system

Abstract

We provide the system. [Solution] A system that includes a means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, a means for linking information such as GPS data, traffic information, travel speed, and weather, and a means for proposing the optimal logistics route plan based on this information.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In BtoC delivery, optimization of delivery time and fuel savings are required. However, to achieve these, complex judgments considering various factors such as delivery success probability, traffic information, and weather are necessary.

Means for Solving the Problems

[0005] The present invention provides means for calculating, based on past delivery completion data, when to perform delivery with the highest success probability, means for coordinating information such as GPS data, traffic information, moving speed, and weather, and means for proposing an optimal plan for the logistics route based on this information. Thereby, shortening of transportation time and fuel savings become possible.

Brief Description of the Drawings

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16]It is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Embodiment Example 3. [Figure 17] It is a sequence diagram showing the processing flow of the data processing system in Example 1 of Embodiment Example 1 when combined with an emotion engine. [Figure 18] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Embodiment Example 1 when combined with an emotion engine. [Figure 19] It is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment Example 2 when combined with an emotion engine. [Figure 20] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Embodiment Example 2 when combined with an emotion engine. [Figure 21] It is a sequence diagram showing the processing flow of the data processing system in Example 3 of Embodiment Example 3 when combined with an emotion engine. [Figure 22] It is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Embodiment Example 3 when combined with an emotion engine. [Figure 23] It is a sequence diagram showing the processing flow of the data processing system in other embodiments.

Embodiments for Carrying Out the Invention

[0007] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the language used in the following description will be explained.

[0009] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)), etc.

[0010] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0011] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0012] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor and 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), or Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0019] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] One embodiment of this system is a B2C delivery system. This system has a function to calculate the optimal delivery time based on past delivery completion data. Specifically, it aggregates past delivery data and uses a machine learning algorithm to calculate the optimal delivery time from that data.

[0029] "Example of form 2"

[0030] Furthermore, this system has the functionality to integrate information such as GPS data, traffic information, travel speed, and weather. This information is acquired in real time and analyzed comprehensively to propose the most suitable delivery route for the current situation.

[0031] "Example of form 3"

[0032] Furthermore, this system has a function to propose the optimal logistics route plan based on this information. Specifically, it proposes routes that can shorten transportation time and save fuel, based on the calculated optimal delivery time and related information. For example, it can avoid routes that are expected to be congested and propose routes optimized for traffic information and weather conditions.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: The system aggregates past delivery completion data. This includes information such as delivery time, delivery destination, and delivery success rate.

[0036] Step 2: Based on the aggregated data, a machine learning algorithm is used to calculate the time of day when deliveries have the highest probability of success. This algorithm takes into account factors such as time of day, location, and weather.

[0037] "Example of form 2"

[0038] Step 1: The system acquires information such as GPS data, traffic information, travel speed, and weather in real time. This information is obtained from various sensors and external APIs.

[0039] Step 2: Analyze the acquired information to propose the optimal delivery route for the current situation. This analysis will take into account factors such as road congestion, traffic restrictions, and weather conditions.

[0040] "Example of form 3"

[0041] Step 1: Based on the calculated optimal delivery time and related information, the system proposes routes that can shorten transportation time and save fuel.

[0042] Step 2: Specifically, suggest routes that are optimized for traffic information and weather conditions, avoiding routes that are expected to be congested. For example, suggest leaving earlier during peak hours and avoiding slippery roads in rainy weather.

[0043] (Example 1)

[0044] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0045] In the logistics industry, improving delivery efficiency and reducing costs are critical challenges. In particular, optimizing delivery times directly leads to increased customer satisfaction and more effective use of transportation resources. However, traditional methods have struggled to calculate optimal delivery times due to the inability to fully utilize historical data. Furthermore, the inability to consider fluctuating factors such as traffic conditions and weather in real time has resulted in reduced accuracy in delivery planning.

[0046] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0047] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion information, means for integrating information such as location information, traffic conditions, travel speed, and weather conditions, and means for proposing an optimal logistics route plan based on this information. This enables the optimization of delivery time and the efficiency of logistics routes.

[0048] "Delivery completion information" refers to data that includes the date and time of past deliveries, delivery destination, and recipient information.

[0049] "Location information" refers to data indicating a geographical location, obtained using methods such as GPS.

[0050] "Traffic conditions" refers to information about road congestion and passable routes.

[0051] "Movement speed" refers to data indicating the speed at which a delivery vehicle moves.

[0052] "Weather conditions" refer to information about weather, such as climate, temperature, and precipitation.

[0053] A "logistics route" is the path that a delivery item takes when it travels from its origin to its destination.

[0054] An "optimal plan" is a delivery schedule designed to reduce transportation time and conserve resources.

[0055] A "machine learning algorithm" is a computational method used to learn patterns from data and perform predictions and classifications.

[0056] "Data preprocessing" refers to the process of shaping data into a format suitable for machine learning.

[0057] "Features" are attributes or metrics of data that machine learning models use when training.

[0058] "Training" is the process by which a machine learning model learns patterns from data.

[0059] "Evaluation" is the process of measuring the performance of a trained machine learning model and verifying its accuracy.

[0060] In an embodiment of this invention, the server runs a program to collect past delivery completion information and calculate the optimal delivery time. The server retrieves delivery completion information from a database and preprocesses the data using the Python Pandas library. Preprocessing includes imputing missing values ​​and removing outliers. Next, the server trains and evaluates a machine learning model using the Scikit-learn library. Algorithms such as random forest and gradient boosting are used to train the model.

[0061] The server integrates information such as location data, traffic conditions, travel speed, and weather conditions, and based on this information, proposes the optimal logistics route plan. This enables the optimization of delivery times and the efficiency of logistics routes.

[0062] For example, the server uses delivery data for a certain region to calculate that "deliveries in this region have a higher success rate between 2 PM and 4 PM." Users can then check this information through their terminal and plan their deliveries accordingly.

[0063] An example of a prompt message is: "Calculate the optimal delivery time based on past delivery data. The data includes delivery date and time, address, and recipient information."

[0064] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0065] Step 1:

[0066] The server retrieves past delivery completion information from the delivery database. Input includes delivery date and time, delivery address, and recipient information. This data is aggregated to prepare for the next processing step. Specifically, it extracts the necessary data using SQL queries.

[0067] Step 2:

[0068] The server preprocesses the acquired data. The input is the delivery completion information aggregated in step 1. The Python Pandas library is used for data preprocessing, including imputing missing values ​​and removing outliers. The output is data formatted in a way that is suitable for machine learning algorithms. Specifically, it cleans the data frame.

[0069] Step 3:

[0070] The server selects features from preprocessed data and generates new features. The input is the data formatted in step 2. Feature selection involves analyzing data correlations and extracting important attributes. The output is a set of features used to train a machine learning model. Specifically, it creates a correlation matrix and selects important features.

[0071] Step 4:

[0072] The server trains a machine learning model using the selected features. The input is the feature set generated in step 3. The Scikit-learn library is used to train the model with algorithms such as random forest and gradient boosting. The output is the trained machine learning model. Specifically, the hyperparameters of the model are tuned to build the optimal model.

[0073] Step 5:

[0074] The server evaluates the trained model. The input is the trained model obtained in step 4. Cross-validation is used to measure the model's accuracy. The output is an indicator of the model's accuracy. Specifically, the server identifies areas for improvement in the model based on the evaluation results.

[0075] Step 6:

[0076] The server calculates the optimal delivery time using a pre-evaluated model. Inputs include real-time location information, traffic conditions, travel speed, and weather conditions. The output is the optimal delivery time for each destination. Specifically, it inputs new data into the model and generates prediction results.

[0077] Step 7:

[0078] The server provides the user with the calculated optimal delivery time. The input is the optimal delivery time obtained in step 6. The output is a delivery schedule that the user can view on their terminal. Specifically, the results are displayed in the user interface to assist the user in planning their delivery.

[0079] (Application Example 1)

[0080] Next, we will describe Application Example 1 of Form 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."

[0081] In food delivery services, determining the optimal delivery time is crucial to ensure customers receive their food in the freshest possible condition. However, traditional systems often fail to adequately optimize delivery times, making it difficult to improve customer satisfaction.

[0082] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0083] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as GPS data, traffic information, travel speed, and weather, means for proposing the optimal logistics route plan based on this information, means for analyzing past delivery data and proposing the optimal delivery time to the user, and means for presenting the optimal delivery time when the user confirms their order. This makes it possible to optimize delivery times so that customers can receive their food in the freshest possible condition.

[0084] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, and whether the delivery was successful.

[0085] "Success probability" is an indicator that shows the likelihood of delivery being completed on schedule, and is calculated based on past data.

[0086] A "machine learning algorithm" is a computational method that allows computers to learn patterns from data and perform predictions and classifications.

[0087] "Optimal delivery time" refers to the time required for delivery to be completed in the most efficient and customer-satisfying manner.

[0088] "Means of suggesting to the user" refers to the methods and functions that the system uses to present the user with the optimal options based on its analysis results.

[0089] An "optimal logistics route plan" is a delivery route plan designed to maximize delivery efficiency and minimize time and costs.

[0090] "Traffic information" refers to real-time data related to traffic, such as road congestion, traffic accidents, and construction information.

[0091] "Means presented to the user when confirming an order" refers to the methods or functions that the system uses to display the optimal delivery time when the user makes a final decision on an order.

[0092] The system for implementing this invention operates in a network environment including a server and user terminals. The server collects past delivery completion data and uses a machine learning algorithm to calculate the optimal delivery time based on this data. Specifically, it uses Python and the Scikit-learn library to build a machine learning model. The server preprocesses the collected data, extracts features, and then trains the model using algorithms such as random forest.

[0093] The user terminal is a device such as a smartphone or tablet that receives the optimal delivery time provided by the server and presents it to the user. When the user confirms their order, the terminal displays the optimal delivery time on the screen based on the server's suggestion. This allows the user to choose the time when they can receive their food in the freshest condition.

[0094] As a concrete example, when a user orders a pizza, the terminal suggests, "Based on past data, specifying 18:30 for delivery is most likely to ensure the food arrives in the freshest condition." This suggestion is the result of the server using a generated AI model to analyze past delivery data and predict the optimal delivery time.

[0095] An example of a prompt message would be: "Based on past delivery data, predict the optimal delivery time. The current order is for pizza, and the user's location is Shibuya Ward, Tokyo."

[0096] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0097] Step 1:

[0098] The server collects past delivery completion data from the database. It takes information such as delivery date and time, delivery destination, and whether the delivery was successful as input. This data is preprocessed to impute missing values ​​and remove outliers. The output is a clean dataset.

[0099] Step 2:

[0100] The server extracts features using pre-processed data. It uses a clean dataset as input and selects features such as delivery time, day of the week, and weather. This results in the output of a dataset suitable for training machine learning models.

[0101] Step 3:

[0102] The server uses the Scikit-learn library to build and train a machine learning model. It uses a feature-extracted dataset as input. It applies the Random Forest algorithm to generate a model that predicts the optimal delivery time. The output is the trained model.

[0103] Step 4:

[0104] The server uses a generative AI model to predict the optimal delivery time based on the user's order information. It uses the user's current order details and location as input. By generating prompt messages and inputting them into the model, it outputs the optimal delivery time.

[0105] Step 5:

[0106] The terminal displays the optimal delivery time received from the server to the user. It receives a suggested delivery time from the server as input. The screen displays a message such as, "Based on past data, specifying 18:30 for delivery is likely to ensure your food arrives in the freshest condition." The output provides information to help the user select the optimal delivery time.

[0107] Step 6:

[0108] The user confirms the optimal delivery time displayed on the terminal and confirms the order. The terminal provides a suggested delivery time as input. The user selects the suggested time and completes the order. The confirmed order information is sent to the server as output.

[0109] (Example 2)

[0110] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0111] In the logistics industry, improving delivery efficiency and reducing costs are crucial challenges. In particular, delivery times are often unpredictable due to traffic congestion and weather changes, leading to delivery delays and wasted fuel. Traditional systems lack sufficient real-time information integration and optimal route suggestions, resulting in decreased delivery efficiency.

[0112] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0113] In this invention, the server includes means for calculating the time of day when delivery is most likely to succeed based on past delivery completion information, means for linking information such as location information, traffic conditions, travel speed, and weather information, and means for proposing an optimal logistics route plan based on this information. This enables real-time information integration and the proposal of the optimal route.

[0114] "Past delivery completion information" refers to data such as the date and time of past deliveries, route, duration, and success rate.

[0115] "Location information" refers to geographical coordinate data of a specific point, obtained using technologies such as GPS.

[0116] "Traffic conditions" refers to real-time information about road traffic, such as road congestion levels, traffic jams, and traffic restrictions.

[0117] "Movement speed" refers to data indicating the speed at which a vehicle is moving, and is usually obtained from speed sensors or similar devices.

[0118] "Weather information" refers to data related to weather conditions, including information such as temperature, precipitation, and wind speed.

[0119] "Optimal logistics route planning" refers to proposed delivery routes calculated to maximize delivery efficiency and minimize time and costs.

[0120] A "generative AI model" refers to a model that has been trained using artificial intelligence technology to perform a specific task.

[0121] A "prompt" refers to text input to give specific instructions or questions to a generative AI model.

[0122] This invention is a system aimed at improving delivery efficiency in the logistics industry. The server calculates the delivery time with the highest probability of success based on past delivery completion information. This is done using a machine learning algorithm. The server collects location information, traffic conditions, travel speed, and weather information in real time and analyzes this information comprehensively. Specifically, it obtains location information using a GPS module and traffic conditions through a traffic information API. Travel speed is obtained using data from a speed sensor, and weather information is obtained using a weather information API.

[0123] The server integrates data using the Python Pandas library and performs analysis using the Scikit-learn library. This calculates the optimal logistics route and proposes it to the terminal. The terminal then displays specific route information to the user.

[0124] As a concrete example, the system starts operating when the user inputs a prompt into the generated AI model. For instance, if the user inputs, "My current location is Tokyo Station, and my destination is Shibuya Station. Please suggest the optimal delivery route," the server immediately begins collecting data and calculates the optimal route in real time. The terminal then displays the calculation results to the user and provides specific route guidance.

[0125] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0126] Step 1:

[0127] The server receives a prompt message from the user. The prompt message includes the current location and destination. For example, "Current location is Tokyo Station, destination is Shibuya Station." Based on this input, the server begins preparing to collect data.

[0128] Step 2:

[0129] The server obtains location information using a GPS module. It also obtains real-time traffic conditions through a traffic information API. Travel speed is obtained from data received from a speed sensor installed in the vehicle, and weather information is obtained using a weather information API. This data is integrated within the server.

[0130] Step 3:

[0131] The server converts the integrated data into a data frame using the Python Pandas library. This data frame includes location information, traffic conditions, travel speed, and weather information. The server then prepares to perform data analysis based on this data.

[0132] Step 4:

[0133] The server uses the Scikit-learn library to apply machine learning algorithms and calculate the optimal delivery route. An integrated dataframe is used as input, and the output provides information about the optimal route. This calculation considers routes that avoid traffic congestion and safe routes based on weather conditions.

[0134] Step 5:

[0135] The server sends the calculated optimal route to the terminal. The terminal displays specific route information to the user. For example, it might say, "Considering current traffic conditions and weather, the best route is via Aoyama Street." The user can then use this information to carry out deliveries.

[0136] (Application Example 2)

[0137] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0138] In food delivery services, delays in delivery times and inefficient route selection are problems that reduce customer satisfaction. Furthermore, the inability to respond quickly to changes in traffic and weather conditions leads to increased delivery times and wasted fuel. There is a need to solve these problems and provide more efficient and reliable delivery services.

[0139] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0140] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather information, means for proposing the optimal logistics route plan based on this information, means for calculating and updating the optimal delivery route in real time, and means for proposing alternative routes to delivery personnel. This makes it possible to shorten delivery times and save fuel.

[0141] "Past delivery completion data" refers to information about deliveries that have been completed in the past, including the delivery date and time, delivery destination, and duration.

[0142] "Location data" refers to information that indicates the current geographical location of an object, obtained using GPS or other position measurement technologies.

[0143] "Traffic information" refers to current traffic conditions, such as road congestion, accident information, and traffic restrictions.

[0144] "Movement speed" is a numerical value that indicates the distance an object travels per unit of time.

[0145] "Weather information" refers to information about current weather conditions, such as weather, temperature, precipitation, and wind speed.

[0146] An "optimal logistics route plan" is a proposal for the most effective delivery route, designed to maximize delivery efficiency.

[0147] "A means of calculating and updating the optimal delivery route in real time" refers to a function that instantly calculates the optimal delivery route based on the current situation and modifies that route as needed.

[0148] "Means of suggesting alternative routes to delivery drivers" refers to a function that presents delivery drivers with new delivery routes in response to unexpected events or changes in traffic conditions.

[0149] The system for realizing this invention consists of a server and a terminal for delivery personnel. The server collects past delivery completion data and calculates the probability of successful delivery based on this data. Furthermore, the server acquires location data, traffic information, travel speed, and weather information in real time and integrates this information to calculate the optimal logistics route. The server obtains the necessary data using the Google® Maps API and the OpenWeatherMap API and processes the data using the Python Pandas library. Dijkstra's algorithm is used for calculations, and the route is updated in real time.

[0150] The delivery driver's terminal receives the optimal delivery route transmitted from the server and presents it to the driver. Depending on changes in traffic and weather conditions, the server calculates alternative routes and suggests new routes to the driver's terminal. This ensures that drivers can always deliver using the most optimal route.

[0151] For example, if a delivery driver is likely to get caught in traffic, the server immediately calculates an alternative route and notifies the driver's terminal. This can shorten delivery times and save fuel. An example of a prompt to the generating AI model might be, "Please suggest the best route from my current location to my destination. Please consider traffic and weather information."

[0152] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0153] Step 1:

[0154] The server collects past delivery completion data. It uses past delivery dates and times, destinations, and delivery durations as input. Based on this data, it prepares the foundational data for calculating the probability of successful delivery. The output is the prepared historical delivery data.

[0155] Step 2:

[0156] The server acquires location data, traffic information, travel speed, and weather information in real time. It uses data from the Google Maps API and OpenWeatherMap API as input. This data is integrated to understand the current delivery environment. The output is integrated, real-time environmental data.

[0157] Step 3:

[0158] The server calculates the optimal logistics route based on well-maintained historical delivery data and integrated real-time environmental data. It uses historical delivery data and real-time environmental data as input. Dijkstra's algorithm is used to calculate the shortest path. The output is the optimal delivery route.

[0159] Step 4:

[0160] The server sends the calculated optimal delivery route to the delivery person's terminal. The optimal delivery route is used as input. The delivery person's terminal displays the received route and presents it to the delivery person. The output is the delivery route presented to the delivery person.

[0161] Step 5:

[0162] The server monitors changes in traffic and weather conditions and calculates alternative routes as needed. It uses real-time environmental data as input. If changes are detected, it recalculates a new route using Dijkstra's algorithm. The output is the updated delivery route.

[0163] Step 6:

[0164] The server sends the updated delivery route to the delivery person's terminal and suggests an alternative route to the delivery person. The updated delivery route is used as input. The delivery person's terminal displays the received alternative route and notifies the delivery person. The output is the alternative route presented to the delivery person.

[0165] (Example 3)

[0166] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0167] In the logistics industry, improving delivery efficiency and reducing fuel consumption are critical challenges. Traditional systems struggled to effectively utilize real-time traffic and weather data, making it difficult to propose optimal delivery routes. Furthermore, there was a lack of effective means to incorporate user feedback. This resulted in delivery delays, fuel waste, and decreased operational efficiency.

[0168] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0169] This invention includes a server that calculates the optimal time for delivery based on past delivery completion data to maximize the chances of success, a means for linking location data, traffic conditions, travel speed, weather conditions, and other information, and a means for proposing an optimal logistics route based on this information. This enables the proposal of an optimal delivery route using real-time traffic and weather data, improving delivery efficiency and reducing fuel consumption.

[0170] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, duration, and whether the delivery was successful.

[0171] "Location data" refers to data that indicates a geographical location, and includes latitude and longitude information obtained using technologies such as GPS.

[0172] "Traffic conditions" refers to information indicating the degree of road congestion and whether roads are passable, and includes real-time changes in traffic flow and congestion information.

[0173] "Movement speed" is an indicator that shows the distance traveled per unit of time, and it measures the speed at which vehicles or people move.

[0174] "Weather conditions" refer to information about the weather, including meteorological elements such as temperature, precipitation, wind speed, and humidity.

[0175] A "logistics route" refers to the path taken when delivering goods, and is used to plan the optimal route from the origin to the destination.

[0176] "Real-time traffic information" refers to information that instantly reflects the current traffic situation, including road congestion levels and accident information.

[0177] The "optimal delivery route" refers to the most efficient route, calculated with the aim of reducing delivery time and saving fuel.

[0178] "Feedback" refers to evaluations and opinions provided by users, and is information used to improve the system and enhance its accuracy.

[0179] A description of embodiments for carrying out this invention will be given.

[0180] The server generates a program to optimize logistics routes. This program collects traffic and weather data and calculates the optimal delivery route based on this information. Specifically, the server uses a geographic information system API to obtain real-time traffic information and a weather data API to collect weather data. By combining this data, it calculates a route that can shorten delivery times and save fuel.

[0181] The user then uses the generated program to optimize logistics routes. For example, if the user inputs the prompt "Suggest the best delivery route from Tokyo to Osaka" into the generating AI model, the server will propose the best route considering traffic information and weather data. This proposal may include alternative routes to avoid congested routes and route selection based on weather conditions.

[0182] As a concrete example, if a user enters the prompt "Tell me the best delivery route from Tokyo to Nagoya tomorrow morning," the server will propose the most efficient route based on the next day's traffic forecast and weather information. In this way, the user can shorten transportation time and save fuel. The flow of the specific processing in Example 3 will be explained using Figure 15.

[0183] Step 1:

[0184] The server collects traffic and weather data. Specifically, it uses a geographic information system API to obtain real-time traffic information and a weather data API to collect weather data. The input requires the current date and time and a geographical range, and the output provides traffic and weather information for the specified range. This allows users to understand the current level of road congestion and weather conditions.

[0185] Step 2:

[0186] The server analyzes the collected traffic and weather data. The input requires the traffic and weather data obtained in Step 1. The server statistically processes this data to identify routes expected to be congested and areas where bad weather is predicted. The output provides congestion and weather forecasts based on the analysis results. This clarifies the factors to consider when selecting delivery routes.

[0187] Step 3:

[0188] The server calculates the optimal delivery route based on the analysis results. The inputs required are the congestion forecast and weather forecast obtained in step 2. The server uses the Dijkstra algorithm or the A algorithm to calculate the route that reaches the destination in the shortest time. The output provides the optimal delivery route and its estimated travel time. This allows for the creation of efficient delivery plans.

[0189] Step 4:

[0190] The server proposes the calculated optimal route to the user. The input requires the optimal delivery route obtained in step 3. The user can receive a proposal from the server by prompting the generating AI model with the message, "Propose the optimal delivery route from Tokyo to Osaka." The output provides specific route information and estimated arrival times. This allows the user to select an efficient route for actual deliveries.

[0191] Step 5:

[0192] After actually using the suggested route, the user provides feedback to the server. The input requires user evaluations and opinions. The server uses this feedback as data to improve the accuracy of the algorithm. The output is an improved algorithm, which enables more accurate route selection in future suggestions.

[0193] (Application Example 3)

[0194] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0195] In the logistics industry, improving delivery efficiency and reducing fuel consumption are critical challenges. Conventional systems struggle to propose optimal delivery routes that fully consider real-time traffic and weather conditions, often resulting in delivery delays and wasted fuel. This hinders the efficiency of logistics operations.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0197] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data; means for linking information such as location data, traffic conditions, travel speed, and weather conditions; means for proposing an optimal logistics route plan based on this information; means for acquiring traffic conditions and weather conditions in real time and calculating the optimal delivery route; and means for generating prompt messages that propose the optimal delivery route using a generative AI model. This makes it possible to shorten delivery times and save fuel.

[0198] "Past delivery completion data" refers to data that includes information such as the date and time of past deliveries, routes, duration, and success rate.

[0199] "Location information data" refers to data that indicates the current location of an object, obtained using technologies such as GPS.

[0200] "Traffic conditions" refers to information about traffic on roads, such as road congestion levels, traffic jam information, and the occurrence of traffic accidents.

[0201] "Movement speed" is data that indicates the speed at which an object moves.

[0202] "Weather conditions" refer to information about weather, such as climate, temperature, precipitation, and wind speed.

[0203] "Optimal logistics route planning" refers to a plan that proposes the most efficient delivery route with the aim of shortening delivery times and saving fuel.

[0204] "Means for obtaining real-time traffic conditions and weather conditions" refers to technologies and methods for instantly obtaining current traffic conditions and weather conditions.

[0205] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0206] A "prompt statement" is an instruction or question that is input into a generative AI model.

[0207] The system for implementing this invention operates through the coordinated efforts of a server, a terminal, and a user. The server calculates the time with the highest probability of successful delivery based on past delivery completion data. This is done using a machine learning algorithm. Furthermore, the server acquires information such as location data, traffic conditions, travel speed, and weather conditions in real time, and proposes an optimal logistics route plan based on this information. External services such as the Google Maps API and OpenWeatherMap API are used to acquire real-time data.

[0208] The terminal receives the optimal delivery route sent from the server and presents it to the user. The user can review the suggested route through the terminal and apply it to the actual delivery. This makes it possible to shorten delivery times and save fuel.

[0209] As a concrete example, the server inputs the prompt "Please suggest the optimal delivery route considering current traffic conditions and weather" into the generating AI model, and calculates the optimal delivery route. This prompt allows the generating AI model to analyze real-time data and suggest the optimal route.

[0210] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0211] Step 1:

[0212] The server retrieves historical delivery completion data. This data includes delivery date and time, route, duration, and success rate. Using this data as input, the server employs a machine learning algorithm to calculate the time with the highest probability of delivery success. The output is the optimal delivery time.

[0213] Step 2:

[0214] The server acquires real-time data such as location information, traffic conditions, travel speed, and weather conditions. This is done using the Google Maps API and the OpenWeatherMap API. The server uses this data as input to plan the optimal logistics route. The output is the optimal delivery route.

[0215] Step 3:

[0216] The server uses a generative AI model to generate prompts for suggesting the optimal delivery route. Specifically, it creates a prompt that says, "Please suggest the optimal delivery route considering current traffic conditions and weather." Using this prompt as input, the generative AI model calculates and outputs the optimal delivery route.

[0217] Step 4:

[0218] The terminal receives the optimal delivery route sent from the server. The terminal uses this route information as input and presents it visually to the user. The output is a display of the delivery route that the user can verify.

[0219] Step 5:

[0220] The user reviews the delivery route presented through the terminal and incorporates it into the actual delivery. The delivery plan is executed based on the user's input. The output is the actual delivery.

[0221] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0222] "Example of form 1"

[0223] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes emotions from the user's tone of voice, facial expressions, behavioral patterns, etc. Specifically, the emotion engine analyzes the tone of voice, facial expressions, and body movements of the user when they receive a package, and feeds the results back into the system.

[0224] "Example of form 2"

[0225] Based on the emotions recognized by the emotion engine, the system adjusts delivery times and routes. For example, if the system detects that the user is in a bad mood, it adjusts the delivery time to a time when the user is calmer. Conversely, if the user expresses joy, the system uses this information as feedback to learn how to improve the success rate of deliveries in similar situations.

[0226] "Example of form 3"

[0227] Furthermore, the emotion engine captures changes in the user's emotions in real time and feeds that information back into the system. This allows the system to respond flexibly according to the delivery situation. For example, if a user suddenly shows anger, the system can immediately receive that information and take action such as alerting the delivery person.

[0228] The following describes the processing flow for each example of the form.

[0229] "Example of form 1"

[0230] Step 1: The emotion engine analyzes the user's tone of voice, facial expressions, body movements, etc., when they receive their package.

[0231] Step 2: The emotion engine feeds back the results of its analysis to the system.

[0232] "Example of form 2"

[0233] Step 1: The emotion engine recognizes the user's emotions.

[0234] Step 2: The system adjusts delivery times and routes based on the recognized emotions.

[0235] Step 3: The system takes that information as feedback and learns to improve the success rate of deliveries under similar circumstances.

[0236] "Example of form 3"

[0237] Step 1: The emotion engine captures changes in the user's emotions in real time.

[0238] Step 2: Feed that information back into the system.

[0239] Step 3: The system can immediately receive this information and take action, such as alerting the delivery person.

[0240] (Example 1)

[0241] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0242] Traditional delivery systems lacked sufficient optimization of delivery times and struggled to provide services that considered user emotions. This resulted in lower delivery success rates and difficulty in improving customer satisfaction.

[0243] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0244] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion data, means for recognizing emotions by analyzing the user's voice, facial expressions, and behavioral patterns, and means for adjusting the delivery plan based on this information. This improves the success rate of deliveries and enables the provision of flexible services that respond to the user's emotions.

[0245] "Delivery completion data" refers to records of past deliveries, including the date and time, success rate, and recipient information.

[0246] "Optimal delivery time" refers to the most suitable time slot for delivery, calculated to maximize the success rate of the delivery.

[0247] "Voice, facial expressions, and behavioral patterns" refer to characteristics such as the tone of voice, facial expressions, and body movements that a user exhibits when receiving a package.

[0248] "Means of recognizing emotions" refers to technologies and devices that analyze and identify emotions from a user's voice and facial expressions.

[0249] "Means of adjusting delivery plans" refers to technologies and methods for optimizing delivery schedules and routes based on calculated optimal delivery times and user sentiment information.

[0250] This invention relates to a delivery system that calculates the optimal delivery time based on past delivery completion data and further adjusts the delivery plan by recognizing the user's emotions.

[0251] The server collects historical delivery completion data and stores it in a database. This data includes delivery date and time, success rate, and recipient information. The server uses the Python Scikit-learn library to apply machine learning algorithms to calculate the optimal delivery time. This model is built using the Random Forest algorithm.

[0252] The device uses a camera and microphone to capture the user's tone of voice, facial expressions, and body movements when they receive their package. This data is transmitted to a server via the internet. The server analyzes the user's emotions using emotion recognition software. Specifically, a common emotion recognition API is used for emotion analysis.

[0253] The server adjusts the delivery plan based on the analysis results. This improves the success rate of deliveries and enables the provision of flexible services that respond to the user's emotions.

[0254] For example, if past data shows that the highest success rate is calculated to be "weekdays between 2 PM and 4 PM," the delivery person will adjust their schedule to deliver during that time. Also, if a user appears dissatisfied when receiving their package, the system will use that information to notify customer support for follow-up.

[0255] Examples of prompt messages include, "Calculate the optimal delivery time based on past delivery data," and "Recognize the user's emotions from their tone of voice and facial expressions, and provide feedback based on the results."

[0256] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0257] Step 1:

[0258] The server collects historical delivery completion data. It retrieves data from the delivery management system via API, including delivery date and time, success rate, and recipient information. This data is stored in a database for later analysis.

[0259] Step 2:

[0260] The server aggregates stored delivery data and extracts necessary information from the database. It uses SQL queries as input to calculate the success rate for each delivery date and time. As output, it stores the aggregated results in a new table, which is then used to train a machine learning model.

[0261] Step 3:

[0262] The server trains a machine learning model using aggregated data. It takes the aggregated results as input to the Python Scikit-learn library and applies the random forest algorithm. The output is a model that predicts the optimal delivery time.

[0263] Step 4:

[0264] The server uses a trained model to calculate the optimal time for the next delivery. The model is fed data from a new delivery request as input. The output predicts the time slot with the highest success rate and notifies the delivery driver.

[0265] Step 5:

[0266] The device uses a camera and microphone to capture the user's tone of voice, facial expressions, and body movements when they receive their package. It acquires real-time audio and video data as input and sends this data to a server as output.

[0267] Step 6:

[0268] The server inputs the received data into the emotion engine to analyze the user's emotions. Audio and video data are passed to the emotion recognition software as input. The user's emotional state is identified as output and stored in a database.

[0269] Step 7:

[0270] The server adjusts the delivery plan based on the analysis results. Inputs include user sentiment information and optimal delivery times. Outputs include generating an adjusted delivery schedule and notifying customer support as needed.

[0271] (Application Example 1)

[0272] Next, we will describe Application Example 1 of Form 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."

[0273] Traditional delivery systems have challenges in optimizing delivery times and improving customer satisfaction. In particular, the accuracy of delivery time predictions is low, and service improvements that take customer feelings into consideration are not being implemented, making it difficult to improve customer satisfaction.

[0274] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0275] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather conditions, and means for analyzing the customer's facial expressions and tone of voice to recognize their emotions. This enables optimization of delivery times and improvement of services based on customer emotions.

[0276] "Delivery completion data" refers to data that includes information such as the date, time, location, and whether or not a delivery was successful in the past.

[0277] "Location information data" refers to data indicating geographical locations obtained using GPS or other location measurement technologies.

[0278] "Traffic information" refers to data containing various information related to traffic, such as road congestion, traffic accidents, and construction information.

[0279] "Moving speed" refers to data indicating the distance traveled by a delivery vehicle or other moving object within a certain period of time.

[0280] "Weather conditions" refers to data containing information related to weather, such as weather, temperature, precipitation, wind speed, etc.

[0281] "Logistics route" refers to the route for a delivered item to move from the departure location to the destination.

[0282] "Means of recognizing emotions by analyzing expressions and tones of voice" refers to the technology for analyzing the facial expressions and voice tones of customers to determine their emotional states.

[0283] "Feedback for improving services" refers to providing information for improving the quality of services based on customer emotion data.

[0284] As a form of implementing this invention, the server collects past delivery completion data and executes a program to calculate the optimal delivery time using machine learning algorithms. Specifically, data analysis is performed using Python, and algorithms such as random forest are used. The server also integrates information such as location information data, traffic information, moving speed, and weather conditions to optimize the logistics route. This requires real-time data processing and utilizes cloud-based databases and APIs.

[0285] The terminal is a device such as a smartphone or tablet, and it uses a camera and microphone to analyze the customer's facial expressions and tone of voice. Using OpenCV and TENSORFLOW®, it performs real-time image processing and voice analysis to recognize the customer's emotions. This customer emotion data is then sent to a server to generate feedback for service improvement.

[0286] As a concrete example, when a user places an order using a food delivery app, the server calculates the optimal delivery time based on past data and notifies the delivery person. When the delivery person arrives, the terminal analyzes the customer's facial expression and recognizes emotions such as "satisfaction." This information is sent to the server and used as feedback to improve the service.

[0287] An example of a prompt to be input into the generating AI model is: "Calculate the optimal delivery time based on past delivery data. Also, recognize the customer's emotions from their facial expressions and tone of voice, and provide feedback."

[0288] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0289] Step 1:

[0290] The server retrieves past delivery completion data from a database. The input includes data such as delivery date and time, location, and whether the delivery was successful or not. Based on this data, a machine learning algorithm (e.g., Random Forest) is used to calculate the optimal delivery time. The output is the delivery time with the highest probability of success.

[0291] Step 2:

[0292] The server obtains real-time data such as location data, traffic information, travel speed, and weather conditions via APIs. This data is then integrated as input to optimize the logistics route. As part of the data processing, an algorithm is applied to integrate the various pieces of information and calculate the shortest route. The output is the optimized logistics route.

[0293] Step 3:

[0294] The user places an order using a food delivery app on their smartphone. The user enters the order details and delivery address information into the app. The server sends a notification to the delivery driver based on the optimal delivery time and route determined in steps 1 and 2. The output is a delivery instruction for the driver.

[0295] Step 4:

[0296] The device captures the customer's facial expressions and tone of voice using the smartphone's camera and microphone when the delivery person arrives. It acquires real-time video and audio data as input. Using OpenCV and TensorFlow, it performs image processing and audio analysis to recognize the customer's emotions. The output is the recognized emotion data.

[0297] Step 5:

[0298] The server receives sentiment data sent from the terminal and generates feedback for service improvement. Sentiment data is used as input. As a data calculation, the sentiment data is analyzed to generate specific suggestions for service improvement. The output is feedback information for service improvement.

[0299] (Example 2)

[0300] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0301] In the logistics industry, improving delivery efficiency and customer satisfaction are crucial challenges. Traditional systems struggle to respond flexibly to real-time changes in circumstances and customer emotions, resulting in insufficient delivery optimization. Furthermore, a lack of learning capabilities to increase delivery success rates makes improvement under similar circumstances difficult.

[0302] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following respective means.

[0303] In this invention, the server includes means for calculating, based on past delivery completion data, the time when the probability of successful delivery is highest, means for coordinating location information data, traffic condition data, moving speed data, and weather data, means for proposing an optimal plan for the logistics route based on this information, means for adjusting the delivery time and delivery route based on the user's emotions using emotion recognition technology, and means for incorporating the user's emotion information as feedback and performing learning to increase the delivery success rate. Thereby, it becomes possible to propose an optimal delivery plan in real time and flexibly adjust the delivery according to the user's emotions, and improvements in delivery efficiency and customer satisfaction can be realized.

[0304] The "past delivery completion data" is data including information such as the date and time, route, required time, and success / failure of past deliveries.

[0305] The "location information data" is geographical information regarding a specific location, acquired using GPS or other location measurement technologies.

[0306] The "traffic condition data" is real-time information regarding traffic, such as road congestion, traffic regulations, and accident information.

[0307] The "moving speed data" is information regarding the moving speed of vehicles or people, acquired from speed sensors or GPS data.

[0308] The "weather data" is information regarding the weather, including weather conditions such as temperature, precipitation, and wind speed.

[0309] The "optimal plan for the logistics route" is an optimal delivery route and schedule calculated based on real-time data in order to maximize the efficiency of delivery.

[0310] "Emotion recognition technology" is a technology that analyzes voice and text data to identify the emotional state of a user.

[0311] "Learning to improve delivery success rates" refers to a machine learning process that uses past delivery data and user feedback to improve the success rate of deliveries.

[0312] This invention is a system aimed at improving logistics efficiency and customer satisfaction. The server first collects past delivery completion data and calculates the time of day when deliveries have the highest probability of success. A machine learning algorithm is used for this calculation. Next, the server acquires location data, traffic data, speed data, and weather data in real time and integrates and analyzes this information. Specifically, location data is acquired using a GPS module, traffic data is acquired through a general map API, speed data is acquired from the vehicle's speed sensor, and weather data is acquired using a weather information API.

[0313] Based on this data, the server proposes an optimal logistics route plan. This plan aims to reduce delivery time and save fuel, and is dynamically updated according to real-time conditions. The terminal also uses emotion recognition technology to recognize emotions from the user's voice and text data. For example, if the user says "I'm busy today," the terminal recognizes that emotion as being in a bad mood. Based on this emotion information, the server adjusts the delivery time and route to ensure that deliveries are made during times when the user is less busy.

[0314] Furthermore, the server incorporates user emotional information as feedback and learns to improve the delivery success rate. This learning process uses a generative AI model. For example, if a user is in a situation where "it's raining today and there's traffic congestion," the server analyzes weather and traffic information and suggests routes that avoid the rain and congestion.

[0315] Examples of prompts to input into the generating AI model include "Please suggest the optimal delivery route considering the current weather and traffic conditions" and "Please adjust the delivery time based on the user's emotions." This enables the suggestion of optimal delivery plans in real time and flexible delivery adjustments based on the user's emotions, leading to improved delivery efficiency and customer satisfaction.

[0316] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0317] Step 1:

[0318] The server collects historical delivery completion data. It uses data such as past delivery date and time, route, duration, and success / failure status as input. Based on this data, a machine learning algorithm is used to calculate the time of day with the highest probability of success for delivery. The output provides recommendations for the optimal delivery time.

[0319] Step 2:

[0320] The server acquires location data, traffic data, speed data, and weather data in real time. It uses data from GPS modules, map APIs, speed sensors, and weather information APIs as input. This data is integrated and analyzed to propose the optimal logistics route plan. The output provides the optimal delivery route and schedule.

[0321] Step 3:

[0322] The device inputs the user's voice and text data into emotion recognition technology to recognize the user's emotions. User statements and messages are used as input. An emotion recognition AI model is used to identify the user's emotional state. The output is the user's emotional information.

[0323] Step 4:

[0324] The server adjusts delivery times and routes based on the user's sentiment information obtained in step 3. It uses the user's sentiment information and the optimal delivery route obtained in step 2 as input. It creates a flexible delivery plan tailored to the sentiment, and the adjusted delivery schedule is output.

[0325] Step 5:

[0326] The server incorporates user emotional information as feedback and learns to improve delivery success rates. Past delivery data and user emotional feedback are used as input. A generative AI model is used to learn how to improve delivery success rates. The output is an improved delivery planning algorithm.

[0327] (Application Example 2)

[0328] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0329] In modern logistics services, improving delivery efficiency and customer satisfaction are crucial challenges. However, conventional systems struggle to propose optimal delivery routes that take real-time traffic and weather conditions into account, and they fail to adjust delivery times to consider the emotional state of the user. As a result, delivery success rates may decrease, potentially compromising customer satisfaction.

[0330] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0331] This invention includes a server that includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic conditions, travel speed, and weather information, means for proposing an optimal logistics route plan based on this information, means for analyzing the user's emotional state using emotion recognition technology and adjusting the delivery time and route, and means for comprehensively analyzing information acquired in real time and learning to improve the delivery success rate based on the user's emotions. This makes it possible to improve delivery efficiency and customer satisfaction.

[0332] "Delivery completion data" refers to data that records detailed information about deliveries made in the past, including delivery time, delivery destination, and whether the delivery was successful or not.

[0333] "Location data" refers to data that indicates the geographical location of a specific object, obtained using GPS or other location measurement technologies.

[0334] "Traffic conditions" refers to information about the flow of traffic on roads, such as the degree of road congestion, traffic jam information, and the occurrence of traffic accidents.

[0335] "Movement speed" is an indicator that shows the distance a particular object travels per unit of time.

[0336] "Weather information" refers to information about weather conditions in a specific region, such as weather, temperature, precipitation, and wind speed.

[0337] A "logistics route" is the path that goods take when traveling from their origin to their destination, and it should be optimized to ensure efficient delivery.

[0338] "Emotion recognition technology" is a technology that analyzes and identifies a user's emotional state based on their facial expressions, voice, and behavior.

[0339] "Delivery success rate" is an indicator that shows the probability of a delivery being completed on schedule, and is used to evaluate the efficiency and reliability of logistics services.

[0340] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user.

[0341] The server calculates the time with the highest probability of successful delivery based on past delivery completion data. This is done using machine learning algorithms. The server also acquires location data, traffic conditions, travel speed, and weather information in real time and analyzes this information comprehensively. Specifically, it obtains location information using the Google Maps API, checks traffic conditions using the Waze API, and obtains weather information using the OpenWeatherMap API. This data is processed using Python's Pandas and NumPy to propose the optimal logistics route.

[0342] The device analyzes the user's emotional state using emotion recognition technology. This utilizes the Microsoft® Azure® Emotion API. Based on the user's emotions, the device sends information to the server to adjust delivery times and routes.

[0343] Users can check the delivery status through their device and adjust the delivery time as needed. If the server detects that the user is in a bad mood, it will adjust the delivery time to ensure the delivery is made when the user is calmer.

[0344] For example, if a user orders "pizza" and the emotion engine detects that the user is "unhappy," the server will check traffic information to confirm that the usual route is congested, and taking into account the weather ("rainy"), it will suggest a route that departs earlier than usual and avoids traffic.

[0345] Examples of prompts for a generative AI model include the following:

[0346] "If the user is unhappy, suggest the optimal delivery time. Current traffic conditions are congested, and the weather is rainy. How would you adjust the route?"

[0347] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0348] Step 1:

[0349] The server retrieves past delivery completion data. It receives data such as past delivery time, destination, and success / failure status as input. Using this data, it applies a machine learning algorithm to calculate the time with the highest probability of delivery success. The output is the optimal delivery time.

[0350] Step 2:

[0351] The server acquires location data, traffic conditions, travel speed, and weather information in real time. It receives data from the Google Maps API, Waze API, and OpenWeatherMap API as input. This data is integrated using Pandas and NumPy to optimize logistics routes. The output is the optimal delivery route.

[0352] Step 3:

[0353] The device analyzes the user's emotional state using emotion recognition technology. As input, it sends data of the user's facial expressions and voice to the Microsoft Azure Emotion API. The response from the API is analyzed to identify the user's emotional state. The output is the user's emotional state.

[0354] Step 4:

[0355] The server adjusts delivery times and routes based on the user's emotional state. It receives the optimal delivery time obtained in step 1, the optimal delivery route obtained in step 2, and the user's emotional state obtained in step 3 as input. This information is integrated to adjust the delivery plan. The output is the adjusted delivery time and route.

[0356] Step 5:

[0357] The user reviews the adjusted delivery plan through their terminal. They receive the adjusted delivery time and route from the server as input. The user can request a readjustment of the delivery time if necessary. The final delivery plan is reviewed as output.

[0358] (Example 3)

[0359] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0360] There is a need to improve delivery efficiency in logistics and to provide flexible responses that respond to customer emotions. Conventional systems have difficulty responding quickly to changes in traffic conditions and weather, and have not adequately adjusted services based on changes in customer emotions. As a result, delays in delivery times and customer dissatisfaction are common challenges.

[0361] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0362] In this invention, the server includes means for calculating delivery time based on past delivery completion information, means for linking information such as location information, traffic conditions, travel speed, and weather conditions, and means for detecting changes in the user's emotions in real time and providing feedback on that information. This enables optimization of delivery routes and flexible responses to the user's emotions.

[0363] "Delivery completion information" refers to data that records the details of past deliveries, including information such as the delivery date and time, delivery destination, and duration.

[0364] "Location information" refers to data indicating a geographical location, specifically latitude and longitude information obtained using technologies such as GPS.

[0365] "Traffic conditions" refer to information indicating the degree of road congestion and passability, and are data that reflects the real-time changes in traffic flow.

[0366] "Movement speed" is an indicator that shows the distance traveled per unit of time, and represents the speed at which vehicles or people move.

[0367] "Weather conditions" refer to information about the weather, including meteorological elements such as temperature, precipitation, and wind speed.

[0368] "Emotional changes" refer to fluctuations in the user's emotional state, which are detected through analysis of voice and facial expressions.

[0369] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate results tailored to a specific purpose.

[0370] "Delivery route" refers to the path taken when delivering goods, and includes the optimal route from the origin to the destination.

[0371] A description of embodiments for carrying out this invention will be given.

[0372] The server generates a program that calculates delivery times based on past delivery completion data to improve delivery efficiency in logistics. This program uses a generating AI model to propose the optimal delivery route by linking data such as location information, traffic conditions, travel speed, and weather conditions. Specifically, it uses external software such as the Google Maps API and OpenWeatherMap API to obtain real-time traffic information and weather data.

[0373] The terminal uses emotion recognition software to detect changes in the user's emotions in real time. This software analyzes the user's voice and facial expressions to detect changes in emotions. If the user shows anxiety or anger, this information is fed back to the server, which then flexibly adjusts the delivery plan.

[0374] For example, if the usual route is congested, the server can suggest an alternative route. Also, if a user expresses concern that a delivery may be delayed, the server can instruct the delivery person to take immediate action.

[0375] Examples of prompts for a generative AI model include the following:

[0376] "Please suggest the optimal delivery route, taking into account current traffic conditions and weather."

[0377] "Adjust the delivery plan based on the user's emotional data." Figure 21 illustrates the flow of the specific processing in Example 3.

[0378] Step 1:

[0379] The server receives past delivery completion information as input and calculates the delivery time. Using a machine learning algorithm, it predicts the delivery time with the highest probability of success based on past data. The output is the optimal delivery time.

[0380] Step 2:

[0381] The server takes location information, traffic conditions, travel speed, and weather conditions as input. This data is collected in real time using the Google Maps API and OpenWeatherMap API. The server integrates this information and uses a generative AI model to calculate the optimal delivery route. The output is the optimized delivery route.

[0382] Step 3:

[0383] The device transmits the user's voice and facial expressions as input to emotion recognition software. This software detects changes in the user's emotions in real time and generates emotion data. The output is the user's emotional state.

[0384] Step 4:

[0385] The device feeds back the detected emotion data to the server. The server adjusts the delivery plan based on this information. For example, if the user shows signs of anxiety, the server instructs the delivery person to take immediate action. The adjusted delivery plan is then output.

[0386] Step 5:

[0387] The server notifies the user of the optimized delivery route and adjusted delivery plan. The terminal displays the new delivery route and estimated arrival time to the user. The output provides the user with the information to be provided.

[0388] (Application Example 3)

[0389] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0390] Optimizing delivery routes in logistics contributes to reducing transportation time and saving fuel, but conventional systems have the challenge of not being able to respond flexibly to the emotional state of users. Furthermore, they cannot provide appropriate feedback in response to the stress and emotional changes of delivery personnel, which may result in a decrease in delivery efficiency.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0392] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather information, means for proposing an optimal logistics route plan based on this information, means for analyzing the user's emotions in real time using an emotion analysis engine and providing feedback, and means for suggesting revised routes or breaks based on the emotional state of the delivery person. This enables flexible responses according to the emotional state of the delivery person while shortening transportation time and saving fuel.

[0393] "Past delivery completion data" refers to data that records detailed information about deliveries made in the past, including information such as delivery date and time, delivery destination, delivery time, and success rate.

[0394] "Location data" refers to data that indicates the geographical location of a specific point, obtained using GPS or other location measurement technologies.

[0395] "Traffic information" refers to real-time information about road traffic, such as road congestion, accident information, and traffic restrictions.

[0396] "Travel speed" is data that indicates the speed at which one moves between specific points, and is usually expressed in time per unit of distance.

[0397] "Weather information" refers to information about the weather, including data such as temperature, precipitation, wind speed, and humidity.

[0398] "Optimal logistics route planning" refers to a plan that proposes the most efficient delivery route with the aim of reducing transportation time and saving fuel.

[0399] An "emotion analysis engine" is a technology that analyzes a user's emotions from their facial expressions and voice, and understands their emotional state in real time.

[0400] "Means of providing feedback" refers to methods for providing appropriate instructions and information to users and delivery personnel based on the analyzed information.

[0401] "Delivery driver's emotional state" refers to the emotional state that a delivery driver experiences while on duty, and includes stress, fatigue, satisfaction, and other factors.

[0402] "Re-proposing routes" means reviewing existing delivery routes based on current circumstances and proposing new, optimal routes.

[0403] "Suggesting breaks" means recommending that delivery drivers take breaks at appropriate times, depending on their emotional state and level of fatigue.

[0404] The system that realizes this invention consists of a server, a delivery person's terminal, and a user's terminal. The server executes an algorithm to calculate the time with the highest probability of successful delivery based on past delivery completion data. Machine learning techniques can be used for this. The server also acquires location data, traffic information, travel speed, and weather information in real time, and integrates this information to generate an optimal logistics route plan.

[0405] The delivery driver's terminal is equipped with an emotion analysis engine that analyzes the driver's emotional state in real time from their facial expressions and voice. This information is sent to a server, and based on the driver's emotional state, the server suggests rerouting or taking a break. Specifically, if the driver is feeling stressed, the server inputs a prompt into the AI ​​model saying, "The driver is feeling stressed, please recalculate the route and suggest a break," and provides appropriate feedback.

[0406] The user's device is used to check the delivery status and receive feedback. If a user expresses dissatisfaction with the delivery, an emotion analysis engine analyzes their emotions and sends feedback to the server. This allows the server to flexibly adjust the delivery plan and improve user satisfaction.

[0407] This system uses the Google Maps API to obtain traffic information and the OpenWeatherMap API to obtain weather data. It also uses the Microsoft Azure Emotion API for sentiment analysis. This allows for shorter delivery times and fuel savings, while also enabling flexible responses based on the emotional state of delivery personnel.

[0408] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0409] Step 1:

[0410] The server retrieves past delivery completion data and uses a machine learning algorithm to calculate the time with the highest probability of successful delivery. This process uses data such as past delivery date and time, success rate, and delivery destination as input and outputs the optimal delivery time. Specifically, the server analyzes the dataset and learns patterns to predict the optimal time for the next delivery.

[0411] Step 2:

[0412] The server acquires location data, traffic information, travel speed, and weather information in real time. This information is obtained using the Google Maps API and the OpenWeatherMap API. The server integrates this data to generate an optimal logistics route plan. Inputs include current location, road congestion, and weather data, and the output is the optimal delivery route. Specifically, the server analyzes each piece of data and calculates the route to reach the destination in the shortest time.

[0413] Step 3:

[0414] The delivery person's terminal uses an emotion analysis engine to analyze their emotional state in real time from their facial expressions and voice. Inputs include the delivery person's facial image and voice data, and output is an evaluation of their emotional state. Specifically, the terminal collects data using a camera and microphone and analyzes emotions using Microsoft Azure's Emotion API.

[0415] Step 4:

[0416] The server suggests alternative routes and breaks based on the delivery person's emotional state. The input is the result of the emotional analysis, and the output is the revised route and break instructions. Specifically, the server generates a prompt such as, "The delivery person is stressed; please recalculate the route and suggest a break," which is input into the AI ​​model, providing appropriate feedback.

[0417] Step 5:

[0418] The user's device is used to check the delivery status and receive feedback. Inputs include delivery status data from the server, and outputs include notifications and feedback to the user. Specifically, the user can check the delivery progress through the application and send feedback as needed.

[0419] (Other examples)

[0420] Next, other embodiments will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0421] In the logistics industry, improving delivery efficiency and customer satisfaction are crucial challenges. Traditional systems often failed to adequately optimize delivery times and routes, making them unable to adapt to changes in traffic conditions and weather. Furthermore, it was difficult to flexibly adjust delivery plans to take customer sentiment into consideration, sometimes leading to a decline in customer satisfaction.

[0422] The identification process performed by the identification processing unit 290 of the data processing device 12 in other embodiments is realized by the following means.

[0423] In this invention, the server includes means for collecting past delivery completion data and calculating the optimal delivery time, means for integrating and analyzing location information, traffic information, and weather conditions in real time, and means for inputting prompts to a generated AI model to propose an optimal logistics route plan. This enables improved delivery efficiency and flexible adjustment of delivery plans that take customer sentiment into consideration.

[0424] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, and whether the delivery was successful.

[0425] A "generative AI model" is a model trained to perform specific tasks using artificial intelligence technology, and possesses functions such as natural language processing and image recognition.

[0426] A "prompt" is an input sentence used to instruct a generative AI model to perform a specific task, and it contains instructions for the model to generate an appropriate response.

[0427] "Location data" refers to data indicating a geographical location, obtained using technologies such as GPS, and includes information such as latitude and longitude.

[0428] "Traffic information" refers to data that includes real-time information related to traffic, such as road congestion, traffic accidents, and construction information.

[0429] "Weather conditions" refer to data that indicates information about the weather, including meteorological elements such as temperature, precipitation, and wind speed.

[0430] "Emotion recognition" is a technology that analyzes a user's tone of voice, facial expressions, and behavioral patterns to identify their emotional state.

[0431] A "delivery route" refers to the path taken during delivery, including the optimal route from the origin to the destination.

[0432] This invention is a system aimed at improving delivery efficiency and customer satisfaction in the logistics industry. The system mainly consists of three elements: a server, terminals, and users.

[0433] Server Processing

[0434] The server retrieves historical delivery completion data from a MySQL® database. This involves extracting data using SQL queries and converting it into a DataFrame using the Python Pandas library. Data preprocessing includes imputing missing values ​​and removing outliers. Next, a pre-trained machine learning model is loaded using TensorFlow to calculate the optimal delivery time. This model is designed to maximize the delivery success rate based on historical data.

[0435] The server uses the Google Maps API to obtain current traffic information and the OpenWeatherMap API to obtain weather data. The responses from these APIs are received in JSON format and parsed using Python's JSON library. The retrieved data is then converted into a NumPy array for integrated analysis. This analysis includes calculations to assess the impact of traffic congestion and the risk of delays due to weather.

[0436] Based on integrated data, prompts are generated to suggest the optimal logistics route. These generated prompts are input into an OpenAI® GPT model to generate the optimal delivery route. Example prompt: "Considering current traffic conditions and weather, please suggest the shortest possible delivery route."

[0437] The server receives user tone and facial expression data transmitted from the terminal. This data is collected via the camera and microphone. Using the Microsoft Azure Emotion API, this data is analyzed to identify the user's emotional state. Based on the recognized emotional data, prompt messages are generated to dynamically adjust delivery times and routes. Example prompt message: "The user seems to be in a hurry, please suggest the fastest delivery route."

[0438] Terminal processing

[0439] The device displays the optimal delivery plan received from the server to the user via a mobile application built with React Native. The user reviews the displayed delivery plan and provides feedback on their satisfaction level and areas for improvement. This feedback is sent to the server through the application and used to improve future algorithms.

[0440] User processing

[0441] Users review the delivery plan displayed on their device and provide feedback as needed. This feedback concerns satisfaction with delivery time and the appropriateness of the route. This feedback is sent to the server and used to improve the algorithm.

[0442] The flow of specific processing in other embodiments will be explained using Figure 23.

[0443] Step 1:

[0444] The server retrieves past delivery completion data from a MySQL database. It uses the SQL query "SELECT FROM delivery_data WHERE status='completed';" as input. The retrieved data is converted into a DataFrame using the Python Pandas library as output. Data preprocessing includes imputation of missing values ​​and removal of outliers.

[0445] Step 2:

[0446] The server loads a machine learning model trained using TensorFlow. It uses pre-processed delivery data as input. As output, it calculates the optimal delivery time. This model is designed to maximize the delivery success rate and makes predictions based on historical data.

[0447] Step 3:

[0448] The server uses the Google Maps API to obtain current traffic information and the OpenWeatherMap API to obtain weather data. It uses API keys and request parameters as input. The output receives traffic and weather data in JSON format. This data is parsed using the Python JSON library and converted into NumPy arrays.

[0449] Step 4:

[0450] The server performs analysis based on integrated traffic and weather data. It uses data converted into NumPy arrays as input. The output provides analysis results for evaluating the impact of traffic congestion and the risk of delays due to weather. This analysis includes calculations that take into account fluctuations in traffic volume and sudden changes in weather.

[0451] Step 5:

[0452] The server generates prompts based on the analysis results. The analysis results are used as input. The output is a prompt to be input into the generated AI model. Example prompt: "Considering current traffic conditions and weather, please suggest the shortest possible delivery route." This prompt is input into OpenAI's GPT model to generate the optimal delivery route.

[0453] Step 6:

[0454] The server receives user voice and facial expression data sent from the terminal. It uses data collected through the camera and microphone as input. As output, it obtains the user's emotional state, analyzed using the Microsoft Azure Emotion API. Based on the emotional data, it generates prompt messages to dynamically adjust delivery time and route. Example prompt message: "The user seems to be in a hurry, please suggest the fastest delivery route."

[0455] Step 7:

[0456] The device displays the optimal delivery plan received from the server to the user via a mobile application built with React Native. It uses delivery plan data from the server as input. The output is a visual presentation of the delivery plan to the user. The user reviews the displayed delivery plan and provides feedback on their satisfaction level and areas for improvement. This feedback is sent to the server through the application and used to improve future algorithms.

[0457] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0458] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0459] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0460] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0461] [Second Embodiment]

[0462] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0463] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0464] The data processing device 12 includes a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a “computer” related to the technology of this disclosure. The computer 22 includes a processor 28, RAM 30, and storage 32.

[0465] The processor 28, RAM 30, and storage 32 are connected to the bus 34. The database 24 and communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to the network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0466] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0467] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0468] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0469] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0470] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0471] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0472] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0473] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0474] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0475] "Example of form 1"

[0476] One embodiment of this system is a B2C delivery system. This system has a function to calculate the optimal delivery time based on past delivery completion data. Specifically, it aggregates past delivery data and uses a machine learning algorithm to calculate the optimal delivery time from that data.

[0477] "Example of form 2"

[0478] Furthermore, this system has the functionality to integrate information such as GPS data, traffic information, travel speed, and weather. This information is acquired in real time and analyzed comprehensively to propose the most suitable delivery route for the current situation.

[0479] "Example of form 3"

[0480] Furthermore, this system has a function to propose the optimal logistics route plan based on this information. Specifically, it proposes routes that can shorten transportation time and save fuel, based on the calculated optimal delivery time and related information. For example, it can avoid routes that are expected to be congested and propose routes optimized for traffic information and weather conditions.

[0481] The following describes the processing flow for each example of the form.

[0482] "Example of form 1"

[0483] Step 1: The system aggregates past delivery completion data. This includes information such as delivery time, delivery destination, and delivery success rate.

[0484] Step 2: Based on the aggregated data, a machine learning algorithm is used to calculate the time of day when deliveries have the highest probability of success. This algorithm takes into account factors such as time of day, location, and weather.

[0485] "Example of form 2"

[0486] Step 1: The system acquires information such as GPS data, traffic information, travel speed, and weather in real time. This information is obtained from various sensors and external APIs.

[0487] Step 2: Analyze the acquired information to propose the optimal delivery route for the current situation. This analysis will take into account factors such as road congestion, traffic restrictions, and weather conditions.

[0488] "Example of form 3"

[0489] Step 1: Based on the calculated optimal delivery time and related information, the system proposes routes that can shorten transportation time and save fuel.

[0490] Step 2: Specifically, suggest routes that are optimized for traffic information and weather conditions, avoiding routes that are expected to be congested. For example, suggest leaving earlier during peak hours and avoiding slippery roads in rainy weather.

[0491] (Example 1)

[0492] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0493] In the logistics industry, improving delivery efficiency and reducing costs are critical challenges. In particular, optimizing delivery times directly leads to increased customer satisfaction and more effective use of transportation resources. However, traditional methods have struggled to calculate optimal delivery times due to the inability to fully utilize historical data. Furthermore, the inability to consider fluctuating factors such as traffic conditions and weather in real time has resulted in reduced accuracy in delivery planning.

[0494] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0495] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion information, means for integrating information such as location information, traffic conditions, travel speed, and weather conditions, and means for proposing an optimal logistics route plan based on this information. This enables the optimization of delivery time and the efficiency of logistics routes.

[0496] "Delivery completion information" refers to data that includes the date and time of past deliveries, delivery destination, and recipient information.

[0497] "Location information" refers to data indicating a geographical location, obtained using methods such as GPS.

[0498] "Traffic conditions" refers to information about road congestion and passable routes.

[0499] "Movement speed" refers to data indicating the speed at which a delivery vehicle moves.

[0500] "Weather conditions" refer to information about weather, such as climate, temperature, and precipitation.

[0501] A "logistics route" is the path that a delivery item takes when it travels from its origin to its destination.

[0502] An "optimal plan" is a delivery schedule designed to reduce transportation time and conserve resources.

[0503] A "machine learning algorithm" is a computational method used to learn patterns from data and perform predictions and classifications.

[0504] "Data preprocessing" refers to the process of shaping data into a format suitable for machine learning.

[0505] "Features" are attributes or metrics of data that machine learning models use when training.

[0506] "Training" is the process by which a machine learning model learns patterns from data.

[0507] "Evaluation" is the process of measuring the performance of a trained machine learning model and verifying its accuracy.

[0508] In an embodiment of this invention, the server runs a program to collect past delivery completion information and calculate the optimal delivery time. The server retrieves delivery completion information from a database and preprocesses the data using the Python Pandas library. Preprocessing includes imputing missing values ​​and removing outliers. Next, the server trains and evaluates a machine learning model using the Scikit-learn library. Algorithms such as random forest and gradient boosting are used to train the model.

[0509] The server integrates information such as location data, traffic conditions, travel speed, and weather conditions, and based on this information, proposes the optimal logistics route plan. This enables the optimization of delivery times and the efficiency of logistics routes.

[0510] For example, the server uses delivery data for a certain region to calculate that "deliveries in this region have a higher success rate between 2 PM and 4 PM." Users can then check this information through their terminal and plan their deliveries accordingly.

[0511] An example of a prompt message is: "Calculate the optimal delivery time based on past delivery data. The data includes delivery date and time, address, and recipient information."

[0512] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0513] Step 1:

[0514] The server retrieves past delivery completion information from the delivery database. Input includes delivery date and time, delivery address, and recipient information. This data is aggregated to prepare for the next processing step. Specifically, it extracts the necessary data using SQL queries.

[0515] Step 2:

[0516] The server preprocesses the acquired data. The input is the delivery completion information aggregated in step 1. The Python Pandas library is used for data preprocessing, including imputing missing values ​​and removing outliers. The output is data formatted in a way that is suitable for machine learning algorithms. Specifically, it cleans the data frame.

[0517] Step 3:

[0518] The server selects features from preprocessed data and generates new features. The input is the data formatted in step 2. Feature selection involves analyzing data correlations and extracting important attributes. The output is a set of features used to train a machine learning model. Specifically, it creates a correlation matrix and selects important features.

[0519] Step 4:

[0520] The server trains a machine learning model using the selected features. The input is the feature set generated in step 3. The Scikit-learn library is used to train the model with algorithms such as random forest and gradient boosting. The output is the trained machine learning model. Specifically, the hyperparameters of the model are tuned to build the optimal model.

[0521] Step 5:

[0522] The server evaluates the trained model. The input is the trained model obtained in step 4. Cross-validation is used to measure the model's accuracy. The output is an indicator of the model's accuracy. Specifically, the server identifies areas for improvement in the model based on the evaluation results.

[0523] Step 6:

[0524] The server calculates the optimal delivery time using a pre-evaluated model. Inputs include real-time location information, traffic conditions, travel speed, and weather conditions. The output is the optimal delivery time for each destination. Specifically, it inputs new data into the model and generates prediction results.

[0525] Step 7:

[0526] The server provides the user with the calculated optimal delivery time. The input is the optimal delivery time obtained in step 6. The output is a delivery schedule that the user can view on their terminal. Specifically, the results are displayed in the user interface to assist the user in planning their delivery.

[0527] (Application Example 1)

[0528] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0529] In food delivery services, determining the optimal delivery time is crucial to ensure customers receive their food in the freshest possible condition. However, traditional systems often fail to adequately optimize delivery times, making it difficult to improve customer satisfaction.

[0530] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0531] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as GPS data, traffic information, travel speed, and weather, means for proposing the optimal logistics route plan based on this information, means for analyzing past delivery data and proposing the optimal delivery time to the user, and means for presenting the optimal delivery time when the user confirms their order. This makes it possible to optimize delivery times so that customers can receive their food in the freshest possible condition.

[0532] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, and whether the delivery was successful.

[0533] "Success probability" is an indicator that shows the likelihood of delivery being completed on schedule, and is calculated based on past data.

[0534] A "machine learning algorithm" is a computational method that allows computers to learn patterns from data and perform predictions and classifications.

[0535] "Optimal delivery time" refers to the time required for delivery to be completed in the most efficient and customer-satisfying manner.

[0536] "Means of suggesting to the user" refers to the methods and functions that the system uses to present the user with the optimal options based on its analysis results.

[0537] An "optimal logistics route plan" is a delivery route plan designed to maximize delivery efficiency and minimize time and costs.

[0538] "Traffic information" refers to real-time data related to traffic, such as road congestion, traffic accidents, and construction information.

[0539] "Means presented to the user when confirming an order" refers to the methods or functions that the system uses to display the optimal delivery time when the user makes a final decision on an order.

[0540] The system for implementing this invention operates in a network environment including a server and user terminals. The server collects past delivery completion data and uses a machine learning algorithm to calculate the optimal delivery time based on this data. Specifically, it uses Python and the Scikit-learn library to build a machine learning model. The server preprocesses the collected data, extracts features, and then trains the model using algorithms such as random forest.

[0541] The user terminal is a device such as a smartphone or tablet that receives the optimal delivery time provided by the server and presents it to the user. When the user confirms their order, the terminal displays the optimal delivery time on the screen based on the server's suggestion. This allows the user to choose the time when they can receive their food in the freshest condition.

[0542] As a concrete example, when a user orders a pizza, the terminal suggests, "Based on past data, specifying 18:30 for delivery is most likely to ensure the food arrives in the freshest condition." This suggestion is the result of the server using a generated AI model to analyze past delivery data and predict the optimal delivery time.

[0543] An example of a prompt message would be: "Based on past delivery data, predict the optimal delivery time. The current order is for pizza, and the user's location is Shibuya Ward, Tokyo."

[0544] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0545] Step 1:

[0546] The server collects past delivery completion data from the database. It takes information such as delivery date and time, delivery destination, and whether the delivery was successful as input. This data is preprocessed to impute missing values ​​and remove outliers. The output is a clean dataset.

[0547] Step 2:

[0548] The server extracts features using pre-processed data. It uses a clean dataset as input and selects features such as delivery time, day of the week, and weather. This results in the output of a dataset suitable for training machine learning models.

[0549] Step 3:

[0550] The server uses the Scikit-learn library to build and train a machine learning model. It uses a feature-extracted dataset as input. It applies the Random Forest algorithm to generate a model that predicts the optimal delivery time. The output is the trained model.

[0551] Step 4:

[0552] The server uses a generative AI model to predict the optimal delivery time based on the user's order information. It uses the user's current order details and location as input. By generating prompt messages and inputting them into the model, it outputs the optimal delivery time.

[0553] Step 5:

[0554] The terminal displays the optimal delivery time received from the server to the user. It receives a suggested delivery time from the server as input. The screen displays a message such as, "Based on past data, specifying 18:30 for delivery is likely to ensure your food arrives in the freshest condition." The output provides information to help the user select the optimal delivery time.

[0555] Step 6:

[0556] The user confirms the optimal delivery time displayed on the terminal and confirms the order. The terminal provides a suggested delivery time as input. The user selects the suggested time and completes the order. The confirmed order information is sent to the server as output.

[0557] (Example 2)

[0558] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0559] In the logistics industry, improving delivery efficiency and reducing costs are crucial challenges. In particular, delivery times are often unpredictable due to traffic congestion and weather changes, leading to delivery delays and wasted fuel. Traditional systems lack sufficient real-time information integration and optimal route suggestions, resulting in decreased delivery efficiency.

[0560] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0561] In this invention, the server includes means for calculating the time of day when delivery is most likely to succeed based on past delivery completion information, means for linking information such as location information, traffic conditions, travel speed, and weather information, and means for proposing an optimal logistics route plan based on this information. This enables real-time information integration and the proposal of the optimal route.

[0562] "Past delivery completion information" refers to data such as the date and time of past deliveries, route, duration, and success rate.

[0563] "Location information" refers to geographical coordinate data of a specific point, obtained using technologies such as GPS.

[0564] "Traffic conditions" refers to real-time information about road traffic, such as road congestion levels, traffic jams, and traffic restrictions.

[0565] "Movement speed" refers to data indicating the speed at which a vehicle is moving, and is usually obtained from speed sensors or similar devices.

[0566] "Weather information" refers to data related to weather conditions, including information such as temperature, precipitation, and wind speed.

[0567] "Optimal logistics route planning" refers to proposed delivery routes calculated to maximize delivery efficiency and minimize time and costs.

[0568] A "generative AI model" refers to a model that has been trained using artificial intelligence technology to perform a specific task.

[0569] A "prompt" refers to text input to give specific instructions or questions to a generative AI model.

[0570] This invention is a system aimed at improving delivery efficiency in the logistics industry. The server calculates the delivery time with the highest probability of success based on past delivery completion information. This is done using a machine learning algorithm. The server collects location information, traffic conditions, travel speed, and weather information in real time and analyzes this information comprehensively. Specifically, it obtains location information using a GPS module and traffic conditions through a traffic information API. Travel speed is obtained using data from a speed sensor, and weather information is obtained using a weather information API.

[0571] The server integrates data using the Python Pandas library and performs analysis using the Scikit-learn library. This calculates the optimal logistics route and proposes it to the terminal. The terminal then displays specific route information to the user.

[0572] As a concrete example, the system starts operating when the user inputs a prompt into the generated AI model. For instance, if the user inputs, "My current location is Tokyo Station, and my destination is Shibuya Station. Please suggest the optimal delivery route," the server immediately begins collecting data and calculates the optimal route in real time. The terminal then displays the calculation results to the user and provides specific route guidance.

[0573] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0574] Step 1:

[0575] The server receives a prompt message from the user. The prompt message includes the current location and destination. For example, "Current location is Tokyo Station, destination is Shibuya Station." Based on this input, the server begins preparing to collect data.

[0576] Step 2:

[0577] The server obtains location information using a GPS module. It also obtains real-time traffic conditions through a traffic information API. Travel speed is obtained from data received from a speed sensor installed in the vehicle, and weather information is obtained using a weather information API. This data is integrated within the server.

[0578] Step 3:

[0579] The server converts the integrated data into a data frame using the Python Pandas library. This data frame includes location information, traffic conditions, travel speed, and weather information. The server then prepares to perform data analysis based on this data.

[0580] Step 4:

[0581] The server uses the Scikit-learn library to apply machine learning algorithms and calculate the optimal delivery route. An integrated dataframe is used as input, and the output provides information about the optimal route. This calculation considers routes that avoid traffic congestion and safe routes based on weather conditions.

[0582] Step 5:

[0583] The server sends the calculated optimal route to the terminal. The terminal displays specific route information to the user. For example, it might say, "Considering current traffic conditions and weather, the best route is via Aoyama Street." The user can then use this information to carry out deliveries.

[0584] (Application Example 2)

[0585] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0586] In food delivery services, delays in delivery times and inefficient route selection are problems that reduce customer satisfaction. Furthermore, the inability to respond quickly to changes in traffic and weather conditions leads to increased delivery times and wasted fuel. There is a need to solve these problems and provide more efficient and reliable delivery services.

[0587] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0588] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather information, means for proposing the optimal logistics route plan based on this information, means for calculating and updating the optimal delivery route in real time, and means for proposing alternative routes to delivery personnel. This makes it possible to shorten delivery times and save fuel.

[0589] "Past delivery completion data" refers to information about deliveries that have been completed in the past, including the delivery date and time, delivery destination, and duration.

[0590] "Location data" refers to information that indicates the current geographical location of an object, obtained using GPS or other position measurement technologies.

[0591] "Traffic information" refers to current traffic conditions, such as road congestion, accident information, and traffic restrictions.

[0592] "Movement speed" is a numerical value that indicates the distance an object travels per unit of time.

[0593] "Weather information" refers to information about current weather conditions, such as weather, temperature, precipitation, and wind speed.

[0594] An "optimal logistics route plan" is a proposal for the most effective delivery route, designed to maximize delivery efficiency.

[0595] "A means of calculating and updating the optimal delivery route in real time" refers to a function that instantly calculates the optimal delivery route based on the current situation and modifies that route as needed.

[0596] "Means of suggesting alternative routes to delivery drivers" refers to a function that presents delivery drivers with new delivery routes in response to unexpected events or changes in traffic conditions.

[0597] The system for realizing this invention consists of a server and a terminal for delivery personnel. The server collects past delivery completion data and calculates the probability of successful delivery based on this data. Furthermore, the server acquires location data, traffic information, travel speed, and weather information in real time and integrates this information to calculate the optimal logistics route. The server obtains the necessary data using the Google Maps API and OpenWeatherMap API and processes the data using the Python Pandas library. Dijkstra's algorithm is used for calculations, and the route is updated in real time.

[0598] The delivery driver's terminal receives the optimal delivery route transmitted from the server and presents it to the driver. Depending on changes in traffic and weather conditions, the server calculates alternative routes and suggests new routes to the driver's terminal. This ensures that drivers can always deliver using the most optimal route.

[0599] For example, if a delivery driver is likely to get caught in traffic, the server immediately calculates an alternative route and notifies the driver's terminal. This can shorten delivery times and save fuel. An example of a prompt to the generating AI model might be, "Please suggest the best route from my current location to my destination. Please consider traffic and weather information."

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The server collects past delivery completion data. It uses past delivery dates and times, destinations, and delivery durations as input. Based on this data, it prepares the foundational data for calculating the probability of successful delivery. The output is the prepared historical delivery data.

[0603] Step 2:

[0604] The server acquires location data, traffic information, travel speed, and weather information in real time. It uses data from the Google Maps API and OpenWeatherMap API as input. This data is integrated to understand the current delivery environment. The output is integrated, real-time environmental data.

[0605] Step 3:

[0606] The server calculates the optimal logistics route based on well-maintained historical delivery data and integrated real-time environmental data. It uses historical delivery data and real-time environmental data as input. Dijkstra's algorithm is used to calculate the shortest path. The output is the optimal delivery route.

[0607] Step 4:

[0608] The server sends the calculated optimal delivery route to the delivery person's terminal. The optimal delivery route is used as input. The delivery person's terminal displays the received route and presents it to the delivery person. The output is the delivery route presented to the delivery person.

[0609] Step 5:

[0610] The server monitors changes in traffic and weather conditions and calculates alternative routes as needed. It uses real-time environmental data as input. If changes are detected, it recalculates a new route using Dijkstra's algorithm. The output is the updated delivery route.

[0611] Step 6:

[0612] The server sends the updated delivery route to the delivery person's terminal and suggests an alternative route to the delivery person. The updated delivery route is used as input. The delivery person's terminal displays the received alternative route and notifies the delivery person. The output is the alternative route presented to the delivery person.

[0613] (Example 3)

[0614] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[0615] In the logistics industry, improving delivery efficiency and reducing fuel consumption are critical challenges. Traditional systems struggled to effectively utilize real-time traffic and weather data, making it difficult to propose optimal delivery routes. Furthermore, there was a lack of effective means to incorporate user feedback. This resulted in delivery delays, fuel waste, and decreased operational efficiency.

[0616] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0617] This invention includes a server that calculates the optimal time for delivery based on past delivery completion data to maximize the chances of success, a means for linking location data, traffic conditions, travel speed, weather conditions, and other information, and a means for proposing an optimal logistics route based on this information. This enables the proposal of an optimal delivery route using real-time traffic and weather data, improving delivery efficiency and reducing fuel consumption.

[0618] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, duration, and whether the delivery was successful.

[0619] "Location data" refers to data that indicates a geographical location, and includes latitude and longitude information obtained using technologies such as GPS.

[0620] "Traffic conditions" refers to information indicating the degree of road congestion and whether roads are passable, and includes real-time changes in traffic flow and congestion information.

[0621] "Movement speed" is an indicator that shows the distance traveled per unit of time, and it measures the speed at which vehicles or people move.

[0622] "Weather conditions" refer to information about the weather, including meteorological elements such as temperature, precipitation, wind speed, and humidity.

[0623] A "logistics route" refers to the path taken when delivering goods, and is used to plan the optimal route from the origin to the destination.

[0624] "Real-time traffic information" refers to information that instantly reflects the current traffic situation, including road congestion levels and accident information.

[0625] The "optimal delivery route" refers to the most efficient route, calculated with the aim of reducing delivery time and saving fuel.

[0626] "Feedback" refers to evaluations and opinions provided by users, and is information used to improve the system and enhance its accuracy.

[0627] A description of embodiments for carrying out this invention will be given.

[0628] The server generates a program to optimize logistics routes. This program collects traffic and weather data and calculates the optimal delivery route based on this information. Specifically, the server uses a geographic information system API to obtain real-time traffic information and a weather data API to collect weather data. By combining this data, it calculates a route that can shorten delivery times and save fuel.

[0629] The user then uses the generated program to optimize logistics routes. For example, if the user inputs the prompt "Suggest the best delivery route from Tokyo to Osaka" into the generating AI model, the server will propose the best route considering traffic information and weather data. This proposal may include alternative routes to avoid congested routes and route selection based on weather conditions.

[0630] As a concrete example, if a user enters the prompt "Tell me the best delivery route from Tokyo to Nagoya tomorrow morning," the server will propose the most efficient route based on the next day's traffic forecast and weather information. In this way, the user can shorten transportation time and save fuel. The flow of the specific processing in Example 3 will be explained using Figure 15.

[0631] Step 1:

[0632] The server collects traffic and weather data. Specifically, it uses a geographic information system API to obtain real-time traffic information and a weather data API to collect weather data. The input requires the current date and time and a geographical range, and the output provides traffic and weather information for the specified range. This allows users to understand the current level of road congestion and weather conditions.

[0633] Step 2:

[0634] The server analyzes the collected traffic and weather data. The input requires the traffic and weather data obtained in Step 1. The server statistically processes this data to identify routes expected to be congested and areas where bad weather is predicted. The output provides congestion and weather forecasts based on the analysis results. This clarifies the factors to consider when selecting delivery routes.

[0635] Step 3:

[0636] The server calculates the optimal delivery route based on the analysis results. The inputs required are the congestion forecast and weather forecast obtained in step 2. The server uses the Dijkstra algorithm or the A algorithm to calculate the route that reaches the destination in the shortest time. The output provides the optimal delivery route and its estimated travel time. This allows for the creation of efficient delivery plans.

[0637] Step 4:

[0638] The server proposes the calculated optimal route to the user. The input requires the optimal delivery route obtained in step 3. The user can receive a proposal from the server by prompting the generating AI model with the message, "Propose the optimal delivery route from Tokyo to Osaka." The output provides specific route information and estimated arrival times. This allows the user to select an efficient route for actual deliveries.

[0639] Step 5:

[0640] After actually using the suggested route, the user provides feedback to the server. The input requires user evaluations and opinions. The server uses this feedback as data to improve the accuracy of the algorithm. The output is an improved algorithm, which enables more accurate route selection in future suggestions.

[0641] (Application Example 3)

[0642] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0643] In the logistics industry, improving delivery efficiency and reducing fuel consumption are critical challenges. Conventional systems struggle to propose optimal delivery routes that fully consider real-time traffic and weather conditions, often resulting in delivery delays and wasted fuel. This hinders the efficiency of logistics operations.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0645] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data; means for linking information such as location data, traffic conditions, travel speed, and weather conditions; means for proposing an optimal logistics route plan based on this information; means for acquiring traffic conditions and weather conditions in real time and calculating the optimal delivery route; and means for generating prompt messages that propose the optimal delivery route using a generative AI model. This makes it possible to shorten delivery times and save fuel.

[0646] "Past delivery completion data" refers to data that includes information such as the date and time of past deliveries, routes, duration, and success rate.

[0647] "Location information data" refers to data that indicates the current location of an object, obtained using technologies such as GPS.

[0648] "Traffic conditions" refers to information about traffic on roads, such as road congestion levels, traffic jam information, and the occurrence of traffic accidents.

[0649] "Movement speed" is data that indicates the speed at which an object moves.

[0650] "Weather conditions" refer to information about weather, such as climate, temperature, precipitation, and wind speed.

[0651] "Optimal logistics route planning" refers to a plan that proposes the most efficient delivery route with the aim of shortening delivery times and saving fuel.

[0652] "Means for obtaining real-time traffic conditions and weather conditions" refers to technologies and methods for instantly obtaining current traffic conditions and weather conditions.

[0653] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[0654] A "prompt statement" is an instruction or question that is input into a generative AI model.

[0655] The system for implementing this invention operates through the coordinated efforts of a server, a terminal, and a user. The server calculates the time with the highest probability of successful delivery based on past delivery completion data. This is done using a machine learning algorithm. Furthermore, the server acquires information such as location data, traffic conditions, travel speed, and weather conditions in real time, and proposes an optimal logistics route plan based on this information. External services such as the Google Maps API and OpenWeatherMap API are used to acquire real-time data.

[0656] The terminal receives the optimal delivery route sent from the server and presents it to the user. The user can review the suggested route through the terminal and apply it to the actual delivery. This makes it possible to shorten delivery times and save fuel.

[0657] As a concrete example, the server inputs the prompt "Please suggest the optimal delivery route considering current traffic conditions and weather" into the generating AI model, and calculates the optimal delivery route. This prompt allows the generating AI model to analyze real-time data and suggest the optimal route.

[0658] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0659] Step 1:

[0660] The server retrieves historical delivery completion data. This data includes delivery date and time, route, duration, and success rate. Using this data as input, the server employs a machine learning algorithm to calculate the time with the highest probability of delivery success. The output is the optimal delivery time.

[0661] Step 2:

[0662] The server acquires real-time data such as location information, traffic conditions, travel speed, and weather conditions. This is done using the Google Maps API and the OpenWeatherMap API. The server uses this data as input to plan the optimal logistics route. The output is the optimal delivery route.

[0663] Step 3:

[0664] The server uses a generative AI model to generate prompts for suggesting the optimal delivery route. Specifically, it creates a prompt that says, "Please suggest the optimal delivery route considering current traffic conditions and weather." Using this prompt as input, the generative AI model calculates and outputs the optimal delivery route.

[0665] Step 4:

[0666] The terminal receives the optimal delivery route sent from the server. The terminal uses this route information as input and presents it visually to the user. The output is a display of the delivery route that the user can verify.

[0667] Step 5:

[0668] The user reviews the delivery route presented through the terminal and incorporates it into the actual delivery. The delivery plan is executed based on the user's input. The output is the actual delivery.

[0669] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0670] "Example of form 1"

[0671] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes emotions from the user's tone of voice, facial expressions, behavioral patterns, etc. Specifically, the emotion engine analyzes the tone of voice, facial expressions, and body movements of the user when they receive a package, and feeds the results back into the system.

[0672] "Example of form 2"

[0673] Based on the emotions recognized by the emotion engine, the system adjusts delivery times and routes. For example, if the system detects that the user is in a bad mood, it adjusts the delivery time to a time when the user is calmer. Conversely, if the user expresses joy, the system uses this information as feedback to learn how to improve the success rate of deliveries in similar situations.

[0674] "Example of form 3"

[0675] Furthermore, the emotion engine captures changes in the user's emotions in real time and feeds that information back into the system. This allows the system to respond flexibly according to the delivery situation. For example, if a user suddenly shows anger, the system can immediately receive that information and take action such as alerting the delivery person.

[0676] The following describes the processing flow for each example of the form.

[0677] "Example of form 1"

[0678] Step 1: The emotion engine analyzes the user's tone of voice, facial expressions, body movements, etc., when they receive their package.

[0679] Step 2: The emotion engine feeds back the results of its analysis to the system.

[0680] "Example of form 2"

[0681] Step 1: The emotion engine recognizes the user's emotions.

[0682] Step 2: The system adjusts delivery times and routes based on the recognized emotions.

[0683] Step 3: The system takes that information as feedback and learns to improve the success rate of deliveries under similar circumstances.

[0684] "Example of form 3"

[0685] Step 1: The emotion engine captures changes in the user's emotions in real time.

[0686] Step 2: Feed that information back into the system.

[0687] Step 3: The system can immediately receive this information and take action, such as alerting the delivery person.

[0688] (Example 1)

[0689] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0690] Traditional delivery systems lacked sufficient optimization of delivery times and struggled to provide services that considered user emotions. This resulted in lower delivery success rates and difficulty in improving customer satisfaction.

[0691] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0692] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion data, means for recognizing emotions by analyzing the user's voice, facial expressions, and behavioral patterns, and means for adjusting the delivery plan based on this information. This improves the success rate of deliveries and enables the provision of flexible services that respond to the user's emotions.

[0693] "Delivery completion data" refers to records of past deliveries, including the date and time, success rate, and recipient information.

[0694] "Optimal delivery time" refers to the most suitable time slot for delivery, calculated to maximize the success rate of the delivery.

[0695] "Voice, facial expressions, and behavioral patterns" refer to characteristics such as the tone of voice, facial expressions, and body movements that a user exhibits when receiving a package.

[0696] "Means of recognizing emotions" refers to technologies and devices that analyze and identify emotions from a user's voice and facial expressions.

[0697] "Means of adjusting delivery plans" refers to technologies and methods for optimizing delivery schedules and routes based on calculated optimal delivery times and user sentiment information.

[0698] This invention relates to a delivery system that calculates the optimal delivery time based on past delivery completion data and further adjusts the delivery plan by recognizing the user's emotions.

[0699] The server collects historical delivery completion data and stores it in a database. This data includes delivery date and time, success rate, and recipient information. The server uses the Python Scikit-learn library to apply machine learning algorithms to calculate the optimal delivery time. This model is built using the Random Forest algorithm.

[0700] The device uses a camera and microphone to capture the user's tone of voice, facial expressions, and body movements when they receive their package. This data is transmitted to a server via the internet. The server analyzes the user's emotions using emotion recognition software. Specifically, a common emotion recognition API is used for emotion analysis.

[0701] The server adjusts the delivery plan based on the analysis results. This improves the success rate of deliveries and enables the provision of flexible services that respond to the user's emotions.

[0702] For example, if past data shows that the highest success rate is calculated to be "weekdays between 2 PM and 4 PM," the delivery person will adjust their schedule to deliver during that time. Also, if a user appears dissatisfied when receiving their package, the system will use that information to notify customer support for follow-up.

[0703] Examples of prompt messages include, "Calculate the optimal delivery time based on past delivery data," and "Recognize the user's emotions from their tone of voice and facial expressions, and provide feedback based on the results."

[0704] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0705] Step 1:

[0706] The server collects historical delivery completion data. It retrieves data from the delivery management system via API, including delivery date and time, success rate, and recipient information. This data is stored in a database for later analysis.

[0707] Step 2:

[0708] The server aggregates stored delivery data and extracts necessary information from the database. It uses SQL queries as input to calculate the success rate for each delivery date and time. As output, it stores the aggregated results in a new table, which is then used to train a machine learning model.

[0709] Step 3:

[0710] The server trains a machine learning model using aggregated data. It takes the aggregated results as input to the Python Scikit-learn library and applies the random forest algorithm. The output is a model that predicts the optimal delivery time.

[0711] Step 4:

[0712] The server uses a trained model to calculate the optimal time for the next delivery. The model is fed data from a new delivery request as input. The output predicts the time slot with the highest success rate and notifies the delivery driver.

[0713] Step 5:

[0714] The device uses a camera and microphone to capture the user's tone of voice, facial expressions, and body movements when they receive their package. It acquires real-time audio and video data as input and sends this data to a server as output.

[0715] Step 6:

[0716] The server inputs the received data into the emotion engine to analyze the user's emotions. Audio and video data are passed to the emotion recognition software as input. The user's emotional state is identified as output and stored in a database.

[0717] Step 7:

[0718] The server adjusts the delivery plan based on the analysis results. Inputs include user sentiment information and optimal delivery times. Outputs include generating an adjusted delivery schedule and notifying customer support as needed.

[0719] (Application Example 1)

[0720] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0721] Traditional delivery systems have challenges in optimizing delivery times and improving customer satisfaction. In particular, the accuracy of delivery time predictions is low, and service improvements that take customer feelings into consideration are not being implemented, making it difficult to improve customer satisfaction.

[0722] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0723] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather conditions, and means for analyzing the customer's facial expressions and tone of voice to recognize their emotions. This enables optimization of delivery times and improvement of services based on customer emotions.

[0724] "Delivery completion data" refers to data that includes information such as the date, time, location, and whether or not a delivery was successful in the past.

[0725] "Location data" refers to data indicating geographical location, obtained using GPS or other location measurement technologies.

[0726] "Traffic information" refers to data that includes various types of information related to traffic, such as road congestion, traffic accidents, and construction information.

[0727] "Movement speed" is data that indicates the distance traveled by delivery vehicles and other moving objects within a certain period of time.

[0728] "Weather conditions" refers to data that includes information about weather, such as weather, temperature, precipitation, and wind speed.

[0729] A "logistics route" refers to the path that a delivery item takes from its origin to its destination.

[0730] "Methods for recognizing emotions by analyzing facial expressions and tone of voice" refers to technologies that analyze a customer's facial expressions and tone of voice to determine their emotional state.

[0731] "Feedback for service improvement" refers to providing information based on customer sentiment data to improve the quality of the service.

[0732] In an embodiment of this invention, the server collects past delivery completion data and runs a program that calculates the optimal delivery time using a machine learning algorithm. Specifically, it uses Python for data analysis and employs algorithms such as random forest. The server also integrates information such as location data, traffic information, travel speed, and weather conditions to optimize logistics routes. This requires real-time data processing and utilizes cloud-based databases and APIs.

[0733] The terminals are devices such as smartphones and tablets, and they use cameras and microphones to analyze customers' facial expressions and tone of voice. Using OpenCV and TensorFlow, real-time image processing and audio analysis are performed to recognize customer emotions. This customer emotion data is then sent to a server to generate feedback for service improvement.

[0734] As a concrete example, when a user places an order using a food delivery app, the server calculates the optimal delivery time based on past data and notifies the delivery person. When the delivery person arrives, the terminal analyzes the customer's facial expression and recognizes emotions such as "satisfaction." This information is sent to the server and used as feedback to improve the service.

[0735] An example of a prompt to be input into the generating AI model is: "Calculate the optimal delivery time based on past delivery data. Also, recognize the customer's emotions from their facial expressions and tone of voice, and provide feedback."

[0736] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0737] Step 1:

[0738] The server retrieves past delivery completion data from a database. The input includes data such as delivery date and time, location, and whether the delivery was successful or not. Based on this data, a machine learning algorithm (e.g., Random Forest) is used to calculate the optimal delivery time. The output is the delivery time with the highest probability of success.

[0739] Step 2:

[0740] The server obtains real-time data such as location data, traffic information, travel speed, and weather conditions via APIs. This data is then integrated as input to optimize the logistics route. As part of the data processing, an algorithm is applied to integrate the various pieces of information and calculate the shortest route. The output is the optimized logistics route.

[0741] Step 3:

[0742] The user places an order using a food delivery app on their smartphone. The user enters the order details and delivery address information into the app. The server sends a notification to the delivery driver based on the optimal delivery time and route determined in steps 1 and 2. The output is a delivery instruction for the driver.

[0743] Step 4:

[0744] The device captures the customer's facial expressions and tone of voice using the smartphone's camera and microphone when the delivery person arrives. It acquires real-time video and audio data as input. Using OpenCV and TensorFlow, it performs image processing and audio analysis to recognize the customer's emotions. The output is the recognized emotion data.

[0745] Step 5:

[0746] The server receives sentiment data sent from the terminal and generates feedback for service improvement. Sentiment data is used as input. As a data calculation, the sentiment data is analyzed to generate specific suggestions for service improvement. The output is feedback information for service improvement.

[0747] (Example 2)

[0748] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0749] In the logistics industry, improving delivery efficiency and customer satisfaction are crucial challenges. Traditional systems struggle to respond flexibly to real-time changes in circumstances and customer emotions, resulting in insufficient delivery optimization. Furthermore, a lack of learning capabilities to increase delivery success rates makes improvement under similar circumstances difficult.

[0750] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0751] This invention includes a server that includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking location data, traffic condition data, travel speed data, and weather data, means for proposing an optimal logistics route plan based on this information, means for adjusting delivery time and route based on the user's emotions using emotion recognition technology, and means for incorporating the user's emotional information as feedback and learning to improve the delivery success rate. This enables the proposal of an optimal delivery plan in real time and flexible delivery adjustments in response to the user's emotions, thereby improving delivery efficiency and customer satisfaction.

[0752] "Past delivery completion data" refers to data that includes information such as the date and time of past deliveries, the route, the duration, and whether or not the deliveries were successful.

[0753] "Location data" refers to geographical information about a specific location, obtained using GPS or other location measurement technologies.

[0754] "Traffic data" refers to real-time information about traffic, such as road congestion, traffic restrictions, and accident information.

[0755] "Movement speed data" refers to information about the movement speed of vehicles and people, and is obtained from speed sensors and GPS data.

[0756] "Weather data" refers to information about the weather, including meteorological conditions such as temperature, precipitation, and wind speed.

[0757] "Optimal logistics route planning" refers to the optimal delivery route and schedule calculated based on real-time data to maximize delivery efficiency.

[0758] "Emotion recognition technology" is a technology that analyzes voice and text data to identify the emotional state of a user.

[0759] "Learning to improve delivery success rates" refers to a machine learning process that uses past delivery data and user feedback to improve the success rate of deliveries.

[0760] This invention is a system aimed at improving logistics efficiency and customer satisfaction. The server first collects past delivery completion data and calculates the time of day when deliveries have the highest probability of success. A machine learning algorithm is used for this calculation. Next, the server acquires location data, traffic data, speed data, and weather data in real time and integrates and analyzes this information. Specifically, location data is acquired using a GPS module, traffic data is acquired through a general map API, speed data is acquired from the vehicle's speed sensor, and weather data is acquired using a weather information API.

[0761] Based on this data, the server proposes an optimal logistics route plan. This plan aims to reduce delivery time and save fuel, and is dynamically updated according to real-time conditions. The terminal also uses emotion recognition technology to recognize emotions from the user's voice and text data. For example, if the user says "I'm busy today," the terminal recognizes that emotion as being in a bad mood. Based on this emotion information, the server adjusts the delivery time and route to ensure that deliveries are made during times when the user is less busy.

[0762] Furthermore, the server incorporates user emotional information as feedback and learns to improve the delivery success rate. This learning process uses a generative AI model. For example, if a user is in a situation where "it's raining today and there's traffic congestion," the server analyzes weather and traffic information and suggests routes that avoid the rain and congestion.

[0763] Examples of prompts to input into the generating AI model include "Please suggest the optimal delivery route considering the current weather and traffic conditions" and "Please adjust the delivery time based on the user's emotions." This enables the suggestion of optimal delivery plans in real time and flexible delivery adjustments based on the user's emotions, leading to improved delivery efficiency and customer satisfaction.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0765] Step 1:

[0766] The server collects historical delivery completion data. It uses data such as past delivery date and time, route, duration, and success / failure status as input. Based on this data, a machine learning algorithm is used to calculate the time of day with the highest probability of success for delivery. The output provides recommendations for the optimal delivery time.

[0767] Step 2:

[0768] The server acquires location data, traffic data, speed data, and weather data in real time. It uses data from GPS modules, map APIs, speed sensors, and weather information APIs as input. This data is integrated and analyzed to propose the optimal logistics route plan. The output provides the optimal delivery route and schedule.

[0769] Step 3:

[0770] The device inputs the user's voice and text data into emotion recognition technology to recognize the user's emotions. User statements and messages are used as input. An emotion recognition AI model is used to identify the user's emotional state. The output is the user's emotional information.

[0771] Step 4:

[0772] The server adjusts delivery times and routes based on the user's sentiment information obtained in step 3. It uses the user's sentiment information and the optimal delivery route obtained in step 2 as input. It creates a flexible delivery plan tailored to the sentiment, and the adjusted delivery schedule is output.

[0773] Step 5:

[0774] The server incorporates user emotional information as feedback and learns to improve delivery success rates. Past delivery data and user emotional feedback are used as input. A generative AI model is used to learn how to improve delivery success rates. The output is an improved delivery planning algorithm.

[0775] (Application Example 2)

[0776] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0777] In modern logistics services, improving delivery efficiency and customer satisfaction are crucial challenges. However, conventional systems struggle to propose optimal delivery routes that take real-time traffic and weather conditions into account, and they fail to adjust delivery times to consider the emotional state of the user. As a result, delivery success rates may decrease, potentially compromising customer satisfaction.

[0778] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0779] This invention includes a server that includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic conditions, travel speed, and weather information, means for proposing an optimal logistics route plan based on this information, means for analyzing the user's emotional state using emotion recognition technology and adjusting the delivery time and route, and means for comprehensively analyzing information acquired in real time and learning to improve the delivery success rate based on the user's emotions. This makes it possible to improve delivery efficiency and customer satisfaction.

[0780] "Delivery completion data" refers to data that records detailed information about deliveries made in the past, including delivery time, delivery destination, and whether the delivery was successful or not.

[0781] "Location data" refers to data that indicates the geographical location of a specific object, obtained using GPS or other location measurement technologies.

[0782] "Traffic conditions" refers to information about the flow of traffic on roads, such as the degree of road congestion, traffic jam information, and the occurrence of traffic accidents.

[0783] "Movement speed" is an indicator that shows the distance a particular object travels per unit of time.

[0784] "Weather information" refers to information about weather conditions in a specific region, such as weather, temperature, precipitation, and wind speed.

[0785] A "logistics route" is the path that goods take when traveling from their origin to their destination, and it should be optimized to ensure efficient delivery.

[0786] "Emotion recognition technology" is a technology that analyzes and identifies a user's emotional state based on their facial expressions, voice, and behavior.

[0787] "Delivery success rate" is an indicator that shows the probability of a delivery being completed on schedule, and is used to evaluate the efficiency and reliability of logistics services.

[0788] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user.

[0789] The server calculates the time with the highest probability of successful delivery based on past delivery completion data. This is done using machine learning algorithms. The server also acquires location data, traffic conditions, travel speed, and weather information in real time and analyzes this information comprehensively. Specifically, it obtains location information using the Google Maps API, checks traffic conditions using the Waze API, and obtains weather information using the OpenWeatherMap API. This data is processed using Python's Pandas and NumPy to propose the optimal logistics route.

[0790] The device analyzes the user's emotional state using emotion recognition technology. This is done using the Microsoft Azure Emotion API. Based on the user's emotions, the device sends information to the server to adjust delivery times and routes.

[0791] Users can check the delivery status through their device and adjust the delivery time as needed. If the server detects that the user is in a bad mood, it will adjust the delivery time to ensure the delivery is made when the user is calmer.

[0792] For example, if a user orders "pizza" and the emotion engine detects that the user is "unhappy," the server will check traffic information to confirm that the usual route is congested, and taking into account the weather ("rainy"), it will suggest a route that departs earlier than usual and avoids traffic.

[0793] Examples of prompts for a generative AI model include the following:

[0794] "If the user is unhappy, suggest the optimal delivery time. Current traffic conditions are congested, and the weather is rainy. How would you adjust the route?"

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0796] Step 1:

[0797] The server retrieves past delivery completion data. It receives data such as past delivery time, destination, and success / failure status as input. Using this data, it applies a machine learning algorithm to calculate the time with the highest probability of delivery success. The output is the optimal delivery time.

[0798] Step 2:

[0799] The server acquires location data, traffic conditions, travel speed, and weather information in real time. It receives data from the Google Maps API, Waze API, and OpenWeatherMap API as input. This data is integrated using Pandas and NumPy to optimize logistics routes. The output is the optimal delivery route.

[0800] Step 3:

[0801] The device analyzes the user's emotional state using emotion recognition technology. As input, it sends data of the user's facial expressions and voice to the Microsoft Azure Emotion API. The response from the API is analyzed to identify the user's emotional state. The output is the user's emotional state.

[0802] Step 4:

[0803] The server adjusts delivery times and routes based on the user's emotional state. It receives the optimal delivery time obtained in step 1, the optimal delivery route obtained in step 2, and the user's emotional state obtained in step 3 as input. This information is integrated to adjust the delivery plan. The output is the adjusted delivery time and route.

[0804] Step 5:

[0805] The user reviews the adjusted delivery plan through their terminal. They receive the adjusted delivery time and route from the server as input. The user can request a readjustment of the delivery time if necessary. The final delivery plan is reviewed as output.

[0806] (Example 3)

[0807] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[0808] There is a need to improve delivery efficiency in logistics and to provide flexible responses that respond to customer emotions. Conventional systems have difficulty responding quickly to changes in traffic conditions and weather, and have not adequately adjusted services based on changes in customer emotions. As a result, delays in delivery times and customer dissatisfaction are common challenges.

[0809] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0810] In this invention, the server includes means for calculating delivery time based on past delivery completion information, means for linking information such as location information, traffic conditions, travel speed, and weather conditions, and means for detecting changes in the user's emotions in real time and providing feedback on that information. This enables optimization of delivery routes and flexible responses to the user's emotions.

[0811] "Delivery completion information" refers to data that records the details of past deliveries, including information such as the delivery date and time, delivery destination, and duration.

[0812] "Location information" refers to data indicating a geographical location, specifically latitude and longitude information obtained using technologies such as GPS.

[0813] "Traffic conditions" refer to information indicating the degree of road congestion and passability, and are data that reflects the real-time changes in traffic flow.

[0814] "Movement speed" is an indicator that shows the distance traveled per unit of time, and represents the speed at which vehicles or people move.

[0815] "Weather conditions" refer to information about the weather, including meteorological elements such as temperature, precipitation, and wind speed.

[0816] "Emotional changes" refer to fluctuations in the user's emotional state, which are detected through analysis of voice and facial expressions.

[0817] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate results tailored to a specific purpose.

[0818] "Delivery route" refers to the path taken when delivering goods, and includes the optimal route from the origin to the destination.

[0819] A description of embodiments for carrying out this invention will be given.

[0820] The server generates a program that calculates delivery times based on past delivery completion data to improve delivery efficiency in logistics. This program uses a generating AI model to propose the optimal delivery route by linking data such as location information, traffic conditions, travel speed, and weather conditions. Specifically, it uses external software such as the Google Maps API and OpenWeatherMap API to obtain real-time traffic information and weather data.

[0821] The terminal uses emotion recognition software to detect changes in the user's emotions in real time. This software analyzes the user's voice and facial expressions to detect changes in emotions. If the user shows anxiety or anger, this information is fed back to the server, which then flexibly adjusts the delivery plan.

[0822] For example, if the usual route is congested, the server can suggest an alternative route. Also, if a user expresses concern that a delivery may be delayed, the server can instruct the delivery person to take immediate action.

[0823] Examples of prompts for a generative AI model include the following:

[0824] "Please suggest the optimal delivery route, taking into account current traffic conditions and weather."

[0825] "Adjust the delivery plan based on the user's emotional data." Figure 21 illustrates the flow of the specific processing in Example 3.

[0826] Step 1:

[0827] The server receives past delivery completion information as input and calculates the delivery time. Using a machine learning algorithm, it predicts the delivery time with the highest probability of success based on past data. The output is the optimal delivery time.

[0828] Step 2:

[0829] The server takes location information, traffic conditions, travel speed, and weather conditions as input. This data is collected in real time using the Google Maps API and OpenWeatherMap API. The server integrates this information and uses a generative AI model to calculate the optimal delivery route. The output is the optimized delivery route.

[0830] Step 3:

[0831] The device transmits the user's voice and facial expressions as input to emotion recognition software. This software detects changes in the user's emotions in real time and generates emotion data. The output is the user's emotional state.

[0832] Step 4:

[0833] The device feeds back the detected emotion data to the server. The server adjusts the delivery plan based on this information. For example, if the user shows signs of anxiety, the server instructs the delivery person to take immediate action. The adjusted delivery plan is then output.

[0834] Step 5:

[0835] The server notifies the user of the optimized delivery route and adjusted delivery plan. The terminal displays the new delivery route and estimated arrival time to the user. The output provides the user with the information to be provided.

[0836] (Application Example 3)

[0837] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0838] Optimizing delivery routes in logistics contributes to reducing transportation time and saving fuel, but conventional systems have the challenge of not being able to respond flexibly to the emotional state of users. Furthermore, they cannot provide appropriate feedback in response to the stress and emotional changes of delivery personnel, which may result in a decrease in delivery efficiency.

[0839] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0840] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather information, means for proposing an optimal logistics route plan based on this information, means for analyzing the user's emotions in real time using an emotion analysis engine and providing feedback, and means for suggesting revised routes or breaks based on the emotional state of the delivery person. This enables flexible responses according to the emotional state of the delivery person while shortening transportation time and saving fuel.

[0841] "Past delivery completion data" refers to data that records detailed information about deliveries made in the past, including information such as delivery date and time, delivery destination, delivery time, and success rate.

[0842] "Location data" refers to data that indicates the geographical location of a specific point, obtained using GPS or other location measurement technologies.

[0843] "Traffic information" refers to real-time information about road traffic, such as road congestion, accident information, and traffic restrictions.

[0844] "Travel speed" is data that indicates the speed at which one moves between specific points, and is usually expressed in time per unit of distance.

[0845] "Weather information" refers to information about the weather, including data such as temperature, precipitation, wind speed, and humidity.

[0846] "Optimal logistics route planning" refers to a plan that proposes the most efficient delivery route with the aim of reducing transportation time and saving fuel.

[0847] An "emotion analysis engine" is a technology that analyzes a user's emotions from their facial expressions and voice, and understands their emotional state in real time.

[0848] "Means of providing feedback" refers to methods for providing appropriate instructions and information to users and delivery personnel based on the analyzed information.

[0849] "Delivery driver's emotional state" refers to the emotional state that a delivery driver experiences while on duty, and includes stress, fatigue, satisfaction, and other factors.

[0850] "Re-proposing routes" means reviewing existing delivery routes based on current circumstances and proposing new, optimal routes.

[0851] "Suggesting breaks" means recommending that delivery drivers take breaks at appropriate times, depending on their emotional state and level of fatigue.

[0852] The system that realizes this invention consists of a server, a delivery person's terminal, and a user's terminal. The server executes an algorithm to calculate the time with the highest probability of successful delivery based on past delivery completion data. Machine learning techniques can be used for this. The server also acquires location data, traffic information, travel speed, and weather information in real time, and integrates this information to generate an optimal logistics route plan.

[0853] The delivery driver's terminal is equipped with an emotion analysis engine that analyzes the driver's emotional state in real time from their facial expressions and voice. This information is sent to a server, and based on the driver's emotional state, the server suggests rerouting or taking a break. Specifically, if the driver is feeling stressed, the server inputs a prompt into the AI ​​model saying, "The driver is feeling stressed, please recalculate the route and suggest a break," and provides appropriate feedback.

[0854] The user's device is used to check the delivery status and receive feedback. If a user expresses dissatisfaction with the delivery, an emotion analysis engine analyzes their emotions and sends feedback to the server. This allows the server to flexibly adjust the delivery plan and improve user satisfaction.

[0855] This system uses the Google Maps API to obtain traffic information and the OpenWeatherMap API to obtain weather data. It also uses the Microsoft Azure Emotion API for sentiment analysis. This allows for shorter delivery times and fuel savings, while also enabling flexible responses based on the emotional state of delivery personnel.

[0856] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0857] Step 1:

[0858] The server retrieves past delivery completion data and uses a machine learning algorithm to calculate the time with the highest probability of successful delivery. This process uses data such as past delivery date and time, success rate, and delivery destination as input and outputs the optimal delivery time. Specifically, the server analyzes the dataset and learns patterns to predict the optimal time for the next delivery.

[0859] Step 2:

[0860] The server acquires location data, traffic information, travel speed, and weather information in real time. This information is obtained using the Google Maps API and the OpenWeatherMap API. The server integrates this data to generate an optimal logistics route plan. Inputs include current location, road congestion, and weather data, and the output is the optimal delivery route. Specifically, the server analyzes each piece of data and calculates the route to reach the destination in the shortest time.

[0861] Step 3:

[0862] The delivery person's terminal uses an emotion analysis engine to analyze their emotional state in real time from their facial expressions and voice. Inputs include the delivery person's facial image and voice data, and output is an evaluation of their emotional state. Specifically, the terminal collects data using a camera and microphone and analyzes emotions using Microsoft Azure's Emotion API.

[0863] Step 4:

[0864] The server suggests alternative routes and breaks based on the delivery person's emotional state. The input is the result of the emotional analysis, and the output is the revised route and break instructions. Specifically, the server generates a prompt such as, "The delivery person is stressed; please recalculate the route and suggest a break," which is input into the AI ​​model, providing appropriate feedback.

[0865] Step 5:

[0866] The user's device is used to check the delivery status and receive feedback. Inputs include delivery status data from the server, and outputs include notifications and feedback to the user. Specifically, the user can check the delivery progress through the application and send feedback as needed.

[0867] (Other examples)

[0868] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0869] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0870] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0871] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0872] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0873] [Third Embodiment]

[0874] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0875] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0876] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0877] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0878] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0879] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0880] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0881] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0882] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0883] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0884] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0885] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0886] "Example of form 1"

[0887] One embodiment of this system is a B2C delivery system. This system has a function to calculate the optimal delivery time based on past delivery completion data. Specifically, it aggregates past delivery data and uses a machine learning algorithm to calculate the optimal delivery time from that data.

[0888] "Example of form 2"

[0889] Furthermore, this system has the functionality to integrate information such as GPS data, traffic information, travel speed, and weather. This information is acquired in real time and analyzed comprehensively to propose the most suitable delivery route for the current situation.

[0890] "Example of form 3"

[0891] Furthermore, this system has a function to propose the optimal logistics route plan based on this information. Specifically, it proposes routes that can shorten transportation time and save fuel, based on the calculated optimal delivery time and related information. For example, it can avoid routes that are expected to be congested and propose routes optimized for traffic information and weather conditions.

[0892] The following describes the processing flow for each example of the form.

[0893] "Example of form 1"

[0894] Step 1: The system aggregates past delivery completion data. This includes information such as delivery time, delivery destination, and delivery success rate.

[0895] Step 2: Based on the aggregated data, a machine learning algorithm is used to calculate the time of day when deliveries have the highest probability of success. This algorithm takes into account factors such as time of day, location, and weather.

[0896] "Example of form 2"

[0897] Step 1: The system acquires information such as GPS data, traffic information, travel speed, and weather in real time. This information is obtained from various sensors and external APIs.

[0898] Step 2: Analyze the acquired information to propose the optimal delivery route for the current situation. This analysis will take into account factors such as road congestion, traffic restrictions, and weather conditions.

[0899] "Example of form 3"

[0900] Step 1: Based on the calculated optimal delivery time and related information, the system proposes routes that can shorten transportation time and save fuel.

[0901] Step 2: Specifically, suggest routes that are optimized for traffic information and weather conditions, avoiding routes that are expected to be congested. For example, suggest leaving earlier during peak hours and avoiding slippery roads in rainy weather.

[0902] (Example 1)

[0903] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0904] In the logistics industry, improving delivery efficiency and reducing costs are critical challenges. In particular, optimizing delivery times directly leads to increased customer satisfaction and more effective use of transportation resources. However, traditional methods have struggled to calculate optimal delivery times due to the inability to fully utilize historical data. Furthermore, the inability to consider fluctuating factors such as traffic conditions and weather in real time has resulted in reduced accuracy in delivery planning.

[0905] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0906] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion information, means for integrating information such as location information, traffic conditions, travel speed, and weather conditions, and means for proposing an optimal logistics route plan based on this information. This enables the optimization of delivery time and the efficiency of logistics routes.

[0907] "Delivery completion information" refers to data that includes the date and time of past deliveries, delivery destination, and recipient information.

[0908] "Location information" refers to data indicating a geographical location, obtained using methods such as GPS.

[0909] "Traffic conditions" refers to information about road congestion and passable routes.

[0910] "Movement speed" refers to data indicating the speed at which a delivery vehicle moves.

[0911] "Weather conditions" refer to information about weather, such as climate, temperature, and precipitation.

[0912] A "logistics route" is the path that a delivery item takes when it travels from its origin to its destination.

[0913] An "optimal plan" is a delivery schedule designed to reduce transportation time and conserve resources.

[0914] A "machine learning algorithm" is a computational method used to learn patterns from data and perform predictions and classifications.

[0915] "Data preprocessing" refers to the process of shaping data into a format suitable for machine learning.

[0916] "Features" are attributes or metrics of data that machine learning models use when training.

[0917] "Training" is the process by which a machine learning model learns patterns from data.

[0918] "Evaluation" is the process of measuring the performance of a trained machine learning model and verifying its accuracy.

[0919] In an embodiment of this invention, the server runs a program to collect past delivery completion information and calculate the optimal delivery time. The server retrieves delivery completion information from a database and preprocesses the data using the Python Pandas library. Preprocessing includes imputing missing values ​​and removing outliers. Next, the server trains and evaluates a machine learning model using the Scikit-learn library. Algorithms such as random forest and gradient boosting are used to train the model.

[0920] The server integrates information such as location data, traffic conditions, travel speed, and weather conditions, and based on this information, proposes the optimal logistics route plan. This enables the optimization of delivery times and the efficiency of logistics routes.

[0921] For example, the server uses delivery data for a certain region to calculate that "deliveries in this region have a higher success rate between 2 PM and 4 PM." Users can then check this information through their terminal and plan their deliveries accordingly.

[0922] An example of a prompt message is: "Calculate the optimal delivery time based on past delivery data. The data includes delivery date and time, address, and recipient information."

[0923] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0924] Step 1:

[0925] The server retrieves past delivery completion information from the delivery database. Input includes delivery date and time, delivery address, and recipient information. This data is aggregated to prepare for the next processing step. Specifically, it extracts the necessary data using SQL queries.

[0926] Step 2:

[0927] The server preprocesses the acquired data. The input is the delivery completion information aggregated in step 1. The Python Pandas library is used for data preprocessing, including imputing missing values ​​and removing outliers. The output is data formatted in a way that is suitable for machine learning algorithms. Specifically, it cleans the data frame.

[0928] Step 3:

[0929] The server selects features from preprocessed data and generates new features. The input is the data formatted in step 2. Feature selection involves analyzing data correlations and extracting important attributes. The output is a set of features used to train a machine learning model. Specifically, it creates a correlation matrix and selects important features.

[0930] Step 4:

[0931] The server trains a machine learning model using the selected features. The input is the feature set generated in step 3. The Scikit-learn library is used to train the model with algorithms such as random forest and gradient boosting. The output is the trained machine learning model. Specifically, the hyperparameters of the model are tuned to build the optimal model.

[0932] Step 5:

[0933] The server evaluates the trained model. The input is the trained model obtained in step 4. Cross-validation is used to measure the model's accuracy. The output is an indicator of the model's accuracy. Specifically, the server identifies areas for improvement in the model based on the evaluation results.

[0934] Step 6:

[0935] The server calculates the optimal delivery time using a pre-evaluated model. Inputs include real-time location information, traffic conditions, travel speed, and weather conditions. The output is the optimal delivery time for each destination. Specifically, it inputs new data into the model and generates prediction results.

[0936] Step 7:

[0937] The server provides the user with the calculated optimal delivery time. The input is the optimal delivery time obtained in step 6. The output is a delivery schedule that the user can view on their terminal. Specifically, the results are displayed in the user interface to assist the user in planning their delivery.

[0938] (Application Example 1)

[0939] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0940] In food delivery services, determining the optimal delivery time is crucial to ensure customers receive their food in the freshest possible condition. However, traditional systems often fail to adequately optimize delivery times, making it difficult to improve customer satisfaction.

[0941] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0942] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as GPS data, traffic information, travel speed, and weather, means for proposing the optimal logistics route plan based on this information, means for analyzing past delivery data and proposing the optimal delivery time to the user, and means for presenting the optimal delivery time when the user confirms their order. This makes it possible to optimize delivery times so that customers can receive their food in the freshest possible condition.

[0943] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, and whether the delivery was successful.

[0944] "Success probability" is an indicator that shows the likelihood of delivery being completed on schedule, and is calculated based on past data.

[0945] A "machine learning algorithm" is a computational method that allows computers to learn patterns from data and perform predictions and classifications.

[0946] "Optimal delivery time" refers to the time required for delivery to be completed in the most efficient and customer-satisfying manner.

[0947] "Means of suggesting to the user" refers to the methods and functions that the system uses to present the user with the optimal options based on its analysis results.

[0948] An "optimal logistics route plan" is a delivery route plan designed to maximize delivery efficiency and minimize time and costs.

[0949] "Traffic information" refers to real-time data related to traffic, such as road congestion, traffic accidents, and construction information.

[0950] "Means presented to the user when confirming an order" refers to the methods or functions that the system uses to display the optimal delivery time when the user makes a final decision on an order.

[0951] The system for implementing this invention operates in a network environment including a server and user terminals. The server collects past delivery completion data and uses a machine learning algorithm to calculate the optimal delivery time based on this data. Specifically, it uses Python and the Scikit-learn library to build a machine learning model. The server preprocesses the collected data, extracts features, and then trains the model using algorithms such as random forest.

[0952] The user terminal is a device such as a smartphone or tablet that receives the optimal delivery time provided by the server and presents it to the user. When the user confirms their order, the terminal displays the optimal delivery time on the screen based on the server's suggestion. This allows the user to choose the time when they can receive their food in the freshest condition.

[0953] As a concrete example, when a user orders a pizza, the terminal suggests, "Based on past data, specifying 18:30 for delivery is most likely to ensure the food arrives in the freshest condition." This suggestion is the result of the server using a generated AI model to analyze past delivery data and predict the optimal delivery time.

[0954] An example of a prompt message would be: "Based on past delivery data, predict the optimal delivery time. The current order is for pizza, and the user's location is Shibuya Ward, Tokyo."

[0955] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0956] Step 1:

[0957] The server collects past delivery completion data from the database. It takes information such as delivery date and time, delivery destination, and whether the delivery was successful as input. This data is preprocessed to impute missing values ​​and remove outliers. The output is a clean dataset.

[0958] Step 2:

[0959] The server extracts features using pre-processed data. It uses a clean dataset as input and selects features such as delivery time, day of the week, and weather. This results in the output of a dataset suitable for training machine learning models.

[0960] Step 3:

[0961] The server uses the Scikit-learn library to build and train a machine learning model. It uses a feature-extracted dataset as input. It applies the Random Forest algorithm to generate a model that predicts the optimal delivery time. The output is the trained model.

[0962] Step 4:

[0963] The server uses a generative AI model to predict the optimal delivery time based on the user's order information. It uses the user's current order details and location as input. By generating prompt messages and inputting them into the model, it outputs the optimal delivery time.

[0964] Step 5:

[0965] The terminal displays the optimal delivery time received from the server to the user. It receives a suggested delivery time from the server as input. The screen displays a message such as, "Based on past data, specifying 18:30 for delivery is likely to ensure your food arrives in the freshest condition." The output provides information to help the user select the optimal delivery time.

[0966] Step 6:

[0967] The user confirms the optimal delivery time displayed on the terminal and confirms the order. The terminal provides a suggested delivery time as input. The user selects the suggested time and completes the order. The confirmed order information is sent to the server as output.

[0968] (Example 2)

[0969] Next, we will describe Example 2 of the morphological example. 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."

[0970] In the logistics industry, improving delivery efficiency and reducing costs are crucial challenges. In particular, delivery times are often unpredictable due to traffic congestion and weather changes, leading to delivery delays and wasted fuel. Traditional systems lack sufficient real-time information integration and optimal route suggestions, resulting in decreased delivery efficiency.

[0971] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0972] In this invention, the server includes means for calculating the time of day when delivery is most likely to succeed based on past delivery completion information, means for linking information such as location information, traffic conditions, travel speed, and weather information, and means for proposing an optimal logistics route plan based on this information. This enables real-time information integration and the proposal of the optimal route.

[0973] "Past delivery completion information" refers to data such as the date and time of past deliveries, route, duration, and success rate.

[0974] "Location information" refers to geographical coordinate data of a specific point, obtained using technologies such as GPS.

[0975] "Traffic conditions" refers to real-time information about road traffic, such as road congestion levels, traffic jams, and traffic restrictions.

[0976] "Movement speed" refers to data indicating the speed at which a vehicle is moving, and is usually obtained from speed sensors or similar devices.

[0977] "Weather information" refers to data related to weather conditions, including information such as temperature, precipitation, and wind speed.

[0978] "Optimal logistics route planning" refers to proposed delivery routes calculated to maximize delivery efficiency and minimize time and costs.

[0979] A "generative AI model" refers to a model that has been trained using artificial intelligence technology to perform a specific task.

[0980] A "prompt" refers to text input to give specific instructions or questions to a generative AI model.

[0981] This invention is a system aimed at improving delivery efficiency in the logistics industry. The server calculates the delivery time with the highest probability of success based on past delivery completion information. This is done using a machine learning algorithm. The server collects location information, traffic conditions, travel speed, and weather information in real time and analyzes this information comprehensively. Specifically, it obtains location information using a GPS module and traffic conditions through a traffic information API. Travel speed is obtained using data from a speed sensor, and weather information is obtained using a weather information API.

[0982] The server integrates data using the Python Pandas library and performs analysis using the Scikit-learn library. This calculates the optimal logistics route and proposes it to the terminal. The terminal then displays specific route information to the user.

[0983] As a concrete example, the system starts operating when the user inputs a prompt into the generated AI model. For instance, if the user inputs, "My current location is Tokyo Station, and my destination is Shibuya Station. Please suggest the optimal delivery route," the server immediately begins collecting data and calculates the optimal route in real time. The terminal then displays the calculation results to the user and provides specific route guidance.

[0984] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0985] Step 1:

[0986] The server receives a prompt message from the user. The prompt message includes the current location and destination. For example, "Current location is Tokyo Station, destination is Shibuya Station." Based on this input, the server begins preparing to collect data.

[0987] Step 2:

[0988] The server obtains location information using a GPS module. It also obtains real-time traffic conditions through a traffic information API. Travel speed is obtained from data received from a speed sensor installed in the vehicle, and weather information is obtained using a weather information API. This data is integrated within the server.

[0989] Step 3:

[0990] The server converts the integrated data into a data frame using the Python Pandas library. This data frame includes location information, traffic conditions, travel speed, and weather information. The server then prepares to perform data analysis based on this data.

[0991] Step 4:

[0992] The server uses the Scikit-learn library to apply machine learning algorithms and calculate the optimal delivery route. An integrated dataframe is used as input, and the output provides information about the optimal route. This calculation considers routes that avoid traffic congestion and safe routes based on weather conditions.

[0993] Step 5:

[0994] The server sends the calculated optimal route to the terminal. The terminal displays specific route information to the user. For example, it might say, "Considering current traffic conditions and weather, the best route is via Aoyama Street." The user can then use this information to carry out deliveries.

[0995] (Application Example 2)

[0996] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0997] In food delivery services, delays in delivery times and inefficient route selection are problems that reduce customer satisfaction. Furthermore, the inability to respond quickly to changes in traffic and weather conditions leads to increased delivery times and wasted fuel. There is a need to solve these problems and provide more efficient and reliable delivery services.

[0998] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0999] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather information, means for proposing the optimal logistics route plan based on this information, means for calculating and updating the optimal delivery route in real time, and means for proposing alternative routes to delivery personnel. This makes it possible to shorten delivery times and save fuel.

[1000] "Past delivery completion data" refers to information about deliveries that have been completed in the past, including the delivery date and time, delivery destination, and duration.

[1001] "Location data" refers to information that indicates the current geographical location of an object, obtained using GPS or other position measurement technologies.

[1002] "Traffic information" refers to current traffic conditions, such as road congestion, accident information, and traffic restrictions.

[1003] "Movement speed" is a numerical value that indicates the distance an object travels per unit of time.

[1004] "Weather information" refers to information about current weather conditions, such as weather, temperature, precipitation, and wind speed.

[1005] An "optimal logistics route plan" is a proposal for the most effective delivery route, designed to maximize delivery efficiency.

[1006] "A means of calculating and updating the optimal delivery route in real time" refers to a function that instantly calculates the optimal delivery route based on the current situation and modifies that route as needed.

[1007] "Means of suggesting alternative routes to delivery drivers" refers to a function that presents delivery drivers with new delivery routes in response to unexpected events or changes in traffic conditions.

[1008] The system for realizing this invention consists of a server and a terminal for delivery personnel. The server collects past delivery completion data and calculates the probability of successful delivery based on this data. Furthermore, the server acquires location data, traffic information, travel speed, and weather information in real time and integrates this information to calculate the optimal logistics route. The server obtains the necessary data using the Google Maps API and OpenWeatherMap API and processes the data using the Python Pandas library. Dijkstra's algorithm is used for calculations, and the route is updated in real time.

[1009] The delivery driver's terminal receives the optimal delivery route transmitted from the server and presents it to the driver. Depending on changes in traffic and weather conditions, the server calculates alternative routes and suggests new routes to the driver's terminal. This ensures that drivers can always deliver using the most optimal route.

[1010] For example, if a delivery driver is likely to get caught in traffic, the server immediately calculates an alternative route and notifies the driver's terminal. This can shorten delivery times and save fuel. An example of a prompt to the generating AI model might be, "Please suggest the best route from my current location to my destination. Please consider traffic and weather information."

[1011] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1012] Step 1:

[1013] The server collects past delivery completion data. It uses past delivery dates and times, destinations, and delivery durations as input. Based on this data, it prepares the foundational data for calculating the probability of successful delivery. The output is the prepared historical delivery data.

[1014] Step 2:

[1015] The server acquires location data, traffic information, travel speed, and weather information in real time. It uses data from the Google Maps API and OpenWeatherMap API as input. This data is integrated to understand the current delivery environment. The output is integrated, real-time environmental data.

[1016] Step 3:

[1017] The server calculates the optimal logistics route based on well-maintained historical delivery data and integrated real-time environmental data. It uses historical delivery data and real-time environmental data as input. Dijkstra's algorithm is used to calculate the shortest path. The output is the optimal delivery route.

[1018] Step 4:

[1019] The server sends the calculated optimal delivery route to the delivery person's terminal. The optimal delivery route is used as input. The delivery person's terminal displays the received route and presents it to the delivery person. The output is the delivery route presented to the delivery person.

[1020] Step 5:

[1021] The server monitors changes in traffic and weather conditions and calculates alternative routes as needed. It uses real-time environmental data as input. If changes are detected, it recalculates a new route using Dijkstra's algorithm. The output is the updated delivery route.

[1022] Step 6:

[1023] The server sends the updated delivery route to the delivery person's terminal and suggests an alternative route to the delivery person. The updated delivery route is used as input. The delivery person's terminal displays the received alternative route and notifies the delivery person. The output is the alternative route presented to the delivery person.

[1024] (Example 3)

[1025] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1026] In the logistics industry, improving delivery efficiency and reducing fuel consumption are critical challenges. Traditional systems struggled to effectively utilize real-time traffic and weather data, making it difficult to propose optimal delivery routes. Furthermore, there was a lack of effective means to incorporate user feedback. This resulted in delivery delays, fuel waste, and decreased operational efficiency.

[1027] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1028] This invention includes a server that calculates the optimal time for delivery based on past delivery completion data to maximize the chances of success, a means for linking location data, traffic conditions, travel speed, weather conditions, and other information, and a means for proposing an optimal logistics route based on this information. This enables the proposal of an optimal delivery route using real-time traffic and weather data, improving delivery efficiency and reducing fuel consumption.

[1029] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, duration, and whether the delivery was successful.

[1030] "Location data" refers to data that indicates a geographical location, and includes latitude and longitude information obtained using technologies such as GPS.

[1031] "Traffic conditions" refers to information indicating the degree of road congestion and whether roads are passable, and includes real-time changes in traffic flow and congestion information.

[1032] "Movement speed" is an indicator that shows the distance traveled per unit of time, and it measures the speed at which vehicles or people move.

[1033] "Weather conditions" refer to information about the weather, including meteorological elements such as temperature, precipitation, wind speed, and humidity.

[1034] A "logistics route" refers to the path taken when delivering goods, and is used to plan the optimal route from the origin to the destination.

[1035] "Real-time traffic information" refers to information that instantly reflects the current traffic situation, including road congestion levels and accident information.

[1036] The "optimal delivery route" refers to the most efficient route, calculated with the aim of reducing delivery time and saving fuel.

[1037] "Feedback" refers to evaluations and opinions provided by users, and is information used to improve the system and enhance its accuracy.

[1038] A description of embodiments for carrying out this invention will be given.

[1039] The server generates a program to optimize logistics routes. This program collects traffic and weather data and calculates the optimal delivery route based on this information. Specifically, the server uses a geographic information system API to obtain real-time traffic information and a weather data API to collect weather data. By combining this data, it calculates a route that can shorten delivery times and save fuel.

[1040] The user then uses the generated program to optimize logistics routes. For example, if the user inputs the prompt "Suggest the best delivery route from Tokyo to Osaka" into the generating AI model, the server will propose the best route considering traffic information and weather data. This proposal may include alternative routes to avoid congested routes and route selection based on weather conditions.

[1041] As a concrete example, if a user enters the prompt "Tell me the best delivery route from Tokyo to Nagoya tomorrow morning," the server will propose the most efficient route based on the next day's traffic forecast and weather information. In this way, the user can shorten transportation time and save fuel. The flow of the specific processing in Example 3 will be explained using Figure 15.

[1042] Step 1:

[1043] The server collects traffic and weather data. Specifically, it uses a geographic information system API to obtain real-time traffic information and a weather data API to collect weather data. The input requires the current date and time and a geographical range, and the output provides traffic and weather information for the specified range. This allows users to understand the current level of road congestion and weather conditions.

[1044] Step 2:

[1045] The server analyzes the collected traffic and weather data. The input requires the traffic and weather data obtained in Step 1. The server statistically processes this data to identify routes expected to be congested and areas where bad weather is predicted. The output provides congestion and weather forecasts based on the analysis results. This clarifies the factors to consider when selecting delivery routes.

[1046] Step 3:

[1047] The server calculates the optimal delivery route based on the analysis results. The inputs required are the congestion forecast and weather forecast obtained in step 2. The server uses the Dijkstra algorithm or the A algorithm to calculate the route that reaches the destination in the shortest time. The output provides the optimal delivery route and its estimated travel time. This allows for the creation of efficient delivery plans.

[1048] Step 4:

[1049] The server proposes the calculated optimal route to the user. The input requires the optimal delivery route obtained in step 3. The user can receive a proposal from the server by prompting the generating AI model with the message, "Propose the optimal delivery route from Tokyo to Osaka." The output provides specific route information and estimated arrival times. This allows the user to select an efficient route for actual deliveries.

[1050] Step 5:

[1051] After actually using the suggested route, the user provides feedback to the server. The input requires user evaluations and opinions. The server uses this feedback as data to improve the accuracy of the algorithm. The output is an improved algorithm, which enables more accurate route selection in future suggestions.

[1052] (Application Example 3)

[1053] Next, we will describe application example 3 of form example 3. 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."

[1054] In the logistics industry, improving delivery efficiency and reducing fuel consumption are critical challenges. Conventional systems struggle to propose optimal delivery routes that fully consider real-time traffic and weather conditions, often resulting in delivery delays and wasted fuel. This hinders the efficiency of logistics operations.

[1055] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1056] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data; means for linking information such as location data, traffic conditions, travel speed, and weather conditions; means for proposing an optimal logistics route plan based on this information; means for acquiring traffic conditions and weather conditions in real time and calculating the optimal delivery route; and means for generating prompt messages that propose the optimal delivery route using a generative AI model. This makes it possible to shorten delivery times and save fuel.

[1057] "Past delivery completion data" refers to data that includes information such as the date and time of past deliveries, routes, duration, and success rate.

[1058] "Location information data" refers to data that indicates the current location of an object, obtained using technologies such as GPS.

[1059] "Traffic conditions" refers to information about traffic on roads, such as road congestion levels, traffic jam information, and the occurrence of traffic accidents.

[1060] "Movement speed" is data that indicates the speed at which an object moves.

[1061] "Weather conditions" refer to information about weather, such as climate, temperature, precipitation, and wind speed.

[1062] "Optimal logistics route planning" refers to a plan that proposes the most efficient delivery route with the aim of shortening delivery times and saving fuel.

[1063] "Means for obtaining real-time traffic conditions and weather conditions" refers to technologies and methods for instantly obtaining current traffic conditions and weather conditions.

[1064] A "generative AI model" is a model that uses artificial intelligence technology to analyze data and generate output tailored to a specific purpose.

[1065] A "prompt statement" is an instruction or question that is input into a generative AI model.

[1066] The system for implementing this invention operates through the coordinated efforts of a server, a terminal, and a user. The server calculates the time with the highest probability of successful delivery based on past delivery completion data. This is done using a machine learning algorithm. Furthermore, the server acquires information such as location data, traffic conditions, travel speed, and weather conditions in real time, and proposes an optimal logistics route plan based on this information. External services such as the Google Maps API and OpenWeatherMap API are used to acquire real-time data.

[1067] The terminal receives the optimal delivery route sent from the server and presents it to the user. The user can review the suggested route through the terminal and apply it to the actual delivery. This makes it possible to shorten delivery times and save fuel.

[1068] As a concrete example, the server inputs the prompt "Please suggest the optimal delivery route considering current traffic conditions and weather" into the generating AI model, and calculates the optimal delivery route. This prompt allows the generating AI model to analyze real-time data and suggest the optimal route.

[1069] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1070] Step 1:

[1071] The server retrieves historical delivery completion data. This data includes delivery date and time, route, duration, and success rate. Using this data as input, the server employs a machine learning algorithm to calculate the time with the highest probability of delivery success. The output is the optimal delivery time.

[1072] Step 2:

[1073] The server acquires real-time data such as location information, traffic conditions, travel speed, and weather conditions. This is done using the Google Maps API and the OpenWeatherMap API. The server uses this data as input to plan the optimal logistics route. The output is the optimal delivery route.

[1074] Step 3:

[1075] The server uses a generative AI model to generate prompts for suggesting the optimal delivery route. Specifically, it creates a prompt that says, "Please suggest the optimal delivery route considering current traffic conditions and weather." Using this prompt as input, the generative AI model calculates and outputs the optimal delivery route.

[1076] Step 4:

[1077] The terminal receives the optimal delivery route sent from the server. The terminal uses this route information as input and presents it visually to the user. The output is a display of the delivery route that the user can verify.

[1078] Step 5:

[1079] The user reviews the delivery route presented through the terminal and incorporates it into the actual delivery. The delivery plan is executed based on the user's input. The output is the actual delivery.

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

[1081] "Example of form 1"

[1082] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes emotions from the user's tone of voice, facial expressions, behavioral patterns, etc. Specifically, the emotion engine analyzes the tone of voice, facial expressions, and body movements of the user when they receive a package, and feeds the results back into the system.

[1083] "Example of form 2"

[1084] Based on the emotions recognized by the emotion engine, the system adjusts delivery times and routes. For example, if the system detects that the user is in a bad mood, it adjusts the delivery time to a time when the user is calmer. Conversely, if the user expresses joy, the system uses this information as feedback to learn how to improve the success rate of deliveries in similar situations.

[1085] "Example of form 3"

[1086] Furthermore, the emotion engine captures changes in the user's emotions in real time and feeds that information back into the system. This allows the system to respond flexibly according to the delivery situation. For example, if a user suddenly shows anger, the system can immediately receive that information and take action such as alerting the delivery person.

[1087] The following describes the processing flow for each example of the form.

[1088] "Example of form 1"

[1089] Step 1: The emotion engine analyzes the user's tone of voice, facial expressions, body movements, etc., when they receive their package.

[1090] Step 2: The emotion engine feeds back the results of its analysis to the system.

[1091] "Example of form 2"

[1092] Step 1: The emotion engine recognizes the user's emotions.

[1093] Step 2: The system adjusts delivery times and routes based on the recognized emotions.

[1094] Step 3: The system takes that information as feedback and learns to improve the success rate of deliveries under similar circumstances.

[1095] "Example of form 3"

[1096] Step 1: The emotion engine captures changes in the user's emotions in real time.

[1097] Step 2: Feed that information back into the system.

[1098] Step 3: The system can immediately receive this information and take action, such as alerting the delivery person.

[1099] (Example 1)

[1100] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1101] Traditional delivery systems lacked sufficient optimization of delivery times and struggled to provide services that considered user emotions. This resulted in lower delivery success rates and difficulty in improving customer satisfaction.

[1102] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1103] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion data, means for recognizing emotions by analyzing the user's voice, facial expressions, and behavioral patterns, and means for adjusting the delivery plan based on this information. This improves the success rate of deliveries and enables the provision of flexible services that respond to the user's emotions.

[1104] "Delivery completion data" refers to records of past deliveries, including the date and time, success rate, and recipient information.

[1105] "Optimal delivery time" refers to the most suitable time slot for delivery, calculated to maximize the success rate of the delivery.

[1106] "Voice, facial expressions, and behavioral patterns" refer to characteristics such as the tone of voice, facial expressions, and body movements that a user exhibits when receiving a package.

[1107] "Means of recognizing emotions" refers to technologies and devices that analyze and identify emotions from a user's voice and facial expressions.

[1108] "Means of adjusting delivery plans" refers to technologies and methods for optimizing delivery schedules and routes based on calculated optimal delivery times and user sentiment information.

[1109] This invention relates to a delivery system that calculates the optimal delivery time based on past delivery completion data and further adjusts the delivery plan by recognizing the user's emotions.

[1110] The server collects historical delivery completion data and stores it in a database. This data includes delivery date and time, success rate, and recipient information. The server uses the Python Scikit-learn library to apply machine learning algorithms to calculate the optimal delivery time. This model is built using the Random Forest algorithm.

[1111] The device uses a camera and microphone to capture the user's tone of voice, facial expressions, and body movements when they receive their package. This data is transmitted to a server via the internet. The server analyzes the user's emotions using emotion recognition software. Specifically, a common emotion recognition API is used for emotion analysis.

[1112] The server adjusts the delivery plan based on the analysis results. This improves the success rate of deliveries and enables the provision of flexible services that respond to the user's emotions.

[1113] For example, if past data shows that the highest success rate is calculated to be "weekdays between 2 PM and 4 PM," the delivery person will adjust their schedule to deliver during that time. Also, if a user appears dissatisfied when receiving their package, the system will use that information to notify customer support for follow-up.

[1114] Examples of prompt messages include, "Calculate the optimal delivery time based on past delivery data," and "Recognize the user's emotions from their tone of voice and facial expressions, and provide feedback based on the results."

[1115] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1116] Step 1:

[1117] The server collects historical delivery completion data. It retrieves data from the delivery management system via API, including delivery date and time, success rate, and recipient information. This data is stored in a database for later analysis.

[1118] Step 2:

[1119] The server aggregates stored delivery data and extracts necessary information from the database. It uses SQL queries as input to calculate the success rate for each delivery date and time. As output, it stores the aggregated results in a new table, which is then used to train a machine learning model.

[1120] Step 3:

[1121] The server trains a machine learning model using aggregated data. It takes the aggregated results as input to the Python Scikit-learn library and applies the random forest algorithm. The output is a model that predicts the optimal delivery time.

[1122] Step 4:

[1123] The server uses a trained model to calculate the optimal time for the next delivery. The model is fed data from a new delivery request as input. The output predicts the time slot with the highest success rate and notifies the delivery driver.

[1124] Step 5:

[1125] The device uses a camera and microphone to capture the user's tone of voice, facial expressions, and body movements when they receive their package. It acquires real-time audio and video data as input and sends this data to a server as output.

[1126] Step 6:

[1127] The server inputs the received data into the emotion engine to analyze the user's emotions. Audio and video data are passed to the emotion recognition software as input. The user's emotional state is identified as output and stored in a database.

[1128] Step 7:

[1129] The server adjusts the delivery plan based on the analysis results. Inputs include user sentiment information and optimal delivery times. Outputs include generating an adjusted delivery schedule and notifying customer support as needed.

[1130] (Application Example 1)

[1131] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1132] Traditional delivery systems have challenges in optimizing delivery times and improving customer satisfaction. In particular, the accuracy of delivery time predictions is low, and service improvements that take customer feelings into consideration are not being implemented, making it difficult to improve customer satisfaction.

[1133] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1134] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather conditions, and means for analyzing the customer's facial expressions and tone of voice to recognize their emotions. This enables optimization of delivery times and improvement of services based on customer emotions.

[1135] "Delivery completion data" refers to data that includes information such as the date, time, location, and whether or not a delivery was successful in the past.

[1136] "Location data" refers to data indicating geographical location, obtained using GPS or other location measurement technologies.

[1137] "Traffic information" refers to data that includes various types of information related to traffic, such as road congestion, traffic accidents, and construction information.

[1138] "Movement speed" is data that indicates the distance traveled by delivery vehicles and other moving objects within a certain period of time.

[1139] "Weather conditions" refers to data that includes information about weather, such as weather, temperature, precipitation, and wind speed.

[1140] A "logistics route" refers to the path that a delivery item takes from its origin to its destination.

[1141] "Methods for recognizing emotions by analyzing facial expressions and tone of voice" refers to technologies that analyze a customer's facial expressions and tone of voice to determine their emotional state.

[1142] "Feedback for service improvement" refers to providing information based on customer sentiment data to improve the quality of the service.

[1143] In an embodiment of this invention, the server collects past delivery completion data and runs a program that calculates the optimal delivery time using a machine learning algorithm. Specifically, it uses Python for data analysis and employs algorithms such as random forest. The server also integrates information such as location data, traffic information, travel speed, and weather conditions to optimize logistics routes. This requires real-time data processing and utilizes cloud-based databases and APIs.

[1144] The terminals are devices such as smartphones and tablets, and they use cameras and microphones to analyze customers' facial expressions and tone of voice. Using OpenCV and TensorFlow, real-time image processing and audio analysis are performed to recognize customer emotions. This customer emotion data is then sent to a server to generate feedback for service improvement.

[1145] As a concrete example, when a user places an order using a food delivery app, the server calculates the optimal delivery time based on past data and notifies the delivery person. When the delivery person arrives, the terminal analyzes the customer's facial expression and recognizes emotions such as "satisfaction." This information is sent to the server and used as feedback to improve the service.

[1146] An example of a prompt to be input into the generating AI model is: "Calculate the optimal delivery time based on past delivery data. Also, recognize the customer's emotions from their facial expressions and tone of voice, and provide feedback."

[1147] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1148] Step 1:

[1149] The server retrieves past delivery completion data from a database. The input includes data such as delivery date and time, location, and whether the delivery was successful or not. Based on this data, a machine learning algorithm (e.g., Random Forest) is used to calculate the optimal delivery time. The output is the delivery time with the highest probability of success.

[1150] Step 2:

[1151] The server obtains real-time data such as location data, traffic information, travel speed, and weather conditions via APIs. This data is then integrated as input to optimize the logistics route. As part of the data processing, an algorithm is applied to integrate the various pieces of information and calculate the shortest route. The output is the optimized logistics route.

[1152] Step 3:

[1153] The user places an order using a food delivery app on their smartphone. The user enters the order details and delivery address information into the app. The server sends a notification to the delivery driver based on the optimal delivery time and route determined in steps 1 and 2. The output is a delivery instruction for the driver.

[1154] Step 4:

[1155] The device captures the customer's facial expressions and tone of voice using the smartphone's camera and microphone when the delivery person arrives. It acquires real-time video and audio data as input. Using OpenCV and TensorFlow, it performs image processing and audio analysis to recognize the customer's emotions. The output is the recognized emotion data.

[1156] Step 5:

[1157] The server receives sentiment data sent from the terminal and generates feedback for service improvement. Sentiment data is used as input. As a data calculation, the sentiment data is analyzed to generate specific suggestions for service improvement. The output is feedback information for service improvement.

[1158] (Example 2)

[1159] Next, we will describe Example 2 of the morphological example. 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."

[1160] In the logistics industry, improving delivery efficiency and customer satisfaction are crucial challenges. Traditional systems struggle to respond flexibly to real-time changes in circumstances and customer emotions, resulting in insufficient delivery optimization. Furthermore, a lack of learning capabilities to increase delivery success rates makes improvement under similar circumstances difficult.

[1161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1162] This invention includes a server that includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking location data, traffic condition data, travel speed data, and weather data, means for proposing an optimal logistics route plan based on this information, means for adjusting delivery time and route based on the user's emotions using emotion recognition technology, and means for incorporating the user's emotional information as feedback and learning to improve the delivery success rate. This enables the proposal of an optimal delivery plan in real time and flexible delivery adjustments in response to the user's emotions, thereby improving delivery efficiency and customer satisfaction.

[1163] "Past delivery completion data" refers to data that includes information such as the date and time of past deliveries, the route, the duration, and whether or not the deliveries were successful.

[1164] "Location data" refers to geographical information about a specific location, obtained using GPS or other location measurement technologies.

[1165] "Traffic data" refers to real-time information about traffic, such as road congestion, traffic restrictions, and accident information.

[1166] "Movement speed data" refers to information about the movement speed of vehicles and people, and is obtained from speed sensors and GPS data.

[1167] "Weather data" refers to information about the weather, including meteorological conditions such as temperature, precipitation, and wind speed.

[1168] "Optimal logistics route planning" refers to the optimal delivery route and schedule calculated based on real-time data to maximize delivery efficiency.

[1169] "Emotion recognition technology" is a technology that analyzes voice and text data to identify the emotional state of a user.

[1170] "Learning to improve delivery success rates" refers to a machine learning process that uses past delivery data and user feedback to improve the success rate of deliveries.

[1171] This invention is a system aimed at improving logistics efficiency and customer satisfaction. The server first collects past delivery completion data and calculates the time of day when deliveries have the highest probability of success. A machine learning algorithm is used for this calculation. Next, the server acquires location data, traffic data, speed data, and weather data in real time and integrates and analyzes this information. Specifically, location data is acquired using a GPS module, traffic data is acquired through a general map API, speed data is acquired from the vehicle's speed sensor, and weather data is acquired using a weather information API.

[1172] Based on this data, the server proposes an optimal logistics route plan. This plan aims to reduce delivery time and save fuel, and is dynamically updated according to real-time conditions. The terminal also uses emotion recognition technology to recognize emotions from the user's voice and text data. For example, if the user says "I'm busy today," the terminal recognizes that emotion as being in a bad mood. Based on this emotion information, the server adjusts the delivery time and route to ensure that deliveries are made during times when the user is less busy.

[1173] Furthermore, the server incorporates user emotional information as feedback and learns to improve the delivery success rate. This learning process uses a generative AI model. For example, if a user is in a situation where "it's raining today and there's traffic congestion," the server analyzes weather and traffic information and suggests routes that avoid the rain and congestion.

[1174] Examples of prompts to input into the generating AI model include "Please suggest the optimal delivery route considering the current weather and traffic conditions" and "Please adjust the delivery time based on the user's emotions." This enables the suggestion of optimal delivery plans in real time and flexible delivery adjustments based on the user's emotions, leading to improved delivery efficiency and customer satisfaction.

[1175] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1176] Step 1:

[1177] The server collects historical delivery completion data. It uses data such as past delivery date and time, route, duration, and success / failure status as input. Based on this data, a machine learning algorithm is used to calculate the time of day with the highest probability of success for delivery. The output provides recommendations for the optimal delivery time.

[1178] Step 2:

[1179] The server acquires location data, traffic data, speed data, and weather data in real time. It uses data from GPS modules, map APIs, speed sensors, and weather information APIs as input. This data is integrated and analyzed to propose the optimal logistics route plan. The output provides the optimal delivery route and schedule.

[1180] Step 3:

[1181] The device inputs the user's voice and text data into emotion recognition technology to recognize the user's emotions. User statements and messages are used as input. An emotion recognition AI model is used to identify the user's emotional state. The output is the user's emotional information.

[1182] Step 4:

[1183] The server adjusts delivery times and routes based on the user's sentiment information obtained in step 3. It uses the user's sentiment information and the optimal delivery route obtained in step 2 as input. It creates a flexible delivery plan tailored to the sentiment, and the adjusted delivery schedule is output.

[1184] Step 5:

[1185] The server incorporates user emotional information as feedback and learns to improve delivery success rates. Past delivery data and user emotional feedback are used as input. A generative AI model is used to learn how to improve delivery success rates. The output is an improved delivery planning algorithm.

[1186] (Application Example 2)

[1187] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1188] In modern logistics services, improving delivery efficiency and customer satisfaction are crucial challenges. However, conventional systems struggle to propose optimal delivery routes that take real-time traffic and weather conditions into account, and they fail to adjust delivery times to consider the emotional state of the user. As a result, delivery success rates may decrease, potentially compromising customer satisfaction.

[1189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1190] This invention includes a server that includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic conditions, travel speed, and weather information, means for proposing an optimal logistics route plan based on this information, means for analyzing the user's emotional state using emotion recognition technology and adjusting the delivery time and route, and means for comprehensively analyzing information acquired in real time and learning to improve the delivery success rate based on the user's emotions. This makes it possible to improve delivery efficiency and customer satisfaction.

[1191] "Delivery completion data" refers to data that records detailed information about deliveries made in the past, including delivery time, delivery destination, and whether the delivery was successful or not.

[1192] "Location data" refers to data that indicates the geographical location of a specific object, obtained using GPS or other location measurement technologies.

[1193] "Traffic conditions" refers to information about the flow of traffic on roads, such as the degree of road congestion, traffic jam information, and the occurrence of traffic accidents.

[1194] "Movement speed" is an indicator that shows the distance a particular object travels per unit of time.

[1195] "Weather information" refers to information about weather conditions in a specific region, such as weather, temperature, precipitation, and wind speed.

[1196] A "logistics route" is the path that goods take when traveling from their origin to their destination, and it should be optimized to ensure efficient delivery.

[1197] "Emotion recognition technology" is a technology that analyzes and identifies a user's emotional state based on their facial expressions, voice, and behavior.

[1198] "Delivery success rate" is an indicator that shows the probability of a delivery being completed on schedule, and is used to evaluate the efficiency and reliability of logistics services.

[1199] The system for implementing this invention is composed of three main elements: a server, a terminal, and a user.

[1200] The server calculates the time with the highest probability of successful delivery based on past delivery completion data. This is done using machine learning algorithms. The server also acquires location data, traffic conditions, travel speed, and weather information in real time and analyzes this information comprehensively. Specifically, it obtains location information using the Google Maps API, checks traffic conditions using the Waze API, and obtains weather information using the OpenWeatherMap API. This data is processed using Python's Pandas and NumPy to propose the optimal logistics route.

[1201] The device analyzes the user's emotional state using emotion recognition technology. This is done using the Microsoft Azure Emotion API. Based on the user's emotions, the device sends information to the server to adjust delivery times and routes.

[1202] Users can check the delivery status through their device and adjust the delivery time as needed. If the server detects that the user is in a bad mood, it will adjust the delivery time to ensure the delivery is made when the user is calmer.

[1203] For example, if a user orders "pizza" and the emotion engine detects that the user is "unhappy," the server will check traffic information to confirm that the usual route is congested, and taking into account the weather ("rainy"), it will suggest a route that departs earlier than usual and avoids traffic.

[1204] Examples of prompts for a generative AI model include the following:

[1205] "If the user is unhappy, suggest the optimal delivery time. Current traffic conditions are congested, and the weather is rainy. How would you adjust the route?"

[1206] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1207] Step 1:

[1208] The server retrieves past delivery completion data. It receives data such as past delivery time, destination, and success / failure status as input. Using this data, it applies a machine learning algorithm to calculate the time with the highest probability of delivery success. The output is the optimal delivery time.

[1209] Step 2:

[1210] The server acquires location data, traffic conditions, travel speed, and weather information in real time. It receives data from the Google Maps API, Waze API, and OpenWeatherMap API as input. This data is integrated using Pandas and NumPy to optimize logistics routes. The output is the optimal delivery route.

[1211] Step 3:

[1212] The device analyzes the user's emotional state using emotion recognition technology. As input, it sends data of the user's facial expressions and voice to the Microsoft Azure Emotion API. The response from the API is analyzed to identify the user's emotional state. The output is the user's emotional state.

[1213] Step 4:

[1214] The server adjusts delivery times and routes based on the user's emotional state. It receives the optimal delivery time obtained in step 1, the optimal delivery route obtained in step 2, and the user's emotional state obtained in step 3 as input. This information is integrated to adjust the delivery plan. The output is the adjusted delivery time and route.

[1215] Step 5:

[1216] The user reviews the adjusted delivery plan through their terminal. They receive the adjusted delivery time and route from the server as input. The user can request a readjustment of the delivery time if necessary. The final delivery plan is reviewed as output.

[1217] (Example 3)

[1218] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1219] There is a need to improve delivery efficiency in logistics and to provide flexible responses that respond to customer emotions. Conventional systems have difficulty responding quickly to changes in traffic conditions and weather, and have not adequately adjusted services based on changes in customer emotions. As a result, delays in delivery times and customer dissatisfaction are common challenges.

[1220] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1221] In this invention, the server includes means for calculating delivery time based on past delivery completion information, means for linking information such as location information, traffic conditions, travel speed, and weather conditions, and means for detecting changes in the user's emotions in real time and providing feedback on that information. This enables optimization of delivery routes and flexible responses to the user's emotions.

[1222] "Delivery completion information" refers to data that records the details of past deliveries, including information such as the delivery date and time, delivery destination, and duration.

[1223] "Location information" refers to data indicating a geographical location, specifically latitude and longitude information obtained using technologies such as GPS.

[1224] "Traffic conditions" refer to information indicating the degree of road congestion and passability, and are data that reflects the real-time changes in traffic flow.

[1225] "Movement speed" is an indicator that shows the distance traveled per unit of time, and represents the speed at which vehicles or people move.

[1226] "Weather conditions" refer to information about the weather, including meteorological elements such as temperature, precipitation, and wind speed.

[1227] "Emotional changes" refer to fluctuations in the user's emotional state, which are detected through analysis of voice and facial expressions.

[1228] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate results tailored to a specific purpose.

[1229] "Delivery route" refers to the path taken when delivering goods, and includes the optimal route from the origin to the destination.

[1230] A description of embodiments for carrying out this invention will be given.

[1231] The server generates a program that calculates delivery times based on past delivery completion data to improve delivery efficiency in logistics. This program uses a generating AI model to propose the optimal delivery route by linking data such as location information, traffic conditions, travel speed, and weather conditions. Specifically, it uses external software such as the Google Maps API and OpenWeatherMap API to obtain real-time traffic information and weather data.

[1232] The terminal uses emotion recognition software to detect changes in the user's emotions in real time. This software analyzes the user's voice and facial expressions to detect changes in emotions. If the user shows anxiety or anger, this information is fed back to the server, which then flexibly adjusts the delivery plan.

[1233] For example, if the usual route is congested, the server can suggest an alternative route. Also, if a user expresses concern that a delivery may be delayed, the server can instruct the delivery person to take immediate action.

[1234] Examples of prompts for a generative AI model include the following:

[1235] "Please suggest the optimal delivery route, taking into account current traffic conditions and weather."

[1236] "Adjust the delivery plan based on the user's emotional data." Figure 21 illustrates the flow of the specific processing in Example 3.

[1237] Step 1:

[1238] The server receives past delivery completion information as input and calculates the delivery time. Using a machine learning algorithm, it predicts the delivery time with the highest probability of success based on past data. The output is the optimal delivery time.

[1239] Step 2:

[1240] The server takes location information, traffic conditions, travel speed, and weather conditions as input. This data is collected in real time using the Google Maps API and OpenWeatherMap API. The server integrates this information and uses a generative AI model to calculate the optimal delivery route. The output is the optimized delivery route.

[1241] Step 3:

[1242] The device transmits the user's voice and facial expressions as input to emotion recognition software. This software detects changes in the user's emotions in real time and generates emotion data. The output is the user's emotional state.

[1243] Step 4:

[1244] The device feeds back the detected emotion data to the server. The server adjusts the delivery plan based on this information. For example, if the user shows signs of anxiety, the server instructs the delivery person to take immediate action. The adjusted delivery plan is then output.

[1245] Step 5:

[1246] The server notifies the user of the optimized delivery route and adjusted delivery plan. The terminal displays the new delivery route and estimated arrival time to the user. The output provides the user with the information to be provided.

[1247] (Application Example 3)

[1248] Next, we will describe application example 3 of form example 3. 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."

[1249] Optimizing delivery routes in logistics contributes to reducing transportation time and saving fuel, but conventional systems have the challenge of not being able to respond flexibly to the emotional state of users. Furthermore, they cannot provide appropriate feedback in response to the stress and emotional changes of delivery personnel, which may result in a decrease in delivery efficiency.

[1250] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1251] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as location data, traffic information, travel speed, and weather information, means for proposing an optimal logistics route plan based on this information, means for analyzing the user's emotions in real time using an emotion analysis engine and providing feedback, and means for suggesting revised routes or breaks based on the emotional state of the delivery person. This enables flexible responses according to the emotional state of the delivery person while shortening transportation time and saving fuel.

[1252] "Past delivery completion data" refers to data that records detailed information about deliveries made in the past, including information such as delivery date and time, delivery destination, delivery time, and success rate.

[1253] "Location data" refers to data that indicates the geographical location of a specific point, obtained using GPS or other location measurement technologies.

[1254] "Traffic information" refers to real-time information about road traffic, such as road congestion, accident information, and traffic restrictions.

[1255] "Travel speed" is data that indicates the speed at which one moves between specific points, and is usually expressed in time per unit of distance.

[1256] "Weather information" refers to information about the weather, including data such as temperature, precipitation, wind speed, and humidity.

[1257] "Optimal logistics route planning" refers to a plan that proposes the most efficient delivery route with the aim of reducing transportation time and saving fuel.

[1258] An "emotion analysis engine" is a technology that analyzes a user's emotions from their facial expressions and voice, and understands their emotional state in real time.

[1259] "Means of providing feedback" refers to methods for providing appropriate instructions and information to users and delivery personnel based on the analyzed information.

[1260] "Delivery driver's emotional state" refers to the emotional state that a delivery driver experiences while on duty, and includes stress, fatigue, satisfaction, and other factors.

[1261] "Re-proposing routes" means reviewing existing delivery routes based on current circumstances and proposing new, optimal routes.

[1262] "Suggesting breaks" means recommending that delivery drivers take breaks at appropriate times, depending on their emotional state and level of fatigue.

[1263] The system that realizes this invention consists of a server, a delivery person's terminal, and a user's terminal. The server executes an algorithm to calculate the time with the highest probability of successful delivery based on past delivery completion data. Machine learning techniques can be used for this. The server also acquires location data, traffic information, travel speed, and weather information in real time, and integrates this information to generate an optimal logistics route plan.

[1264] The delivery driver's terminal is equipped with an emotion analysis engine that analyzes the driver's emotional state in real time from their facial expressions and voice. This information is sent to a server, and based on the driver's emotional state, the server suggests rerouting or taking a break. Specifically, if the driver is feeling stressed, the server inputs a prompt into the AI ​​model saying, "The driver is feeling stressed, please recalculate the route and suggest a break," and provides appropriate feedback.

[1265] The user's device is used to check the delivery status and receive feedback. If a user expresses dissatisfaction with the delivery, an emotion analysis engine analyzes their emotions and sends feedback to the server. This allows the server to flexibly adjust the delivery plan and improve user satisfaction.

[1266] This system uses the Google Maps API to obtain traffic information and the OpenWeatherMap API to obtain weather data. It also uses the Microsoft Azure Emotion API for sentiment analysis. This allows for shorter delivery times and fuel savings, while also enabling flexible responses based on the emotional state of delivery personnel.

[1267] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1268] Step 1:

[1269] The server retrieves past delivery completion data and uses a machine learning algorithm to calculate the time with the highest probability of successful delivery. This process uses data such as past delivery date and time, success rate, and delivery destination as input and outputs the optimal delivery time. Specifically, the server analyzes the dataset and learns patterns to predict the optimal time for the next delivery.

[1270] Step 2:

[1271] The server acquires location data, traffic information, travel speed, and weather information in real time. This information is obtained using the Google Maps API and the OpenWeatherMap API. The server integrates this data to generate an optimal logistics route plan. Inputs include current location, road congestion, and weather data, and the output is the optimal delivery route. Specifically, the server analyzes each piece of data and calculates the route to reach the destination in the shortest time.

[1272] Step 3:

[1273] The delivery person's terminal uses an emotion analysis engine to analyze their emotional state in real time from their facial expressions and voice. Inputs include the delivery person's facial image and voice data, and output is an evaluation of their emotional state. Specifically, the terminal collects data using a camera and microphone and analyzes emotions using Microsoft Azure's Emotion API.

[1274] Step 4:

[1275] The server suggests alternative routes and breaks based on the delivery person's emotional state. The input is the result of the emotional analysis, and the output is the revised route and break instructions. Specifically, the server generates a prompt such as, "The delivery person is stressed; please recalculate the route and suggest a break," which is input into the AI ​​model, providing appropriate feedback.

[1276] Step 5:

[1277] The user's device is used to check the delivery status and receive feedback. Inputs include delivery status data from the server, and outputs include notifications and feedback to the user. Specifically, the user can check the delivery progress through the application and send feedback as needed.

[1278] (Other examples)

[1279] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[1280] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1281] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1282] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1283] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1284] [Fourth Embodiment]

[1285] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1286] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1287] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1288] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1289] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1290] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1291] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1292] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1293] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1294] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1295] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1296] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1297] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1298] "Example of form 1"

[1299] One embodiment of this system is a B2C delivery system. This system has a function to calculate the optimal delivery time based on past delivery completion data. Specifically, it aggregates past delivery data and uses a machine learning algorithm to calculate the optimal delivery time from that data.

[1300] "Example of form 2"

[1301] Furthermore, this system has the functionality to integrate information such as GPS data, traffic information, travel speed, and weather. This information is acquired in real time and analyzed comprehensively to propose the most suitable delivery route for the current situation.

[1302] "Example of form 3"

[1303] Furthermore, this system has a function to propose the optimal logistics route plan based on this information. Specifically, it proposes routes that can shorten transportation time and save fuel, based on the calculated optimal delivery time and related information. For example, it can avoid routes that are expected to be congested and propose routes optimized for traffic information and weather conditions.

[1304] The following describes the processing flow for each example of the form.

[1305] "Example of form 1"

[1306] Step 1: The system aggregates past delivery completion data. This includes information such as delivery time, delivery destination, and delivery success rate.

[1307] Step 2: Based on the aggregated data, a machine learning algorithm is used to calculate the time of day when deliveries have the highest probability of success. This algorithm takes into account factors such as time of day, location, and weather.

[1308] "Example of form 2"

[1309] Step 1: The system acquires information such as GPS data, traffic information, travel speed, and weather in real time. This information is obtained from various sensors and external APIs.

[1310] Step 2: Analyze the acquired information to propose the optimal delivery route for the current situation. This analysis will take into account factors such as road congestion, traffic restrictions, and weather conditions.

[1311] "Example of form 3"

[1312] Step 1: Based on the calculated optimal delivery time and related information, the system proposes routes that can shorten transportation time and save fuel.

[1313] Step 2: Specifically, suggest routes that are optimized for traffic information and weather conditions, avoiding routes that are expected to be congested. For example, suggest leaving earlier during peak hours and avoiding slippery roads in rainy weather.

[1314] (Example 1)

[1315] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1316] In the logistics industry, improving delivery efficiency and reducing costs are critical challenges. In particular, optimizing delivery times directly leads to increased customer satisfaction and more effective use of transportation resources. However, traditional methods have struggled to calculate optimal delivery times due to the inability to fully utilize historical data. Furthermore, the inability to consider fluctuating factors such as traffic conditions and weather in real time has resulted in reduced accuracy in delivery planning.

[1317] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1318] In this invention, the server includes means for calculating the optimal delivery time based on past delivery completion information, means for integrating information such as location information, traffic conditions, travel speed, and weather conditions, and means for proposing an optimal logistics route plan based on this information. This enables the optimization of delivery time and the efficiency of logistics routes.

[1319] "Delivery completion information" refers to data that includes the date and time of past deliveries, delivery destination, and recipient information.

[1320] "Location information" refers to data indicating a geographical location, obtained using methods such as GPS.

[1321] "Traffic conditions" refers to information about road congestion and passable routes.

[1322] "Movement speed" refers to data indicating the speed at which a delivery vehicle moves.

[1323] "Weather conditions" refer to information about weather, such as climate, temperature, and precipitation.

[1324] A "logistics route" is the path that a delivery item takes when it travels from its origin to its destination.

[1325] An "optimal plan" is a delivery schedule designed to reduce transportation time and conserve resources.

[1326] A "machine learning algorithm" is a computational method used to learn patterns from data and perform predictions and classifications.

[1327] "Data preprocessing" refers to the process of shaping data into a format suitable for machine learning.

[1328] "Features" are attributes or metrics of data that machine learning models use when training.

[1329] "Training" is the process by which a machine learning model learns patterns from data.

[1330] "Evaluation" is the process of measuring the performance of a trained machine learning model and verifying its accuracy.

[1331] In an embodiment of this invention, the server runs a program to collect past delivery completion information and calculate the optimal delivery time. The server retrieves delivery completion information from a database and preprocesses the data using the Python Pandas library. Preprocessing includes imputing missing values ​​and removing outliers. Next, the server trains and evaluates a machine learning model using the Scikit-learn library. Algorithms such as random forest and gradient boosting are used to train the model.

[1332] The server integrates information such as location data, traffic conditions, travel speed, and weather conditions, and based on this information, proposes the optimal logistics route plan. This enables the optimization of delivery times and the efficiency of logistics routes.

[1333] For example, the server uses delivery data for a certain region to calculate that "deliveries in this region have a higher success rate between 2 PM and 4 PM." Users can then check this information through their terminal and plan their deliveries accordingly.

[1334] An example of a prompt message is: "Calculate the optimal delivery time based on past delivery data. The data includes delivery date and time, address, and recipient information."

[1335] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1336] Step 1:

[1337] The server retrieves past delivery completion information from the delivery database. Input includes delivery date and time, delivery address, and recipient information. This data is aggregated to prepare for the next processing step. Specifically, it extracts the necessary data using SQL queries.

[1338] Step 2:

[1339] The server preprocesses the acquired data. The input is the delivery completion information aggregated in step 1. The Python Pandas library is used for data preprocessing, including imputing missing values ​​and removing outliers. The output is data formatted in a way that is suitable for machine learning algorithms. Specifically, it cleans the data frame.

[1340] Step 3:

[1341] The server selects features from preprocessed data and generates new features. The input is the data formatted in step 2. Feature selection involves analyzing data correlations and extracting important attributes. The output is a set of features used to train a machine learning model. Specifically, it creates a correlation matrix and selects important features.

[1342] Step 4:

[1343] The server trains a machine learning model using the selected features. The input is the feature set generated in step 3. The Scikit-learn library is used to train the model with algorithms such as random forest and gradient boosting. The output is the trained machine learning model. Specifically, the hyperparameters of the model are tuned to build the optimal model.

[1344] Step 5:

[1345] The server evaluates the trained model. The input is the trained model obtained in step 4. Cross-validation is used to measure the model's accuracy. The output is an indicator of the model's accuracy. Specifically, the server identifies areas for improvement in the model based on the evaluation results.

[1346] Step 6:

[1347] The server calculates the optimal delivery time using a pre-evaluated model. Inputs include real-time location information, traffic conditions, travel speed, and weather conditions. The output is the optimal delivery time for each destination. Specifically, it inputs new data into the model and generates prediction results.

[1348] Step 7:

[1349] The server provides the user with the calculated optimal delivery time. The input is the optimal delivery time obtained in step 6. The output is a delivery schedule that the user can view on their terminal. Specifically, the results are displayed in the user interface to assist the user in planning their delivery.

[1350] (Application Example 1)

[1351] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1352] In food delivery services, determining the optimal delivery time is crucial to ensure customers receive their food in the freshest possible condition. However, traditional systems often fail to adequately optimize delivery times, making it difficult to improve customer satisfaction.

[1353] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1354] In this invention, the server includes means for calculating the time of day with the highest probability of success for delivery based on past delivery completion data, means for linking information such as GPS data, traffic information, travel speed, and weather, means for proposing the optimal logistics route plan based on this information, means for analyzing past delivery data and proposing the optimal delivery time to the user, and means for presenting the optimal delivery time when the user confirms their order. This makes it possible to optimize delivery times so that customers can receive their food in the freshest possible condition.

[1355] "Delivery completion data" refers to data containing detailed information about past deliveries, including delivery date and time, delivery destination, and whether the delivery was successful.

[1356] "Success probability" is an indicator that shows the likelihood of delivery being completed on schedule, and is calculated based on past data.

[1357] A "machine learning algorithm" is a computational method that allows computers to learn patterns from data and perform predictions and classifications.

[1358] "Optimal delivery time" refers to the time required for delivery to be completed in the most efficient and customer-satisfying manner.

[1359] "Means of suggesting to the user" refers to the methods and functions that the system uses to present the user with the optimal options based on its analysis results.

[1360] An "optimal logistics route plan" is a delivery route plan designed to maximize delivery efficiency and minimize time and costs.

[1361] "Traffic information" refers to real-time data related to traffic, such as road congestion, traffic accidents, and construction information.

[1362] "Means presented to the user when confirming an order" refers to the methods or functions that the system uses to display the optimal delivery time when the user makes a final decision on an order.

[1363] The system for implementing this invention operates in a network environment including a server and user terminals. The server collects past delivery completion data and uses a machine learning algorithm to calculate the optimal delivery time based on this data. Specifically, it uses Python and the Scikit-learn library to build a machine learning model. The server preprocesses the collected data, extracts features, and then trains the model using algorithms such as random forest.

[1364] The user terminal is a device such as a smartphone or tablet that receives the optimal delivery time provided by the server and presents it to the user. When the user confirms their order, the terminal displays the optimal delivery time on the screen based on the server's suggestion. This allows the user to choose the time when they can receive their food in the freshest condition.

[1365] As a concrete example, when a user orders a pizza, the terminal suggests, "Based on past data, specifying 18:30 for delivery is most likely to ensure the food arrives in the freshest condition." This suggestion is the result of the server using a generated AI model to analyze past delivery data and predict the optimal delivery time.

[1366] An example of a prompt message would be: "Based on past delivery data, predict the optimal delivery time. The current order is for pizza, and the user's location is Shibuya Ward, Tokyo."

[1367] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1368] Step 1:

[1369] The server collects past delivery completion data from the database. It takes information such as delivery date and time, delivery destination, and whether the delivery was successful as input. This data is preprocessed to impute missing values ​​and remove outliers. The output is a clean dataset.

[1370] Step 2:

[1371] The server extracts features using pre-processed data. It uses a clean dataset as input and selects features such as delivery time, day of the week, and weather. This results in the output of a dataset suitable for training machine learning models.

[1372] Step 3:

[1373] The server uses the Scikit-learn library to build and train a machine learning model. It uses a feature-extracted dataset as input. It applies the Random Forest algorithm to generate a model that predicts the optimal delivery time. The output is the trained model.

[1374] Step 4:

[1375] The server uses a generative AI model to predict the optimal delivery time based on the user's order information. It uses the user's current order details and location as input. By generating prompt messages and inputting them into the model, it outputs the optimal delivery time.

[1376] Step 5:

[1377] The terminal displays the optimal delivery time received from the server to the user. It receives a suggested delivery time from the server as input. The screen displays a message such as, "Based on past data, specifying 18:30 for delivery is likely to ensure your food arrives in the freshest condition." The output provides information to help the user select the optimal delivery tim...

Claims

1. Equipped with a processor, The aforementioned processor, We collect historical delivery completion data, including at least the delivery date and time, delivery destination, delivery success rate, and duration, and use a trained machine learning model based on the said delivery completion data to calculate the optimal delivery time, which is the time to start a delivery or the time period during which a delivery is made that maximizes the delivery success rate. We acquire current location information, traffic information, and weather conditions in real time, and perform analyses to evaluate the impact of traffic congestion and the risk of delays due to weather. The system receives and analyzes facial expression data and tone of voice data of the user receiving the delivery, collected through the terminal's camera and microphone, to identify the user's emotional state. A system that generates prompt messages to dynamically adjust the delivery time and delivery route based on the calculated optimal delivery time, the results of the delay risk assessment based on the analysis, and the identified user's emotional state, and inputs the generated prompt messages into a generating AI model to generate an optimal logistics route plan, The system includes a processor that incorporates the identified user's emotional information as feedback and updates the machine learning model by learning to improve the success rate of deliveries under similar circumstances.

2. The system according to claim 1, wherein the processor inputs the user's facial expression data and tone data into a pre-trained neural network and identifies the user's emotional state by obtaining an emotion value representing each emotion in an emotion map where emotions are arranged radially from the center.

3. The system according to claim 1, wherein the processor, when it recognizes that the identified user's emotional state is one of urgency or irritability, generates the prompt statement to suggest a route that avoids traffic congestion or the fastest delivery route.

Images