Step 5:

[1071] The terminal provides the prediction result to the user.

[1072] Input: Delivery delay prediction list

[1073] How it works: The device displays a list of predicted possible delay dates on the user's device, and notifies them via a smartphone app or web interface.

[1074] Output: Delay prediction notification

[1075] Step 6:

[1076] The user adjusts the delivery schedule.

[1077] Input: Delay forecast notification

[1078] How it works: The user adjusts their delivery schedule appropriately based on the forecast information provided, which may include changing delivery times or making advance preparations.

[1079] Output: Adjusted delivery schedule

[1080] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1081] The present invention provides a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes user emotions. The system includes a weather information acquisition means, a past snow quality data acquisition means, a machine learning model training means, a prediction means for future snow quality, a means for providing the prediction results to the user, and an emotion engine that recognizes user emotions.

[1082] Get weather information

[1083] The server retrieves weather data for a specific location from a weather API. It sends a request to the weather API using an API key and receives a 10-day weather forecast in JSON format in response. This data includes information such as average daily temperatures and snowfall amounts.

[1084] Obtaining past snow quality data

[1085] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a particular location, forming a training dataset for learning correlations between weather conditions and snow quality.

[1086] Training an AI model

[1087] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting snow types (labels). This training allows the model to predict snow types under specific weather conditions.

[1088] Powder weather forecast

[1089] The server uses a trained AI model to predict snow quality based on future weather forecast data. The weather forecast data includes average daily temperatures and snowfall amounts, which are input into the model to determine future snow quality. The server selects days for which the forecast results are "very good" (ideal for powder skiing) and adds those dates to the list.

[1090] Utilizing the Emotion Engine

[1091] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[1092] Providing prediction results

[1093] When the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is in high spirits, the device will notify them of the perfect day for powdering in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data, and can suggest the best day for powdering for the user.

[1094] Specific examples

[1095] User example: Suppose a user is planning to go to a popular ski resort. The device responds to the user's question, "When will the weather be good for powder snow at Niseko?" by obtaining a prediction result from the server. Furthermore, if the emotion engine evaluates the user's level of expectation highly, the device notifies the user, "Next weekend will be the best weather for powder snow!"

[1096] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict the best days for powder weather. If the prediction is "2023-01-02," the device will display "The best days for powder weather you're looking forward to are 2023-01-02" based on the analysis results of the emotion engine.

[1097] In this way, by predicting and notifying users of powder weather taking their emotions into consideration, we provide a system that allows users to enjoy a better experience.

[1098] The processing flow will be explained below.

[1099] Step 1:

[1100] The server retrieves weather data for a specific location from a weather API, uses an API key to access the weather API, and sends a request. From the returned JSON response, the server parses the 10-day weather forecast data and extracts the average temperature and snowfall for each day.

[1101] Step 2:

[1102] The server retrieves historical snow data from a database, including past daily temperatures, snowfall amounts, and the snow quality for that day (e.g., good, very good, poor), and then collects and analyzes it.

[1103] Step 3:

[1104] The server trains a machine learning model based on past weather and snow quality data. Specifically, it uses a random forest classifier to train the model to take temperature and snowfall features as input and output snow quality. This model can then predict snow quality under specific weather conditions.

[1105] Step 4:

[1106] The server uses a trained machine learning model to predict snow quality based on future weather forecast data. It inputs average temperature and snowfall from 10 days of weather data and determines the predicted snow quality for each day. Days predicted as "very good" (perfect for powder) are added to the list.

[1107] Step 5:

[1108] To recognize the user's emotions, the server acquires the user's emotion data using an emotion engine. The emotion engine collects data from sensors (e.g., heart rate sensors, facial recognition technology) installed on the user's device and analyzes the user's excitement and expectation.

[1109] Step 6:

[1110] The device receives the prediction results and the user's emotional data from the server. Based on this, the prediction results are displayed in a way that is optimal for the user. For example, if the user is in an excited state, the device will notify the user of the date when it will be a good day for powdering in a more positive way.

[1111] Step 7:

[1112] The user checks the display on their device and plans their skiing or snowboarding trip based on the best powder weather. Information, including the analysis results of the emotion engine, allows the user to enjoy the trip under the best conditions. Specifically, the user will receive a notification saying, "Next weekend is the best powder weather!" and adjust their travel plans to target that day.

[1113] Example 2

[1114] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1115] Conventional snow condition prediction systems can predict future snow conditions based on weather information and past snow quality data, but they cannot customize the prediction results to take the user's emotional state into account. This makes it difficult to provide optimal information to users. Furthermore, detailed data analysis and customization to improve prediction accuracy are time-consuming. The purpose of this invention is to solve these problems and provide a more accurate and user-friendly snow condition prediction system.

[1116] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1117] In this invention, the server includes means for acquiring weather information, means for acquiring past snow quality data, means for training a machine learning model using the data, means for predicting future snow quality based on the machine learning model, means for providing the prediction results to the user, means for acquiring the user's emotional state, and means for customizing the prediction results according to the user's emotional state. This enables highly accurate prediction and notification of powder weather according to the user's emotions.

[1118] "Weather information" means data about weather conditions, such as temperature, snowfall, and wind speed, at a particular location.

[1119] "Snow Quality Data" means information about past or current snow conditions at a particular location, including ratings such as good, very good, or poor.

[1120] A "machine learning model" is an algorithm that uses past data to learn certain patterns and relationships, and then uses that to predict future events or situations.

[1121] "Weather Forecast Data" means data that indicates future weather conditions at a particular location, including predicted temperature, snowfall, and wind speed.

[1122] "Prediction results" are information about future snow quality and weather conditions predicted by the machine learning model.

[1123] "User" refers to any individual or organization that uses this system to obtain weather and snow quality information.

[1124] "Emotional state" refers to a user's current mental and emotional situation or state, including emotions such as excitement, anticipation, and anxiety.

[1125] "Customization" means changing the way prediction results and information are presented according to the user's needs and situation.

[1126] This invention relates to a snow condition forecasting system that accurately predicts powder weather and combines it with an emotion engine that recognizes the user's emotions. This system is realized using the following hardware and software.

[1127] First, the server uses a weather API (e.g., OpenWeatherMap) to obtain weather data for a specific location. Specifically, the server uses an API key to send a request to the weather API and receives 10-day weather forecast data in JSON format in response. This data includes information such as the average daily temperature and amount of snowfall. For example, the server can obtain the required data by entering a prompt statement such as "I want to get the 10-day weather forecast for Niseko."

[1128] The server then retrieves historical snow quality data from a database that stores past daily temperatures, snowfall amounts, and snow quality (e.g., good, very good, poor) for a specific location. This information is used to form a training dataset for learning correlations between weather conditions and snow quality. For example, the server can collect the required data by entering a prompt statement such as, "Get snow quality data for Niseko for the past year."

[1129] The server then uses machine learning algorithms, such as a random forest classifier, to train an AI model based on historical data. This training enables the model to predict snow conditions under specific weather conditions. For example, the server can do this by entering the prompt "Train a snow condition prediction model using historical data."

[1130] Using the trained AI model, the server predicts snow quality from future weather forecast data. Specifically, the model inputs the daily average temperature and snowfall amount from the weather forecast data to determine future snow quality. Days for which the forecast result is "very good" (powder weather) are added to a list and the date is saved. For example, the server can make this prediction by entering a prompt statement such as "Predict powder weather conditions in Niseko for the next 10 days."

[1131] Furthermore, the server uses an emotion engine to recognize the user's emotional state. The emotion engine acquires data from sensors (e.g., heart rate sensors, facial recognition technology) installed in the user's device and measures the user's level of excitement and expectation. This allows the server to analyze the user's emotions under specific conditions. For example, emotion analysis is performed by the server inputting a prompt statement such as, "Analyze the user's emotional state and evaluate the expectation level."

[1132] Finally, when the device provides the user with the prediction results, it takes into account the user's emotional state. For example, if the user is excited, it will notify them of the perfect day for powder snow in a more positive manner. The device analyzes past behavioral history and emotional data from the emotion engine, and can suggest the best day for powder snow for the user. For example, the device can heighten the user's expectations by notifying them, "Next weekend will be the perfect day for powder snow!"

[1133] In this way, a specific system configuration is provided for highly accurate prediction and notification of powder weather according to the user's feelings.

[1134] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1135] Step 1:

[1136] The server retrieves weather information. The input is the name of a specific location (e.g., a ski resort) and the access key provided by the weather API. The server accesses the weather API (e.g., OpenWeatherMap) and retrieves 10-day weather forecast data for the specific location. Specifically, the server generates an API request and accesses the URL using the HTTP protocol. The output is data such as the average daily temperature and snowfall amount in JSON format.

[1137] Step 2:

[1138] The server retrieves historical snow quality data. The input requires a specific location and time period (e.g., the past year). The server connects to the database and queries for snow quality data (temperature, snowfall, snow quality rating) based on the specified location and time period. Specifically, it runs an SQL query to extract the relevant data and converts it into a format that can be used within the program. The output is a dataset of the query results.

[1139] Step 3:

[1140] The server trains the AI ​​model. Historical weather data and snow quality data are required as input. The server preprocesses this data (e.g., imputing missing values ​​and normalizing data) and trains it using a machine learning algorithm (e.g., random forest classifier). Specifically, it preprocesses the data and trains the model using a machine learning library. The output is a trained AI model.

[1141] Step 4:

[1142] The server predicts the best days for powder snow. The inputs required are a trained AI model and future weather forecast data (daily temperature and snowfall). The server inputs this data into the AI ​​model to predict future snow conditions. Specifically, it works by listing the dates for which the prediction results (such as "very good," "good," or "poor") are available. The output is a list of the days predicted to be good for powder snow.

[1143] Step 5:

[1144] The server uses an emotion engine to obtain the user's emotional state. Sensor data (e.g., heart rate, facial recognition data) from the user's device is required as input. The server uses an emotion recognition algorithm to analyze the user's emotions from this sensor data. Specifically, the server collects sensor data and evaluates emotions using an algorithm. The output is the user's emotional state (e.g., excitement, anticipation, anxiety).

[1145] Step 6:

[1146] The device provides the prediction results to the user. The inputs required are a list of predicted powder days and the user's emotional state. The device generates a message based on this information and notifies the user. Specific operations include generating and notifying a message. For example, if the user is excited, the device sends a positive message such as "Next weekend will be perfect powder days!" The output is a customized notification message of the prediction results.

[1147] (Application example 2)

[1148] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1149] In modern food delivery services, methods for improving the accuracy of demand forecasts and increasing customer satisfaction are extremely important. However, systems that effectively utilize various factors such as weather, local characteristics, and past order data to predict future demand remain limited. Furthermore, there is a lack of means to recognize users' real-time emotions and provide customized notifications and services based on them. Therefore, there is a need to solve these issues and provide a more accurate and user-friendly demand forecasting system.

[1150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1151] In this invention, the server includes a means for acquiring weather information, a means for acquiring past order data, a means for training a machine learning model using the acquired data, a means including an emotion engine for recognizing user emotions, and a means for providing the user with the prediction results. This makes it possible to integrate various data to achieve highly accurate demand forecasts and provide customized notifications and services based on the user's emotions.

[1152] The "weather information acquisition means" is a means for acquiring weather forecast data for a specific area.

[1153] The "means for obtaining past order data" is a means for obtaining order history from a past database.

[1154] A "machine learning model" is a model that uses a learning algorithm based on past data to predict future demand.

[1155] An "emotion engine" is a system for recognizing and analyzing a user's real-time emotions.

[1156] The "means for providing predicted results" is a means for notifying and providing the user with the results predicted based on the machine learning model.

[1157] The present invention provides a highly accurate system that integrates weather information, past order data, and user sentiment to predict food delivery demand and notify users. The system includes the following means:

[1158] Get weather information

[1159] The server retrieves weather information for a specific region from a weather API. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format in response. This data includes information such as average daily temperatures and precipitation amounts.

[1160] Obtaining historical order data

[1161] The server retrieves historical order data from a database, including past daily temperature, precipitation, and order counts for a particular region, forming a training data set for learning correlations between weather conditions and order counts.

[1162] Training an AI model

[1163] The server uses historical data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn past weather data (features) and the resulting order numbers (labels). This training enables the model to predict order numbers under specific weather conditions.

[1164] Demand forecasting

[1165] The server uses a trained AI model to predict demand based on future weather forecast data. The weather forecast data, including average daily temperatures and precipitation, is input into the model to determine future order quantities. The server selects days with "high demand" and adds them to the list.

[1166] Utilizing the Emotion Engine

[1167] The server uses an emotion engine that recognizes the user's emotions and customizes the display of prediction results. The emotion engine measures the user's excitement and expectation using sensors (e.g., heart rate sensor, facial recognition technology) installed in the user's device. This allows it to analyze the emotions the user will have under certain conditions.

[1168] Providing prediction results

[1169] The device takes the user's emotional state into account when providing predictions to the user. For example, if the user is in high spirits, it will notify them of high demand days in a more positive manner. The emotion engine analyzes the user's past behavioral history and emotional data to suggest the best food delivery days for the user.

[1170] Specific use cases

[1171] User example: Suppose a user is planning to use food delivery services over the weekend. The device responds to the user's question, "What will the demand for food delivery be this weekend?" by obtaining the predicted results from the server. Furthermore, if the emotion engine evaluates the user's expectations highly, the device will notify the user, "High demand is predicted for next weekend! Please plan your order early."

[1172] Server processing example: The server sends a request to the weather API to obtain weather data for the next 10 days. It then trains an AI model based on past data and uses future weather data to predict demand. If the prediction results in a "good day for high demand," the device will display, based on the analysis results of the emotion engine, a message saying, "The high demand day you're looking forward to is next weekend."

[1173] Example prompt: A user asks, "What will the food delivery demand be in Tokyo next week?"

[1174] In this way, the system integrates a variety of data to achieve highly accurate demand forecasts and enables the provision of customized notifications and services based on user emotions.

[1175] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1176] Step 1:

[1177] The server retrieves weather information. Specifically, it sends a request to the weather API using an API key and receives 10-day weather forecast data in JSON format as a response. This data includes average daily temperatures and precipitation amounts. The input is the region information and API key, and the output is the weather forecast data.

[1178] Step 2:

[1179] The server retrieves historical order data from a database, which includes past daily temperature, precipitation, and order counts for a particular region. The input is the region information and the output is the historical order data. The server uses SQL queries to extract the required data from the database.

[1180] Step 3:

[1181] The server uses past order data to train the AI ​​model. Specifically, it uses machine learning algorithms such as random forest classifiers to learn the correlation between past weather data and order numbers. The input is past order data and weather data, and the output is the trained AI model.

[1182] Step 4:

[1183] The server uses a trained AI model to predict demand from future weather forecast data. The weather forecast data is input into the model to predict future order numbers. The input is weather forecast data, and the output is the predicted future order numbers.

[1184] Step 5:

[1185] The server customizes the display of prediction results using an emotion engine that recognizes the user's emotions. The emotion engine measures the user's excitement and expectation by obtaining data from sensors (e.g., heart rate sensors and facial recognition technology) installed on the user's device. The input is sensor data, and the output is the user's emotional state.

[1186] Step 6:

[1187] The terminal provides the user with the prediction results. The prediction results are customized based on the user's emotional state. For example, if the user is excited, the terminal may notify the user, "High demand is predicted for the next weekend! Please plan your orders early." The inputs are the prediction results and the user's emotional state, and the output is a customized notification.

[1188] Step 7:

[1189] Users plan their food delivery orders based on notifications provided by their devices, which are timed to optimally accommodate predicted demand and user sentiment. The input is a customized notification, and the output is the user's plan of action.

[1190] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1191] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1192] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1193] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1194] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1195] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1196] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1197] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1198] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1199] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1200] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1201] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1202] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1203] 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.

[1204] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1205] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1206] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1207] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1208] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1209] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1210] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1211] The following is further disclosed regarding the above embodiment.

[1212] (Claim 1)

[1213] A weather information acquisition means;

[1214] A means of obtaining past snow quality data,

[1215] a means of training a machine learning model using these data;

[1216] A means of predicting future snow conditions based on machine learning models; and

[1217] a means for providing the prediction result to a user;

[1218] Snow condition forecasting system including.

[1219] (Claim 2)

[1220] 2. The snow condition prediction system of claim 1, wherein the weather information acquisition means acquires weather forecast data based on a specific location.

[1221] (Claim 3)

[1222] 2. The snow condition prediction system of claim 1, wherein the machine learning model uses a random forest classifier.

[1223] "Example 1"

[1224] (Claim 1)

[1225] A means for obtaining weather information;

[1226] A means of obtaining past snow quality data;

[1227] a means of training a machine learning model using these data;

[1228] A means of predicting future snow conditions based on machine learning models; and

[1229] a means for providing the prediction result to a user;

[1230] A means to retrieve and analyze weather forecast data in JSON format from the weather API,

[1231] means for obtaining detailed weather information based on a particular geographic location;

[1232] a means for formatting historical weather data as a training set;

[1233] a terminal that displays prediction results in response to a user request;

[1234] A system including:

[1235] (Claim 2)

[1236] 10. The system of claim 1, wherein the weather information obtaining means obtains weather forecast data based on a particular geographic location.

[1237] (Claim 3)

[1238] 10. The system of claim 1, wherein the machine learning model uses a random forest classifier and utilizes historical weather and snow quality data as a training data set.

[1239] "Application Example 1"

[1240] (Claim 1)

[1241] A weather information acquisition means;

[1242] A means of obtaining past data;

[1243] a means of training a machine learning model using these data;

[1244] a means for predicting future conditions based on a machine learning model; and

[1245] a means for providing the prediction result to a user;

[1246] A means of predicting and informing delivery efficiency and potential delays;

[1247] A system including:

[1248] (Claim 2)

[1249] 10. The system of claim 1, wherein the weather information obtaining means obtains weather forecast data based on a specific location.

[1250] (Claim 3)

[1251] 10. The system of claim 1, wherein the machine learning model uses a random forest classifier.

[1252] "Example 2: Combining Emotion Engines"

[1253] (Claim 1)

[1254] A means for obtaining weather information;

[1255] A means of obtaining past snow quality data;

[1256] a means of training a machine learning model using these data;

[1257] A means of predicting future snow conditions based on machine learning models; and

[1258] a means for providing the prediction result to a user;

[1259] means for capturing an emotional state of a user;

[1260] means for customizing the prediction results according to the emotional state of the user;

[1261] A system including:

[1262] (Claim 2)

[1263] 10. The system of claim 1, wherein the weather information obtaining means obtains weather forecast data based on a specific location.

[1264] (Claim 3)

[1265] 10. The system of claim 1, wherein the machine learning model uses a random forest classifier.

[1266] "Application example 2 when combining emotion engines"

[1267] (Claim 1)

[1268] A weather information acquisition means;

[1269] A means of obtaining past order data;

[1270] a means of training a machine learning model using these data;

[1271] A means of forecasting future demand based on machine learning models; and

[1272] means including an emotion engine for recognizing an emotion of a user;

[1273] a means for providing the prediction result to a user;

[1274] Demand forecasting system including.

[1275] (Claim 2)

[1276] 2. The demand forecasting system according to claim 1, wherein the weather information acquisition means acquires weather forecast data based on a specific region.

[1277] (Claim 3)

[1278] 2. The demand forecasting system of claim 1, wherein the machine learning model uses a random forest classifier. [Explanation of symbols]

[1279] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A weather information acquisition means; A means of obtaining past snow quality data, a means of training a machine learning model using these data; A means of predicting future snow conditions based on machine learning models; and a means for providing the prediction result to a user; Snow condition forecasting system including.

2. 2. The snow condition prediction system of claim 1, wherein the weather information acquisition means acquires weather forecast data based on a specific location.

3. The snow condition prediction system of claim 1 , wherein the machine learning model uses a random forest classifier.

Images